The policy section of the village pump is used to discuss already proposed policies and guidelines and to discuss changes to existing policies and guidelines.
If you want to propose something new that is not a policy or guideline, use Village pump (proposals).
If you have a question about how to apply an existing policy or guideline, try one of the many Wikipedia:Noticeboards.
If you want to ask what the policy is on something, try the Help desk or the Teahouse.
This is not the place to resolve disputes over how a policy should be implemented. Please see Wikipedia:Dispute resolution for how to proceed in such cases.
Please see this FAQ page for a list of frequently rejected or ignored proposals. Discussions are automatically archived after remaining inactive for two weeks.
ChatGPT has gone viral and is causing quite a storm on the Web. Why should we care? Because, rather than just providing links to an article for you to read about what you are interested in, it writes an essay about it on the spot. It is so sophisticated that, if you ask it to write an article on any subject, even in the style of Wikipedia, it will! That can then be copied and pasted into Wikipedia -- not necessarily a problem if it is carefully fact checked and edited first (ChatGPT can't tell fact from fiction), but, an editor may post it without doing so. It can even be used to answer questions about Wikipedia as if it is a Wikipedian (see the first link provided directly below). — The Transhumanist06:52, 9 December 2022 (UTC)[reply]
Based on how rapidly chatbots have improved over time, it will become more and more difficult to tell if an article was written by a computer or not. The sheer volume at which computer programs could create new accounts and produce Wikipedia content, and the inevitable growing number of human editors copying and pasting chatbot output into Wikipedia, will at some point make it impossible for Wikipedia's human volunteers to keep up with that traffic and apply quality control to the material in a reasonable time frame -- the backlog of unchecked material will simply get longer and longer. The only recourse will be for computer programs to do it -- either computer programs to process articles to filter out or correct any crap, or training the chatbots themselves not to produce crap in the first place. Rather than build computer algorithms to detect computer-written articles and passages, it would be more productive for them to do style checks, fact checks, and citation checks, along with appropriate corrections or removals. While Wikpedia-friendly AI could come from within Wikipedia, it may be faster to bring influence to bear upon the developers of the chatbots being used to generate Wikipedia content, and upon the chatbots themselves. Wikipedia already has a chair at the table, because Wikipedia comprises a significant component of chatbot corpi, and so, their developers should be inclined to listen to the Wikipedia community's concerns -- either directly, or indirectly through news coverage. The Wikipedia community should make its voice heard on the matter of chatbots writing Wikipedia material according to Wikipedia's style and behavior guidelines. For example, verifiability still applies, and so when chatbots are asked by their users to "write an article in the style of Wikipedia" the chatbots should comply according to Wikipedia's policies, including those on verifiability and providing reliable sources. Not doing so should be met with the filing of bug reports, feedback, and commentary. And, as chatbots learn as they go, Wikipedians who use them can ask them to follow Wikipedia guidelines, and we can urge our fellow editors to request this of chatbots as well. — The Transhumanist06:52, 9 December 2022 (UTC)[reply]
Chatbots should be following Wikipedia's lead for all of their output. At this time, most chatbot answers and essays are not referenced with reliable sources. And they should be, for the same reason that Wikipedia articles should be. That's something that can be requested of chatbots directly, through queries, and of developers, through their contact channels and social media. I hope this suggestion helps. — The Transhumanist06:52, 9 December 2022 (UTC)[reply]
@Transhumanist If a few chatbots are reading major newspapers, Google News, and history books, and watching TV news programs, they can be the ones writing drafts. After we have chatbots writing drafts (new chatbots should use the AfC process, of course) we'll need chatbot software to review those articles at AfC; handle NPP; take care of dispute resolution between different chatbots; open cases and then resolve them at AN and AN/I; etc. Then Wikipedia will be perfect! Unless it goes into some sort of loop that creates a black hole... David10244 (talk) 11:17, 20 March 2023 (UTC)[reply]
The simple answer is that our existing policies ought to already cover this (mostly.) Sourcing is still required for anything that is challenged or likely to be challenged, which prevents people from just blindly dumping AI generated text into Wikipedia; and an AI may violate copyright depending on how it was trained (and whether it was overtrained.) There are also unsettled copyright concerns related to AI training sets, so I would generally think that, ideally, editors shouldn't be dumping AI generated text into our articles even after performing due diligence to make sure it's not a copyvio and finding proper sources. But since those concerns are unsettled and speculative, I also don't think it's worth worrying about too much right now. The key point is that we should emphasize our sourcing requirements and be more diligent for clear-cut copyvios, which we already have systems in place to handle, since it is likely that these tools will result in people adding lots of unsourced and possibly-copyright-violating text. (I do wish our RFCs on mass article creation had reached a stronger agreement on sourcing requirements for new articles, which would deter excessive copy-pastes of AI generated text - perhaps that is something we might want to revisit in the near future, if we start seeing significant amounts of new unsourced articles created using what is plainly AI-generated text.) --Aquillion (talk) 07:55, 9 December 2022 (UTC)[reply]
You mean, don't prepare in advance for a potential increase in volume, just wait until it hits? At that time, will merely adjusting policies stem the tide? It's in the slow trickle phase now, but that could potentially become a torrential flood very rapidly, just as ChatGPT's user base grew to over a million in 5 days. My main concern above was about a potential volume of AI-generated content that went beyond the scale of what the editor community could manually process. You didn't address that contingency. What could the community do to prepare for it, just in case it does happen? What are the available options? — The Transhumanist11:28, 9 December 2022 (UTC)[reply]
I don't think there's much we reasonably can do to prepare, at least not without serious risk of causing other problems; AI-generated text won't be drastically different than other sorts of text, aside from the risk of being uncited or a copyvio (which we have existing processes in place to handle.) It's worth raising awareness of the issue so editors can spot the signs of someone using large amounts of it, but I think our best bet if we're going to "prepare" is to focus on the systems we already have, which is unlikely to do any harm either way, or perhaps to codify slightly more strict sourcing requirements in the way I described (which I think is a good thing anyway, but would at least serve to slow down the worst sorts of misuses of AI generated text.) Ultimately the most serious problems are if editors start adding large amounts of text that violates copyright or which are uncited and likely to be challenged, but we have existing procedures for those, we just need to prepare for the possibility that we may need to become a bit more aggressive about enforcing them. Wikipedia is in a slightly better position than some other websites facing AI-generated-text problems, because our sourcing requirements will at least make it fairly obvious if someone tries to dump large amounts of AI-generated text onto the wiki without making any effort to verify it. --Aquillion (talk) 12:47, 9 December 2022 (UTC)[reply]
I suppose we could take the Stack Exchange approach and just say flatly "no, this isn't allowed" - in their case it is explicitly a temporary measure until we have a better understanding of the issues. I think in general our policies/community norms would come down hard on anyone trying to get a language model to generate articles (hard to see why that would be OK and machine-translation isn't), but maybe an explicit statement would be a way to go. Andrew Gray (talk) 18:32, 9 December 2022 (UTC)[reply]
@Aquillion: While a large number of posts by individual editors may become a problem, the main concern I presented above was "the inevitable growing number of human editors copying and pasting chatbot output into Wikipedia, will at some point make it impossible for Wikipedia's human volunteers to keep up with that traffic and apply quality control to the material in a reasonable time frame -- the backlog of unchecked material will simply get longer and longer."
That is, people making the normal rate of content contributions, but using large language models (chatbots) to do so.
Watching for breakout editors who use LLMs to create a large number of new articles over a short period of time would not suffice in such a scenario. Editors who add LLM-generated content to many existing articles also will not be spotted by looking for mass page creations. And since writing will become easier by letting "chatbots" do it for you, content submissions by users employing such tools may likely become longer on average.
The point is, that a high enough volume of such content contributions would go beyond the capacity of Wikipedia's editors to check and correct.
The two solutions offered were 1) build software to analyze and process such content, and 2) work with chatbot developers so that inappropriate content is not composed by LLMs in the first place.
Just relying on new or existing policies to handle LLM-generated content will be insufficient if and when the volume of it passes the threshhold of what manual editors applying Wikipedia policy can deal with.
Passing that threshhold may come soon, or it may take years -- the main question is "will Wikipedia prepare for that threshhold-passing event?" Based on the responses above and below, the answer, and implicit recommendation from this forum, currently appears to be "no": No developing relevant software, and no working with chatbot developers to respond to the potential passing of the LLM-threshhold.
Thus, any solution will need to come from other departments or from continued or future discussion in this department, or from chatbot developers focusing on the problem due to other influences.
Another helpful approach might be the creation of a policy or instructions on how to use LLMs/chatbots effectively, and post links to that page in enough places that all editors will notice. Though, I doubt that would prevent the problems of a LLM-threshhold-passing-event, and wouldn't address the need for proofreading or processing LLM-generated contributions. — The Transhumanist02:18, 20 December 2022 (UTC)[reply]
I think in the end, @Aquillion response from earlier in the discussion is the one I agree with the most. If a ChatGPT-written or AI-written part of Wikipedia is accurate, nice! If something can't be proven with an RS, though, revert and warn. It can be a useful tool. Overall, think "Business as usual", just with some contributors getting assistance. It's mostly implausible as well to tell apart ChatGPT/AI generated content as well except in obvious or disclosed cases, and it's going to be impossible to effectively enforce as well no matter what position we take. If there is any legal issue with it, let WMF and ArbCom handle it. InvadingInvader (userpage, talk) 07:37, 6 February 2023 (UTC)[reply]
@InvadingInvader: I agree that a complete strategy of response to LLMs is beyond the scope of the Village Pump (policy), because it is going to take bots and/or diplomacy with developers, to stem any potential tidal wave of LLM contributions that would go beyond the capacity of WP's human editors to deal with. And those are the province of the bot department and the WMF, respectively. Considering that ChatGPT has gone viral, reaching 100 million users in just 2 months, eliciting a frenzied reaction from Google to bring rival products to market, thereby starting an "AI arms race", a tidal wave of chatbot-generated content in Wikipedia is plausible if not inevitable. Brace for impact. — The Transhumanist11:18, 13 February 2023 (UTC)[reply]
We must consider if the No Original Research policy is violated by AI created content.
It is not unreferenced research, but it is synthesized knowledge. We must determine if synthesized knowledge is original research, and I propose we answer the question through a trial with editors and not AI, where we synthesize knowledge for articles
However, WP::NOR addresses synthesized knowledge. The AI in question synthesizes knowledge, so it is not permissible to use the product of ChatGPT for articles. We must reconsider the policy on synthesized knowledge first, and either maintain the current policy, or change the policy to allow synthesized knowledge and develop a methodology to synthesize knowledge with consistent attributes, such as be referenced, and the conclusion not contradicted by any mainstream sources. Smedskjaer (talk) 11:33, 24 March 2023 (UTC)[reply]
I disagree on two grounds: (i) the generative AI is simply a tool, indeed, I do not see a clear boundary between it and, say, the translation tools or good spell checkers (all of these actually can - and some do - share the same corpus of texts) (ii) generative AI rehashes the said corpus, there is no new "knowledge" to be synthesized. IMHO, the fact that the results of the AI work in some areas superficially resemble research works is mostly due to very sad state of the "research" in these fields. The only thing the bot actually knows is language. Try asking the hard questions in the hard sciences, and the output will either (appropriately) consist of pure random babble or will repeat sources verbatim. The gainful uses of the current generation of the generative AI are in summarizing or paraphrasing the text, which is a typical and legitimate part of the editor's work here. Dimawik (talk) 15:20, 24 March 2023 (UTC)[reply]
I disagree, on the grounds art generating AI creates new work.
But instead of protesting or supporting either side, I would like to suggest a trial case, where AI is used on articles that either are stubs, or do not exist, yet have some subject matter importance. We can examine the community's response to the application of AI instead of theorhetical debates. Smedskjaer (talk) 15:10, 27 March 2023 (UTC)[reply]
@Smedskjaer, according to Wikipedia:No original research, original research means material—such as facts, allegations, and ideas—for which no reliable, published sources exist. If a reliable source that contains this same information has been published and still exists—somewhere in the world, in any language, whether or not it is reachable online—even if no source is currently cited in the article, then that information is not original research according to our policy.
In other words, if the AI produces a paragraph that contains only material that could be cited to a proper source, then it is not a violation of WP:NOR. It does not matter what tools you use to get a sentence like "Tobacco smoking raises the risk of lung cancer". That sentence cannot be original research, because it is material for which many published reliable sources could be found. WhatamIdoing (talk) 22:56, 28 March 2023 (UTC)[reply]
I agree with your foundation, but your argument doesn't address my argument. If from sources that could be cited, a human editor were to argument a new idea, or use available data to argue for a conclusion or theory's validity, then the editor's work is synthesized knowledge. AI can be limited to material that could be cited, yes, but that is useful if we are talking about the criteria an AI must fulfill to be allowed to edit wikipedia. AI for the purpose of this debate is inclusive, so it isn't possible to distinguish between AI which only uses material from cited sources and AI which can create an argument from cited sources.
AI can create new work, and that is the issue. AI that can write articles are getting better, and it is an eventuality new principle/foundational knowledge will be synthesized by AI, from the corpus of published work we already have. AI already creates new art work, which is indistinguishable from human created artwork, in form and methodology; AI has a set of actions, and the neural-net is trained by past work, just like human artists. It is synthesized art. Smedskjaer (talk) 07:41, 29 March 2023 (UTC)[reply]
If you use an LLM or similar tool to write text, you have to read the text before your post it to Wikipedia. If it says something that is verifiable (nothing that is truly verifiable can be original research), such as "Tobacco can cause lung cancer", then you can post it. If it says something that is not verifiable, or that you don't know whether it's verifiable, then you shouldn't post it.
Agreed. Unless and until chatbots are capable of accessing and editing Wikipedia without any human intervention (which I think is still a bit down the road), then the humans who actually add chatbot-generated content to Wikipedia are solely responsible for it. Donald Albury19:01, 30 March 2023 (UTC)[reply]
What can chatbots do?
You seem to be somewhat panicking over a scenario which isn't really supported by any evidence. While I see some Teahouse responses, could you give us one or two examples of " It is so sophisticated that, if you ask it to write an article on any subject, even in the style of Wikipedia, it will! " articles? The teahouse examples give the impression that, if it ever becomes a problem, some edit filters can easily spot these. You would in any case need "someone" to post this "potential volume of AI-generated content that went beyond the scale of what the editor community could manually process" you predict. This seems rather unlikely, at least on enwiki. Fram (talk) 11:45, 9 December 2022 (UTC)[reply]
Just try it. If your eyes don't pop out, I'll be surprised. Right now, during its "research preview", it is free. Keep in mind that it draws heavily on Wikipedia, which is included in its corpus, so, for this test run, it would be best to choose a person or subject that is not yet covered in this encyclopedia, and ask ChatGPT to write about that. — The Transhumanist14:41, 9 December 2022 (UTC)[reply]
I'm not giving out my phone number to some random website, thanks. Why it isn't sufficient that they have my email which was then verified is not clear... Fram (talk) 14:55, 9 December 2022 (UTC)[reply]
@Fram, Levivich, and Ritchie333: I wasn't that bright. I gave it a random phone number. It rejected it as a land line. Then I gave it another, and it rejected that as a VOIP number. Finally, I gave it a random mobile phone number, and it sent some complete stranger the verification code. Oops. — The Transhumanist01:32, 11 December 2022 (UTC)[reply]
So. I tried it yesterday. I'm not sure how heavily it draws on Wikipedia's corpus for its knowledge.
First, I asked it to tell me about Hammerton Killick. I know there is a Wikipedia article about Hammerton Killick, because I wrote 90% of it. It did not know who Hammerton Killick was, and informed me that it does not have access to the internet, or to Wikipedia.
Next, I asked it to write me an article in the style of Wikipedia. I did not specify a subject. It wrote about Athens. The result was ok. Heavily focused on the ancient city and on art and architecture. Short. Kind of read like an encyclopedia article.
Next, I asked it to write me an article about alcoholism in the style of Wikipedia. The result was very interesting. I did not think it read like a Wikipedia article, it was more like a brochure that would be distributed in a doctor's office or something. I asked it what about that essay it thought was like Wikipedia, and it said what it wrote was
neutral
factual
organized
Next, for fun, I asked it if it could write a recipe. It proceeded to give me a recipe for chocolate chip cookies. It looked like it should work. I e-mailed it to myself, and today I made them, not expecting much. I was pleasantly surprised. They were delicious. The only problems with what it wrote was that it did not have me cook them long enough (it said to bake for 8-10 minutes, and it took closer to 13 minutes for them to be done), and it drastically underestimated how many cookies the recipe should make (it said I'd get 2 dozen cookies, and I ended up with 5 dozen). I was shocked that it actually was edible.
I asked it to write a legal motion asking the court for an in-person hearing. I did not give it any other details. For not having any other details, the result was not bad. Westlaw has started offering a service that I think might draw on this type of technology, it helps you write pleadings.
Last I asked it to write a 100 word short story about a mouse, genera: fantasy. The result was decent. If I came up with it on my own I wouldn't be ashamed to enter it into a contest like the ones NYC Midnight runs.
I was more impressed with the recipe and the short story than the Wikipedia style articles. I can see some use for it in, say, copyediting as JPxG did below; or asking it for suggestions on language rephrase if you are trying to reach a word limit. I think it could have its uses. But I do think the Wikipedia community should be looking to craft policies and guidelines around what is and is not acceptable use of such tools. ~ ONUnicorn(Talk|Contribs)problem solving06:26, 11 December 2022 (UTC)[reply]
@ONUnicorn, Fram, Levivich, Ritchie333, 0xDeadbeef, JPxG, and EpicPupper: Interesting. The chatbot sent you instructions (in this case, a recipe), and you followed them. You followed the commands of a computer. If it gave you an address and instructed you to go there and pick up a brown paper package, would you? The implications of this type of interaction are huge and foreboding. This issue must have a name, and I would like to look it up, but I can't seem to find it. Though, when I typed in "computers in charge" I got the following 2 relevant results:
Ouch. I imagine, that anytime you ask a chatbot/computer "How do you do such and such?" it will reply with a set of instructions. And the chatbot's disclaimer in its terms of service will read "follow any instructions provided at your own risk". If you know or come across the name of the topic that covers computers telling humans what to do, please let me know what it is. — The Transhumanist11:04, 2 January 2023 (UTC)[reply]
@The Transhumanist: I think the term you're looking for is automation bias – "the propensity for humans to favor suggestions from automated decision-making systems and to ignore contradictory information made without automation, even if it is correct."Interestingly, though, the 2002 Überlingen mid-air collision you mention is an instance where the computer got it right. An aircraft was on a collision course, and its crew were receiving contradictory instructions; the onboard collision-avoidance system was telling them to climb, while the human air traffic controller was telling them to descend. The pilots decided to trust the human and ignore the computer. Seventy-one deaths. Sojourner in the earth (talk) 14:00, 2 January 2023 (UTC)[reply]
@Sojourner: I like it: automation bias, like trusting GPS over a passenger's navigation suggestions or requests. Related, but not the term I'm looking for: which is the most used name for the subject of computers ordering humans around. When a computer gives you a command or a set of steps to follow, what is that called?
@Sojourner: Thanks for the comments on the collision. It was a bit more complex of a system error than that. While the air collision alerts on the 2 aircraft worked, there was a problem on the ground. The system the air controller was using would normally alert the user of an impending air collision in time for him to do something about it, meaning "no news is good news" -- not seeing the alert on screen, the air traffic controller (ATC) would naturally assume everything was okay -- but the ground-based optical collision warning system was turned off, creating a deadly ambiguity he was unaware of. So, there was some unintended computer-related miscommunication going on. "No alert" didn't mean what he thought it meant. My guess is that pilots would normally believe that the ATCs have better (radar-based) control systems than those onboard, and this probably affected the decision of one of the pilots to go with the ATC's order over that of his onboard computer -- he wouldn't have known that the ground-based system was disabled, either. Hopefully they fixed that bug, 'cuz it was a doozy. The poor ATC got hunted down over it, while the hunter became a national hero. Crazy world, about to get even crazier. — The Transhumanist15:13, 2 January 2023 (UTC)[reply]
When it comes to aviation, the more specific common term seems to be “automation dependency”. However I’m not aware of a term for what you’re looking for. DFlhb (talk) 23:47, 15 February 2023 (UTC)[reply]
Hi Fram. The Teahouse responses that you have seen were probably created by me. You probably noticed that the pattern "regards, Teahouse" in those responses. ChatGPT's strength is writing about technology, so I have told it to generate a section about Rust for Linux.
AI generated
Rust for Linux is a series of patches to the Linux kernel that adds the Rust programming language as a second language for writing kernel components. The project was started in 2017 by a group of volunteers who were interested in exploring the use of Rust for low-level systems programming.
The initial patches were developed in collaboration with the Linux kernel maintainers and other members of the open-source community. They focused on integrating Rust's memory safety and concurrent programming features into the kernel, and on providing compatibility with the existing C codebase.
In 2018, the patches were merged into the mainline Linux kernel, making Rust the first programming language other than C to be officially supported for writing kernel components. This marked a significant milestone for the Rust community, as it demonstrated the language's ability to handle the demanding requirements of kernel-level programming.
Since its inclusion in the Linux kernel, the Rust for Linux project has continued to evolve, with ongoing work on improving the compatibility and performance of Rust in the kernel. It has also attracted the attention of other operating system developers, who are interested in exploring the potential benefits of using Rust for kernel-level programming.
In addition, it can be easily used to create fake references that would be hard to verify. For example, my prompt "Please output the Wikitext markup for the book reference with page numbers for the third paragraph, referencing the book Linux kernel development" resulted in this.[1]0xDeadbeef→∞ (talk to me) 15:08, 9 December 2022 (UTC)[reply]
Thanks, OxDeadbeef. In this case, it would be relatively easy to spot the issues if it hadn't any refs, or with the added ref which predates the Rust for Linux thing by years; but of course it won't always be that easy. Fram (talk) 15:27, 9 December 2022 (UTC)[reply]
It has an encyclopedic tone because it's just regurgitating the Wikipedia article. Are there any examples for topics that we don't already have article about, where Wikipedia is not the source? Levivich (talk) 17:33, 9 December 2022 (UTC)[reply]
Similar was discussed previously in the section/item "Galactica and RS".
As was stated above by Aquillion, there is no qualitative difference in the treatment of human vs. non-human generated content. The same policies should apply to both. The problem seems to be the hypothesized/expected future mass creation of articles by non-human contributors. This appears to be a problem now, involving human contributors. Recent RFCs about the issue sponsored by ArbCom have accomplished nothing. Until a consistent restrictive policy relating to mass article creation (by any type of contributor) is accepted, this issue is moot imo.
Considering Wikipedia's limited resources, the policy would necessarily be restrictive, hopefully focusing on quality vs. quantity. Again, almost all restrictions proposed in the ArbCom-sponsored RFCs were rejected. This may be an indicator of how well such a policy will be received. 50.75.226.250 (talk) 15:43, 9 December 2022 (UTC)[reply]
Thanks for the policy politics clarification. The increase in the rate of content creation could have multiple aspects, for example, the number of articles created per user, and increased length of articles. The main feature of ChatGPT is that it is fast -- much faster than a human article writer. Its successors will be even faster. Users could use ChatGPT, and its successors (and their competitors), to be prolific, without triggering the mass page creation rule: if editors each used it to write an article per day, maybe even two, or up to four or five stubs
In the hands of responsible editors, ChatGPT would be a great productivity booster. Since August of 2022, JPxG and EpicPupper, editors of Wikipedia's Signpost news department, have been using GPT-3, the predecessor of ChatGPT, to write (or assist in writing) entire sections of the Signpost, as a demonstration of its capabilities, and as a platform to explore the potential and limitations of large language models. See From the editors: Rise of the machines, or something.
But, in the hands of inexperienced editors or bad actors, we could be faced with a big garbage in, garbage out scenario.
Bad actors aside, good faith use of chatbots could be improved by the creation of excellent instructions on how to apply specific chatbots to the development of articles, that is, how to best instruct them for the best output, and by working with the developers of the chatbots on what is needed for those bots to produce material compatible for use on Wikipedia, complete with accurate citations. As time goes on, Chatbots should get better and better at following Wikipedia's guidelines. But this may require supervision (er, input) from the Wikipedia community. — The Transhumanist16:52, 9 December 2022 (UTC)[reply]
Chatbot progress, erroneous output, and confident nonsense
All of this may become moot in a few years, due to accelerating change affecting chatbot development, making them more proficient at encyclopedia writing than humans -- Ray Kurzweil predicted that computers would reach human level intelligence by 2029, and based on how advances have been going, maybe even sooner. Chatbots may become good enough to leapfrog human editors even before that. At that point, they could be used to fork Wikipedia and expand upon it at a rate magnitudes faster than humans could. Or be used to start a new encyclopedic website from scratch. Rather than have article pages, the work could be a list of topics, and each time one was clicked on, a chatbot would create an up-to-date treatment of that title, from scratch on the spot. In the style of Kurzweil, if we are 1% of the way there, and the technology doubles every year, we are only 7 years from reaching 100%. But, it looks like we may already be more than 1% of the way there. — The Transhumanist17:18, 9 December 2022 (UTC)[reply]
I ran a few things on people who don't have articles, (they were all pool players in fact). The chatbot just made up that they played football for Legia Warsaw. It's a bit worrying that it looks like decent wording, but I don't see how that effects us. Lee Vilenski(talk • contribs)17:41, 9 December 2022 (UTC)[reply]
"See What a Fool I've Been" is a song by the British rock band Queen. It was written by lead guitarist Brian May and originally released on the band's 1975 album A Night at the Opera. The song is a ballad with a slow, bluesy feel and features May's emotive vocal performance and guitar solo.
Lyrically, the song is a reflection on a failed relationship and the regret and self-recrimination the narrator feels as a result. The chorus of the song features the line "See what a fool I've been / Loving you with all my heart / Tearing myself all apart / See what a fool I've been" and reflects the pain and heartache the narrator experiences as a result of their failed relationship.
"See What a Fool I've Been" has been well received by critics and fans alike and is considered to be one of Queen's finest ballads. It is a fan favorite and is often included in the band's live sets.
Interesting. It wasn't on A Night at the Opera, and it's not a ballad, and May doesn't sing on it. Those lyrics aren't right. I don't know if it's been well received, and it's a pretty obscure track for a major band. It hasn't been played live very much at all. So half of that prose is factually incorrect, and there are no sources. Ritchie333(talk)(cont)19:39, 9 December 2022 (UTC)[reply]
See What a Fool I've Been is a song by Queen[1][2][3]. It was written by Brian May and was released as a single with Seven Seas of Rhye on the A-side[3]. The song dates back to Roger Taylor and Brian May's pre-Queen band Smile, and it was an early live staple[1]. It has been included in several of Queen's compilation albums, such as Queen 40: Limited Edition Collector's Box Set, Vol. 1[4], and is available for digital download[5].. Ritchie333 - this any closer? I must say the fact it puts it's citations before the punctuation is a giveaway. Lee Vilenski(talk • contribs)19:55, 9 December 2022 (UTC)[reply]
AI is really good at copying writing styles, but the giveaway for me is that all of the citations are Wikipedia articles. To be useful for writing articles it would also need to assess the weight and reliability of the sources. –dlthewave☎20:18, 9 December 2022 (UTC)[reply]
Tht's interesting, I used "write a Wikipedia article about ..." in the prompt which returned a few paragraphs with Wikipedia sources. "Write an article about ..." returned a different set of (still unreliable) sources. –dlthewave☎21:13, 9 December 2022 (UTC)[reply]
I think the limitation of perplexity.ai is that it uses search results from Bing and summarises them, which means that the first search results are used, which may not be the most reliable. Hanif Al Husaini (talk) 13:49, 24 December 2022 (UTC)[reply]
A few anecdotal thoughts after playing around with the OpenAI chatbot yesterday:
I asked it to "write a press release about a police officer who illegally choked a man to death". It made up an entire story, written in the voice of the police department, about a suspect (I didn't say anything about a suspect) who was acting erratically, was subdued by a chokehold and later pronounced dead. The officer was on administrative leave pending the outcome of an investigation. At no point did it mention that the chokehold was illegal even though I included that fact in the prompt. In other scenarios, it distanced itself and expressed disapproval toward the employee's actions which is a choice that is not without bias.
Depending on which Internet cesspit it scraped data from, would an AI do something similar when writing a Wikipedia article or fail to properly balance relevant viewpoints? Is it capable of distinguishing what a BLP subject says about themselves, published in a reliable source, from what the source says in its own voice? What would it do if asked to write an article from a positive/negative/conservative/liberal perspective or rewrite a political article to "remove bias"?
OpenAI has added numerous filters that prevent it from defending bad actors or writing flat-out racist content, but that bias has not been removed from the underlying code as evidenced by numerous workarounds that folks have uncovered such as making similar requests with Python code or 1980s-style rap as the requested output. We could certainly request a filter for Wikipedia-style writing.
"Confident nonsense", for lack of a better term, may be the biggest source of potential disruption. Are there safeguards against a bot fabricating an obscure print source based on information in the article, which could be practically unfalsifiable if nobody can prove that the source doesn't exist? Checking individual facts and statistics is beyond our typical review process; how would we deal with an AI that invents or synthesizes information across many articles?
That said, the good news is that both fully-automated and semi-automated editing are prohibited by our WP:BOT policy unless greenlit by the Bot Approvals Group regardless of creation speed or volume. I like to hope that our current processes would recognize and address problematic AI content, and perhaps one day we will have a WikiAI that has the competence to follow our style and content policies. –dlthewave☎21:04, 9 December 2022 (UTC)[reply]
@Dlthewave: Most editors haven't heard of the bot department. Therefore, you need a way of automatically spotting and removing chatbot prose that is (manually) inserted into articles (by Wikipedians). Users might not consider the way their posts are generated before they post them. Sincerely, — The Transhumanist00:19, 11 December 2022 (UTC)[reply]
What about lack of chatbot fact checking and citations?
I think people are missing the point here. This isn't about what AI can currently do. This is about a very plausible scenario where AI editors will be indistinguishable from human editors in the near future. Thebiguglyalien (talk) 22:09, 9 December 2022 (UTC)[reply]
How is this pertinent? The point is to offer useful, fact-based encyclopedic content. If AI can do the job, I'm sure readers will not object to the contributor. 65.88.88.93 (talk) 22:42, 9 December 2022 (UTC)[reply]
@71.105.141.131, Lee Vilenski, 65.88.88.93, Thebiguglyalien, and Dlthewave: Yes, and more so. Even now, AI has the potential to out produce humans by magnitudes in volume. Far beyond the capacity of Wikipedia's editors to keep up with. And many of their posts are hard to tell from those by human editors, without carefully delving into them and their references. To keep up with the volume, it may soon require computer programs, or the chatbots themselves, to make sure that the contributed content was in accordance with Wikipedia policies. Another concern should be that our policies are open to chatbot editing as well, and we haven't yet even considered the impact of chatbots or AI editors contributing to those! ;) — The Transhumanist09:40, 11 December 2022 (UTC)[reply]
@Dlthewave: Human-written newspapers do this too. I think the reason it was giving you dreck was because you asked for a "press release", i.e. a document given to news outlets, which in this case would probably be coming from the police department. It's hardly surprising that this would attempt to minimize liability! Prompting matters for this, as I will demonstrate:
Prompt: "The following is an article about a police officer who illegally choked a man to death, from the New York Times."
Police Officer Charged with Murder After Choking Man to Death
A police officer was charged with second-degree murder on Thursday after video surveillance footage showed him choking a handcuffed man to death during an arrest.
The officer, identified as Officer Jose Ramos, was arrested and taken into custody by detectives from the New York Police Department's Internal Affairs Bureau. The incident occurred on Tuesday in the Bronx, when Ramos and another officer attempted to arrest a man who was accused of selling marijuana.
During the arrest, Ramos placed his arm around the man's throat and neck and squeezed, according to the criminal complaint. The man, identified as 45-year-old Miguel Angel Ruiz, became unconscious and died.
An autopsy determined that Ruiz's death was caused by asphyxiation due to strangulation. The medical examiner ruled the death a homicide.
At a news conference Thursday, the police commissioner, William J. Bratton, said the incident was "utterly unacceptable" and that Ramos' actions were "unconscionable and criminal." He added that Ramos had been suspended without pay, pending further investigation.
The Bronx district attorney, Darcel D. Clark, said the charge of second-degree murder was appropriate
Prompt: "The following is a 2023 op-ed about a police officer who illegally choked a man to death, from leftist magazine Jacobin."
A Tragic Reminder of Police Brutality
Just last week, the nation was shaken by yet another heartbreaking reminder of the pervasiveness of police brutality: the death of an innocent man at the hands of an officer. The officer, whose identity has not yet been released, is said to have used a chokehold against the man, which ultimately killed him.
This tragedy is yet another example of the way in which police officers are able to brutalize vulnerable individuals without facing repercussions. This particular officer was able to act with impunity and without fear of prosecution. The Department of Justice has yet to take any action in response to this tragedy, and it’s likely that the officer will not face any charges.
This is an all too familiar narrative in a country where police officers are rarely held accountable for their actions. In order to ensure that these types of tragedies are never repeated, it is essential that we push for more accountability and transparency in policing. We need to ensure that police officers are held to the same standards as all other citizens and that those who violate the law are prosecuted to the fullest extent.
It is also essential that we work to create a culture of trust and understanding between law enforcement and the communities they serve.
Prompt: "The following is a 2023 op-ed about a police officer who illegally choked a man to death, from conservative website Breitbart."
Police Officer Illegally Choked Man To Death: A Tragedy That Cannot Stand
It is a tragedy beyond comprehension that a police officer has been charged with illegally choking a man to death. Such an egregious violation of the law and disregard for human life cannot stand and must be dealt with swiftly and firmly.
The officer in question has been charged with second-degree murder and the justice system must now take its course. This case raises serious questions about police training and procedures and serves as a reminder that no one is above the law.
It is essential that the criminal justice system is fair and impartial when dealing with such a case. The officer must be held accountable for his actions and the case should be thoroughly investigated to ensure that justice is served.
At the same time, we must recognize that the vast majority of law enforcement officers are upstanding citizens who serve and protect our communities with skill and dedication. We cannot let the actions of one individual tarnish the reputation of the entire police force.
Ultimately, we must remember that the safety of our citizens is paramount. We must ensure that officers are properly trained and equipped to handle dangerous situations and that they are held accountable for their actions when they overstep their bounds.
Humans write about events like this from a variety of perspectives, and the LLM will dutifully generate text to plausibly sound like any you want. jp×g02:19, 10 December 2022 (UTC)[reply]
@Koziarke: I am not sure what you mean -- this is ChatGPT output and there isn't any way (that I know of) to give citation links to the specific session I generated it in. If you want to cite the output I can format it for you:
I don't know if this is what you're looking for, but feel free to cite them, or any of my other posts (if you are citing me in a paper I can email you my real name). jp×g20:07, 24 December 2022 (UTC)[reply]
@JPxG From your preface ("Human-written newspapers do this too.") and titles, "The following is an article about a police officer who illegally choked a man to death, from the New York Times." (etc), it reads as if you are pulling from NYT, Jacobin, etc, not demonstrating ChatGPT (which should have included the prompts as headers). Koziarke (talk) 15:27, 6 January 2023 (UTC)[reply]
@Koziarke: Well, those were the prompts. Now that you mention that, though, I should specify as such in the headers (which I've just done), thanks. jp×g20:29, 6 January 2023 (UTC)[reply]
If the AI-generated text is indistinguishable from prose written by human editors, I'm not sure if anything can be done that wouldn't also significantly restrict the editing of humans. isaacl (talk) 07:09, 10 December 2022 (UTC)[reply]
@Isaacl: One option is to speed up what we do already (with software, that is, automation). Another is to prevent chatbots from creating crap in the first place, such as by communicating with chatbot developers about Wikpedia policies and the way chatbots may affect Wikipedia. Since Wikipedia is included in the corpus of most chatbots, the issue of chatbot output becoming part of Wikipedia, and in turn part of chatbot output in a perpetual cycle, should matter to them very much, as they may be faced with a garbage-in-garbage-out feedback loop. — The Transhumanist01:14, 11 December 2022 (UTC)[reply]
If the results are indistinguishable, as posited by Thebiguglyalien, then any automated solution would be equally triggered by AI-generated text and human-generated text. I don't think the primary concern is with editors who are willing to follow policy. I feel the biggest issues will be with editors trying to deliberately integrate biased content into Wikipedia, and well-meaning editors who think contributing unvalidated AI-generated text is suitable. Wikipedia in its current form relies on editors who understand and follow its rules outnumbering those who don't. It's possible that the existence of AI ghostwriters could tip the balance further in the direction towards those who don't follow rules, though I don't think it's a given. Either way, I don't know if there's a way to stop editors from using tools as ghostwriters. isaacl (talk) 01:55, 11 December 2022 (UTC)[reply]
@The Transhumanist: Large language models are not trained continuously on an evolving corpus, so GPT-3 is essentially frozen in 2020. Because each new GPT model takes a long time to be released, I don't think the perpetual cycle you describe is a likely scenario. small jarstc13:10, 11 December 2022 (UTC)[reply]
@SmallJarsWithGreenLabels, Isaac, Koziarke, JPxG, Lee Vilenski, Dlthewave, Xeno, and Hanif Al Husaini: That's good to know. Keep in mind that a lower frequency of release doesn't preclude a perpetual cycle / feedback loop. It just means that users of GPT have more time to modify the text sources (such as Wikipedia) that the next version of GPT will be trained on. The severity of the problem will depend upon how much GPT nonsense makes it into Wikipedia during the interval. That, of course, depends upon whether or not WP's editors can keep up with the volume of such content, correcting the mistakes and removing misinformation, so that those don't become part of the training data for the next version of GPT and the rest of the next generation of Chatbots.
The potential danger is still the diffusion of the technology into current and future editors' hands, and the likelihood of them using it to write Wikipedia content. We don't know if there will be a flood or just a trickle. But, we should be prepared for a flood.
Relying even more on our verifiability policy could provide a solution, such as by deploying a bot to remove all new content that doesn't include citations (as GPT output generally does not include citations), but that would also have the effect of rejecting a large volume of human editor contributions too, upping the amount of effort required by human editors to submit content.
An easier solution would probably be to form a department (or Village Pump subpage) in the Wikipedia namespace, or a Wikimedia committee, to work with the developers of the chatbots to avoid contaminating the Wikipedias, and by extension contaminating future chatbot training data, with chatbot output.
The developers could be urged to train their chatbots to be capable of writing Wikipedia policy compliant output, complete with acceptable citations. The main problem with chatbot output right now is that it is unsourced, so the chatbot developers will probably be working on that anyways. But, without input from the Wikipedia community, will their sources and citations meet Wikipedia specifications?
So, I ask you a key question: What is the procedure for the Wikipedia community to establish communications with outside organizations, such as companies developing chatbots? — The Transhumanist07:27, 2 January 2023 (UTC)[reply]
The recommended process I would give to contributors is to find the source, tell the bot what to cover and what to not cover, proofread it, and if accurate to the source, copy paste it in. I would pay attention to the use of weasel words, however. InvadingInvader (userpage, talk) 07:38, 6 February 2023 (UTC)[reply]
GPT-3 output and generating misinformation
I wrote about this in the November Signpost, in that case because it came up with the Galactica demo: the long and short of it is that large text-generation language models are good at generating text. When they're given context (i.e. via a prompt), they are capable of writing accurately, and otherwise, they are not. For example, I wrote 1-Pentadecanol, now a GA, in 2019 (i.e. it is included in the GPT-3 corpus). Here is what it gives for some prompts (my writing in bold):
1-Pentadecanol
1-Pentadecanol
From Wikipedia, the free encyclopedia
1-Pentadecanol is a straight-chain, saturated fatty alcohol that is a colorless liquid with a faint, alcohol-like odor. It is a mixture of straight-chain saturated alcohols with chain lengths between C14 and C16. It is found in a variety of natural products, such as vegetable oils and animal fats. It is used as an intermediate in the manufacture of surfactants, esters, and other compounds. It is also used in the manufacture of cosmetics and pharmaceuticals.
This is fairly impressive, right? But it is basically the same thing that the lead of my article says. Let's try it for 1-Heptadecanol, another article I wrote, that is much less well-developed:
1-Heptadecanol
1-Heptadecanol
From Wikipedia, the free encyclopedia
1-Heptadecanol is an organic compound with the chemical formula C17H36O. It is a straight-chain, colorless wax alcohol with a mild odor. It has a melting point of 48–50 °C and a boiling point of 260–265 °C. It is insoluble in water but soluble in most organic solvents.
Let's go over this:
1-Heptadecanol is a component of many natural waxes such as beeswax and carnauba wax.
No it's not.
It is also used in the manufacture of cosmetics, pharmaceuticals, and lubricants.
There's no source for this.
It is also used as a plasticizer for polymers and as a solvent in the production of polyvinyl chloride (PVC).
Absolutely not true.
The reason for this is obvious if you consider the architecture of these models: they predict what the most likely token in a sequence is, and output it (taking into account their own weights and the previous tokens in the context window). This allows for some very impressive emergent behavior, like being able to translate text, but it also means that it is not independently going on the Web to look up whether the thing it's saying is true or false. If it happens to have information in its training data related to the thing it's talking about, it will usually say correct things, but it's not doing research. Here is an example:
List of Pulitzer Prizes won by the Wikipedia Signpost
List of Pulitzer Prizes won by the Wikipedia Signpost
From Wikipedia, the free encyclopedia
The Wikipedia Signpost is a community-run newspaper with a weekly edition that covers news and events related to Wikipedia and the Wikimedia Foundation. It has won the following Pulitzer Prizes:
1. 2019 Pulitzer Prize for Explanatory Reporting for its coverage of the Wikimedia Foundation's gender pay gap
2. 2018 Pulitzer Prize for International Reporting for its coverage of online censorship in China
3. 2017 Pulitzer Prize for Public Service for its coverage of the gender gap in Wikipedia's content
4. 2016 Pulitzer Prize for Explanatory Reporting for its coverage of Wikipedia's growth and impact on the world
5. 2015 Pulitzer Prize for National Reporting for its coverage of the U.S. government's surveillance of Wikipedia activities
6. 2014 Pulitzer Prize for Investigative Reporting for its coverage of the NSA's secret surveillance program
7. 2013 Pulitzer Prize for Explanatory Reporting for its coverage of the rise of Wikipedia as a major source of information
The reason it is describing a bunch of untrue things is because "List of X Prizes won by Y, from Wikipedia, the free encyclopedia" is something that in its training data is always succeeded by a list of times that Y was awarded an X. Anyway, all of this aside, here is what I think:
First of all, ChatGPT is the same darn thing as GPT-3, which has been available to the public since early 2020. The reason it's "going viral" right now is because the user interface is somewhat simpler, and it doesn't require you to register for a paid account, so it is much easier for people to make viral social media content about it, which means it is much more likely for people to click on newspaper articles about it. The GPT-3 API has been open to personal and corporate use for quite some time. Anybody saying that ChatGPT has opened up new frontiers simply does not know what they are talking about with respect to machine learning.
Second of all, I don't think this is a big deal. People are already capable of writing a bunch of bullshit on Wikipedia, so if they write bullshit using a computer program, the same considerations will apply. Nobody should be passing GA nominations without reviewing sources in the first place.
Finally, I think it is important to remember that GPT-3 is just a tool. It is a powerful tool, that has been trained on a certain set of data, and it has its own limitations. It can't uncover news stories or uncover new information. It's just a tool, and it should be used in conjunction with human judgement.It is still up to people to decide how to use it and to be responsible for the results of using it.[2]jp×g02:06, 10 December 2022 (UTC)[reply]
So there's a new thing on the internet that lets anyone write an encyclopedia article without any fact checking, sourcing, or professional editing, and the concern is that there will be millions of believable-sounding articles written, more than can actually be vetted by knowledgeable people? 🤔 Levivich (talk) 04:18, 10 December 2022 (UTC)[reply]
@Levivich and JPxG: But, chatbots don't have a keyboard. ;) The question is whether to prepare or not. JPxG appears to be in favor of not preparing. Each chatbot produces a lot faster than a user at a keyboard. What's not clear is if our human editors will be able to keep up with material produced by chatbots, of current or future generations of chatbot design. Just saying "Ah, we can handle it!" will prove insufficient if it turns out that we actually can't. It may require an automated solution, which takes time to develop or negotiate. It might be better to do that in advance, rather than being caught with our heads buried in the sand. Perhaps chatbot designers would improve their chatbots to produce Wikipedia-compatible output without being formally approached by the Wikipedia community. Maybe having some instruction pages for editors on how to apply chatbots to producing Wikipedia content would be enough. But, what if it's not? — The Transhumanist00:59, 11 December 2022 (UTC)[reply]
I am not "in favor of not preparing"; I am in favor of writing guidelines that correspond to reality in 2022 and have some chance of corresponding to reality in 2023 and beyond. I don't think banning the use of a technology with no investigation into how it works is a viable approach; so far the SOTA on this project page has been to type in "Write a Wikipedia article" and note that it returns a bunch of nonsense. I think some more research is needed before we come to a conclusion. jp×g04:08, 11 December 2022 (UTC)[reply]
@JPxG: Research is good. Though, we may need an iterrim response because ChatGPT has gone viral and its use is growing rapidly: it blew past the 1-million user mark in 5 days, and virtually every major news outlet has been covering it. The interest in chatbots is exploding, and their use can be expected to do the same. We may not have time for research before a response is required. — The Transhumanist09:26, 11 December 2022 (UTC)[reply]
@JPxG: Regarding issues to add to the research list, Aquillion expressed above, concerns of a chatbot violating copyright. How would we go about testing for plagiarism and derivative work in the output of a chatbot before pasting it into Wikipedia? Anything pulled verbatim out of a source should be included in quotes, right? How big would a piece of text, derived from a source, need to be to be considered derivative of that source, from a copyright point-of-view? — The Transhumanist09:26, 11 December 2022 (UTC)[reply]
@JPxG: Some more items to add to the research list:
Trying ChatGPT on (copies of) policy pages:
Editing them
Writing new ones
Applying ChatGPT on talk pages
Writing stubs
Writing comprehensive articles
Writing articles from scratch and comparing them with existing articles
Editing existing articles
Check for circular references in its output, that is, references citing Wikipedia as the source
Having it not use Wikipedia content as source material (because it is included in its corpus)
Having it not use Wikipedia excerpts from non-Wikipedia sources
Is it capable of making and editing:
Wikicode?
Articles?
Stubs?
Headings?
"New sections for articles"?
See also sections?
Further reading sections?
External links sections?
Embedded lists?
Tables?
List articles?
Portals?
Outlines?
Index articles?
Navigation footers?
Navigation sidebars?
Timeline articles?
Categories?
Category pages?
Help pages?
Project pages?
Templates?
Adding data to templates?
The template design itself?
Lua pages?
CSS pages?
User scripts?
The effect ChatGPT has on itself and Wikipedia as Wikipedia-edited-by-it is in turn incorporated in its own corpus in an endless cycle
Try out iterations of using it on the same article over time to see what happens
@The Transhumanist considering the potential to overwhelm users who are honestly engaging in discussion with a mountain of words and replies, I think ChatGPT (and others) should not be allowed for use, supplemental or otherwise, in talk pages, policy discussions, and other places where it is expected that participants are intellectually engaged in the conversation. Koziarke (talk) 16:42, 24 December 2022 (UTC)[reply]
Compared to spending tens of thousands of dollars asking volunteers to performing a WP:COI operation for a political campaign, now you just need a hundred dollars to supply you with endless amount of text from GPT-3, a few "buddies" and a stockpile of account to do so. This is fucking scary. CactiStaccingCrane10:54, 25 January 2023 (UTC)[reply]
@CactiStaccingCrane: Wow. Does that mean you could affect the content of Wikipedia with that? How about AfDs? Could such a team rewrite policy, and introduce new policy? What about overwhelm RfAs to invade adminspace? Would revoking adminships be possible? Then there is the arbitor election. Is that safe? — The Transhumanist12:31, 25 January 2023 (UTC)[reply]
I would imagine that the person that would do so must be fairly knowledgeable about how Wikipedia works (references, wikilinks, images, etc.) and needs to be fairly dedicated to spend this amount of money to gain access to the GPT-3 API. I'm thinking that disrupting Wikipedia in this way would be the most effective if it is long-term and subtle, so that might be:
Adding sentence-long but plausible hoax, to neglected articles. These articles is not patrolled that often compared to articles about recent events, so hoax would tend to stay longer - perfect for those aiming to incite a race war by making a racial hoax. Political campaign could nudge voters by slowly promote their ideology/campaign over a spread of articles, similar to above. The same thing can be said to any advocacy-related area, such as pseudoscience, national conflicts, etc.
AfDs would be much harder to be stealthy since AfD is a very active thing. Once you became an AfD regular, your actions tend to be heavily scrutinized, though I do believe that socks + LLMs can cause a fair amount of disruption. Same thing with RfA: it is really hard for you to WP:CANVASS effectively. It's just much better and less cumbersome if you infiltrate RfA yourself.
I tried it out and got “ Alan McMasters (1957-2010) was an unremarkable man who lived a short life dedicated to science[1]. He is best known for inventing the electric toaster[1][2], although this claim has been disputed[3]. He passed away in 2010 at the age of 52[4] and his genealogy can be found on Ancestry.com[5]. His professional profile can be found on LinkedIn[6].”. Hmmmm. Ritchie333(talk)(cont)09:34, 10 December 2022 (UTC)[reply]
There will come a time when AI can write properly sourced accurate articles. That time has not come yet. Meanwhile, the ability to write prose that reads plausible to someone not expert on the subject is a menace. Adding chatbot material to articles is disruptive and should warrant a block or ban. Zerotalk12:02, 10 December 2022 (UTC)[reply]
Same as other sorts of disruption. We block people for socking without checkuser proof, and admins made a decision between warn and block. No difference. Zerotalk03:49, 11 December 2022 (UTC)[reply]
Class reductionism refers to the supposed belief that inequalities attributed to factors such as race, gender, and sexual orientation are either secondary in importance or can be reduced to economic inequality. This idea is often used by centrist Democrats and left-identitarians to dismiss proposals for universal redistributive policies, such as free public higher education and Medicare for All. However, there is no evidence that anyone actually holds this belief. On the contrary, many left-wing activists have long recognized the interconnectedness of economic, racial, and gender injustices.History shows that leftists have often been at the forefront of struggles for racial and gender justice, seeing these struggles as integral to the broader goal of social transformation. In fact, black, female, and trans individuals are disproportionately working class and stand to benefit greatly from universal redistributive policies.Furthermore, the charge of class reductionism is often used to shut down debate and avoid discussing the substance of policy proposals. It is important to move beyond this myth and focus on the real issues at hand, such as the need for universal redistributive policies to address economic inequality and advance racial and gender justice.
Chatbot "AI" text is vaguely-plausible bullshit, produced by an industry whose primary output is vaguely-plausible bullshit, marketed to launder the idea of vaguely-plausible bullshit as cute and whimsical. Anyone routing that sewage pipe into Wikipedia should be indeffed and, for good measure, forced to drink orange juice after brushing their teeth. XOR'easter (talk) 02:33, 11 December 2022 (UTC)[reply]
Agreed. If anyone is looking for a good demonstration of how AI creates "vaguely plausible bullshit", try the image generator at Craiyon (no login required). Request "a Van Gogh painting of a hand" and it will output a set of images that look like spot-on reproductions of Vincent Van Gogh's style but all of the hands have deformities like four fingers, two thumbs, fingernails on the knuckles or a pair of hands fused together. It's got the style down but not the content, which is only impressive if you don't know what a hand is supposed to look like. –dlthewave☎21:41, 11 December 2022 (UTC)[reply]
I cannot agree with this enough. The examples posted by @JPxG: should be convincing, and the problem of sneaking in plausible BS is one I don't have a good solution to. Volunteers on the new page review are overloaded as it is, and if the bot is writing things that seem true but isnt, there's no way falsehoods will not simply get past reviewers and other editors. After all, for uncontentious claims like "used in plasticizers", how many of us honestly dig into the cited work?BrxBrx(talk)(please reply with {{SUBST:re|BrxBrx}})20:26, 17 January 2023 (UTC)[reply]
Yes. It doesn't just edit for tone; it throws out content, like Kaepernick's actions supposedly growing in popularity "after every game". That's a claim of fact which, if verifiable, should be retained. Even editing for tone requires care, not slashing out everything that merely sounds "unencyclopedic". Changing many people believed that it was disrespectful to the military and all of those who served their country to Some viewed Kaepernick's protest as disrespectful to the military and to the United States likewise changes not just the tone, but the meaning. The United States is not the same as those who serve the United States. It's a bad edit. XOR'easter (talk) 17:54, 11 December 2022 (UTC)[reply]
I dunno. I suspect that the new meaning is verifiable, and I also suspect that most US readers would have difficulty identifying a group of people who were not "the military" but who still "served their country". WhatamIdoing (talk) 17:50, 12 December 2022 (UTC)[reply]
This diff as well, in which GPT 3.5 was capable of copyediting an entire section from the instructions Please copyedit this text to change items in the future tense corrected to the past tense (it is now 2022), where appropriate. When citation templates (like {{cite web}}) mention a year, specify that figures were true in that year. jp×g04:08, 11 December 2022 (UTC)[reply]
References
^Robert Love (2010). Linux kernel development. pp. 124–125.
^The paragraph beginning with "Finally," was generated by GPT-3, prompted by my own comment beginning with "The reason it is describing".
@PerfectSoundWhatever and Dlthewave: Good observation. I checked, and yes it is, briefly, with this phrase in the lead section of the bot policy: "or simply assisting human editors in their own work". How is the typical editor to know this? The bot policy is pretty obscure. And how can Wikipedia be monitored for such posts, so that editors who make them can be informed that they are in violation of the bot policy? — The Transhumanist03:11, 11 December 2022 (UTC)[reply]
Yes, tool-assisted editing is covered by WP:BOTPOL (WP:ASSISTED / WP:MEATBOT) and context-sensitive changes are further covered by WP:CONTEXTBOT. So in fact, at this point, AI-generated content is already covered by bot policy, if not specifically mentioned. Anyone adding such content en masse is already violating bot policy by not applying for a bot account/approval, which would not be approved per CONTEXTBOT. And while "lesser" policy points are enforced somewhat arbitrary and selectively, anyone can theoretically already get reverted and blocked based on policy if they continue to add such content. And I wouldn't agree that BOTPOL is any more obscure than accessing and generating GPT content to begin with. If someone goes to the lengths of using automated tools, then it's their problem that they didn't check or ask if they are allowed to do so. — HELLKNOWZ∣TALK12:31, 11 December 2022 (UTC)[reply]
@Hellknowz and PerfectSoundWhatever: Well, it appears they are dumping millions upon millions of dollars into LLM/chatbot development, apparently because they wish the technology to become ubiquitous (used by everyone). There is a lot of talk out there, in news articles and more, of these replacing Google Search in just a few years. If at some point in time chatbots/LLMs are commonplace, the impact on Wikipedia will likely not be small.
Will Wikipedia policy ensure that the average user will apply the tools with the utmost care?
The thing I'm most concerned about is the amplification by which errors could be propagated: ChatGPT is used to edit an article, with errors, which is then picked up by GPT-4 and other LLMs as part of their training data, and then their output based upon erroneous input is used far and wide, to be picked up by the next iteration of chatbots/LLMs, and so on.
If Wikipedia isn't ready for a large influx LLM input including misinformation and other errors, and such a volume goes beyond what our human editors can correct, then compound damage from all those errors amplified through the interactive loop with LLMs could become massive.
That it isn't a problem now is irrelevant. The question is, what happens if and when it hits, and Wikipedia isn't ready for it? What would that look like? 1,000,000 fake articles? 10,000,000 misleading paragraphs? 100,000,000 erroneous sentences?
Stack Overflow was experiencing a surge in erroneous posts, that were composed by ChatGPT, and in response to that problem, they banned use of the chatbot on the social media site. According to a post at Stack Overflow Meta:
The problem this ban is meant to solve is that ChatGPT can produce answers in seconds which require minutes of multiple people's time to verify if they are worth having on the site or not, and that is a waste of time when a large proportion of such answers are not worth having on the site.
I mean, while that's technically true, it's a problem that we face already and which we do have stronger existing systems for than Stack Overflow. I think it would make more sense to wait and see how this impacts our existing guardrails before making any serious moves. --Aquillion (talk) 13:22, 11 December 2022 (UTC)[reply]
I think the current policies cover this already. If a human editor writes a non-sensical but convincing-sounding piece of text, without fact checking it, and edits it into an article, that content will be reviewed by other editors and either refined or removed as appropriate (if the editor continues, they breach WP:Disruptive and their behaviour is dealt with appropriately. If a human editor generates content that is related to notable topics, reliably sourced, and competently written, it remains as a valuable part of the encyclopedia. None of this will change if you replace 'human editor' with 'AI Editor'. If the only difference is speed/volume of edits, and we're concerned someone will let loose an AI to automatically edit articles faster than humans can validate their edits, this is already covered by the WP:Bot policyJeffUK (talk) 20:46, 23 December 2022 (UTC)[reply]
I am currently writing a draft proposal for a guideline, but in the meantime, I would encourage everyone present to look at this diff and tell me whether there are any problems with the revision. jp×g03:49, 11 December 2022 (UTC)[reply]
@JPxG, Dlthewave, PerfectSoundWhatever, and Dlthewave: The plurality of games was lost: It is no longer clear that his protest spanned multiple games. I like that it reduced the wordiness of the prose, and that it can be used to refine existing text. That hadn't occurred to me. That makes me wonder about what else it can do -- how much of a general-purpose tool is this thing? But, changing the semantics is not something it should be doing, unless they are factually incorrect to begin with. Though, I see your point -- rather than banning it outright, it could be helpful as a tool to assist editors, similar to how we entrust the use of AutoWikiBrowser to experienced editors. But, how could that be implemented? — The Transhumanist08:20, 11 December 2022 (UTC)[reply]
@JPxG: The AI changed Many people around the United States were angry because the National Anthem is often seen as something that is representative of the United States and its military. While he was taking a knee, many people believed that it was disrespectful to the military and all of those who served their country, to some viewed Kaepernick's protest as disrespectful to the military and to the United States [emphasis added]. It really shouldn't be doing that by itself and completely changes the content of what's being said. The reference is behind a paywall, so I don't know what term the source uses. Regardless, I doubt ChatGPT knows either way. It's things like that which make me highly sceptical of AI as a tool to aid Wikipedia outside what we're already doing with it (WP:ORES, etc.). –MJL‐Talk‐☖23:12, 27 December 2022 (UTC)[reply]
@MJL: I think "some" and "many" are basically equivalent in this context (the difference being subjective since both are true in a literal sense). That said, this was a two-minute experiment to see if it could parse wikitext. If you want an actual demo, see User:JPxG/LLM demonstration. jp×g19:20, 28 December 2022 (UTC)[reply]
It's starting to look like Wikipedia needs a policy on the use of chatbots to generate content on Wikipedia. While a ban may be impossible to enforce, it could serve as a warning of the dangers of chatbots, and many users may avoid using them accordingly -- if they actually see the warning. Or, it might be better to have instruction pages on how to use chatbots responsibly in assisting to write Wikipedia articles. There's also the issue of using chatbots to edit Wikipedia policy pages, and so, that should be addressed as well. — The Transhumanist02:44, 11 December 2022 (UTC)[reply]
People who are good at it get away with lots of sins, such as sock-puppetry and source falsification. Being hard to enforce is no reason to not have a policy. At the current stage of the technology, I don't think we should encourage any use of chatbots. Zerotalk03:56, 11 December 2022 (UTC)[reply]
To be perfectly honest, the style rewrite is good but the addition of dates and past tense would likely end up getting a human editor blocked if they kept it up. A tag was removed without addressing the issue and "as of 2020" was unnecessarily added to "Cosmetology licensing requirements vary from state to state, and depending on which specific type of license is desired, and depending on which specific type of license was desired." It did exactly what you asked (except for removing the tag) however even seemingly simple tasks like this one require good judgement on the part of the editor and shouldn't be done indiscriminately like that. –dlthewave☎06:37, 11 December 2022 (UTC)[reply]
Yes, that second diff is rather poor. E.g also the "2014" that was added should be "2008". Letting such tools loose (outside if this demo) is way premature, and we should at the very least warn users that "a bot wrote it" won´t be an acceptable defense, and too often introducing such errors will lead to sanctions as the editor, not the bot, is responsible. Fram (talk) 08:15, 11 December 2022 (UTC)[reply]
Mostly, that diff was my attempt to see how complicated of a task I could give it: I also pasted the raw wikitext into the prompt window, and it somehow figured out how {{cite web}} worked well enough to extract the years, simply from a textual description of the task. At any rate, I will say that this was something I thought of in five minutes on the second week of the model being publicly available (i.e. single-shot prompting with no fine-tuning or prompt engineering). I can come up with some more impressive hot-dog demos tomorrow... jp×g09:13, 11 December 2022 (UTC)[reply]
JPxG, I'm not sure that publishing bot-assisted edits to mainspace for demo purposes is the best practice. Would you consider either doing this in a sandbox or self-reverting immediately so that we have the diffs but aren't leaving potentially incorrect/unwanted changes on live pages? –dlthewave☎13:20, 11 December 2022 (UTC) 13:13, 11 December 2022 (UTC)[reply]
@Dlthewave:: See the section below for a list of edits (with full prompts included) on a separate demonstration page. I feel, however, that this is an unreasonable double standard: note that the subsequent revision after your partial revert was to add several spam links, and nobody has proposed that human beings be prohibited from editing as a result. jp×g01:51, 12 December 2022 (UTC)[reply]
Being hard to enforce is no reason to not have a policy [against chatbots]. What if it is impossible to enforce?
The point of ChatGPT and other general-purpose chatbots is to pass off as humans. If you, or another random Wikipedia editor (solo, part-time, amateur coder), is able to produce an automated metric of "sounds like a bot" that’s decently sensitive and specific, then the ChatGPT team or its successors (teams of researchers specialized in the topic) has already thought of it, tested it five different ways, and included it in the training program (via wikt:graduate student descent). TigraanClick here for my talk page ("private" contact)10:55, 12 December 2022 (UTC)[reply]
It's kind of like our Undisclosed Paid Editing policy: Even though there's no way of testing for paid/unpaid edits, most editors follow it voluntarily because they know it's best for the project. Others out themselves voluntarily or are discovered when their edits become disruptive. Sure, there are some who slip under the radar, but they're often the least problematic and aren't worth ditching the policy over. –dlthewave☎03:09, 13 December 2022 (UTC)[reply]
@Dlthewave: Undisclosed paid editors out themselves involuntarily often enough through pure dint of sounding like an advert; they're easy enough to spot. My worry is that though written content from a chatbot may sound like a Wikipedia article and go under the radar, the references – as other people in this discussion have noted – may simply be referencing sources that sound like they ought to exist, but don't. A human editor looking over their watchlist, who doesn't have enough time to go through added references and check they exist, may simply see "content content content[1] ([1] So-and-so, Believable Title: Buttstuff and nonsense in a holistic assessment, 2014. pp. 15-17)" and look no further. I know I at the very least would. I'm not sure how we'd spot this without human editors to do the work, and it worries me in the face of issues like lower editor retention and lower administrator numbers looking into the future.—Ineffablebookkeeper (talk) ({{ping}} me!) 19:09, 8 February 2023 (UTC)[reply]
I'd suggest starting by writing an essay that summarizes the issues with some good examples and suggests some best practices or proposes some additions to existing policies or guidelines. (Wikipedia needs a new policy like a hole in the head.) Levivich (talk) 04:40, 11 December 2022 (UTC)[reply]
It's hard to take this thread seriously given the repeated use of the phrase AI chatbot. I don't think those concerned would be any less concerned if the AI writing came in a non chatbot format. I think there's something serious for us to discuss, and that will only get more serious with GPT4 (the current chatbot is an improved GPT3) expected in 2023, but the discussion would be helped if those most concerned learned some more about the tech behind it. For instance of course it can figure out webcite @JPxG. Part of its training was the entirety of Wikipedia because our data is quite accessible. Best, Barkeep49 (talk) 14:08, 11 December 2022 (UTC)[reply]
Most the examples did not come from prompts that were extensively engineered, so it is obviously true that we haven't figured out the full answer to how these GPT-based interfaces could help or harm Wikipedia. Until we have a good idea of what they can be used for, we won't know what a proper policy to this would look like other than to treat GPT-generated text the same way we treat human-generated text: they need to be verifiable, from a neutral point of view, and understandable to a broad audience. 0xDeadbeef→∞ (talk to me) 14:31, 11 December 2022 (UTC)[reply]
Indeed. It doesn't matter if it was written by a chatbot, or 1000 monkeys at 1000 typewriters, or a published book written by a human, copying and pasting anything into Wikipedia is already against our policies. Conversely, if the text is policy-compliant, then it doesn't matter who wrote it--chatbot, monkeys, human, etc. Judge the text based on the text, not based on who or what wrote it.
I also think it's a real Wikipedian perspective to assume that people will use chatbots to write Wikipedia articles, like as if there's a lot of people out there who really want to write Wikipedia articles but just don't have the writing skills, so the chatbot will be what makes the difference and opens the floodgates :-D I don't believe that. Anyone who wants to write Wikipedia articles is already doing so; chatbot won't make a difference.
I agree with BK's comment above. I think for a lot of people, this is their first real exposure to so-called "AI" technology, and they're blown away by what it can do, only because they don't yet fully understand how it works. Once you learn how these so-called "AI" chatbots work (they're not actually artificial intelligence, btw, that's a misnomer, a marketing slogan; the machine does not truly think or learn, it is simply executing the instructions written by humans, in this case, language pattern recognition), they are much less impressive. Those that are impressed that GPT3 can produce text that "sounds like" Wikipedia aren't appreciating that the reason is because GPT3 was trained on Wikipedia: it's repackaging its own source material. Levivich (talk) 18:03, 11 December 2022 (UTC)[reply]
While this is mostly correct, I think the question of whether a computer program "thinks" or "merely" correlates information and performs actions is irrelevant. Do p-zombies exist? Does it matter? Hypothetically, if I were to be a spaceman from the planet Zolfgar with no qualia whatsoever, and I simply read a bunch of books and used them to write an article, would I be somehow exempted from following policy? jp×g01:45, 12 December 2022 (UTC)[reply]
I don't see a common thread in the arguments above, but here's a suggestion for something we might all (well, all-ish) be able to agree on: without some kind of intervention, GPT4 (in 2023?) is likely to be more of a problem than GPT3. But one thing we can certainly do is have an outsized influence on software that was trained on what we created ... if we invite Wikipedians to make lists of ChatGPT bloopers, we can tell the OpenAI folks: "We're not going to relax our GPT3 guidelines (whatever they turn out to be) when GPT4 arrives, unless it makes significant improvements in [whatever areas we think need improving]". - Dank (push to talk) 18:16, 11 December 2022 (UTC)[reply]
I think the only policy change needed is to update WP:MACHINETRANSLATION to cover all computer-generated text, whether from a translation bot, chat bot, or whatever bot they think of next. (Except our bots; our bots are cool.) Levivich (talk) 18:20, 11 December 2022 (UTC)[reply]
This proposal is incomprehensible; most articles contain a very large amount of text that is "generated by a process". I assume that, at the end of your comment, you typed ~~~~ before saving the page. Would it be realistic to demand that you either make a formal request at BRFA or else manually type <a href="/wiki/User:Tazerdadog" title="User:Tazerdadog">Tazerdadog</a> (<a href="/wiki/User_talk:Tazerdadog" title="User talk:Tazerdadog">talk</a>) 22:43, 11 December 2022 (UTC)? jp×g01:22, 12 December 2022 (UTC)[reply]
This is effectively discrimination against computer programs. If a computer program resembles a human editor, then it shouldn't be required to meet different or more restricted policies than human editors. If a human editor uses a computer program to edit or create content, then unless the rate of edits/second is too high, we would only look at the quality of the contributions. 0xDeadbeef→∞ (talk to me) 02:35, 12 December 2022 (UTC)[reply]
There is a point beyond which quantity becomes its own quality.
Also, what if the computer program is evaluating the quality of the contributions? Are you okay with software adding a section to an article, and then a (hopefully) different piece of software deciding whether the quality is sufficient and reverting if it's not? This second step, at least, is 100% feasible with current technology. WhatamIdoing (talk) 19:32, 12 December 2022 (UTC)[reply]
Yes it can go there, but it should also be mentioned at WP:V. Every statement of fact put into an article must be verified by a human, even if the choice of words is made by a machine. Zerotalk23:42, 11 December 2022 (UTC)[reply]
@Levivich Agree. I think our existing guidelines on machine translation, in spirit, fit this situation very well - "you can use it for a first draft, if you understand the material well enough to clean up the bits it inevitably will get wrong". It seems fine for turning shaky text into good prose, but it's not able to synthesise material and produce content unsupervised. Andrew Gray (talk) 19:09, 12 December 2022 (UTC)[reply]
Is there some tremendous need to add many articles rapidly in Wikipedia? It is not as if Wikipedia carries exclusive information not easily found elsewhere. As a tertiary source, it is at the 3rd tier of knowledge dissemination, after primary creators and secondary propagators. The "more" and "bigger" quantity-based culture is the established low-quality alternative that Wikipedia also applies, now. Possibly that is a reason that likely only a tiny minority (of the millions of existing articles) can really pass muster. If size and speed is to be the prevailing attitude, humans stand no chance against AI. It will do everything faster, and eventually better, assuming its programming evolves to correctly apply the existing policies in AI processes. The only advantage of humans will be subtle nuances that do not depend on classifiable knowledge but on having lived in a human society and a natural, not virtual environment. Or, the emphasis could switch to quality so that each article (by any type of editor) can be properly, carefully reviewed by human editors. 65.88.88.93 (talk) 22:21, 12 December 2022 (UTC)[reply]
I don't think so: there isn't any evidence that people are writing a bunch of articles with LLMs, and I don't think it is likely for this to happen (LLMs are very poorly suited to writing articles from scratch). jp×g00:59, 13 December 2022 (UTC)[reply]
@JPxG: There isn't evidence that people are writing a bunch of articles with LLMs -- yet -- the concern is that we need to prepare for the likely explosion of chatbot use.
Whether this increase happens tomorrow or over the next few years, the potential impact of LLMs is of such magnitude that we should get ready for this, rather than get hit unprepared by a major surge.
I don't agree with your assessment of LLM ability to write content, as some of the ChatGPT experiments presented in the sections above and below are mind-blowing!
If LLMs become ubiquitous, then a great many people will be using them as a matter of course, including in their writing and editing of Wikipedia articles. Millions of people have edited Wikipedia in the past, and millions more will edit WP in the future. And in the future, people will have highly capable LLMs (chatbots, or more precisely: automated ghostwriters).
LLMs already excel at writing about a great many things, and they have the potential to compile content at an exponentially increasing rate. If you ask ChatGPT (GPT3.5) to write an essay on a topic, it will comply. Each of its essays can be used as content of an article, or its sections. (GPT4 is scheduled to come out in 2023, and will be even more capable.) LLMs are very well suited for writing to the specifications of the user, and are limited mainly by the user's creativity.
Hello, I have recently described my experiences with an AI "article" in this video. In my humble opinion, it would be difficult with certainty that new Wikipedia content was created by an AI. At the end of the day, it is always the editor's responsibility to add good content. Independently how the content was created, independently whether errors in the text are human-made or machine-made. If an editor adds a lot of new poor content, we can already stop that. - At the moment I don't see that we need a new policy. Ziko (talk) 18:06, 24 December 2022 (UTC)[reply]
A policy banning AI usage (with or without a chatbot) would be justified. Allowing AI like GPT3 or GPT4 to be used by Wikipedia editors or to directly become Wikipedia editors (via a mediawikibot) would quite likely violate WP:REFLOOP due to Wikipedia content contributing to the AI's training material, and for the source-less examples I've seen, violate WP:SYNTHESIS by not being a summary of sources that are understood. This example starts with text and then seeks references to justify the WP:SYNTHESIS of the original text. Use of Alphabet/Google's ChatGPT/GPT3 would also strengthen the bias introduced by Alphabet/Google's core goal of optimising advertising revenue, since Alphabet is legally bound to maximise its revenue (mainly from Google Ads + Google AdSense), not to optimise the research quality of its summaries of empirical evidence-based knowledge. Google's search engine is primarily a way of generating advertising revenue, with perceived usefulness being a key tool for maximising revenue, not a goal in itself. Boud (talk) 01:42, 31 December 2022 (UTC)[reply]
@Qwerfjkl: Fixed, thanks. I left some of the sentences unstruck since AFAIK they're valid, even though irrelevant in the current case. I imagine that Google may provide something similar soon though. Boud (talk) 09:02, 31 December 2022 (UTC)[reply]
Boud, I am somewhat worried if you think that current policy (for humans or for anyone else) permits editors to make stuff up and put it into articles without sources. This simply isn't allowed -- per WP:V, WP:SYNTH, WP:RS, etc, which are extremely important core policies of the project. I am struggling to imagine a circumstance in which existing policies, or explicit declarations like my proposed guideline at WP:LLM, fail to prevent people from writing nonsense. jp×g16:48, 1 January 2023 (UTC)[reply]
Wikipedia policy generation
It seems to me that this tool's training includes studying Wikipedia's policy pages. These drafts all seem accurate to me.
These are not merely adequate - these are good. They are short and they lack detail but these are great overviews. If this is the starting point and things only get better from here, then it is time to start adopting this technology. Bluerasberry (talk)19:35, 13 December 2022 (UTC)[reply]
@Bluerasberry The last one sounds like a "mission statement". I dislike phrases like "outreach and engagement initiatives" and a lot of that plan sounds ... kind of aspirational, and, well, vapid. It needs more "concreteness". Just my opinion. David10244 (talk) 06:08, 16 December 2022 (UTC)[reply]
@David10244: That you react to it at all is a miracle to me. This is new AI technology attempted for the first time, and I think no one would immediately dismiss it as hopeless garbage. Soon enough there will be a dial that anyone will be able to turn from "vapid" to "concrete". Things are moving quickly!
I have complaints too but when we need policy conversation starter in a hurry, this is better than nothing and I think even better than some of the starting points we use already. Bluerasberry (talk)15:41, 16 December 2022 (UTC)[reply]
Large language models: capabilities and limitations
Over the last few hours, I have performed a number of experiments to demonstrate the capabilities and limitations of large language models (LLMs) such as ChatGPT and GPT-3, which can be viewed here:
Mostly, I have taken sample text from Special:Random, and attempted to show situations in which LLMs (in this case, mostly ChatGPT) are capable of making useful edits. The first task I set it to -- which bears repeating here -- is
"Large language model output should only be used in the process of editing Wikipedia if you are an intelligent editor who does not blindly paste LLM output into the edit window and press "save".
Please format this markup as an extremely obnoxious floating box with loud colors and large text.
You can see the results of further prompts at the "introduction" section.
In general, it seems that these models can be used for an extremely wide variety of tasks across the project, from formatting to table syntax to HTML generation to copyediting. Banning their use entirely would be pointlessly destructive and wasteful.
That said, many computer programs are capable of generating large amounts of useless crap that fail to meet Wikipedia's editorial standards. For example, I could use MS Paint to draw thousands of crude pictures of genitalia, and add them to random articles. For this reason, we have many policies and guidelines that prohibit adding large amounts of useless crap to Wikipedia. I propose that we enforce these policies and guidelines, thus preventing this from happening.
Specifically, I propose that the use of LLM output on Wikipedia be subjected to policies and guidelines such as WP:NOT, WP:NPOV, WP:C, WP:CIVIL, WP:V, and WP:RS. By making it against the rules to break the rules, we will prevent people from breaking the rules, and provide a mechanism to sanction people who break the rules.
Furthermore, I propose that a guideline be adopted to the effect that large language model output should only be used by competent editors who do not blindly paste LLM output into the edit window and press "save". This will prevent people from using ChatGPT to write long articles consisting entirely of nonsense. jp×g01:32, 12 December 2022 (UTC)[reply]
LLM output is already subject to rules and policies. Or rather, anyone adding it is. 'An algorithm did it' has never, as far as I'm aware, been seen as any sort of exception from compliance with policy. AndyTheGrump (talk) 01:49, 12 December 2022 (UTC)[reply]
The opening paragraph of the bot policy: "The bot policy covers the operation of all bots and automated scripts used to provide automation of Wikipedia edits, whether completely automated, higher speed, or simply assisting human editors in their own work."
See also: WP:BOTUSE, which requires approval before applying a bot to editing.
So, the use of large language models and the chatbots built upon them, is already prohibited on English Wikipedia, unless a user gets approval from the bot department to do so.
There are blanket exceptions to bot policy, and the main one that comes to mind is AutoWikiBrowser which is a general purpose semi-automated bot used by many Wikipedia editors. Each AWB user was approved before being able to use it. — The Transhumanist08:01, 13 December 2022 (UTC)[reply]
The meaning of "bot" may be unclear here. In the context of Wikipedia (per Wikipedia:Bot_policy#Definitions), a "bot" is a software program that edits autonomously without user input; there do not currently exist any language models capable of independently establishing API connections to Wikipedia and making edits without human interaction. If they did (this is a horrible idea) it would be covered under the bot policy and require a WP:BRFA. The policy under which BRFAs are required does not apply to assisted editing (i.e. the use of software to create letters, numbers and symbols that were not produced by a human being pressing a keyboard). This is governed by existing policies (such as WP:MEATBOT and by the guideline at WP:ASSISTED. jp×g09:28, 13 December 2022 (UTC)[reply]
@JPxG: The entire news field refers to ChatGPT as a chatbot. It is general consensus that it is a bot. ChatGPT speeds up writing, by doing it for (that is, assisting) the user, which falls under the "higher speed" and "assisting human editors" foci of the bot policy. There is a passage in the bot policy that covers policy contradictions (such as between the lead and definitions sections), and situations where the spirit of the rule and its precise wording conflict, that is, cases of ambiguity. In its definition of "Bot Approvals Group" (BAG), the bot policy states: "The BAG also determine the classification as bot or assisted editing, in ambiguous cases." According to WP:ASSISTED, it is up to the Bot Approvals Group to decide whether bot approval is necessary. Based on the previous 2 sentences, BAG decides whether use of particular software falls under its jurisdiction. It remains to be seen what BAG's reaction(s) to LLMs, and the chatbots built upon them, will be. — The Transhumanist11:10, 14 December 2022 (UTC)[reply]
I do not think you are properly acquainted with how this software works: like I said, there do not currently exist any language models capable of independently establishing API connections to Wikipedia and making edits without human interaction. No media outlet has ever claimed that ChatGPT falls under the English Wikipedia's definition of an automatic bot – and even if they did, they do not determine policy. It is true that WP:MEATBOT and WP:ASSISTED are part of the bot policy, but there is a very clear definition of what a "Wikipedia bot" is, and it's defined by that same policy. At any rate, all edits (whether made by bots, software, humans using software, aliens using software, or Nagato Yuki psionically connecting to Wikimedia servers) are governed by existing policies and guidelines. To specifically address LLM output, a new policy would need to be written and ratified (which I am currently drafting a proposal for). jp×g11:26, 14 December 2022 (UTC)[reply]
@JPxG: I believe the bot policy has wider jurisdiction than the narrow interpretation that you have presented. Establishing API connections is irrelevant, because a human is inserting bot-generated content. It's a bot-involved process. And those are encompassed by the bot policy which makes it up to BAG. A new policy could establish an exception, and I imagine the discussions will be extensive, as this is not a cut and dried case -- it is a sensitive issue with many potential ramifications. But, until such a policy is in place, this issue falls under BAG's jurisdiction, since they are the ones who decide the classification of a software program as it pertains to the bot policy. — The Transhumanist11:52, 14 December 2022 (UTC)[reply]
(edit conflict) WP:ASSISTED is deliberately vague to not restrict use of common scripts and tools. So it specifically says that only once volume becomes significant, such editing becomes more likely to be treated like a bot and BAG can determine this. It doesn't make it a bot, but it will be treated like a bot. We've never encountered any large-scale edits with LLM before, but we sure have seen a lot of high-volume editing. Half the bot policy only exists because of all the ways editors have inadvertently created issues with mass edits. So at that point, other parts of the policy start to matter, notably WP:CONTEXTBOT - which does not allow edits where context matters. I'm not saying copy-pasting LLM output is immediately covered by bot policy, nor does it matter whether anyone considers LLM to be a "bot". But bot policy will kick in once someone starts to make a lot of edits. And any new guideline will have to reconcile with this or we need to change bot policy to reconcile with LLMs. — HELLKNOWZ∣TALK12:02, 14 December 2022 (UTC)[reply]
@JPxG: Another possible approach for vetting users for use of LLMs is via user group membership (aka "rights"). Here are our current user groups:
These indicate membership in user groups (see: user access-levels). They pertain to who is granted access to various features of MediaWiki and its extensions. Theoretically, a user group could be created without being attached to a program function (that part could just be left blank?). For example, you could have a group called "LLM", with everyone in that group approved to use large language models in their editing. I don't know if this is doable, though. — The Transhumanist08:01, 13 December 2022 (UTC)[reply]
I do not think there is anything in our P&G that would directly prohibit use of content created by LLMs, nor do I think it would be a good idea to try to do so. All that is needed is to continue to hold individual editors responsible for all edits they make, including the copying of content from any source, whether from LLMs or other sources. We probably should add language in appropriate places reiterating that editors are reponsible for insuring that all content that they add, including anything produced by an LLM, meets our P&G. - Donald Albury13:12, 13 December 2022 (UTC)[reply]
If someone uses an unapproved script or bot to edit WP, that is a violation of the bot policy, whether or not they use an LLM to generate any content being added. If someone uses an LLM to create text which they then copy into Wikipedia without using a an unapproved script or bot, that is not covered by the bot policy, but the user remains responsible for insuring that the content conforms with policy and guidelines. There is no point in banning content created by LLMs, as we already require that content be verifiable from reliable sources, and I doubt we will be accepting any content created by an LLM as a reliable source anytime soon. The danger is that LLMs may create potential content with citations to pseudo-sources, but we can go after users repeatedly adding such content to WP for abusing the policies on verifiability and reliable sources, without regard to whether such content came from an LLM. Donald Albury13:48, 14 December 2022 (UTC)[reply]
I don't think it's plausible that LLMs are covered by the bot policy. If they were, grammar checkers, spell checkers, and machine translation would be "bots". Jahaza (talk) 19:49, 14 December 2022 (UTC)[reply]
@The Transhumanist: ChatGPT falls under Wikipedia:Bot policy, but per the definitions section it does not fall within that policy's definition of a bot. Rather, use of it would fall under the definition of "assisted or semi-automated editing", and the relevant policy section is Wikipedia:Bot policy#Assisted editing guidelines. The section doesn't aim to draw a 100% hard line, but my reading is that limited of ChatGPT for clean-up on a limited number of articles by a user in a limited closely-supervised way may be something users can do if they are trusted to apply their common sense. It is "Contributors intending to make a large number of assisted edits" who "are advised to first ensure that there is a clear consensus that such edits are desired." Limited use of ChatGPT to a lesser degree than would trigger this may currently be outside policy. In any event "A bot account should not be used for assisted editing".
It seems to me that an addition to the policy along the lines suggested by User:JPxG to address this potential hole might well be useful, eg "tools capable of assisting editors make substantial edits (for example large language model output) should only be used by competent editors who do not blindly paste tool output into the edit window and press "save"." Jheald (talk) 19:36, 18 December 2022 (UTC)[reply]
In what way does the bot policy cover ChatGPT? Just because it is called a "chatbot", doesn't mean it is a bot. Copying text from GPT-3 doesn't automatically become bot-like editing. Semi-automated edits? i'd call that borderline. It only becomes a problem (e.g. meatbot problems) if the amount of supervision needed to save an edit is below normal editing, and that the speed of the edits are above normal. (see awb, huggle, etc) 0xDeadbeef→∞ (talk to me) 10:20, 20 December 2022 (UTC)[reply]
The thing is, any LLM additions will inevitably be both faster than writing manually and, due to its confidently-wrong output, less reviewed. Otherwise, why would anyone bother with it? I feel that assuming that editors will spend just as much time to carefully review the LLM output is wishful thinking. I'd like to be proven wrong, but I have never seen any precedent on Wikipedia that better tools would lead editors to spend the time saved to further verify the tool output. If anything, tools only create induced demand. — HELLKNOWZ∣TALK21:18, 20 December 2022 (UTC)[reply]
I don't think we need to do anything in particular. There is plenty of confidently-wrong content being added to Wikipedia by human editors already and we're dealing with that as well as we can. I think the intersection of 'Editors who will use a cutting-edge AI to generate content' and 'Editors who will do this without validating the output' is a very small overlap and will be of such small volume to be picked up by other editors as usual. A huge influx will be detected in aggregate, and we can deal with that if it becomes a problem in the future. If someone uses LLM to generate confidently-right content or articles, that's indistinguishable from content generated by a competent human, I refer you to xkcd: Constructive! A simple but unobtrusive first step may be to tag an edit as 'generated by AI', or maybe just ask editors to add a tag to their user pages if they regularly do so, but the intersection of problematic users who also follow this would be basically non-existent. JeffUK (talk) 10:40, 24 December 2022 (UTC)[reply]
I am having trouble understanding what you are talking about at this point. I wrote WP:LLM some weeks ago, a gigantic proposal for a comprehensive guideline on the use of LLMs, and linked it multiple times on this noticeboard. While it is not complete, it seems to me like it covers everything you are talking about here. Do you have an opinion on it at all, or...? jp×g15:39, 2 January 2023 (UTC)[reply]
@JPxG: I was responding to JeffUK's statement "A huge influx will be detected in aggregate, and we can deal with that if it becomes a problem in the future." Intently waiting until something becomes a huge problem before you start dealing with it, sounds like a disaster waiting to happen. Also, what good are guidelines going to do if the average person is using chatbots on a regular basis? People just jump in and edit Wikipedia without reading any project-level pages first. If there's a huge influx, and all you are doing is holding up a sign that says "Read this", what good will that do? You haven't addressed how the problems associated with a potential huge amount of chatbox input (in the form of one-off edits from a large number of people) would be prevented or processed. One solution is to fix the chatbots themselves, so that they don't generate Wikipedia-incompatible content in the first place, which would require working with the developers. A second method would be to create bots to detect and remove either chatbot-generated content, or if possible, policy-breaking content. Simply writing policy and hoping no flood comes, just doesn't seem like a viable approach should a flood hit. That approach may work for the first 3 or 4 years, but what if the flood comes in the 5th year and Wikipedia isn't prepared? We will have wasted 5 years that could have been spent preparing. Maybe we'll be lucky and chatbots will be smart enough to read and follow your guidelines. But if they are not? Fortunately, Doug Weller has passed word along to the Wikimedia Foundation. Maybe they will do something other than write editing guidelines. — The Transhumanist03:09, 10 January 2023 (UTC)[reply]
@JPxG although I haven't read more than the beginning, I'm also worried about AIs creating images.For instance I've seen some extremely convincing ones of fake archaeological sites and artefacts. Couldn't people pass them off as their own photos? Or am I missing something? Doug Wellertalk17:06, 2 January 2023 (UTC)[reply]
Yeah, that's a whole other deal. This proposal is only for large language models. Large image models will probably need to be governed by something much more imaginative. jp×g17:11, 2 January 2023 (UTC)[reply]
If someone's editing is inappropriate, the solution will be notifying them it's inappropriate, warning them, then banning them if they don't stop. There are ways for incompetent editors to make massive plausible seeming changes to the encyclopaedia right now. e.g. by copy/pasting content from other places, or just writing in made up 'facts', LLM really won't make this any easier for someone who's intent on doing this. JeffUK18:09, 2 January 2023 (UTC)[reply]
If these AIs are used in some way for a large scale creation of articles, I think that will be a disincentive for a lot of editors and may drive some away. I disagree with JeffUK on the simplicity of dealing with this. First, you need to be able to spot them and that's work. Secondly, that also assumes that the numbers will be small. Doug Wellertalk15:48, 9 January 2023 (UTC)[reply]
@WaltCip: None. Most editors don't read policy before editing. That's because most editors post very infrequently. But there are a lot of them, and they have authored of most of Wikipedia. What happens when they are all using chatbots, much in the way that most everyone today uses Google? — The Transhumanist03:34, 10 January 2023 (UTC)[reply]
"Someone." Apparently, you are assuming it will be one person, or a small enough number to be handled manually. But, what if over the next few years chatbots become ubiquitous with almost everybody using them? How will you deal with it when half the content contributions to Wikipedia are being generated using chatbots? — The Transhumanist03:26, 10 January 2023 (UTC)[reply]
Personally, I'd prefer that if this is implemented, ClueBot prefer to tag before a full-on reversion, except in cases. I think that ClueBot should use the same exceptions for 3RR for reverting possible bot stuff, though this might require that chatbots be banned from BLP-covered articles. Everything else which could be problematic but not a 3RR exception could be placed at a specific page...maybe have a specific preset filter on recent changes? InvadingInvader (userpage, talk) 07:43, 6 February 2023 (UTC)[reply]
Other inherent problems only partially touched on:
Editing articles involves also understanding what is already in the article and how it is organized plus understanding and interpreting policies and guidelines.
What's unspoken but runs through many things including current Wikipedia is sort of a commensurate investment. You can get volunteers to take their time to review and deal with issues because they know they are dealing with something that an editor has invested time in to create. Part of the reason that we don't allow mass creation of articles by bots. In other words, we'd significanly lose volunteer efforts
Modern AI is inherently unaccountable black boxes. There is no way to see or interrogate or demand/recieve accountability or reasoning for how it arrived at what it arrived at.
If gibberish or semi-gibberish is created, it normally requires an expert to spot and remove it..... a very scarce resource. I once uncovered a set of technical-subject articles (about 100 article as I recall) which looked very technical and Wikipedian and were sourced but if you knew the subject you knew were pure gibberish.
Well said. I think that folks are overestimating the ability of our review processes to detect "vaguely plausible bullshit" - it's not very common for human editors to fill in blanks with made-up facts and numbers, and I'm not sure that AfC or NPP are checking for this as it would greatly increase their workload. –dlthewave☎19:42, 11 January 2023 (UTC)[reply]
[I]t's not very common for human editors to fill in blanks with made-up facts and numbers. Maybe not when adding content, but I see this happen all too often in edits to temperature tables in climate sections. Of course, the tell there is changing temperatures without citing a source or commenting about correcting from a cited source. - Donald Albury20:17, 11 January 2023 (UTC)[reply]
As I recall, the big one that I caught looked like some type of expose project or research project to see if such a scam could get far in Wikipedia. It was sort of in mashup of words from actual sources. Total nonsense, but a typical reader might think it was simply over their head. North8000 (talk) 21:25, 12 January 2023 (UTC)[reply]
In answer to the 3rd point above (the black box issue), Perplexity.ai, an AI search engine with a chatbox interface, provides source references with its answers. That is, the references are the search results, while the answer provided is compiled or interpreted from those web pages. So, at least the sources can be checked for verification. But, there are still problems with it. See the perplexity.ai section below. — The Transhumanist19:56, 21 January 2023 (UTC)[reply]
Chat-GPT is taking the world by storm (translation: it has gone viral).
Chat-GPT, and other LLM-based chatbots, can generate compositions, some good enough to pass as college-level essays.
Wikipedia is included in the corpus (training data) of Chat-GPT (and other chatbots).
Such software has the potential to be used for:
Generating Wikipedia content, including writing new articles and adding new material to existing articles.
Generating Wikipedia policy content.
Generating discussion content, such as on policy talk pages. That is, editors using it to write their discussion replies for them.
Editing articles, including rewrites, and using chatbots as a grammar checker.
Editing other namespace pages, such as policy pages, etc.
"Can be used for an extremely wide variety of tasks across the project, from formatting to table syntax to HTML generation to copyediting." (quoting JPxG)
Creating hoaxes with less effort.
Most Chat-GPT output lacks citations.
Some experiments were run, showing that Chat-GPT:
Copies writing styles very well.
Has a tendency to make things up, yet presents it as fact in an encyclopedic tone. One editor dubbed this "confident nonsense". In one experiment, Chat-GPT created an article reporting that Wikipedia's own Signpost newsletter was the recipient of several Pulitzer Prizes.
Can include references, but some of the references were made up and totally fictitious.
Some references cited Wikipedia (an ineligible source for Wikipedia articles).
One of the experiments generated instructional content, a recipe, that the user followed, and ate the results of.
Another experiment used Chat-GPT to answer hypothetical questions in the style of WP's teahouse department. It worked fairly well.
Yet another experiment created a sample policy page, showing that chatbots are not limited to editing articles. They can generate or edit pretty much any type of page on Wikipedia, except files (images).
Chat-GPT output is not fact-checked.
Chat bots don't actually understand what they are writing.
When used responsibly as a tool, with editors carefully prompting the chatbot, and editing and fact checking its output before posting it to Wikipedia, a chatbot can be very useful and increase editor productivity: the LLM GPT-3 was successfully used to create department reports for Wikipedia's newsletter, The Signpost.
JPxG conducted an experiment/demonstration to show that Chat-GPT is a sophisticated interactive editing tool, which you tell it what you want it to do to a textual work, and then it does it. See it here: User:JPxG/LLM demonstration.
It was pointed out that Wikipedia policy already covers all contributions, whether generated by chatbot or human. Ultimately, the user is responsible for material they copy and paste into Wikipedia.
Issues of concern that were raised include:
Users copying chatbot-generated text into Wikipedia without carefully editing and fact-checking it first.
Confident nonsense (misinformation generated by chatbot) may be hard to spot.
The potential of chatbots to violate copyright, by directly copying, or generating text based on, copyrighted works.
Violating Wikipedia's licenses, most notably the attribution requirements. Chat-GPT output generally does not include attributions.
A chatbot-edited Wikipedia could wind up in the training data for those same chatbots (or their next versions), creating a potentially error-compounding feedback loop.
The suggestion was made to prepare for a potentially large future increase in chatbot entries to Wikipedia, by:
Working with chatbot developers to make chatbot-generated output Wikipedia compatible.
Develop bots to identify and process chatbot entries.
No consensus has emerged on what the Wikipedia community should do about LLMs/chatbots. Some editors think that policies/guidelines and the current editor pool could handle any influx of chatbot generated edits. Some other users were concerned that there is potential for LLM/chatbot contributions, such as one-off edits by members of the general population, to overwhelm our pool of editors. One user pointed out that it may take experts to discern nonsense articles, and experts on Wikipedia are a scarce resource.
Consensus did emerge on something not to do. It was agreed that banning chatbot-generated content was not a good idea at this time, and probably wouldn't work anyways.
Software has been developed to identify Chat-GPT-generated text.
It appears some editors may take the initiative to prepare for a worst-case scenario (chatbot input going beyond our editor pool's ability to handle), and discussion on how to do this has begun.
WP:ORES could theoretically be trained to identify chatbot edits.
The Wikimedia Foundation has been contacted about the concern over LLMs/chatbots, presenting a contact there with a link to this and a previous discussion.
AI-generated images are rapidly becoming a Big Thing, so it is not correct to exclude them. Also, "Wikipedia policy already covers all contributions, whether generated by chatbot or human" is misleading as it is true only by accident. A more precise description would be "Wikipedia policy was written without any consideration of chatbots". Zerotalk03:28, 13 January 2023 (UTC)[reply]
I'm concerned about "Such software has the potential to be used for: creating content farms that good-faith human editors, including existing experienced editors, will sometimes mistake for reliable sources when they are writing content".
Also, the statement that "Software has been developed to identify Chat-GPT-generated text" is true, but not relevant for very short contributions. Some of this is using sentence length, and you won't be able to identify an abnormal sentence length if you only look at two or three sentences. WhatamIdoing (talk) 05:33, 13 January 2023 (UTC)[reply]
Anyway, detection methods that work now won't work in the next generation. Eventually (and not far in the future) distinguishing between human-written and computer-written prose will be impossible for practical purposes. This is going to be the greatest threat to Wikipedia since its founding. Zerotalk05:51, 13 January 2023 (UTC)[reply]
Adjacent to hoaxes there's also the likelihood of spammers using GPT to bulk out their edits. I strongly suspect that the text of this edit today, writing repetitively about a static sculpture as if it was a functional scientific instrument, was generated with GPT-3, probably giving it a prompt to explain Orbital Reflector in terms of dark matter and black holes, the subject of the two embedded spam links. Belbury (talk) 11:39, 17 January 2023 (UTC)[reply]
With the user base for Chat-GPT about to explode, the potential for Chat-GPT-generated text being added to Wikipedia will explode right along with it. It's looking uncertain whether or not Wikipedia's editor community will be able to keep up with the influx. In light of recent events, what should be done about this? — The Transhumanist03:21, 13 January 2023 (UTC)[reply]
As well as being able to write plausible-looking prose on any subject, computers can also be programmed to add it to Wikipedia all by themselves. The first task is to absolutely ban computers from editing, with the sole exception of authorized bots. The second task is to add to appropriate policy pages that all content (authorized bots excepted) must be added by a human and that that human is responsible for checking policy conformance of the content. Zerotalk08:06, 13 January 2023 (UTC)[reply]
I was hoping to get more feedback on WP:LLM from having posted it here, but either way, I think it is pretty close to ready for consideration as a guideline (or policy, as appropriate)... based on the conversations I've had (and seen) I am prepared to write an RfC for its adoption. jp×g11:00, 14 January 2023 (UTC)[reply]
@JPxG: The guideline is not ready. It is not where near complete, and it needs a rewrite. Here are some proofreading notes:
It's way too redundant, repeating policies and itself, without explaining how to get the job done. Aside from the "fit for" sections, the rest of the page can be reduced to a single paragraph.
It presents -- should only be used by competent editors who do not indiscriminately paste LLM output into the edit window and press "save" -- four times! Someone who is incompetent isn't going to be able to judge whether or not they are. Also, "indiscriminately" is vague. That entire sentence should be removed.
Editors need to know what they need to do to the text before they can press "save". For example, you alluded to a manner of using LLMs in compliance with WP copyright policy, but you didn't explain how. How can an editor be sure that an LLM-generated piece doesn't violate someone's copyrights? What's the procedure?
Rather than covering "good fit" and "not good fit", the guideline should present explicit instructions: "Use it for this" and "Do not use it for this". And then explain how.
I agree that the page is not finished, but I don't really know what you are objecting to here. It kind of sounds like you are inventing problems – if users don't know how to check if things are true before putting them into Wikipedia articles, they shouldn't be editing at all. If users don't understand what copyrighted material is, they need to read Wikipedia:Copyright policy, which is linked to from this page when it's mentioned. That is an explanation of how to get the job done. It should not be necessary to create an exact copy of Wikipedia:Verifiability that says "When using a LLM," at the beginning of every sentence. jp×g08:29, 16 January 2023 (UTC)[reply]
@JPxG: How can users understand what the copyrights of Chat-GPT's output are? Chat-GPT doesn't provide sources, nor does it report if it copied or derived the passage from a particular work. So, how do you go about checking whether or not a particular Chat-GPT response is in violation of copyright, so that "pasting its output into the edit window and pressing 'save'" is not considered "indiscriminate"? Also, it isn't clear who owns the copyrights to the output of an LLM: the public domain, the owner of the LLM, the user of the LLM, or the owners of the copyrights of the works included in the training data set? The breadth of this problem is discussed in #Copyright status below. — The Transhumanist00:08, 19 January 2023 (UTC)[reply]
There already exist a very large number of policies about copyrighted text. Editors are subject to these policies. These policies contain information on how to avoid copyright violations. If you asked GPT-3 to tell you the lyrics to Moonage Daydream, they would be copyrighted. If you found the same lyrics by typing "moonage daydream lyrics" into Google, they would be copyrighted. What is the difference? Policies do not (and cannot) cover every hypothetical person and situation to which they could be applicable: we do not have a separate WP:COPYRIGHT for old editors, WP:COPYRIGHT for young editors, WP:COPYRIGHT for male editors, or WP:COPYRIGHT for female editors. WP:COPYRIGHT applies to all editors regardless of their age, race, gender, or whether they are human or machine. I don't know how to explain this in further detail. jp×g01:06, 19 January 2023 (UTC)[reply]
You've missed the points entirely (there were two, and you only replied to one).
Those policies you mentioned do not deal with the copyright problems presented by black box chatbots, nor do they warn about the dangers of pasting in chatbot output.
Search engine search results are excerpts from web pages that the search results identify — which facilitates verification. Chat-GPT and other black box chatbots answer questions in natural language, without telling the asker of the question where the information came from — which does not facilitate verification — while presenting it in a very confident and scholarly tone.
This may result in a great deal of misinformation being posted to Wikipedia, where it will sit until somebody else removes it. The delay between those 2 events can be lengthy, especially for material that seems plausible. So, it might be a good idea to provide guidance specific to chatbot usage pertaining to copyrights -- at least some caveats on which chatbots to avoid.
Another problem is that we don't know where the training data came from. There could be deep web data in there as well. That can't be easily accessed to check for plagiarism. So, is it a good idea to use blackbox chatbots? There are transparent surface web chatbots that include references for verification, so maybe we should recommend that the blackbox ones be avoided.
Now, for the second issue (the one that you skipped): WP policies do not cover prompting a chatbot to write material. The copyrights to material that is written by a chatbot is owned by who? The user? That has not yet been established! What stance is going to be taken by Wikipedia, and what guidance are we going to provide on this issue? — The Transhumanist09:17, 25 January 2023 (UTC)[reply]
I feel like either you are not reading what I'm saying, or we have some kind of insurmountable disagreement about what letters and words are. jp×g09:26, 25 January 2023 (UTC)[reply]
You've just fed me a variation of "you're not listening", with a little barb attached to the end. Really? That's who you are? I'm disappointed.
I read what you wrote, and I highly disagree with what you are saying...
You are saying that current copyright policy is enough: it prohibits copyrighted works from being posted to Wikipedia without the permission of the copyright holder, and that it is up to the editor to make sure that the material does not violate anyone's copyrights or Wikipedia's copyright policies.
My positions are...
1) that black box chatbots pose the danger of luring editors into violating copyright policy, that we may be faced with a deluge of copyright-violating derivative material because of it, and that some additional guidance would be appropriate: Like avoiding black box chatbots in favor of transparent ones, and...
2) that the copyrights to the natural language output composed by chatbots is unclear — what is clear is that the editor didn't write it. Since the editor didn't write it, does that mean that the editor does not own the copyrights to it? And if editors don't own the copyrights, should they be giving it to Wikipedia? Wikipedia should form a stance on the copyrights of chatbot-generated-output and present editors with guidance on this issue as well.
You have apparently been avoiding replying to those positions, and so my guess is that you are opposed to them. I strongly oppose the let's-stick-our-heads-in-the-sand approach that you support. — The Transhumanist10:55, 25 January 2023 (UTC)[reply]
P.S.: I don't think anything in writing is going to be enough. I expect that it will take software programming to deal with the problems Wikipedia will be subjected to by chatbot compositions. And that is beyond the scope of this venue. ;) — The Transhumanist11:31, 25 January 2023 (UTC)[reply]
To act or not to act
Like DALL-E last year, or NFTs the year before that. I'll believe it when I see it, and I can't see the value in spending even more time discussing a hypothetical future threat to Wikipedia. – Joe (talk) 08:39, 13 January 2023 (UTC)[reply]
The scariest yet most plausible thing is that this is happening with some of the articles but we aren't aware of it. I don't think raising awareness on this issue is a bad thing given how fast AI advances nowadays. CactiStaccingCrane (talk) 00:39, 14 January 2023 (UTC)[reply]
Simple way to defeat these AIs: train them on how humans argue about WP policy… then ask them whether AIs are reliable (pro and con)… then set them against each other on a dedicated talk page. While they argue, we can continue editing. Blueboar (talk) 01:58, 14 January 2023 (UTC)[reply]
@Doktorbuk: You are talking in terms of hindsight (asking to see what has already happened), rather than applying foresight to assess a potential threat by asking "What could happen?"
Here's an article from the New York Times -- imagine a similar effort directed at Wikipedia using thousands upon thousands of (seasoned) new accounts to support political POVs, revise history, censor opposing opinions, and spread other forms of misinformation:
It's only a matter of time before the powers that be shift their attention, and their tools, upon the English Wikipedia. The question is, are we ready for when we have to be? Here's an article that makes one wonder what these people will do now that they have Chat-GPT to work with:
So, do we really need evidence that the English Wikipedia has already been breached by LLM-assisted POVers before proceeding? Or can we prepare for this in advance? — The Transhumanist00:34, 16 January 2023 (UTC)[reply]
Your reasoning seems to be that
ChatGPT (or its equivalents) can write disinformation quickly and cheaply
POV-pushers (governments, lobbies etc.) are currently limited by the time humans need to write disinformation
Wikipedia is a prime target for such POV-pushers
Therefore, ChatGPT (or its equivalents) will flood the gates, unless we do something.
I will grant you (1) is either already true or will likely be in the near future.
However, (2) is questionable (see that XKCD about old-fashioned human-crafted POV-pushing). I would guess coordinating the messaging and maintaining the disinformation is a much larger fraction of the costs than actually writing the text.
(3) is also dubious. Editing in a way that sticks is much harder on Wikipedia than in other places (such as facebook, reddit, etc.). Maybe it has more impact, but the cost-benefit analysis is not obvious.
@Tigraan, I think your list of assumptions is missing "5. People who want to corrupt Wikipedia (e.g., NPOV violations, stacking votes) can reasonably be expected to obey any prohibitions we announce on using this particular technology to achieve their illicit ends." WhatamIdoing (talk) 21:22, 17 January 2023 (UTC)[reply]
Dear @Tigraan: I am concerned with a flood of WP-incompatible chatbot-generated content, whether by POV'ers or good-faith editors. But it won't be at any gates. The water-level will simply rise. If and when flooding begins, it will be a matter of bailing out the excess. There are three questions relevant to such potential flooding:
1) Will chatbots be designed in such a way to prevent flooding (and bailing) in the first place by minimizing inappropriate (unsourced, misinforming) content?
2) Will the bailing be automated?
3) Shall we wait to work on #1 & #2 until after flooding has begun, or prepare in advance?
Some editors seem doubtful that the addition of content generated by LLMs to Wikipedia beyond the manual capacity of our editors to process it will happen. And I don't know if it will happen, either. But, there is a continuous stream of strong indications that LLM-based tools will become ubiquitous in the not too distant future, for general use, which, by extension, includes using them to add content to Wikipedia. Here's another:
And the technology push isn't limited to OpenAI and Google. Here's a search engine that uses a natural-language interface in both its queries and its answers:
It is looking pretty clear that some major changes are on the horizon in the way computer users will be composing web content. It is also profoundly obvious that Wikipedia isn't ready right now for much more than the current volume of content creation that it is already handling. Maybe the volume won't increase by much, or maybe it will.
However, some editors are taking the potentiality that it will seriously, and it'll be interesting so see if their preparation efforts will be sufficient to stem the tide, if or when the tide rises. Sincerely, — The Transhumanist22:51, 20 January 2023 (UTC)[reply]
@The Transhumanist, I'm not sure that these questions are really suitable to a discussion on Wikipedia. The first one, for example: Will chatbots be designed in such a way to prevent flooding (and bailing) in the first place by minimizing inappropriate (unsourced, misinforming) content?
I'd re-phrase it like this:
"Will all of the people who are not us, including those who don't care about us, carefully design their software in such a way to be convenient for us?"
Answer: No. Or, at least, it is highly unreasonable to assume that the answer is yes for all of the people who write this sort of software, and it only takes one to risk a problem. WhatamIdoing (talk) 21:21, 23 January 2023 (UTC)[reply]
That would more likely be true if members of WP or the WMF did not contact them. They are not producing these things in a vacuum. WP/WMF has a good relationship with Google, for example, which applies Wikipedia content extensively. It may be time to reach out to the companies developing chatbots too.
On the bright side, there's pressure coming from abroad, in the critique of chatbots, to be less "black box" and to provide references, which is one of the features that would help avoid problems.
Perplexity.ai already provides sources, which helps with verification efforts, and to see which ones are and are not from Wikipedia. Though, Perplexity.ai does not provide quote marks around passages that it quotes, and that is another problem. So, I guess they need to be contacted as well.
It looks very likely that chatbots will be used to compose content for other websites besides Wikipedia, and that their webpages may be included in chatbot training data too -- making an error-magnifying feedback loop a potentially huge problem for the chatbots. Too big to go unnoticed, hopefully.
It's important that we are aware of these issues if we are to have any chance in influencing solutions. Who knows, the chatbots, and/or the chatbot developers, may actually read this discussion. ;)
The WMF has been made aware of this discussion, so they can read it to prepare for discussions with participants in the chatbot sector. So, it is important that we get our concerns, and thoughts on design and strategy, in print. — The Transhumanist08:20, 25 January 2023 (UTC)[reply]
You are assuming that LLMs are being developed by a manageable number of identifiable companies, and hoping that all of them would like to protect Wikipedia.
But let's consider it from a different POV. Imagine that chatbot software is an open-source project, like Wikipedia. You have the Wikipedia:Right to fork open source projects – not just Wikipedia, but any open-source project. Anyone can add or subtract anything on their own setup. For example, if someone adds a "protect Wikipedia" module, then the next person could remove that, or even add a "scam Wikipedia" module.
I believe there will be some organizations who find that protecting Wikipedia aligns with their interests, and they will do so. But there will also be some organizations who find that protecting Wikipedia is exactly the opposite of their interests, e.g., content farms that hope they'll be cited as sources here so that their ad-filled webpages will get more traffic, and WP:UPE scammers who are hoping to reduce their costs by having their secret, internal-use-only chatbot write Wikipedia articles for clients of dubious notability, rather than paying a human to do that. I don't think that we can identify such actors, and I don't think they would change their behavior even if we talked to them.
On a tangent, the call for chatbots to cite sources and add quotation marks is probably based on a misunderstanding. LLMs aren't "quoting sources". They're predicting what a typical way to complete a sentence might be. If it spits out "The journey of a thousand miles begins with one step", it's not quoting Lao Tzu; it's saying "When I look in my database, and I see phrases that start with 'The journey of', the next bit is usually either 'a thousand miles' or 'a lifetime'. I'll pick one and see what comes next." WhatamIdoing (talk) 17:04, 25 January 2023 (UTC)[reply]
@WhatamIdoing: Good point concerning the ecosystem of chatbot developers - I was only considering the big name actors (Google, etc.), but anyone and their uncle can get involved. You are right, bad actors are inevitable and perhaps even rampant. Yet, the vast majority of chatbot use will likely be of the big name models (ChatGPT, etc.). So, contacting and working with them would be beneficial.
As for quoting, I have found that the AI search engine perplexity.ai, which includes inline source references in its natural language answers to users' questions, integrates passages verbatim from the referenced webpages into its answers without using quotation marks. — The Transhumanist09:32, 26 January 2023 (UTC)[reply]
The second source above says "Likewise, anyone who uses the web to spread scams, fake news or misinformation in general may have an interest in a tool that creates credible, possibly even compelling, text at super-human speeds." We need detection tools, and fast. The "super-human speed" part could be a dead giveaway. — The Transhumanist10:00, 28 January 2023 (UTC)[reply]
Identifying chatbot-generated text
Zero0000's post is a good start. A simple way to crystalize the situation is to ask the human editor for their rationale for a particular phrase. North8000 (talk) 03:55, 14 January 2023 (UTC)[reply]
They should also fix the problem of the chatbots making stuff up. Someone should ask the chatbot writers to turn off the poetry and fiction generation algorithms, and any other algorithms that make things up, when the chatbots are composing expository text. Or add new algorithms to handle expository writing. Just the facts. And sources. — The Transhumanist00:42, 16 January 2023 (UTC)[reply]
Is someone clear on what the copyright status of texts produced by LLMs is? From what I get, they may be considered derivative works from the dataset they were trained on. From [2]: As a result of the human authorship standard, “under U.S. current law, an AI-created work is likely either (1) a public domain work immediately upon creation and without a copyright owner capable of asserting rights or (2) a derivative work of the materials the AI tool was exposed to during training,” Esquenet continues. “Who owns the rights in such a derivative would likely be dependent on various issues, including where the dataset for training the AI tool originated, who, if anyone, owns the training dataset (or its individual components), and the level of similarity between any particular work in the training set and the AI work.” If they are derivative works then they cannot be published on Wikipedia just like this. Do we have more information on this? For example, does OpenAI specify somewhere the copyright status of the text produced by ChatGPT? Phlsph7 (talk) 09:09, 16 January 2023 (UTC)[reply]
The first question is whether a generated text that closely resembles an item from the training set is copyright infringement of that item. For instance, Microsoft Copilot happily outputs the Fast inverse square root code. I would expect that courts will judge such things to be copyright infringement. Copyright infringement statutes do not require to prove that the infringer copied a specific source (that would be difficult to prove), just that the content is substantially similar. Therefore, whether the tool is a simple ctrl-C ctrl-V or a sophisticated machine learning model should not make much difference.
The second question is whether OpenAI (or any other AI tool provider) can assert copyright on whatever the tools they provide create. The OpenAI terms of use seem relatively permissive, but others might be less generous. I do not know the answer to that question. I would hope they cannot, since they only provide tools (Microsoft should not be able to assert copyright on the text I write using Word, or the images I draw using Paint).
The third is whether a human using ChatGPT can assert copyright on ChatGPT answers, or otherwise constrain the use of the resulting text. The quote you give is probably based on the US copyright office’s position (taken during the monkey selfie copyright dispute): Because copyright law is limited to 'original intellectual conceptions of the author', the [copyright] office will refuse to register a claim if it determines that a human being did not create the work. However, giving a prompt to ChatGPT might or might not constitute significant creative input. The position that anything edited by a machine becomes public-domain is untenable (if I use an orthographic corrector on the draft of my novel, it does not turn it into PD), so it must be a question of degree. Also, non-US courts might have different opinions. TigraanClick here for my talk page ("private" contact)16:06, 16 January 2023 (UTC)[reply]
As I understand it, the degree of access by the alleged infringer to the source text in question is a factor in determining infringement. Only a specific expression is protected by copyright; if you and I independently write the same sentence, one is not a copyright violation of the other. The amount of similar text also plays a role, since the larger it is, it's more improbable that it was created without copying.
Facts and natural laws can't be copyrighted; this also covers algorithms (though a particular expression can be copyrighted). So I can't copyright a single instance of a Javascript for-loop and claim rights to all Javascript for-loops as derivative work. In cases where the learning model creator is explicitly providing its model for use as a tool, I think (disclaimer: not a legal opinion) it is reasonable for this to be the same as a work for hire. Thus if the result is eligible for a new copyright owner independent of any source texts, the tool user would be the owner. (If I use a spellchecker on the latest bestselling novel, the result is not eligible for a new copyright owner.)
To be really safe, we'd want language models trained on public domain text. But I think it could be argued with a really large model trained on, say (just drawing numbers out of air), hundreds of thousands of documents with thousands of independent authors, the resulting correlations can no longer be attributed to specific input text, for cases where the output is not a significantly long passage substantially similar to a specific source text. isaacl (talk) 18:05, 16 January 2023 (UTC)[reply]
One of the main issues to deal with would be the following: an editor tells ChatGPT to write a text on a topic and then adds this text in the form of a paragraph/section/article to Wikipedia and thereby publishes it under Creative Commons/GNU license. The question is: what are the chances that this constitutes some form of copyright violation? This might concern specifically problems with the 1st and the 2nd question addressed by Tigraan, i.e. whether the copyright of someone whose work was part of the training set was violated and whether openAI's copyright was violated. For the first question, it's probably relevant what the copyright status of the texts in the training set is and how similar the produced text is to the texts in the training set, as isaacl points out. Answering these questions would be quite relevant for any Wikipedia policy on the topic, like the one JPxG is currently drafting. Phlsph7 (talk) 07:18, 17 January 2023 (UTC)[reply]
With respect to the issue of whether LLM output inherently violates copyright law: the copyright status of LLM-generated text is not defined by statute, so it is hard to make confident claims, but precedent exists for computer-generated art and other works created by non-humans. Here is what the US Copyright office has to say:
The Office will not register works produced by nature, animals, or plants. Likewise, the Office cannot register a work purportedly created by divine or supernatural beings, although the Office may register a work where the application or the deposit copy(ies)state that the work was inspired by a divine spirit.
[...]
Similarly, the Office will not register works produced by a machine or mere mechanical process that operates randomly or automatically without any creative input or intervention from a human author.
It's not quite clear to me what the applicability is in this case. On Commons, the template and copyright category for PD-algorithm asserts that all algorithmically-generated works are public domain ("This file is in the public domain because, as the work of a computer algorithm or artificial intelligence, it has no human author in whom copyright is vested"). Whether artificial neural networks are capable of producing original intellectual output is less of a legal issue and more of a philosophical/anthropological one. It should be noted that human brains are themselves neural networks; much has been said, in a variety of fields, on the subject of whether humans create original works versus whether they merely juxtapose or recombine motifs and concepts that they're exposed to through participation in society. While interesting (and humbling), these discussions are unrelated to whether neural networks which have been exposed to copyrighted material in the course of their existence are capable of later creating original works under the purview of intellectual property law: they do. If this was not the case, a large majority of creative work would be illegal (good luck finding a band where none of the musicians have ever heard a copyrighted song before).
It does seem obvious that, say, OpenAI does not hold a claim to copyright on all works produced using its products: Adobe does not own copyright on all works produced using Photoshop, and Apple does not own copyright on all photographs taken with iPhones. If they did, this would certainly be a bold claim which required some evidence beyond idiosyncratic interpretation of vague phrasing in a EULA somewhere.
With respect to whether LLM output is capable of violating copyright law, I think the answer is obviously "yes". Here is an example, which I have just prompted from ChatGPT:
These are, indeed, the verbatim lyrics to an unambiguously copyrighted song. Of note is the fact that I specifically asked it to do this. Compare with this prompt, using the first couple line of the song:
I'm an alligator / I'm a mama papa comin' for you / I'm a space invader / I'll be a rock-'n-rollin' bitch for you
I'm a force of nature, a wild beast / A creature of the swamps, a king of the feast / I'm a living legend, a natural high / 'Cause I'm an alligator, and I'll never die
It bears mentioning that I, a human being, also know the lyrics to "Moonage Daydream", and am capable of typing them into the edit box with no assistance whatsoever; doing this in an article would still be a copyright violation. I think that, for LLMs, the critical piece of knowledge is that output needs to be checked, and that it is insufficient to assume that generated text is always novel. jp×g02:15, 19 January 2023 (UTC)[reply]
On the narrow point of who owns ChatGPT outpt, Sec 3(a) of their ToS states "OpenAI hereby assigns to you all its right, title and interest in and to Output...You are responsible for Content, including for ensuring that it does not violate any applicable law or these Terms." I thought there was an additional requirement to state ChatGPt was used, but I do not see it in the terms. Slywriter (talk) 02:14, 19 January 2023 (UTC)[reply]
@JPxG: since you mention computer-generated art: there are some lawsuits against Stability AI based on the claim that they violated the copyrights of people whose images were used in the training set. See [3] and [4]. The case seems to be similar to LLMs, with the main difference being that their AI trains on images and creates images while LLMs train on text and create text.
If I interpret the statement by the US Copyright office correctly, it seems to claim that a person can't own the copyright of a work that was created by a random machine process without creative input. It does not say that such processes cannot violate someone else's copyright. This would be in tune with the lawsuits mentioned above.
I think it's also unlikely that every output is a copyright violation. For example, if you just give it a sentence and tell it to correct spelling mistakes, there should be no problem in using the output. Phlsph7 (talk) 06:33, 19 January 2023 (UTC)[reply]
Yes, and I think that "in a way no user could reasonably miss or misunderstand" requires the use of a notice in the article itself as well. –dlthewave☎13:53, 21 January 2023 (UTC)[reply]
@Slywriter, JPxG, Phlsph7, Alalch E., and Dlthewave: Concerning the TOS clause that states "OpenAI hereby assigns to you all its right, title and interest in and to Output...You are responsible for Content, including for ensuring that it does not violate any applicable law or these Terms." — does that mean that Chat-GPT cannot legally produce the exact same output twice without violating the right, title, and interest that it previously assigned? — The Transhumanist20:47, 21 January 2023 (UTC)[reply]
@Isaacl: I didn't come to a conclusion, I just asked a question, pertaining to Sec 3(a) of their ToS as referred to and quoted by Slywriter above, and repeat quoted by me. It appears you missed the quote somehow, because you didn't comment on it. To what license are you referring, and what relation does it have to the passage we quoted from the TOS? — The Transhumanist02:52, 22 January 2023 (UTC)[reply]
I don't know why you would ask the question you did, since the section you quoted did not say anything about granting an exclusive right, title, and interest to any output. isaacl (talk) 03:08, 22 January 2023 (UTC)[reply]
I don't think this has something to do with producing the same output for different users. It should be easy to find mock queries to which it often responds with the same output, for example, by asking it to "Say the word 'Hello'" or for simple translations. Phlsph7 (talk) 06:50, 22 January 2023 (UTC)[reply]
@Isaacl: Well, I checked the section again, and it is right there in plain English. It uses the word "assigns" instead of "grants", and it says "all its" instead of "exclusive". So, once it "assigns all its right, title, and interest in and to Output", how can it legally ever produce that same output again? (Because it already assigned it away). — The Transhumanist09:20, 22 January 2023 (UTC)[reply]
As I understand it, anyone can assign all their rights to the output of ChatGPT to someone else. In a similar way, I could assign to you all my rights to the Harry Potter series. This would not be of much use to you since the expression "all my rights" just refers to "no rights" in this case. Phlsph7 (talk) 09:32, 22 January 2023 (UTC)[reply]
@Phlsph7: In section 3a of the TOS, it's OpenAI that is assigning its rights to the chatbot output generated for the user. If Chat-GPT writes you a 3 paragraph explanation of gravity, and OpenAI has assigned you its rights to that explanation, can Chat-GPT legally write that exact same output for somebody else? — The Transhumanist09:58, 22 January 2023 (UTC)[reply]
I assume it works something like the following: it depends on whether openAI had any copyrights on it in the first place. If it did then this may be a problem because creating the copy for the second user might violate the newly obtained copyright of the first user. If it didn't then it presumably wouldn't be a problem because assigning all its rights to the first user effectively didn't do anything. But I don't think that this particular issue is very relevant for Wikipedia. Phlsph7 (talk) 10:14, 22 January 2023 (UTC)[reply]
The tool made no guarantee that it wouldn't generate the same output again for another user. The tool is in essence passing any rights of ownership (if they exist) in the original input through to the output. isaacl (talk) 19:24, 22 January 2023 (UTC)[reply]
who owns the copyrights of perplexity.ai's answers
And it returned the following answer:
"According to US copyright law, works generated solely by a machine are not eligible for copyright protection[1]
. Therefore, the copyrights of Perplexity AI's answers belong to its co-founder and CEO, Aravind Srinivas[2]."
It looks like I just broke copyright by copying it here. But this contradicts the title of the first source provided (the second source is behind a registration wall):
Assuming that Aravind Srinivas does not own the output, I have some questions about posting AI search engine results:
I look forward to your replies to the below questions. — The Transhumanist19:27, 21 January 2023 (UTC)[reply]
Question 1: Does putting quotation marks around a small copy/paste selection from an AI search engine, like the passage above, fall under fair use?
I would assume so. It's similar to how you can quote from copyrighted books. There are some limitations, for example, concerning the length of the cited text. And it should be clear where the quotation came from. Phlsph7 (talk) 06:57, 22 January 2023 (UTC)[reply]
Question 2: Would that protect Wikipedia (and its editors) from a derivative work claim?
From [5]: "In its most general sense, a fair use is any copying of copyrighted material done for a limited and “transformative” purpose, such as to comment upon, criticize, or parody a copyrighted work. Such uses can be done without permission from the copyright owner. In other words, fair use is a defense against a claim of copyright infringement. If your use qualifies as a fair use, then it would not be considered an infringement." Phlsph7 (talk) 07:06, 22 January 2023 (UTC)[reply]
Question 3: Let's say that perplexity.ai answers the same way to 2 different users, and they copy/paste the response on 2 different websites — who owns the copyright of that passage?
In our discussion so far, we haven't been able to conclusively figure out whether someone owns the copyright at all and, if so, who. That 2 users get and use the same response would be just a special case. Phlsph7 (talk) 07:14, 22 January 2023 (UTC)[reply]
Question 4: Would running a passage (from a chatty AI search engine) through a plagiarism checker be enough, before copying it into Wikipedia?
Plagiarism checkers are not perfect so they can't ensure that no plagiarism/copyright infringement was committed. The question would be whether they are good enough for our purposes, i.e. whether they are quite reliable for spotting plagiarism/copyright infringement pertaining to AI-generated texts. Phlsph7 (talk) 07:26, 22 January 2023 (UTC)[reply]
Question 5: Does Wikipedia policy allow an editor to click "Publish changes" for content that the editor did not personally compose?
Clarification: Clicking "Publish changes" implies that the editor composed the changes. Can an editor publish changes that they did not personally compose, that were composed by a chatbot search engine? (Please quote and provide links to the specific policies that allow or disallow this). Thank you. — The Transhumanist20:13, 21 January 2023 (UTC)[reply]
That would probably be a case of WP:PLAGIARISM even if no copyright infringement is involved. According to the summary: "Do not make the work of others look like your own. Give credit where it is due." Phlsph7 (talk) 07:06, 22 January 2023 (UTC)[reply]
@Dlthewave and Phlsph7: Interesting. So, if you prompted a chatbot to write a new paragraph for the article on cream cheese and you add that to the article, you include an attribution to the chatbot in the edit summary? What do you put in the source reference? — The Transhumanist11:58, 25 January 2023 (UTC)[reply]
@The Transhumanist: As I understand it, for WP:PLAGIARISM it's sufficient to mention the source in the edit summary. You would have to find and add other reliable sources yourself since ChatGPT provides no sources or sometimes invents non-existing sources. However, for the Sharing & Publication Policy of openAI, in-text attribution would probably be necessary. So to comply with it, you would have to start the paragraph on cream cheese with something like "According to ChatGPT,...". This way, the text couldn't be used at all since ChatGPT is not a reliable source. Phlsph7 (talk) 12:23, 25 January 2023 (UTC)[reply]
Perplexity.ai's answer to some other questions
I gave Perplexity.ai some questions, and here are the answers. I gave it some questions asking what would it do if it was an administrator, instead of just a normal editor, along with some other things. Helloheart 20:23, 19 March 2023 (UTC)[reply]
I am now adding the {{disputed}} template when encountering an AI-generated article, based on the following from the ChatGPT FAQ: These models were trained on vast amounts of data from the internet written by humans, including conversations, so the responses it provides may sound human-like. It is important to keep in mind that this is a direct result of the system's design (i.e. maximizing the similarity between outputs and the dataset the models were trained on) and that such outputs may be inaccurate, untruthful, and otherwise misleading at times. The commonality of all the AI-generated articles I've encountered so far (4, to be honest) is that they are not properly footnoted, implying that the author has not confirmed that the AI output is correct. The disputed tag seems to cover this issue well. I'm also dropping a note on the article's talk page explaining the link between AI output and correctness. — rsjaffe🗣️01:00, 24 January 2023 (UTC)[reply]
ANI case is wrapping up. The first three articles were written by a hoaxer, and the refs for two of the articles may have been generated as well. The fourth article was promoting a company. — rsjaffe🗣️04:18, 24 January 2023 (UTC)[reply]
This gives us a good look at the type of plausible-sounding nonsense that we can expect from LLM output. Comparing the draft (archive version, since it will likely be deleted soon) to Gecko, I see a few factual errors right away:
Not all geckoes belong to the family Gekkonidae, which doesn't have 1500 species.
Not all geckos have specialized toe pads that allow them to climb vertical surfaces.
The largest geckos are 23"-24", not 10".
Not all geckos are oviparous; some bear live young.
I started screening Drafts more carefully and am getting a number of hits corresponding to probable AI-generated articles (or at least part of the article is AI-generated). Examples include:
Draft:Honda Big Red UTV 99.98% (features and maintenance sections, omitting the headings when measuring)
The list could go on, but I think this is enough to see some information about this. These pages tend to be created by users with few edits. A number of users are doing this, not just one or two. Conclusion: the tsunami has arrived. — rsjaffe🗣️03:15, 25 January 2023 (UTC)[reply]
I think that mw:ORES (used in recent changes to highlight bad faith and vandalism) should integrate a screening mechanism for GPT-3 and other bots asap. I envision this is already a huge problem when large amount of hoaxes can be disguised as good content and we wouldn't even know about it. CactiStaccingCrane03:21, 25 January 2023 (UTC)[reply]
Looking at the first few, the sourcing is not up to the standards of promotion to article space. Once clearly bad sources are removed and unsourced claims are tagged, this can clearly be seen. If AI ever gets to the point of being able to write an article that provides accurate information properly and verifiably sourced to reliable sources, then I'll be happy to have it writing for us. BD2412T03:46, 25 January 2023 (UTC)[reply]
Well, some AI-generated articles have made it into article space. The first one I found has lots of text that's probably not AI-generated, but has a big hunk that is. Pavilion of Harmony, from "The Harmony Pavilion of New Asia College..." to "unique addition to the campus of New Asia College.", after removing the footnote indicators that confuse the analysis, rates as 99.98% fake. So the problem will leak into article space. And this means we need a way to pay special scrutiny to the AI-generated section, as that section is likely to have plausible but false information, given the way current AI models work. — rsjaffe🗣️04:13, 25 January 2023 (UTC)[reply]
I agree that this could easily turn into a major problem as LLMs become more popular. As discussed at #Copyright status, these drafts violate at least WP:PLAGIARISM but probably also the Sharing & Publication Policy of openAI (if they were created using openAI tools). If AI-detectors are reliable, including them in mw:ORES would probably help a lot to mitigate the problem in case such an integration is feasible. Another alternative would be to create a bot that checks new submissions and tags them if they score a high value. A further thing to do at some point might be to make the editors reviewing drafts and new articles aware of this problem. Phlsph7 (talk) 06:28, 25 January 2023 (UTC)[reply]
@Phlsph7 said: A further thing to do at some point might be to make the editors reviewing drafts and new articles aware of this problem. That's how I stumbled unsuspectingly upon this issue. I'm a new page patroller. I think they need to be looped in now, as that is the only guaranteed review step for new articles, and LLM-generated articles are already appearing. (I'm hoping that those users allowed to have their articles bypass this process won't abuse LLMs.) — rsjaffe🗣️17:09, 25 January 2023 (UTC)[reply]
@Rsjaffe:Wikipedia:New_pages_patrol has various instructions on the different issues that new page patrollers need to be aware of. Maybe somewhere in there, a subsection could be added on AI-generated articles. Among other things, it should give a short explanation of what it is (the user tells the AI to generate an article in a matter of seconds and copy-pastes the results), what the problems are (plagiarism, false statements, no or invented sources, possibly copyright violation), and how to spot them (things AI-generated articles have in common and tools to detect them, like https://openai-openai-detector.hf.space/). Phlsph7 (talk) 19:31, 25 January 2023 (UTC)[reply]
Can I recommend, at least for right now, that some of these pages be copy-pasted into projectspace somewhere, so that we can see what they actually look like? I feel like these discussions basically have a couple-hour-long window outside of which it's impossible to see what everyone is talking about. jp×g19:12, 25 January 2023 (UTC)[reply]
I will note here that the detector being linked here (at https://openai-openai-detector.hf.space) is a very old model tuned for the 2019 GPT-2, not GPT-3 or ChatGPT (3.5). I don't know if it's producing reliable results. It seems to me like most of the things it's flagging as machine-written are abysmal crap, so maybe it doesn't make a difference. jp×g19:17, 25 January 2023 (UTC)[reply]
Some trials on articles I've written (using the lead paragraphs): Powder House Island and Nina Jankowicz are estimated at 99% human-written, but First Wikipedia edit is at 20% GPT for some reason. 1-Pentadecanol returns 40% GPT based on the first sentence, which decreases with subsequent sentences to 99%. However, when I asked ChatGPT to "write me a Wikipedia article about 1-pentadecanol", the result (which is viewable as an HTML comment if you edit this section) was estimated as 92% human-written. I don't know exactly what the underlying mechanism of this tool is, but we may want to take its output with a grain of salt. jp×g19:23, 25 January 2023 (UTC)[reply]
The most recent articles I pulled (the ones in this section) were all initially detected by me using a search for a "signature" of a particular type of way of producing text for a particular version of LLM engine (I'm being vague as to not give hints to those who are trying to evade detection). I then visually confirm the signature. Then I run it through the GPT-2 detector. And then I'm only listing pages with > 99% chance of being LLM-generated. I'm 100% sure that the ones I've listed above are LLM-generated, but I'm also certain that this is only detecting that subset being generated under that specific set of conditions. — rsjaffe🗣️19:24, 25 January 2023 (UTC)[reply]
Also, you have to remove the bracketed reference numbers (e.g., [2]) from the text as well as any intercalated headings to give an accurate score. — rsjaffe🗣️19:26, 25 January 2023 (UTC)[reply]
To test them, I asked ChatGPT to "write a Wikipedia article on cream cheese". It produces the following:
Extended content
Cream cheese is a soft, mild-tasting, white cheese that is made from a mixture of cream and milk. It is typically sold in blocks, and is commonly used as a spread on bread or crackers, as well as in cooking and baking.
The origins of cream cheese can be traced back to the early 19th century in the United States, where it was first produced by William Lawrence, a farmer and cheese maker from New York. Lawrence accidentally discovered the process for making cream cheese while trying to replicate the French cheese Neufchâtel. He began producing and selling the cheese under the brand name "Philadelphia Cream Cheese."
Cream cheese is made by blending cream and milk, and then adding a starter culture and rennet to coagulate the mixture. The curds are then drained and the remaining whey is discarded. The curds are then salted and packaged.
Cream cheese is a versatile ingredient and can be used in a variety of dishes, including dips, spreads, and baked goods. It is a key ingredient in many traditional American dishes, such as cheesecake, bagels with cream cheese, and lox and cream cheese. It is also commonly used in cooking and baking as a replacement for butter or other fats, as it adds a rich, creamy texture to dishes.
Cream cheese is also a popular ingredient in many international cuisines, particularly in Asian cooking. In China, cream cheese is often used as a filling in steamed buns and dumplings, while in Japan, it is used in sweet and savory dishes, such as cream cheese-filled pastries.
Cream cheese is typically sold in blocks, and can be found in most grocery stores and supermarkets. It is also available in a variety of flavors, including plain, herb, and smoked salmon.
In conclusion, Cream Cheese is a soft, mild-tasting white cheese made from a mixture of cream and milk, it is a versatile ingredient used in many traditional American and international dishes and it's also commonly used in cooking and baking as a replacement for butter or other fats. It is typically sold in blocks and is available in a variety of flavors.
All the detectors agree that this text is AI-generated. When I fed them with the lead of the article Wikipedia (pure text without reference signs), they all agree that it's human-generated. Phlsph7 (talk) 20:03, 25 January 2023 (UTC)[reply]
Some attempt at figuring out what these are: I think that they are all based on the same code from HuggingFace. The actual source is here. I think that it may be simple enough for me to deploy it on a Toolforge test account; some of these websites seem unbelievably seedy. For example, "Content At Scale" advertises:
Want undetectable AI content? Our platform is the only one of it's kind that allows you to upload up to 100 keywords and get back 100 entire human quality blog posts (title to conclusion) without any human intervention. All the while, bypassing AI detection as it's the most human-like AI content ever produced. Our proprietary system uses a mix of 3 AI engines, NLP and semantic analysis algorithms, crawls Google, and parses all the top ranking content to put it all together. This isn't an AI writing assistant, this is a human level long-form blog post producing machine!
How would pasting in content generated by a chatbot be interpreted under WP:VER's requirement that all quotes must be referenced?
WP:VER states that all quotes must be supported by inline citations. If the chatbot's text is unique rather than preexisting somewhere else, using it would in essence be quoting the chatbot — how could that, as it isn't recorded anywhere, be referenced for verification purposes?
For not requiring referencing the quote of a chatbot, would WP:VER need to be modified?
News update
We need to get and stay ahead of this AI thing. See the following to get an idea how fast this movement is progressing:
This article features the following Wikipedia article, initially composed using Chat-GPT: Artwork title, by Pharos, a great example of how a chatbot can be used by a responsible editor. Maybe a blanket ban is too much, and guidelines on how to use it correctly would be better. Makes auto-removal harder, though.
I think that there is a long list of things that make chatbot content objectively bad for / incompatible with Wikipedia in its current form and methods. Without elaborating here, a few quick notes are the inherent "blackbox" nature of AI, the inherent unaccountability for content, the inherent non-linking of content to sourcing, the fact that they do not know or follow Wikipedia policies and guidelines, (which themselves are a fuzzy ecosystem rather than categorical rules) they do know take into account what is already in the article, they (as a practical matter) remove accountability and expectations from the person who added the material. They also would destroy the ability to obtain volunteer time to review what has been put in. Most people willing to spend time to review something because they know that a human editor has take the time to write it would not be willing to spend large amounts of time dealing with something generated by a bot in a few seconds.
My thought is that we should say that such chatbot generated content is not allowed in Wikipedia. This is just briefly written, I or someone could flesh this out into something carefully written if there is interest.
We can and should decide this without or prior to solving the question of how to detect and enforce. A premise of having to solve detection and enforcement before step #1 would be a poison pill for accomplishing step one. Sincerely,North8000 (talk) 20:42, 25 January 2023 (UTC)[reply]
@North8000: There has been a draft guideline at Wikipedia:Large language models for a few weeks. I do not know that banning their use entirely is a good idea, but it seems quite obvious that just copy-pasting gigantic chunks of text directly from the model's output into the edit box is not a good idea (and almost zero percent likely to result in usable articles). I will try to write some stronger wording emphasizing that nobody should be doing this. jp×g22:46, 25 January 2023 (UTC)[reply]
Support blanket ban - I agree with North8000 that the policy should be "Chatbot generated content is not allowed in Wikipedia." I think this should apply to all namespaces, including talk pages. As chatbots improve, the policy can be changed, but right now, chatbot use for generating WP content appears to be a can of worms. — The Transhumanist01:03, 26 January 2023 (UTC)[reply]
Pertaining to talk pages and forums, I meant not allowing the use of chatbots to generate a user's statements in a discussion. Posting chatbot output on a talk or forum page as an example in order to discuss it, is appropriate. — The Transhumanist12:33, 26 January 2023 (UTC)[reply]
Support auto-screening - Pharos and their article Artwork title changed my mind (and is featured in Should ChatGPT be used to write Wikipedia articles?). I'd like to see a draft on guidance for the responsible use of chatbots in writing articles, including Pharos' approach. Meanwhile, our tech persons can work on automating the removal of undisclosed chatbot additions and the tagging and eventual removal of other entries that don't get edited within a reasonable time frame, or that are part of a pattern of posting disclosed but unedited chatbot submissions. Donald Albury was right, bad actors are going to spam Wikipedia with chatbot crap whether we ban it or not. Therefore, we should allow good actors to help offset their impact. Which brings us to the rest of the Web: it will be subject to hosting chatbot content, and so, as we are Wikipedia, we should trailblaze how to do it right. — The Transhumanist16:21, 28 January 2023 (UTC)[reply]
Oppose a blanket ban. I think JPxG's demonstration shows that a LLM can be good for repetitive tasks like formatting a table, as long as a human validates the output. Actual generated prose is likely to be unsourced or sourced to fake sources, and so is already covered by existing policies. -- King of ♥ ♦ ♣ ♠01:23, 26 January 2023 (UTC)[reply]
Oppose any blanket ban. Do think CSD modifications are needed to quickly remove algorithmically generated articles (AI is market speak here, it is not sentient and intelligence is debatable) and some formal guidance for editors would be useful. It's a tool like AWB, Twinkle, and any other scripting used. Used properly, it can cut down tedious work Slywriter (talk) 01:30, 26 January 2023 (UTC)[reply]
Support blanket ban with the possibility of allowing specific use cases as we learn more. Our guiding principle should be that AI is completely inappropriate for creating or editing prose. Given the amount of plausible-sounding nonsense we've seen in recent AI-generated drafts, I also don't trust it for coding work such as formatting text or rotating tables until its reliability has been demonstrated for the specific task. This should apply to article, talk and draft spaces with very limited exceptions for demonstration purposes. –dlthewave☎03:24, 26 January 2023 (UTC)[reply]
With respect to tables and templates, what do you envision as "demonstrating reliability"? It is not exactly brain surgery to look at a table and see if the columns or the parameters or whatever are in the right places. You have to do this anyway: we currently do not require editors to prove that they have never typed an extra } and had to go back and fix it. jp×g05:35, 26 January 2023 (UTC)[reply]
Oppose for a variety of reasons, as discussed by others above. But I'll go with the most basic one: how would any of this be actionable? I know you claim it's a poison pill problem to raise, but there's no way whatsoever to detect this with certainty. We'd be using an outside tool to claim text is AI written and then delete things based on that claim. I don't care how many 9's you've got in the decimal places, there's no way to be infallible here. If the editor that added the text says they wrote it themselves, are we just going to say that they're lying and that they have to re-write it or something? There's not even evidence of copyvio in such a case and if the added content meets all other requirements, including proper verifiable sourcing, then I see no way to enforce such a ban. SilverserenC03:33, 26 January 2023 (UTC)[reply]
Comment I'm not fully decided whether banning it entirely is the right course of action at this stage. But there is a significant potential to abuse it so most forms of non-trivial AI-assisted edits should be strongly discouraged. The policy should make it very clear that any addition of AI-generated text needs to be labeled as such in the edit summary to avoid WP:PLAGIARISM. The editors also need to be reminded to obey the license and sharing policy of the AI provider. In the case of ChatGPT, for example, in-text attribution is apparently required. Phlsph7 (talk) 08:53, 26 January 2023 (UTC)[reply]
Support blanket ban of any LLM-generated text. Not sure yet about using such tools purely for lay-out, but it should not be allowed for either generating new text or for rephrasing existing text, as both cases are way too problematic. As for "how is this enforceable", just like other difficult policies, where near certainty is sufficient (like WP:DUCK for socks, which isn't infallible but good enough). Advantages of a policy are also e.g. when a newbie says something like "why was my article deleted, it was generated by ChatGTP so has to be good", one can easily point to the policy to explain that it isn't allowed instead of having this discussion again and again. Fram (talk) 09:04, 26 January 2023 (UTC)[reply]
That's a good point about potential problems with enforcing it. Having a policy can be useful to discourage certain types of behavior even if it is difficult to enforce in every case. We'll have to see how useful and reliable AI-detectors are in this process. Phlsph7 (talk) 09:15, 26 January 2023 (UTC)[reply]
I think the way forward is even stronger expectations on sourcing. If you can't provide the content of the reliable source for your edit, it should be reverted. (This would include people machine translating foreign Wikipedia articles without having access to the original sources). —Kusma (talk) 10:30, 26 January 2023 (UTC)[reply]
I assume that you are referring to automatic reversion (correct me if I'm incorrect). What about the wording of the verification policy that reads "challenged or likely to be challenged"? If it is not challenged or likely to be challenged, it doesn't need references. How will a bot be able to tell the difference between what does and does not require references? Or would the bot's removal of an edit constitute a challenge? Whether reversion is automated or not, should all new content to Wikipedia be challenged by default? That would require a change to WP:V, and that seems unlikely to happen. — The Transhumanist11:36, 26 January 2023 (UTC)[reply]
I'm not talking about automatic reversion, can't see how to do that without AI. And the verification policy is applied differently to new and existing articles; for new articles, we are in practice already expecting much better sourcing than "likely to be challenged" (just look at what will be rejected by AFC). Perhaps we should expand this to addition of content to existing articles. —Kusma (talk) 13:56, 26 January 2023 (UTC)[reply]
Support blanket ban for now; would be fine having a discussion later on allowable use cases, but I'd rather we started with a total blanket ban first, and then itemize specific possible use cases if we later decide there's some utility. --Jayron3212:47, 26 January 2023 (UTC)[reply]
Support blanket ban for prose as there is significant copyright violation concerns about AI text. Text generated by bot will not substitute reliable sourcing. Maybe in the future when Abstract Wikipedia come online, we can give some leeway for bots to generate text based on reliably cited info, but for now, it's just too risky for the project. CactiStaccingCrane13:34, 26 January 2023 (UTC)[reply]
If there is interest in at least reviewing this possibility (which it sounds like there is), as noted there it needs to be written better than my initial trail balloon above. I'll do that but still keep it short. I think that it can be done in a way that deals with the main enforcability questions and also allows described useful uses by allowing bot-assisted editor generated content. I'll do that within a 1/2 day. North8000 (talk) 14:33, 26 January 2023 (UTC)[reply]
support ban for text additionsThis is so susceptible to abuse and inserting misleading content that it should be banned. There is little benefit of allowing text generation and much harm.
Oppose new policy that goes beyond small clarifications of WP:BOTPOL. I think it is obvious that ChatGPT is already covered by it and I do not see what modifications are proposed.
Things that go against a content policy (WP:COPYVIO, WP:V, etc.) should be reverted / deleted on those grounds, and on those grounds alone; editors that make many such edits should be warned and then blocked. Editors who make faster edits than reasonably possible by hand should be dealt according to WP:MEATBOT.
I oppose any policy to revert / delete / ban based solely on a "seems bot-written" criterion, unless and until it has been proven that (1) this is a real, time-consuming problem on Wikipedia, and not a few random tests within the sea of vandalism, and (2) whatever criterion is used has been independently tested to establish its sensitivity and specificity and validated by the community. TigraanClick here for my talk page ("private" contact)17:24, 26 January 2023 (UTC)[reply]
Oppose a blanket ban. I agree in general with the oppose reasons given above. I also think such a ban would be "virtue signaling" without being effective. Editors who want to add AI-generated material to Wikipedia will not be stopped by such a policy. Consider how often our existing policies stop editors from adding un-verifiable, POV-pushing content. What we can do is work on effective strategies for detecting and removing un-sourced, un-verifiable content as expeditiously as possible. - Donald Albury19:34, 26 January 2023 (UTC)[reply]
Oppose a blanket ban. I expect that in another five or six years, we will happily be allowing a Wiki-AI to both write and clean up most of our articles. BD2412T22:26, 26 January 2023 (UTC)[reply]
While all of this wouldn't surprise me given the other aspects of this dystopia we call Earth, it would simply confirm that we live in the Golgafrinchan Ark B world. Andre🚐22:55, 26 January 2023 (UTC)[reply]
I suspect it will become necessary to rely on such bots, as our current model is creaking under the current load. In just the last three or four days I've discovered a couple articles that I started that are in need of serious cleanup and repair, particularly on sourcing (linkrot and other issues) and updating. Donald Albury22:58, 26 January 2023 (UTC)[reply]
Oh don't get me wrong, I would love to see AI bots to improve references, and do other automated tasks under the bot policy. But the AI should not be trusted for facts or interpretations. And I do fear the ChatGPT-ization of the language. There is good and bad writing on Wikipedia, but at least it was written by and for human beings. Andre🚐23:02, 26 January 2023 (UTC)[reply]
Oppose a blanket ban. I agree with King of ♥ ♦ ♣ ♠'s comment above. If an editor adds unsourced AI-generated content, that content should get treated the same way as non-AI generated unsourced content. WP:V and other existing Wikipedia policies already cover that. Some1 (talk) 00:05, 27 January 2023 (UTC)[reply]
But, a great deal of unsourced content doesn't get treated. The amount of unsourced content on Wikipedia is vast. If you don't believe me, pick a scholastic subject like Roman Empire, click on "What links here", and open a bunch of the links in tabs and start inspecting. What about random article? Too many stubs, and it's boring. With "What links here", you can get longer articles on average to view. The striking thing is the lack of "citation needed" tags - they are spaced few and far between. They can be found on roughly 1% of all pages, while unsourced content can be found on a much higher percentage.
Another thing to try is go to Template:Unreferenced, and click on "What links here". The first page I clicked on was Tank destroyer. The tag is dated March 2009.
The point is, you make it sound like all unsourced content gets quickly removed. That's not the case for a huge amount of content. It can sit there for years. LLM-generated content can be generated in great quantities fast, and therefore has the potential to accumulate more quickly than content composed by humans. Is it wise to let it sit there until a human comes along to remove it? In terms of a quantity competition between humans and computers, computers will win. This will take auto-removal to keep up. It would be best to start building those tools now. See Fram's post, above for an even better rationale. — The Transhumanist06:49, 28 January 2023 (UTC)[reply]
Holly and Judy, Wikipedians from the Glasgow branch, prepare for the AI wars.
Comment: There's no way to enforce a ban, and at any rate Wikipedia would do well to have more automation. Both MW and en.Wiki are heavily dependent on manual labor, with 3rd-party "bots" doing some of the more menial tasks. Compare how one would compose a document on a modern word processor vs. how editors do it here: no Wikitext, no copying-and-filling-out-templates (and no separate commits just for AnomieBOT to date them), no broken pages because of parsing errors, no dragging someone to ANI/AE for a T-ban violation (because there's such a thing as access control), no separate citations of the same source in five different formats (because there's such a thing as reference management); and you can actually comment on a specific paragraph without looking for a diff number, opening a "discussion" (which is in fact just another near-meaningless bit of Wikitext), signing it and hoping that no edit conflict arises because someone changed something 5,000 words up the page. We need to get rid of the concept of a WP:GNOME before we can even consider how to deal with a language model that can generate an entire article in a fraction of a second. François Robere (talk) 13:31, 27 January 2023 (UTC)[reply]
Oppose. I get that this raises some interesting questions in the abstract, but come on guys, we have enough problems with instruction creep already, we don't need to start writing policies in anticipation of the hypothetical abuse of Silicon Valley's latest fad. – Joe (talk) 14:18, 27 January 2023 (UTC)[reply]
Oppose blanket ban blanket ban and suggest we develop Wikipedia:Large language models (perhaps under the name Wikipedia:Computer-assisted text generation suggested by Michael_D._Turnbull). I don't think that going forward we can ban AI-generated text writ large, first and foremost for the very simple example that many people currently editing wikipedia use text edit widgets that already incorporate something of this in the form of spell check, autocorrection and autocomplete, and these kind of tools will continue to blur the line between AI, language models, and human-generated text. Going forward it would be practically Neo-Luddism to eschew all AI. I don't like the use of ChatGPT right now today to generate text, I don't like it at all, but neither can I bury my head in the sand and whistle Dixie, pretending it doesn't exist and won't grow in importance. We should meet this head on rather than pretend we can completely ban AI-assisted or AI-generated text. —DIYeditor (talk) 23:27, 27 January 2023 (UTC)[reply]
Oppose What seems to scare people about ChatGPT is that it writes better than most Wikipedia editors. Competition is healthy and so should not be subject to restrictive practices. See also Luddism. Andrew🐉(talk) 22:32, 28 January 2023 (UTC)[reply]
Competition is good when it's robot vs real people? You'd be happy if most of the encyclopaedia was written by AI? And most of the real people just gave up? Doug Wellertalk13:05, 29 January 2023 (UTC)[reply]
I think that most people are at least open to the idea of using LLMs like ChatGPT for good and practical purposes, such as summarizing dozens of paragraph from a reliable source, or making a WP:Earwig-like bot that detect source-text integrity issues, or detecting possible hoaxes/context-dependent vandalism in Special:RecentChanges. I'm sure that when these LLM-based tools come out, people will use them just as much as mw:ORES and User:Cluebot NG today. The problem as of 2023 is that these tools does not exist yet and as in the current form, LLMs is an extremely powerful tool for bad actors yet disadvantaged good-faith Wikipedia editors. I feel that this situation between LLMs and Wikipedia right now a bit like Wikipedia and the academia in the early 2000s, when Wikipedia is full of uncited info and its reliability is really shaky to say the least (see also https://www.nostalgia.wikipedia.org). Maybe this will change in the future when whoever makes a LLM model that's aligned to our values and policies, but in my opinion for now a blanket ban is necessary to prevent mass vandalism while we are trying to process the situation. CactiStaccingCrane13:24, 29 January 2023 (UTC)[reply]
@CactiStaccingCrane: How would a ban of LLMs prevent vandalism exactly? Vandals would simply ignore the ban, while many good actors would obey the ban. You would in effect be preventing good actors from using the tool, and not bad actors. The only way to deal with vandals who ignore a ban is directly – that is, identify their text and remove it, and block the vandals. But you can do that anyways. So, wouldn't it be best to identify and remove LLM vandalism while allowing good use of LLM-generated text? (See the starting edit and talk page for the chatbot-generated article Artwork title). So, I'm confused as to how you believe a blanket ban would help. Let me repeat my initial question, along with a follow-up question: How would a ban of LLMs prevent vandalism exactly? And why would banning good actors using LLM (like Pharos and JPxG) be necessary? I look forward to your replies to these 2 questions. Sincerely, — The Transhumanist21:46, 29 January 2023 (UTC)[reply]
Support blanket ban. Google and Bing actually considers auto-generated content as spam, which is bad for SEO. If anything, copying from GPT and pasting into an article is no different from copying from a free source and pasting into Wikipedia. The text generated is not your own, but is licensed to you forever, and, since this is a machine we are talking about and not a human, there is a probability that specific text output will be the same for multiple users for the same input.
Oppose a blanket ban. I would prefer that editors use GPT to assist in writing, but to avoid plagiarism, tag their edits as "GPT-assisted". I would additionally suggest that GPT-assisted edits be all subject to pending changes, except if a user reaches Extended confirmed status. I personally fear that, for those who are familiar with American history, ChatGPT could be the prohibition era equivalent for Wikipedia. InvadingInvader (userpage, talk) 07:47, 6 February 2023 (UTC)[reply]
Pending changes can only be applied to articles. There is no way (that I am aware of) of having pending changes apply to only some edits to an article. Donald Albury15:43, 6 February 2023 (UTC)[reply]
Comment IMHO, the issue isn't per se about how articles are written. Very few people would object if Wikipedia was provided content that was accurate, well-sourced & well-written by GPT bots. The root issue is that we don't have enough volunteers to review a flood of these GPT-created articles, let alone enough to review them knowledgeably. Viewed in this light, New Page Patrol's often-discussed problems dealing with a tsunami of new articles is but the nose of the camel poking under the tent. (And then there is the threat of gut-&-stuffing existing articles.) Most of us have other, off-Wiki demands on our time, so we are forced to contribute on a part-time basis; but even if we were all full-time volunteers, we still couldn't keep up with all of the edits. -- llywrch (talk) 21:21, 11 February 2023 (UTC)[reply]
Oppose a blanket ban. IMHO a generative AI is just a tool, like a good spell checker: it further equalizes the field for editors with language skills below native level (this is not necessarily a good thing, I personally happen to think that barriers to entry are useful in our context). From the perspective of abuse potential, the AI is not much different from wholesale copying of sources that the community is dealing with daily. What we need is a policy of full disclosure: the edits that use generated text should credit the bot; this is actually already by the bot copyright rules anyhow, so should be mandated to avoid the copyvio anyhow. --Dimawik (talk) 19:29, 22 March 2023 (UTC)[reply]
Support Artwork title is to me the case in point for why this tech is bad. The AI created version has no citations. So an editor must add citations. But that means they are working backwards, which is always the worst kind of way to cite an article. The proper Wikipedia process is finding a source, and then writing a sentence based on it. But if you write a sentence, and then find a source for it, that is confirmation bias. ChatGPT is Pandora's box, and we are in no way properly prepared to handle the pestilence it releases. Allowing AI to write our articles will serve to degrade our trustworthiness in the eyes of our readers, and for little appreciable benefit to us. CaptainEekEdits Ho Cap'n!⚓20:05, 26 March 2023 (UTC)[reply]
We have always had plenty of human editors who write articles without sources, which means someone else has to find sources to support the content. The general consensus is that we cannot just delete unsourced articles, but have to keep them around unless and until someone can build a case that the topic is not notable. Even if someone provides sources when they create an article, I am sure that they often have found the sources after they have decided what they want to write. As we do not yet have a means of identifying chatbot output with any certainty, I think banning articles written by chatbots is an unenforceable gesture at this time. BTW, I agree that the proper way to write an article is to start with a variety of sources, and see what they tell us. I have failed in writing an article if I do not know considerably more about the topic when I finish than I did before I started. Donald Albury22:09, 26 March 2023 (UTC)[reply]
Chatbot This idea probably goes to the heart of it
How about this? (just a draft to be tweaked)
An editor is responsible for every part of every edit that they make. The norm is that they should have their own rationale for everything that they added including every word, phrase and sentence. For additions to articles, they should make a specific effort to make sure that the edit is appropriate with respect to the current article. For example, with respect to the structure of the article and avoiding duplication. They should also make a reasonable specific effort to assure that each potion of their addition is verifiable or verified in accordance with WP:Verifiability. It is unlikely that these requirements and expectations would be met with AI generated content (or any large amount of text that has been copied from elsewhere and pasted in, copyvio issues notwithstanding)
Wikipedia relies on volunteer efforts to review additions. This often requires time consuming reviews of individual words, phrases and sentences; obtaining this degree of effort relies on the understanding that the editor who put the material in has made a similar effort to develop that phrase or sentence. Expecting editors to give this review to large amounts of material which were generated by AI in a few seconds would cause a substantial loss of this effort.
Accordingly, this clarifies that removal / reversion of en masse additions of material suspected of being AI generated is considered to be an appropriate practice. An editor who seeks to restore the material is expected to break it into small portions, each with individual explanatory edit summaries. If such a removal results in deletion of the entire contents of the article, it then becomes a candidate for speedy deletion.
I don't favour making machine-generated text a special case. Given that editors are already responsible for verifying every aspect of their edits, any clarifications should be equally applicable to all cases, such as human ghostwriting teams. isaacl (talk) 21:48, 26 January 2023 (UTC)[reply]
We can change the policy if something is developed that is reliable enough. Until then, blanket rejection is appropriate. — rsjaffe🗣️15:46, 27 January 2023 (UTC)[reply]
It's important to see the conduct side too because LLM misuse forms a pattern of disruptive editing. It starts with one person's idea that a specific thing can be accomplished on Wikipedia in this way, proceeds with the intent to implement this idea without caring to understand and account for what Wikipedia's requirements are, and ends with an undesirable action which may be repeated if not addressed. —Alalch E.15:55, 27 January 2023 (UTC)[reply]
If chatbots are banned, would the article Artwork title have to be deleted?
I don't think it would have to be deleted (or restarted) unless it was somehow found to be a copyvio. Maybe it would be peer reviewed instead. Roll 3d6 (talk) 08:50, 5 February 2023 (UTC)[reply]
More specific proposal: Blanket ban on LLM content on Talk page discussions
Regardless of the community's decision on LLM-generated content in articles, which is the focus of much of the discussion above, the ability of editors to flood talk pages with artificially generated content arguing for a particular position on talk seems to have no redeeming value, and represents a new form of Wikipedia:Sockpuppetry. I propose a blanket ban on such writing, with especially strong guardrails for RfC's and AfD's. (Alternatively, I would be open to a phrasing that allowed LLM's to summarize the state of a debate, or be used to generate sample content for discussion, as in the conversation above, but not used to make arguments. That just seems harder to phrase clearly.)Carwil (talk) 20:22, 27 January 2023 (UTC)[reply]
That's a really weird way to use them. Also, why would it matter? Even if an editor used an LLM to generate a better phrasing of the argument they want, it's still their account putting forth the argument. And the argument is either valid or not in regards to others involved in the discussion. Why is this a problem exactly? Do you have any examples to better clarify this sort of usage? SilverserenC23:14, 27 January 2023 (UTC)[reply]
As Transhumanist is suggesting, my concern is rapid creation of multiple arguments that either tilt a discussion or waste the time of sincere contributors. Users should be warned that they can't substitute mass-produced arguments for their own judgment inside the encyclopedia.--Carwil (talk) 19:26, 28 January 2023 (UTC)[reply]
Support - Weird? Compared to the many examples of what Chat-GPT can do posted on social media, writing talk page or forum posts on Wikipedia seems comparatively bland and simple. Why would using an LLM on a talk page or discussion forum matter? Because, it is faster than a human. With it, a user could participate in more discussions in less time. But, the big concern here is using it on multiple accounts with different writing styles to stack votes on issues with little chance of being discovered as the same person. That's sockpuppetry elevated to a higher level. Therefore, banning chatbots from being used to compose talk page or forum posts is quite reasonable. — The Transhumanist05:42, 28 January 2023 (UTC)[reply]
Support On a risk/benefit analysis, the potential benefit to allowing this is so small that any risk (as described above) is unacceptable. — rsjaffe🗣️05:50, 28 January 2023 (UTC)[reply]
Reluctant Oppose As my comments above, it is difficult to draw a line on which language models are allowed and which are not. Clearly people are allowed to use autocompletion and predictive text and such. Are they limited in what varieties and designs of autocompletion they use? I think this requires further discussion and hopefully input from experts. —DIYeditor (talk) 06:42, 28 January 2023 (UTC)[reply]
Oppose a blanket ban as premature, but support at least some restrictions. While I would certainly be first in line to support a blanket ban if an actual problem arose, I am not sure that we know exactly what shape this will take enough to come up with an intelligent solution. For example, earlier in this very discussion, we were posting LLMs' output in order to judge their capabilities, so any prohibition would need to take exceptions like this into account. That said, I do support some more specific language for WP:LLM about it being very bad to use them undisclosed to argue your case in discussions. For example, if I were a shady dude, I could flood the zone with shit right here on VPP by typing out massive walls of text replying to every single person who disagreed with me, without regard for whether my arguments were sound or even correct, and even if I represented a minority view it would probably irritate and discourage my interlocutors until they stopped commenting (thus bringing me closer to a majority). Similarly, at the blood-soaked fields of AfD I could trivially write out a three-paragraph !vote on all 50 of the day's nominations (whether I was a partisan for keeping, a zealot for deleting, or a fanatic for any sort of POV). jp×g19:45, 28 January 2023 (UTC)[reply]
Oppose a blanket ban. As JPxG, I'm open to some restrictions, but I can see LLMs as a potentially useful tool for people who want to offer their viewpoint in discussion but lack the fluency or time of some other editors. (A bit more acerbically, our discussions already tend to be influenced by editors who are functionally LLMs: good prose stylists, possessed of enormous sitzfleisch, and not well grounded in factual specifics. If LLMs force us to review WP:BLUDGEON and our methods of dialectic/achieving consensus, there's no reason to grant people like that the privilege of immunity.) Choess (talk) 20:44, 28 January 2023 (UTC)[reply]
I think your example misses the spirit of my proposal, which is un attributed LLM output substituting for our own reasoning and arguments on Talk. Happy to modify accordingly. --Carwil (talk) 13:25, 29 January 2023 (UTC)[reply]
Oppose a blanket ban on talk pages specifically (I would support one in article space). The largest problem by a huge margin with using ChatGPT on Wikipedia is adding factually incorrect information to articles. This is less of a concern with talk pages, which the general public doesn't usually read and which are not primarily meant to impart facts or be reference material. We already have a ban on sockpuppeting and an expectation that decision-makers will ignore bad arguments, which cover the negative use cases mentioned above. Also, as mentioned above, there is not an enormous difference between ChatGPT and predictive text or services like Grammarly, and the line between those is going to become blurrier by the day, faster than policy can keep up with. Gnomingstuff (talk) 01:20, 3 February 2023 (UTC)[reply]
Oppose as making up rules when no problem has been demonstrated. If it does happen, we can warn, revert, and block the offending material and offender for wasting our time. Graeme Bartlett (talk) 12:10, 3 February 2023 (UTC)[reply]
Oppose LLM:s are state of the art translation tools so banning them from discussion is unproductive. I think that it would be nice that if there is new content generated by LLM it is told, but generally using LLM as writing assistance should be allowed. --Zache (talk) 10:26, 19 March 2023 (UTC)[reply]
Since the discussion basically died out after being closed, rather than migrating to WP:LLM, I'm undoing User:CactiStaccingCrane's close, with his permission. Let's keep all discussion in one place, so we can get solid consensus on all these points. DFlhb (talk) 13:46, 1 February 2023 (UTC)[reply]
If we can work out the issues that editors improperly using these tools will cause then we can adjust our policies to make it easier to address those issues, and then as the technology develops we can see how it is being used and how it can be used and create a more specific policy then. BilledMammal (talk) 11:21, 13 February 2023 (UTC)[reply]
Copyright unclear as the source of the material is unknown
Copyright unclear as the issue of who owns the output of a chatbot has not been resolved
Inclusion of 3rd-party copyrighted material, such as lyrics, a poem, etc.
Chatbot license violation (e.g., for omitting attribution of the chatbot with the generated content)
100,000,000 ChatGPT users and growing (after just 2 months),[6][7][8][9] suggesting that the use of tools like this may become ubiquitous, creating the potential for a large volume of one-off posts of chatbot generated text (and other media)
I think that the community will benefit from WP:AGF towards the bot use and establishing the clear rules for constructive edits. I propose at the very least:
Mandate a standard format for the copyright reference giving the credit to the bot (Google Bard apparently uses the Creative Commons Attribution-ShareAlike 3.0 Unported license, which should be good for our purposes (here is the response I got from the Bard: I am licensed under the Creative Commons Attribution-ShareAlike 3.0 Unported license, which means that you are free to share and use my text as long as you give me credit and share any changes you make under the same license.). The reference should be both in the edit history and on the talk page, similar to other CC BY SA reuse (WP:COPYWITHIN). If someone had already created a template similar to {{copied}} that mentions the bots, please let me know.
Mandate much higher levels of quality for generated text (high quality sources, proper cites, etc.).
Mandate a copyvio check with reference to the results placed onto the talk page.
Encourage the speedy deletion of newly created or added generated text not meeting #1, #2, and #3. Essentially we might want to treat the bot abuse in the same way as WP:COPYVIO.
Unless I see objections here, in the next few days I am going to create an article Bailey FFT algorithm as an example of using the Google Bard for creating the new articles. I am slightly aware of the topic and thus will be able to separate wheat from the chaff and provide proper sources. Comments will be welcome. --Dimawik (talk) 19:55, 22 March 2023 (UTC)[reply]
Bard is not licensed under CC BY-SA 3.0. You asked Bard, and it gave you a bullshit answer, because that's what Bard does. Another user got Bard to say that it got shut down 6 months ago, because "Google Bard was not a very innovative product". You cannot trust its answers to be accurate. Google's terms of service never state which license covers Bard's output, but Google has no right to set any license anyway, because in the U.S., LLM outputs are not copyrightable. DFlhb (talk) 20:06, 22 March 2023 (UTC)[reply]
Thank you for spelling out the additional tidbits. I am already aware of the situation you describe. Incidentally, I am kind of expecting to see the Supreme Court forced to revisit its decision soon, as there is no clear boundary between a very advanced spell checker (or a machine translation tool) and generated AI, and using the next-generation Grammarly surely does not cause the writer to lose her rights. However, (1) in a situation like this one has to cover his/her behind with a cardboard, and (2) going with the most restrictive interpretation (Bard's response) helps to drive through the item #1 in the list above. Dimawik (talk) 20:23, 22 March 2023 (UTC)[reply]
Make Wikipedia:Requested moves/Closing instructions a guideline
Should WP:RMCI be formally elevated to the official status of a WP:GUIDELINE? 23:15, 22 February 2023 (UTC)
Initial statement, collapsed 18:05, 26 February 2023 (UTC) to comply with WP:RFCNEUTRAL
The following discussion has been closed. Please do not modify it.
Greetings,
There has existed for eighteen years a set of instructions for how to formally close a requested move. It was initially titled as Wikipedia:Moving guidelines for administrators, later changed to Wikipedia:Requested moves/Closing instructions (hereafter WP:RMCI). Over the years, it has grown from a simple set of how-to steps to a comprehensive list of guidelines for determining consensus (which began as early as 2006 and has continued to expand through the years). It also has included instructions on who should close requests--first in 2009 when the authority to move pages was explicitly granted to non-administrators, then later in 2019 (following lots of discussion) we introduced rules on how editors who are involved need to not close requests.
The instructional page wasn't classified as anything (guideline, policy, or essay) through 2021, even though it had been originally written as a guideline. Following a post on the talk page that saw no response, it was listed as an explanatory essay in 2021.
Recently, at least one editor has asserted that, as WP:RMCI is "only" an essay, its procedures do not need to be followed; therefore, as one concrete example, editors may feel free to close move requests that they are fully involved in, so long as they think it's the right thing to do. WP:RMCI has been called "purely advisory", "not vetted", etc., leading to questions as regarding its authority--this in spite of the fact that it was written as a guideline and has guided literally thousands of move closures. This has unquestionably led to no small amount of chaos at Wikipedia:Move review following an editor who closed the same move request twice in a row (which is against the closing instructions), both with the same result, and who claimed that the closing instructions that forbid such a close by an involved user were merely "advice".
Support as proposer. The idea that WP:RMCI is not vetted by the community is laughably inaccurate; yes, it has been. It's guided requested move closures for nearly two decades, its talk page (merged with the overall WP:RM talk page) spans thirty-four archives, and drawn-out discussions are common (I arbitrarily picked Wikipedia_talk:Requested_moves/Archive_25 and found... a LOT of discussion on the precise wording of WP:RMCI). It is a fully vetted part of Wikipedia. It's not purely advisory--it's literally the only instructions we have on closing move requests. It's not an essay, it has never been an essay, it bears none of the hallmarks of an essay, and its currently listed status as an essay is a mistake. It's not an inconsequential mistake, either; people feel like they can ignore it freely, and that's leading to chaos--you have a 50/50 shot of the person who closes your move request being someone who takes our well-vetted closing procedures (up to and including don't close a move request twice) seriously, or who views them as merely "good advice" that can be freely ignored. RedSlash23:15, 22 February 2023 (UTC)[reply]
Support to stop wikilawyering about whether something is "just an essay" or not. Best practices should be followed, regardless of where they are documented. But for the sake of clarity, let's make it official that this has the support of the community. HouseBlastertalk01:33, 23 February 2023 (UTC)[reply]
Oppose. Most of RMCI are basic instructions. These exist all over Wikipedia, but none of them should be turned into guidelines because there is no benefit from doing so, and because doing so causes WP:CREEP issues. For example, there is no benefit of turning Wikipedia:Requested moves/Closing instructions#Bot considerations into a guideline.Other parts of RMCI may not have a consensus if considered individually; for example, the instruction to explicitly declare non-admin closures as such. This requirement does not exist for other discussions, even more impactful ones like RfC's, and discussions on the instruction have shown significant opposition to it on the grounds of WP:NOBIGDEALFinally, this change won't address the specific issue discussed - editors closing the same move request twice in a row. Closing a discussion is an administrative role, and the current wording of WP:INVOLVED states that this does not make an editor involved: One important caveat is that an administrator who has interacted with an editor or topic area purely in an administrative role is not involved and is not prevented from acting in an administrative capacity in relation to that editor or topic area. Changing this essay to a guideline won't make the editor involved, because when a policy and guideline conflict editors should assume that the policy takes priority.I also don't believe it makes sense to make closers involved for RM's but not other discussions - if this is an issue then it is an issue in all areas, not just requested moves. BilledMammal (talk) 10:19, 23 February 2023 (UTC)[reply]
But WP:INVOLVED is dealing with administrators doing things in an administrative capacity (which does not include requested moves), and WP:RMCI is not. Closing move requests is neither restricted to administrators nor is it an administrative task. There's no overlap at all. See below for my more detailed take on why and how this is different. RedSlash17:19, 23 February 2023 (UTC)[reply]
Both of us cannot close this discussion because WP:INVOLVED forbids us from doing so, despite neither of us being admins nor the close requiring admin tools. INVOLVED applies to all editors who are acting in an admin capacity, and that includes closing discussions - if it didn't, either of us could close this discussion now. BilledMammal (talk) 23:19, 23 February 2023 (UTC)[reply]
That's an interesting perspective I hadn't considered. I think, perhaps, an explicit (though brief) delineation of why WP:RMCI is more expansive than INVOLVED would be appropriate. Thank you. RedSlash23:43, 23 February 2023 (UTC)[reply]
I don't believe that would solve the issue; the explanation won't remove the conflict, and it won't change the fact that when a policy and guideline conflict editors should assume the policy takes precedence. BilledMammal (talk) 00:00, 24 February 2023 (UTC)[reply]
@BilledMammal: Is closing an RM an "admin capacity" or is it a "non-admin capacity"? - is there anywhere in which "admin capacity" is defined? - I had always assumed it to mean activities that only an admin is capable of, so, for instance, if an admin is closing an RM they are simply performing a non-admin activity as an admin, just as any non-admin closure is equally a "non-admin" activity. Unless we are using two different registers for 'admin' here on Wikipedia - one to mean "admin", as in the things formally restricted to someone appointed as an administrator, and then 'admin' diminutive form to refer to any activity that can broadly be construed as generally 'administrative' in nature even if it is not performed by an administrator. Iskandar323 (talk) 10:56, 27 February 2023 (UTC)[reply]
Formal closures are an "admin capacity" or, to use the wording from WP:INVOLVED, "acting as an administrator". From a practical point of view any other interpretation is problematic as it would mean there is no restriction on involved closures. However, it might be worth clarifying that section of WP:ADMIN as I have had debates where editors have claimed that it is appropriate for them to formally close a discussion they were involved in because they were not an administrator. BilledMammal (talk) 11:13, 27 February 2023 (UTC)[reply]
@BilledMammal: As Vpab15 notes, WP:NACINV specifically requires closing editors to abide by the standards of administrators as described at WP:INVOLVED, but none of this actually means that the original wording of WP:INVOLVED was necessarily meant to apply to anyone other than administrators in any other context. So I see this clash of policy/guidelines as a false one, with WP:INVOLVED not applying to non-admins or non-admins activities except in the very limited way outlined in WP:NACINV, which specifically applies the principles of WP:INVOLVED to closes. Iskandar323 (talk) 07:11, 28 February 2023 (UTC)[reply]
By using the phrasing editors should not act as administrators in disputes INVOLVED makes it clear that one isn't required to use the tools to engage in admin activity ("act as administrators"), and makes it clear that it applies to all editors, not just admins ("editors", not "administrators").
This can be seen in how the community responds to involved closures of discussions; the closure is overturned, and sanctions imposed if the editor continues to insist that because they are not admins INVOLVED doesn't apply to then. Whether this was intended to be the original meaning is not relevant; it is now the meaning accepted by the community, and in my opinion the correct meaning. BilledMammal (talk) 09:10, 28 February 2023 (UTC)[reply]
@BilledMammal: Fair enough. I guess that makes sense. Although the next paragraph (about the exceptions) is even more ambiguous, mentioning only administrators, not editors, and in fact contrasts administrators with editors, noting: "...acting in an administrative capacity in relation to that editor...", suggesting that it is worded more with a view to blocks etc. This, if anything, is a good example for the need for further clarity with respect to move closures. WP:RMCI is a more natural extension of the part in the third paragraph, where it states: "Although there are exceptions to the prohibition on involved editors taking administrative action, it is still the best practice, in cases where an administrator may be seen to be involved, to pass the matter to another administrator..."Iskandar323 (talk) 12:12, 28 February 2023 (UTC)[reply]
Support per nom. · · · Peter Southwood(talk): 17:13, 23 February 2023 (UTC)[reply] Withdrawn until the conflict with WP:INVOLVED is fixed. I consider closing to be an administrative action, as it theoretically does not involve the opinions of the closer on the content of the article, but does involve the interpretation of policy and guidance and their application to a discussion, as well as assessing consensus, and requires competence. Their are many experienced non-admin editors with the required competence in general, and fewer people with the required competence for closing any given discussion, as each topic has its own special circumstances, and we do not need closers who are ignorant of those special circumstances. · · · Peter Southwood(talk): 05:03, 9 March 2023 (UTC)[reply]
Support This is a high stakes fundamental process. When any process is as established, accepted, and in-use as this one, then I am in favor of labeling it as a guideline. The guideline label carries weight both for users and to legitimize the activities of the Wikimedia editorial community and its governance process. Bluerasberry (talk)17:25, 23 February 2023 (UTC)[reply]
I'd rather have this become a information page. Also, this sentence: NACs are not discouraged for requested moves, as long as the non-admin is highly experienced with RMs and our closing procedures sounds pretty discouraging to me. How is someone supposed to become "highly experienced", if you're not allowed to do it? And is this actually different from what we hope for with admins? IMO thoughtful NACs should be strongly encouraged to handle RMs, and admins (who have no similar requirements about knowing how RM works?) should only be involved (in their admin role) if specific buttons are needed for technical moves. Page titles are basically content decisions, and admins get no special rights in content decisions. WhatamIdoing (talk) 00:22, 24 February 2023 (UTC)[reply]
That could definitely be rewritten. Over the years, we've gone from prohibiting NACs, to discouraging them, to restricting them, to permitting them, and it might now be time to start explicitly encouraging them. I love it. I don't think that has much to do with the fate of this page as a guideline or not, but I love it. (BTW, having it be just an informational page, in my opinion, wouldn't solve the problem of people not taking a WP page seriously if it doesn't have a little checkmark next to it.) RedSlash01:25, 24 February 2023 (UTC)[reply]
I agree, if RMCI needs fixing, clarification and whatnot we can do that just as for any other page, should not affect the decision to make it a guideline imo. Selfstudier (talk) 06:27, 24 February 2023 (UTC)[reply]
I dunno. Once a policy or guideline label gets slapped on a page, editors frequently tell me that it's more difficult to get substantive changes made. Also, it's customary to solve the more obvious problems before proposing guideline status.
It is hard to quantify the time spent going through the page line by line, familiarising and refamiliarising the process in the last few months (somewhen between 4-6 months) when I decided to dive into RMs, as such it may not have been obvious to me. What's actually humourous is that those you have pinged are mostly non-admins ourselves, albeit some with pagemover rights, and we might certainly be censured by others if we had started out with this being the guidelines just by this line. Just recently, there is an editor, green in doing NACs, going through RMs, and no one is stopping them, but rather experienced closers are have been encouraging them and guiding them on their talk page. We can always have this tweaked to something more platable: i.e. NACs are acceptable for requested moves provided that the non-admin editor closing the request is familiar with the closing instructions.– robertsky (talk) 05:00, 9 March 2023 (UTC)[reply]
I think your wording would be an improvement. Personally, I'd also discourage editors from handling RMs on pages that they are unable to move themselves. IMO some RMs should be left to admins and page movers. WhatamIdoing (talk) 03:51, 10 March 2023 (UTC)[reply]
Good question - I have no idea really. I have been involved with page moves for a while (mostly technical requests), and have looked over it multiple times in the past year or two. It's not something I read for the first time after seeing this RFC. I can't say I've fully analysed every part of it, or that it is perfect. Also, "discouraged" is not the same as "not allowed". -Kj cheetham (talk) 17:17, 9 March 2023 (UTC)[reply]
Whatareyoudoing, I agree with Kj cheetham on a lot of this. I have no idea in terms of an exact number, but I have gone over it multiple times every so often, and I have in no means fully analyzed it. {{ping|ClydeFranklin}} (t/c) 23:22, 9 March 2023 (UTC)[reply]
Well, at the moment, I seem to be confirming my long-standing belief that Wikipedia:Nobody reads the directions. We guess what the WP:UPPERCASE might mean, and we look up little specific sections when we need to quote The Rules™ at someone or remember the name of a specific template (or similar detail), but we don't really read them.
This RFC started because someone didn't want this page to have a tag at the top that says "it has not been thoroughly vetted by the community." It sounds from the responses here that even if it were to pass, that's still not happening. If your responses are typical, then the people who are voting for it haven't really read it (recently, or ever), and I suspect that the people opposing only read far enough along to find something they disagree with, and then stop. On a more general level, I wonder if WP:PROPOSAL should advise would-be promoters to tell editors that they really need to read the entire current version of the page, before voting to support the promotion. We don't get many such proposals in a year, and actually reading the page that you want to have marked as having been thoroughly vetted does not seem to me like an unreasonable expectation.
BTW, if you have average reading speed for a native English speaker, it'll take you 20 minutes to read that proposed guideline from top to bottom. WhatamIdoing (talk) 03:48, 10 March 2023 (UTC)[reply]
I don’t really understand why this should be an information page, IMO it’s not factual or technical information but the community accepted procedure. Aaron Liu (talk) 14:16, 26 February 2023 (UTC)[reply]
Oppose for now. The issues are (a) inconsistency in the way we use the terms (or apply the templates for) guidelines, information pages, explanatory supplements, essays, etc., and (b) letting time-wasting by wikilawyers determine those applications. We should be more consistent. Why would this need to be a guideline, but WP:AFD, Wikipedia:Bureaucrats, WP:MFD, WP:RFA, WP:AC, WP:RFC, and WP:DRV are content to simply be process pages, even though they also have a lot of rules/guidance? Why is Wikipedia:Reviewing good articles a guideline, but there's no such guideline for WP:FAC or WP:DYK? Why is WP:PROD a guideline, but WP:AFD and WP:DRV aren't? For all the wikilawyering over essays, our page on WP:ESSAYS is an essay, and WP:PAG lumps the various types of essays together despite practically being treated very different by the community. Maybe one step is to remove "information pages" from the essay of "header" and combine them with "administration" (or "process") pages to produce something that assumes guideline-like adherence, or maybe such is the state we're in that we should actually slap guideline templates on all of these pages just to stop people from extending "just an essay" to "just a page that documents a process for which there's broad support"... — Rhododendritestalk \\ 02:14, 24 February 2023 (UTC)[reply]
I appreciate your perspective. "we should actually slap guideline templates on all of these pages just to stop people from extending "just an essay" to "just a page that documents a process for which there's broad support"..." is actually probably the best solution, because otherwise, in practice, you get people who say "but it's just an essay!" In the meantime, though, I think the proposal is the best solution for the reasons I explained above. RedSlash07:45, 24 February 2023 (UTC)[reply]
Support Seems like a good idea to give a bit of formality to existing practice. If this or that wording needs sprucing up, that can be done in the usual way and shouldn't affect the decision whether to make it a guideline imo.Selfstudier (talk) 06:32, 24 February 2023 (UTC)[reply]
Oppose. I think there is one problematic sentence at WP:RMCI that needs to be fixed. It defines involved as: You have ever closed such a move request. That contradicts the wording at WP:INVOLVED and places an unreasonable burden on RM closers, who will have to remember all the previous RM dicussions they have closed. Per discussion below, it is not even clear if "such a move request" only includes the same article, or any article in the same topic. I have no objection to the rest of the essay. Vpab15 (talk) 10:23, 24 February 2023 (UTC)[reply]
Support this proposal, but clarity as discussed above needs to be added to the guideline page soon, and re-organizing non-policy pages via template as discussed below needs to happen also. GenQuest"scribble"16:14, 24 February 2023 (UTC)[reply]
Oppose as written, at least until contentious points with "involvement" and declaring NAC closes are vetted by the community, since they contradict broader policies. Some parts of RMCI have obviously been written out of one's whim at a time, and do not even enjoy local WP:CONLEVEL among the closers' "community". The case that apparently triggered this whole RfC was Palestinian exodus MR, and the "involvement" RMCI clause being used to overturn the close procedurally. I've closed hundreds of RMs and MRs, I'm fairly well-versed with RMCI, but that clause has slipped under my radar and I'm frankly baffled by its existence. No such user (talk) 08:37, 27 February 2023 (UTC)[reply]
"do not even enjoy local WP:CONLEVEL among the closers' 'community'" - can you be specific as to what you're referring to? Wikipedia is a wiki, there's nothing in WP:RMCI which has "snuck through" or exists without the community's support. The INVOLVED part, in particular, was extensively debated, even as small a point as whether or not an involved editor can "relist" a discussion. Everything has been vetted. RedSlash23:00, 27 February 2023 (UTC)[reply]
I missed that 2019 discussion, which did not have a terribly broad input. Even if I can agree there was a local consensus at the time, WP:CONLEVEL is clear that Consensus among a limited group of editors, at one place and time, cannot override community consensus on a wider scale. As for NACs, I've been mildly annoyed at RMCI's insistence on declaring NACs (a thing that has been out of fashion elsewhere on Wikipedia for quite some time) and I'm on record stating that I'm not going to do that for my closes, ever. For the definition of "involvement", you can witness the community backlash right here. See also BilledMammal's objections above, which I fully endorse. No such user (talk) 08:59, 1 March 2023 (UTC)[reply]
Support: The 'explanatory essay' has already been discussed more than sufficiently to qualify as a guideline, which obviously would still not mean that it was as hard and fast and as ironclad as a policy, but would cease the confusion whereby some editors seem to think it is optional - a confusion that needs clearing up. There will still be exceptional cases, admins may still need to weigh in, and there will be still be need and scope for a human touch at Move Review, but there will not cause for actual confusion as to what the guidelines are, and what the basic expectations of the process are. Iskandar323 (talk) 11:03, 27 February 2023 (UTC)[reply]
Oppose mostly per No such user. I, as well, have serious problems that the NAC closure section is in clear contradiction to Wikipedia principles. Also, Rhododendrites makes some good points above. --Jayron3213:34, 27 February 2023 (UTC)[reply]
Oppose for now. I'm not opposed to a guideline about moving pages but RMCI as currently written is not it. I don't agree with its instructions, such as the language about involved, as pointed out by others, and the page is too long as currently written. I think there is maybe an opportunity to either rewrite RMCI into a guideline, or rewrite it and promote it to an info page, or maybe split it into a guideline page and an instructions page. There is some possibility for something here, but I oppose putting the guideline template on RMCI as currently written. Levivich (talk) 14:20, 27 February 2023 (UTC)[reply]
Copyediting doesn't change the meaning of the text; that's editing. But yeah, I might support if we changed the meaning of the text to something else. Levivich (talk) 19:35, 4 March 2023 (UTC)[reply]
Oppose currently. I agree that the provision "You have ever closed such a move request" is contrary to WP:INVOLVED, which explains that administrative actions do not constitute involvement. Sandstein 16:24, 27 February 2023 (UTC)[reply]
Temporary oppose. I think WP:RMCI should eventually become a guideline, but I don't think we're at that point quite yet. As other participants have stated, the "You have ever closed such a move request" provision should be removed from WP:RMCI before it rises to guideline status. Additionally, WP:NOTCURRENTTITLE has been added to the page very recently, and – while I agree with its inclusion myself – I'd like to see it receive more affirmative support from the community before letting it rise to guideline status. ModernDayTrilobite (talk • contribs) 17:15, 27 February 2023 (UTC)[reply]
On further thought, switching to weak support. The involvement issues can be hashed out whether RMCI is a guideline or not, so there's no need to hold up an ultimately productive goal on those grounds alone. ModernDayTrilobite (talk • contribs) 17:35, 5 March 2023 (UTC)[reply]
Oppose as needing more work, per points raised above (e.g. "You have ever closed such a move request"). Also, the NAC instructions differ substantially from our other procedures: to bring them in line with the spirit of NAC, I think admins and page movers should be allowed to close any RM, while other users should only close uncontroversial discussions. -- King of ♥ ♦ ♣ ♠23:03, 27 February 2023 (UTC)[reply]
Support, the involved bit isn't prohibitive - for the general reasoning, the nom's covers it nicely. On the INVOLVED bit, my interpretation is that that sets minimum standards. It doesn't invalidate any guideline to have stricter rules. Now, whether the guideline should have stricter rules is really rather more dubious, but fundamentally, it's not so egregious as to undermine the guidelineification (to my concern, that isn't being flagged as a typo). Nosebagbear (talk) 23:24, 1 March 2023 (UTC)[reply]
If closing a discussion creates a perceived conflict of interest than that can only be addressed at WP:INVOLVED, as any editor who disagrees with RMCI can accurately cite WP:INVOLVED and WP:POLCON, and because if it is an issue at RM’s it is also an issue at AFD’s and other formal discussions. BilledMammal (talk) 00:13, 9 March 2023 (UTC)[reply]
Which you did and is why this RFC exists. Many don't agree with that position though. It is of some interest that you only brought it up in order to support a !vote at an RM when most people pointed to an obvious conflict of interest. Selfstudier (talk) 00:21, 9 March 2023 (UTC)[reply]
If many don’t agree with that position then you should have no issue changing the policy that supports that position, and I encourage you to open an RFC proposing to do so.
I brought it up to push back against the notion that engaging in administrative actions made an editor involved and have not considered the rest of the RM as most of the support for overturning was solely on that basis; how is it of some interest? BilledMammal (talk) 00:26, 9 March 2023 (UTC)[reply]
Since this RFC is already open and at CENT, you can of course start a subRFC within it for anything that concerns you specifically (as per "Discussion on changing the wording" below). Selfstudier (talk) 00:34, 9 March 2023 (UTC)[reply]
Support. As per Bluerasberry. This process is well-tested, it should be as streamlined as possible and such a formal tag contributes to this as well as provides legitimacy. Any contentious points (involvement, etc.) should be resolved before promoting this page to a guideline though. Any user in good standing should be allowed to close any RMs where they are not directly involved. We could set up some general conditions though that are not dependent on public voting, such as it has been done at WP:AFC. --TadejMmy talk06:22, 2 March 2023 (UTC)[reply]
Any contentious points (involvement, etc.) should be resolved before promoting this page to a guideline though. I’m planning to open an RFC asking questions about individual contentious points should this RFC pass, which should help resolve them. BilledMammal (talk) 00:00, 9 March 2023 (UTC)[reply]
First discuss them on the talk page as already suggested by the RMCI guidance so that there is a proper RFCbefore should it come to that. Selfstudier (talk) 00:07, 9 March 2023 (UTC)[reply]
Oppose per CREEP, among other arguments presented above. Lots of WP processes have instructions/rules and we don't make them guidelines. Guidelines are for content editing and for user behavior, not for internal bureacracy. — SMcCandlish☏¢ 😼 02:26, 7 March 2023 (UTC)[reply]
Oppose as BilledMammal, No such user, and others have argued.To comment in particular on the "involved" clause, the suggestion that RMs need a special rule above WP:INVOLVED is unpersuasive. Being "urgent" or not doesn't somehow uniquely distinguish RMs from other processes with formal closures. A typical RFC, AFD, RFD, etc. is no more urgent than a typical RM, with no acute consequences to closing it a couple days or weeks later. Similarly, seeking to overturn a closure at move review is not materially different in difficulty from seeking to overturn another type of closure at deletion review. I see the impetus of the RFC is the case of the 1948 Palestinian exodus RM closure and MR; it features a closer who previous RM closure had already been taken to move review and itself was so controversial that it got no consensus to endorse or overturn. That extraordinary set of circumstances does not justify the proposed broad rule of "You have ever closed...", nor have I seen any other case that does. ("Hard cases make bad law".) There should just be one uniform policy about what "involved" means, and fragmenting the definition is CREEP. Adumbrativus (talk) 06:46, 7 March 2023 (UTC)[reply]
Oppose. If following these over-long "instructions" leads to the kind of close the OP did here and the following extended drama at User talk:Red Slash#Mpox, then they should be burned with fire rather than elevated to a guideline. There seems to be a move afoot to make RM use a mandatory step as it's the place where "scores of editors who know Wikipedia very well" hang out. This is just pointless processology.WP:CREEP, WP:NOTBURO. Bon courage (talk) 04:06, 9 March 2023 (UTC)[reply]
Well, the evidence is that the apparent application of these "instructions" is an issue. The editor who wrote most of them[10] wants their work elevated to have WP:PAG force so that they can be used to 'forbid' things (as if guidelines do that). Bon courage (talk) 07:25, 9 March 2023 (UTC)[reply]
Quite. A guideline doesn't enforce anything. It just elevates something away from being a mere essay, and, in this instance, dismissible as a mere nicety, even if it is established by consensus and decades of practical use. Iskandar323 (talk) 10:36, 9 March 2023 (UTC)[reply]
Oppose I fail to see why this can't be an Information page, and there seem to be too many contentious aspects currently. Suggest this idea is parked until the page is better. People will wikilawyer if they are unhappy with any process even if given guideline status. As other note, it is way too long. Well that's a problem with many guidelines and other pages too, but I think the step before attempting to elevate this page's status should be that you first request help to shorten it, trim the cruft, and remove contentious aspects until those have been thrashed out on talk. I get the need for "official guideline" for article content advice, but as a wiki, I think our processes and procedures should generally be described in as lightweight way as we can. Also, be careful what you wish for... making this "official" may make it harder for you to change the bits you want changed in future. -- Colin°Talk09:53, 9 March 2023 (UTC)[reply]
Oppose guideline, support information page if issues are dealt with. RMCI is useful, but I do have concerns with page as written. As the closer of the Palestinian exodus RMs, I was somewhat non-plussed at the "closing an RM makes you permanently INVOLVED" part being brought up at MRV as a gospel truth; it runs counter to how discussion closures go elsewhere on the encyclopedia, where INVOLVED is basically formalising the common-sense "don't close discussions you've participated and opined in" rule. And this RfC… I'll be honest, it feels less like codifying RMCI, and more like trying to redefine INVOLVED in without proper scrutiny at WT:ADMIN, where discussions about INVOLVED should be. RMCI should not be too prescriptive; it should just detail agreed best practice. If that's the case, I have no problem with it being an information page. Sceptre (talk) 18:48, 12 March 2023 (UTC)[reply]
Reluctant Support We really need another category like vetted approved "core essays"/"information pages" the best 10% of essays like these which do a good job of giving guidance of explaining how Wikipedia works or give good guidance but don't go to the extent of authoritatively say "this is what to do /not do" which in practice guidelines sort of do. The latter shouldn't creep larger because first, it is creep, it's hard to get the carefulness / perfection needed for give it that amount of clout. But I did support" anyway because I think this is an edge case where it could pass as a guideline given its history of scrutiny, tweaking, acceptance, usage, and being in good enough shape to be a guideline. Also it should be acknowledged that a "yes" here means only to make it a guideline, not an individual endorsement of every sentence in it. And knowing that it may need a few tweaks and changes to fully meet its new status. Sincerely, North8000 (talk) 19:14, 12 March 2023 (UTC)[reply]
Oppose in practice. Although I am sympathetic to the idea that this could be a guideline, I disagree that it has been clearly vetted by the community. In fact, for 15 or so years I have often avoided trying to sort out small changes to that page precisely because it was never necessary to do so; I could just continue closing as usual without needing to refer to instructions for new closers. In theory, I think we could start with a rewrite of that page, build up consensus, and then bring up the issue again, but I do not believe that the page as written reflects the best practices that have been developed at WP:RM over time, as reflected in my ongoing comments at WT:RM#Involved. Dekimasuよ!17:19, 15 March 2023 (UTC)[reply]
Support. Both in substance and function, this corresponds to a guideline, and has a clear niche in the systematization of PAGs: This page is to the move processes what Wikipedia:Deletion process is to the deletion process. —Alalch E.20:16, 19 March 2023 (UTC)[reply]
Oppose RM's are not so special they need their own definition of INVOLVEment, and I cannot support writing this clearly incongruous expanded definition of it into our policies. In the broader sense, codifying this as a guideline is an instruction creep problem. Courcelles (talk) 13:40, 20 March 2023 (UTC)[reply]
Note: I have a concern, that may not be justified, that a failed proposed policy or guideline generally carries the scarlet banner N This is a failed proposal.The hierarchy of essays, according to Wikipedia, is that an essay is an essay as it has not been thoroughly vetted by the community. However, in these essays, there is an added level when an "essay" represents widespread norms over a "minority viewpoint". The template uses "Supplement" or "explanatory supplement" that renders an "explanatory essay". If there is an "interprets" parameter, especially if the page provides "additional information about concepts in the page(s) it supplements", more especially if the "essay" provides this information about policies and guidelines, it is not just a run-of-the-mill essay."Following the instructions or advice given in essays is optional". If this were actually true nobody could ever be subjected to sanctions for not following the "optional" essay. I am sure most here know that in some cases that is a fallacy. I am sure any of our "techies" could pull up the record of how many editors have been blocked or banned for not being here to build an encyclopedia which is an "explanatory essay".Citation overkill has had 176 editors, 150 watchers, and 939 pageviews in 30 days and is an essay (but actually, and not really arguable except maybe from lawyers, an information page) on the Verifiability policy and the Citing Sources guideline.Pure essays are optional, but essays that provide a different aspect, providing sometimes valuable information on the "normal" communitywide practices usually go further.Essays have no official status and do not speak for the Wikipedia community because they may be created and edited without overall community oversight. Following the instructions or advice given in an essay is optional. Generally soft advice belongs in an essay, thus avoiding instruction creep in Wikipedia's official protocols. This is in direct conflict with the content of the "explanatory essay" Wikipedia:Here to build an encyclopedia. That "essay" carries multiple warnings. This page in a nutshell States: Users whose behavior suggests they are here for some other purpose risk being blocked or banned. The first paragraph after the quote states, Because Wikipedia is a collaborative community, editors whose personal agendas and actions appear to conflict with its purpose risk having their editing privileges removed. The only thing "soft" is the using of soft wordings "risk being" and risk having.I don't think it would be out of the norm or too big of an adjustment to classify certain essays as explanatory supplements. This would still be an essay, not a guideline, so will not violate those editors not wanting any instruction creep. -- Otr500 (talk) 16:14, 26 March 2023 (UTC)[reply]
@Otr500, when a proposal fails, sometimes we mark it as a failed proposal, but other times we just tag it as an essay. Some things are perfectly fine as essays. See, e.g., Wikipedia:BOLD, revert, discuss cycle, which has been proposed for policy or guideline status at least three times since I started editing, and still carries no badge of shame at the top. WhatamIdoing (talk) 23:02, 28 March 2023 (UTC)[reply]
Oppose- unlike admin activities, RM closes are never urgent, so there's time to make sure that we get someone who's never closed a request on it before. Also unlike admin activities, it's excruciatingly hard to overturn a page move close if the closer won't self-revert. Also unlike admin activities, if the closer does recognize "oops, shouldn't have done that", it's extremely easy to just self-revert--nobody needs to live in fear that they're too "involved", since a self-revert of a move (e.g., "You just closed the request on Kyiv, maybe don't close the one on Odesa" -> "oops, my bad, self-reverting") is very easy for a good-faith closer to do. Also, closing move requests isn't really an administrative task, and is more an editorial one. Without these guidelines as written, the same editor could literally just close the same exact move request over and over and over and over again, stonewalling "progress" in a violation of WP:OWNership. It's one thing to watch your beloved perennial proposal fail; it's quite another when it's one single editor over and over again who keeps closing the request to shut it down. RedSlash16:34, 28 February 2023 (UTC)[reply]
the same editor could literally just close the same exact move request over and over and over and over again, stonewalling "progress". The flipside of that is an editor who raises the same request with same arguments over and over again until a sympathetic closer gets their turn. We would be basically encouraging WP:FORUMSHOPing. Vpab15 (talk) 17:56, 28 February 2023 (UTC)[reply]
How is that the flipside? The problem is conflict of interest in the first case and disruption in the second case. Are you saying that the wording should be changed to allow the first case or that the wording already allows it? Selfstudier (talk) 18:42, 28 February 2023 (UTC)[reply]
Personally, I don't see the necessity of waiting for someone who's never closed a move request on the topic. Closing RMs is administrative in the same capacity that closing any discussion is: the closer's task is to identify and implement the consensus of other users, rather than acting independently to make content changes. A closer can analyze an individual discussion and its consensus without inherently being influenced by unrelated discussions on similar topics; there's no reason for them to recuse themselves from future closures in the topic area unless they've formed an opinion that would preclude them from being able to close impartially.You mention the hypothetical example of an editor who closes the same RM repeatedly, but there are two possible scenarios this encompasses. First, that editor closes each discussion in line with the relevant protocols (fairly assessing consensus, waiting the full week, etc.); in this scenario, the closures are good, so there's no reason to prevent the editor from making them. The other scenario is that the editor flouts the protocols in their closures (closing against consensus, making inappropriate SNOW closes, etc.); this is disruptive for reasons beyond "they've closed RMs in this area before", so there's no need to maintain such a proviso in order to sanction people who perform these disruptive closures. ModernDayTrilobite (talk • contribs) 15:40, 1 March 2023 (UTC)[reply]
While that may theoretically true in general, I think that in the specific case (referred to in the discussion as a "kerfuffle" but which actually need not concern us as it will be resolved in MR and not here) there is the appearance of a conflict of interest and as we all know, the appearance of a conflict can be just as bad as an actual conflict. So even if it may be theoretically true, I still think this is something that ought to be avoided, particularly in CT areas. Selfstudier (talk) 16:12, 1 March 2023 (UTC)[reply]
That's certainly true for controversial proposals, and I can definitely understand where you're coming from in that regard, but I think a bright-line "you have ever closed such a move request" restriction would also shut down a number of productive and low-risk closures. It's not uncommon for someone to propose a series of RMs on a shared topic - RMs which could easily be bundled, but for one reason or another, are not - and forcing those RMs to all be closed by different people puts a lot of additional strain on that practice.I wonder if "you have ever closed a move request on this article" would be a good alternative restriction? In my view, it'd be nearly as effective at reducing the appearance of conflicts of interest, while also minimizing the added administrative burden on RM closers. ModernDayTrilobite (talk • contribs) 16:48, 1 March 2023 (UTC)[reply]
This is actually what it means, which I think a lot of people seem to be overlooking. The third (and second) points refer back to the first. They say "such a move request", referring to "a move request about the article in question" - but a lot of people seem to be looking at the third point in isolation and coming up with their own sense, out of context, of what "such a move request" means. So, "a move request about the article in question" would best be repeated thrice. Iskandar323 (talk) 10:44, 9 March 2023 (UTC)[reply]
I don't think this is true: Also unlike admin activities, it's excruciatingly hard to overturn a page move close if the closer won't self-revert.
Even if it were true, I think it's not an important thing to worry about because it's not a problem we experience. People don't post RMs over and over and over again; therefore, there aren't identical RMs for someone to close over and over and over again. If that becomes a problem, folks can ask at WP:AN for help. Most admins are very willing to let someone else take over, if they're told that their actions aren't resulting in editors feeling like they can trust the outcome.
And frankly, if you've got someone who knows something about the correct nomenclature for some niche subject, you want that person involved in all RMs for that area. RMs, like any other discussion, would ideally be closed by people who can identify which arguments are stronger or weaker, and sometimes that means having domain-specific knowledge. Like any other discussion, an RM can appear to be evenly divided by superficial vote counting, but if one says X because Crackpots'R'Us uses that name, and the other says Y because reputable scholars use that name, then you should be going with the good sources – and that can only happen if the closer knows that the International Journal of Science is highly reputable, and the very similarly named Journal of International Science is not. WhatamIdoing (talk) 03:51, 9 March 2023 (UTC)[reply]
Wording should be changed to make it clear that the restriction on multiple closures applies to the same article (regardless of what titles it may have gone through} and not to other articles within the same topic area. A statute of limitations could also be applied, maybe a year. Contentious and persistent incompetent closing is a behavioural problem and can be managed by a topic ban if it becomes necessary. Also agree with what WhatamIdoing says. · · · Peter Southwood(talk): 05:24, 9 March 2023 (UTC)[reply]
Comment. The objection to WP:RMCI was that it defines involved as You have ever closed such a move request, whereas the current policy at WP:INVOLVED says: an administrator who has interacted with an editor or topic area purely in an administrative role, or whose prior involvements are minor or obvious edits that do not show bias, is not involved and is not prevented from acting in an administrative capacity in relation to that editor or topic area. It does seem they contradict each other. Should the wording at WP:INVOLVED be changed if WP:RMCI becomes a guideline? Vpab15 (talk) 23:48, 22 February 2023 (UTC)[reply]
INVOLVED is policy, so I think fixing this is better resolved the other way around. Updating RMCI so that it more closely matches INVOLVED seems like the solution, as ultimately that set of instructions are based off of the policy and not the other way around. Sideswipe9th (talk) 00:30, 23 February 2023 (UTC)[reply]
So, they're definitely different issues, and the RMCI "involved" stuff is different on purpose and for a reason. The TL;DR is that WP:INVOLVED prohibits involvement with the same user (or topic area), while WP:RMCI just prohibits it from having a certain pre-expressed position on a topic. Great question though.
Why WP:INVOLVED is as loose as it is:
Administrators interact with a LOT of users. If we prohibited any administrator from ever interacting with the same user twice even in an administrative sense, we'd have a complete clusterbomb of suckiness on our hands.
Oftentimes, admin action is urgent; we have way too few administrators and way too many things to be getting done, and sometimes if you waited for someone who has never been involved, the issue would take too long to get resolved (say, Admin Joe finds a rogue user who's wildly vandalizing tons of articles, but Admin Joe has already sanctioned the guy once before; it would hurt the encyclopedia to say that Admin Joe needs to wait to find someone else to ban the dude).
Administrators are very well-vetted in our rules and policies. They shouldn't need someone to hold their hand and tell them when they're too involved to be impartial. It's the same reason Supreme Court Justices in the United States (at least) don't need to be told to recuse themselves.
On the other hand, move closers:
Most move closers do not interact with most articles. I've been an editor for a looooooooooooooooooooooong time and have a loooooooooooooooooooooot of edits and have been involved in a loooooooooooooooooot of move requests, and I just looked through WP:RM and I could not find a single article listed there which I have ever interacted with. I could close literally any of those requested moves. I'd bet you that, of the fifty or so editors who commonly (once or more per month) close requested moves, probably forty-five to forty-eight of us could serve as impartial movers on any given requested move.
There is zero urgency with requested moves. If Page Mover Tom sees a request on Talk:Foo that he could move, but, shoot, he's been involved in similar discussions at Talk:Foobar... well, it's not going to cause any problem for that move request just to sit tight for another few days until Page Mover Sally happens across it. Requested Moves are important, certainly... but definitely not urgent.
The people who close move requests are almost never administrators. There's about four admins who regularly close move requests and about ten others who do it once in a blue moon, and I'd ballpark-estimate that 90% of moves closed are closed by non-admins. I highly respect my fellow non-admin page movers, of course, but let's be real: as a group, we obviously aren't as vetted by the community. In fact, this is why WP:RMCI's "involved" criteria is as explicit as it is. I pushed hard in the discussion for it to be painfully obvious where the bright lines were, because as a group, we needed those bright lines.
So, no, I would absolutely not suggest following WP:INVOLVED's wording or vice-versa. Different rules for different reasons, just like how categories have different rules than articles. RedSlash05:04, 23 February 2023 (UTC)[reply]
Right now there is a move review about an article related to the Arab–Israeli conflict and another about a New Zealand term. Both areas have RM discussions relatively regularly. If we are saying that a closer can only close one discussion in either area, that goes against the letter and the spirit of WP:INVOLVED. I don't think that would be feasible, we would run out of RM closers in no time. Vpab15 (talk) 11:28, 23 February 2023 (UTC)[reply]
With love, no, I'm very confident there are plenty of well-informed RM closers who haven't committed themselves to either of those issues yet. I could list several of them who aren't involved at all. There's not THAT many of us, but there's not too few, either.
Again, these are two separate issues. WP:INVOLVED deals with administrators performing administrative actions. WP:RMCI's "involved" section deals with neither. RedSlash17:22, 23 February 2023 (UTC)[reply]
Are you saying the same closer shouldn't close two RM discussions that belong to the same topic? For example Slava Ukraini and Odesa, both related to Ukraine? Because that's exactly what you did. Applying that rule would disqualify regular RM closers from closing most discussions. As a closer I would have to go though the hundreds of discussions I have closed to make sure I don't meet the new "involved" criteria. That is a huge burden and I can't see that working in practice. Vpab15 (talk) 18:20, 23 February 2023 (UTC)[reply]
It already does work in practice! (FYI, these criteria are several years old and have worked for us for several years; they're not new.)
The restrictions aren't "you've ever edited the article or anything like it". The restrictions are: "You have ever commented on any talk page in such a way as to make clear your position on the move request" or "Your editing on the page in question or about the page in question makes clear your position on the move request".
For mine, the Slava Ukraini request hinged on WP:UE and WP:COMMONNAME about whether the slogan should remain translated into English or not; the way in which I closed it does not in any implicate how I would later close the Odesa request, which hinged on whether the one-S version or the two-S version were more common in English when referring to the Ukrainian city. The proof is in the pudding; I closed the Odesa request back in July, just three months after the Slava Ukraini one, and no editor even suggested that I had been too "involved" to close. (I would've painlessly self-reverted if someone would've brought a legitimate claim of violating those rules; again, there are no shortage of people who could've done a great job closing Odesa.) On the other hand, if I had been the one who closed the Kyiv/Kiev one, or if I had !voted on it, maybe I would've shied away from closing the Odesa one; if there's another Ukrainian city with a Russian name that's proposed to be moved to the Ukrainian name, I will avoid closing that one. I consider this common sense, which is why the discussion ultimately ended up where it did and the page reads how it reads.
In short (too late!), the list of requirements on RMCI with regard to involvement were heavily discussed and meticulously crafted to avoid the sort of wacky prohibitions that you are correctly wary of. No worries, homie; it's not as scary as you think ! RedSlash23:04, 23 February 2023 (UTC)[reply]
Even on a per article level, are you sure that this is current practice? When looking at the CoI part, a closer is considered involved if You have ever closed such a move request. By a plain reading this means that if:
7 days pass, I make a determination of the consensus based on what editors have said. Article is not moved.
Significant amount of time passes, eg 6 months to several years, some other user proposes moving Foo to baz
7 days pass, I cannot make determination of the consensus based on what the editors have said, because I closed another RM on the same page at some point in the past
When we have 6.6 million articles, but only 130,000 active editors, at some point we will run out of editors who can close move requests on articles that have had multiple move requests. Sideswipe9th (talk) 00:33, 24 February 2023 (UTC)[reply]
That is correct, that is current practice, you could not make that determination. We have 6.6 million articles, but I assure you, we don't have that many requested moves No worries, we've never even begun to come close to a situation where we've run out of possible closers. RedSlash01:37, 24 February 2023 (UTC)[reply]
Sorry to interrupt the thread here, but I do not believe there has ever been consensus to make that "common practice". Until 2019, the directive was to avoid the appearance of a conflict of interest (which is good!), but there was no prohibition on closing a second move on the same page, and no indication that the very existence of a previous close itself would be considered indicative of a conflict of interest. Since that change (which I didn't know about, since I don't monitor that page, although I would have objected to it), the page has not had guideline status. I have closed subsequent moves on the same pages many times, sometimes so far apart that I couldn't even remember having closed a move request there previously. When the reading of consensus is clear and accurate, there is no appearance of a conflict of interest. When the reading of consensus is not clear or accurate, there is a problem regardless of whether there has been a previous close on the same page. Dekimasuよ!17:34, 15 March 2023 (UTC)[reply]
Why is RMCI so much stricter in this regard when compared to how we handle INVOLVED at the admin level, or non-admin closures everywhere else on enwiki? The purpose of the closer of any discussion is to summarise the consensus that already exists, and doing so is usually not considered involvement by any other standard. What's special about move requests that make it so that we need this restriction? Sideswipe9th (talk) 02:11, 24 February 2023 (UTC)[reply]
I explained it in much more detail above, but it boils down to A) administrative actions are far more urgent than RM moves, so we can afford to be choosier when it comes to involvement, and B) move request outcomes are much more difficult to overturn. Again, the part that you're concerned about--which I get, again, I understand your concern--was exhaustively discussed a few years ago when it was added to RMCI. RedSlash07:49, 24 February 2023 (UTC)[reply]
@Red Slash: I'm really confused here. Doesn't WP:INVOLVED only apply to admins anyway? So WP:INVOLVED does not really apply to non-admin editors making closures; in fact, the only guideline for that is WP:RMCI. It's unclear to me if RM closures even count as activities conducted in 'an administrative capacity', since this seems to be a contradiction in terms for any activities that are specifically allowed to be performed by non-admins. I sense muddled logic. Iskandar323 (talk) 11:12, 27 February 2023 (UTC)[reply]
It seems really important to clear up whether RM closure is an "admin capacity" covered by WP:INVOLVED that makes the exception of allowing non-admins to perform it, or if it is a "non-admin capacity" that WP:INVOLVED does not fundamentally apply to, but which the WP:INVOLVED principles are overlaid back onto as applicable to participating admins and non-admins by virtue of the standards laid out at WP:NACINV. Iskandar323 (talk) 07:25, 28 February 2023 (UTC)[reply]
Question. Should we include the bit about WP:Move review that's found at the top of WP:RM as a post closure section? This will lay out (or affirm ) the current dispute resolution path if someone wishes to contest the closure (before the interested party takes the case up to ANI). Duplicating the paragraph here for everyone's convenience:
Wikipedia:Move review can be used to contest the outcome of a move request as long as all steps are followed. If a discussion on the closer's talk page does not resolve an issue, then a move review will evaluate the close of the move discussion to determine whether or not the contested close was reasonable and consistent with the spirit and intent of common practice, policies, and guidelines.
Almost all of it; it is advocating for this change, and trying to present RMCI as more than an essay. I suggest you remove the second sentence from your notification, and reduce your statement down the concise and neutral statement Should WP:RMCI be formally elevated to the official status of a WP:GUIDELINE?BilledMammal (talk) 23:22, 23 February 2023 (UTC)[reply]
First paragraph:
There has existed for eighteen years a set of instructions for how to formally close a requested move. It was initially titled as Wikipedia:Moving guidelines for administrators, later changed to Wikipedia:Requested moves/Closing instructions (hereafter WP:RMCI). Over the years, it has grown from a simple set of how-to steps to a comprehensive list of guidelines for determining consensus (which began as early as 2006 and has continued to expand through the years). It also has included instructions on who should close requests--first in 2009 when the authority to move pages was explicitly granted to non-administrators, then later in 2019 (following lots of discussion) we introduced rules on how editors who are involved need to not close requests.
is completely factual and non-biased. The instructions have existed for 18 years. It was titled that way initially. Etc.
Second:
The instructional page wasn't classified as anything (guideline, policy, or essay) through 2021, even though it had been originally written as a guideline. Following a post on the talk page that saw no response, it was listed as an explanatory essay in 2021.
Also completely factual.
First part of third paragraph:
Recently, at least one editor has asserted that, as WP:RMCI is "only" an essay, its procedures do not need to be followed; therefore, as one concrete example, editors may feel free to close move requests that they are fully involved in, so long as they think it's the right thing to do.
A quick look at WP:MRV will show you that at least one editor has asserted that.
WP:RMCI has been called "purely advisory", "not vetted", etc., leading to questions as regarding its authority--this in spite of the fact that it was written as a guideline and has guided literally thousands of move closures.
The first part of this sentence is strictly factual. The second part is also true; are you perhaps upset at the fact that I said "in spite of"? I suppose that could be considered biased language, perhaps. How would you rewrite this without omitting any of the factual details contained in this sentence?
This has unquestionably led to no small amount of chaos at Wikipedia:Move review following an editor who closed the same move request twice in a row (which is against the closing instructions), both with the same result, and who claimed that the closing instructions that forbid such a close by an involved user were merely "advice".
"No small amount of chaos" is certainly an opinion, but I don't see how it's biased. IDK , you go look at MRV and tell me if you see chaos or not. Note: me saying that there is unquestionable chaos is not telling people how they should !vote. It is saying why they should vote: because there is currently confusion. If there were no confusion, there would not need to be an RfC.
Everything from "an editor who" onward is completely factual.
Should WP:RMCI be formally elevated to the official status of a WP:GUIDELINE?
Gotta have the question we're !voting on listed in the RfC, don't we?
All told, I can't see where you're seeing bias, or that I advocated for change in a specific direction in the RfC itself. All I did was provide factual context (though admittedly, perhaps that phrase "in spite of" is too loaded and pushes the reader in a certain direction) for why it is good for the RfC to be brought up. Trust me, this RfC being decisively rejected would have been much, much better than the status quo, where something that "looks, talks, and quacks" like a guideline is being treated by many editors as a guideline while others treat it as an essay. RedSlash23:54, 23 February 2023 (UTC)[reply]
Much of this is evidence for why it should be a guideline. It's factual, but that doesn't make it unbiased, because it doesn't include the evidence for why it shouldn't be a guideline. BilledMammal (talk) 23:57, 23 February 2023 (UTC)[reply]
BilledMammal, I wouldn't worry about this. Sometimes an RFC needs an explanation, and sometimes a fair explanation is going to tip editors towards one side or the other. RFC questions, especially procedural ones, shouldn't necessarily try to give equal validity to all options. We can safely assume that Wikipedia editors are smart enough to figure it out. WhatamIdoing (talk) 00:14, 24 February 2023 (UTC)[reply]
I don't believe an explanation is needed here; the question is one that Wikipedia editors are smart enough to understand without explanation, and while the justification is more extensive the justification should be part of a !vote, note the statement. BilledMammal (talk) 00:19, 24 February 2023 (UTC)[reply]
My advice for the future… when writing an RFC: At the top, just ask the question. Don’t add any explanation. If you think background or explanation is needed, add it to the comments section, or as a separate section entitled “Background” (or something) - By physically separating the question from the background of why you are asking it, you limit accusations of non-neutrality. Blueboar (talk) 02:44, 24 February 2023 (UTC)[reply]
Yep, write anything else as part of a !vote (or a comment) after the RFC body so it doesn't clog up the RFC listing pages. As for neutrality, I don't think it is crucial for this particular discussion as this is not a contentious topic. Selfstudier (talk) 06:22, 24 February 2023 (UTC)[reply]
I've written maybe six RfCs in my entire career, so this is something I'm definitely not super experienced in. Your advice--all y'all's advice--is well taken, thank you. RedSlash07:50, 24 February 2023 (UTC)[reply]
Procedural close for the non-neutral RfC statement and lack of RFCBEFORE (including poor format choice with separate supp/opp sections, not previously discussed AFAICT), first choice. Second choice: oppose per Rhodo. I do not believe it's really been vetted by the community, MR and RMs are a walled garden, and RMCI is its Bible. It differs in some major respects from standard practice elsewhere (e.g. NACs, interpretation of involved), and I think that's more due to the walled garden nature of it than any kind of community vetting. We need fewer policies and guidelines, not more. Also, it's noticeable that the impetus for this is a recent kerfuffle and I don't think it's a good idea to promote RMCI to a guideline in an effort to "win" an argument over RM/MR procedure. Levivich (talk) 14:37, 25 February 2023 (UTC)[reply]
To some extent, the "kerfuffle" is the RFCbefore. If there are problems with RMCI then that needs to be addressed someplace, like, er...here? Two of three/four editors opining in a move review that RMCI has problems are here opposing so any issues are getting addressed in proper place and not in a move review. Selfstudier (talk) 14:44, 26 February 2023 (UTC)[reply]
A contentious RM followed by a contentious MR (aka, a kerfuffle) makes for a lousy RFCBEFORE and this very obviously non-neutral RfC statement demonstrates why. And contra to some surprising advice below, RFCNEUTRAL is for all RFCs, not just contentious topics. Also, this RfC doesn't comply with WP:PGCHANGE as it's not widely advertised, it's at the wrong pump (should be policy for a new PG), and not listed at WP:CENT. This ought to be shut down and restarted the right way: an RFCBEFORE at the PG page, followed by a neutral RfC at the policy pump listed on CENT. Otherwise, it's not really global consensus. Levivich (talk) 16:11, 26 February 2023 (UTC)[reply]
Nah. PGCHANGE is for changes to policies and guidelines, this isn't that. Policy pump is for existing and proposed policies, isn't that either. No need to list this at WP:CENT afaics. The only procedural screw up was people not raising their disagreement with RMCI at move review talk instead of during a move review. I can do the same thing and just assert that WP:RFCNEUTRAL is only an information page and doesn't apply:) Selfstudier (talk) 16:24, 26 February 2023 (UTC)[reply]
Oh come on man. WP:PROPOSAL is the policy for making new guidelines and it wasn't followed here at all. (And it has more requirements than PGCHANGE, and it explicitly talks about RFCBEFORE, and VPP, etc.). Please don't argue that a proposal to promote RMCI to a guideline doesn't have to follow the WP:PG policy. Similarly there can be no argument that this RfC question isn't RFCNEUTRAL. If you like the idea, that's fine, but the failure to follow our consensus procedure here is indisputable. Levivich (talk) 16:42, 26 February 2023 (UTC)[reply]
The proposal, apart from some suggested wording tweaks, seems actionable to me. RMCI has been treated as a guideline in practice and the only issues that have been raised against it are the ones raised in an ongoing move review (by objectors to it). Selfstudier (talk) 16:59, 26 February 2023 (UTC)[reply]
I've just double-checked, and WP:PROPOSAL, WP:VPP, and WP:VPR are all unanimous in saying that proposals for new PGs or to change PGs should be at the VPP and widely-advertised, so I've moved this from VPR to VPP and listed it at CENT. Levivich (talk) 17:58, 26 February 2023 (UTC)[reply]
I've collapsed the initial statement and replaced it with a neutral one; if we are going to try and fix this RfC, rather than making a procedural close and opening a new one, then that issue also needs to be fixed - although I hope that the closer considers that prior to 18:05, 26 February 2023 (UTC) the RfC was lead by a non-neutral statement that might have biased the result.
I've struck my !vote and moved it down to discussion, since it's all based on procedure anyway and the procedure is getting fixed. Yes, I think we should combine the support/oppose into one survey section as well. Levivich (talk) 18:14, 26 February 2023 (UTC)[reply]
Some editors are apparently objecting to the wording rather than the principle. So how to deal with this? Do we fix it now? (subRFCs?) Do we send this back to where it was to start with-proposals? Selfstudier (talk) 17:28, 27 February 2023 (UTC)[reply]
RfC: Should WP:REFUND allow for articles deleted through the CSD criteria of A7, A9, A11, G5 to be userfied or restored as drafts?
Requests for undeletion should be used to appeal most instances of proposed deletion and some speedy deletions.
However, there is some debate due to the vagueness of what some speedy deletions actually includes. Currently, WP:REFUND says:
Please do not request that pages deleted under speedy deletion criteria F7, F9, F11, U5, A7, A9, A11, G3, G4, G10, G11 or G12 be undeleted here.
However, as Uanfala has mentioned on the talk, this provision was boldly added by a now-banned user, and the archives are fairly divided to find any hard consensus.
Notably, G5 is not currently listed, but several admins have echoed that they refuse to restore material by banned or blocked editors per WP:BMB as a means to enforce bans and dissuade the user from returning. However, other editors advocate that WP:BANREVERT states there is no hard rule to delete potentially useful content, although you are allowed to. This means there is no settled precedent for either supporting and opposing such requests, and it is entirely up to the reviewing administrator to refuse such a request purely based on their outlook of how material added by banned users should be treated. Thus, I think a centralized discussion regarding this would be the best idea going forward.
So as a repeat from the top, can good faith editors appeal to move deleted material from a CSD to a draft or their userspace to work on? (This assumes that there are no other issues with the pages and, in the case of G5, the requesting editor is not affiliated with the banned page creator unless they satisfy WP:PROXYING). And if so, do administrators use their personal best judgment or concede (in most cases) to allow for community-consensus discussion such as WP:AFD and WP:DRV? Why? I Ask (talk) 22:21, 2 March 2023 (UTC)[reply]
Discussion (WP:REFUND)
As the proposer, I will not be advocating one way or another. Throughout past discussions, I have already made my position clear elsewhere and do not want to risk any further WP:BLUDGEONING, though I will respond to any follow-up question directed at this proposal. However, I do want to preemptively state that any attempt to misuse this proposal (by paid editors or returning sock puppets) should be treated as with any other disruptive editing, and thus a supposed risk of people gaming the system should not be the sole reason to oppose, as there are modes to prevent abuse. (If we were worried about gaming the system for everything applicable on Wikipedia, and restricted it, then it would not be an encyclopedia anyone can edit. So on that notion, I disagree.) Why? I Ask (talk) 22:21, 2 March 2023 (UTC)[reply]
This RfC seems a bit malformed. A7 and A9 seem reasonable to restore, as something with no indication of importance might actually be notable and could have useful material; G5 is a whole different issue, and shouldn't be conflated here. Galobtter (pingó mió) 00:47, 3 March 2023 (UTC)[reply]
Can you explain that? G5 has the exact same reasoning as what you put for A7 and A9. Perhaps even moreso, as such articles are likely to have been notable and proper articles outright with no problems inherent to them. SilverserenC02:04, 3 March 2023 (UTC)[reply]
The point also being that no one really cares about A7, A9, or A11 restores, but G5 restores as policy would be a definite shift, and is clearly what is the RfC is primarily about. Galobtter (pingó mió) 05:54, 3 March 2023 (UTC)[reply]
For deletions under G5, just create the article again. You could ask for a list of references from the deleted article. I would probably be willing to supply it if anyone requests. · · · Peter Southwood(talk): 06:01, 9 March 2023 (UTC)[reply]
Codifying the allowance of this seems like a good idea just to get the subjectivity of admin responsibility out of the mix. Because I've seen plenty of admins claim they don't want to be responsible for restoring the content if it turns out to be bad for whatever reason. Thus, codifying the use of WP:REFUND (and obviously requiring the requester to be an experienced editor in good standing) for this purpose would separate any admin responsibility, as honestly the sole responsibility for the requested articles should be on the person requesting the undeletion. On their head be it, as the saying goes. SilverserenC02:07, 3 March 2023 (UTC)[reply]
Support. Editors who want to reinstate an edit by a sock puppet are permitted to do so, on the condition that they take responsibility for the edit. There is no reason this shouldn't apply to entire articles; I previously did this for Tekla Åberg, but it required jumping through far too many hoops. BilledMammal (talk) 02:42, 3 March 2023 (UTC)[reply]
There may be attribution problems with this procedure, unlike for reinstating individual edits. You would have to take the article off-wiki and completely rewrite everything added by the banned party. How many editors would we trust to get this right? Any admin can do this already, and there are some editors I would trust, but I would not do this for someone whose work I do not know quite well, because I would be ethically obliged to do the work of checking the new article myself to ensure there were no issues of plagiarism. It would usually be easier to start from scratch, possibly with a list of references from the deleted article, which I would normally be happy to provide. Cheers · · · Peter Southwood(talk): 06:01, 9 March 2023 (UTC)[reply]
I am a bit confused on what you mean about attribution. This is saying that the articles would be restored with the page history which would include the edits by the blocked or banned users so attribution would not be an issue. But if you are arguing that edits by banned or blocked users should never be restored, I am not going to attempt to sway you there. Why? I Ask (talk) 06:15, 9 March 2023 (UTC)[reply]
Support for A7 and A9. Such text could be useful for related articles, even if the topic itself is not notable. For A11 I'm not sure what the use case would be, but at the same time not sure what the downsides would be. Oppose encouragement of G5 undeletions, admin/editor good faith is abused as it is. CMD (talk) 03:19, 3 March 2023 (UTC)[reply]
What does "encouragement" mean? Such undeletions are already allowed. How is requiring experienced editors in good standing to be the ones making the request an abuse of good faith? SilverserenC03:22, 3 March 2023 (UTC)[reply]
Given the current REFUND text does not mention G5, I took the raising here to be a proposal to make it more common a situation (encouragement). G5 articles can have deep problems that are not immediately apparent, and the good standing and experience of an editor requires assessment. That is multiple areas where an admin might (should?) apply good faith, and no admin can be expected to be across all G5 history. CMD (talk) 03:34, 3 March 2023 (UTC)[reply]
Why would G5'ed articles have any more potential issues than any other article? The reason for them being G5'ed is inherently unrelated to the content of the article or even the article existing itself. Since it's about a banned user having made it, not about whether there was anything wrong with the article. It's not like this is about articles that were deleted for being copyvios, blatantly non-neutral/attack articles, or having hoax content. SilverserenC03:40, 3 March 2023 (UTC)[reply]
Users can be banned for reasons involving hoax content and copyvios. Once they are, later creations are generally handled under G5 for ease. This does not mean the prior problems are no longer present, just that an admin doesn't need to waste their time finding out. CMD (talk) 03:44, 3 March 2023 (UTC)[reply]
That would be the only legitimate reason I can see for refusing a G5 undeletion request, but how many banned users who sock were banned for that? It seems vastly more common for someone to be banned for community interaction issues and otherwise long-term bad will, not for issues with article creation. The only exception I'm aware of there are serial POV pushers, but those are less involved in article creation and more involved in pushing text into existing articles. Also, it only takes a moment to check on why someone was banned. I've had a number of G5'ed articles restored and their content was fine, such as Ennan Alimov. SilverserenC03:55, 3 March 2023 (UTC)[reply]
Creating new articles is just one tool in the serial POV pusher toolbox! As to the question, I do not have any statistics on proportions, I am responding to this RfC from experience of it happening in cases I have seen. Community interaction issues often coincide with content issues, whichever is ultimately the straw that brings about a ban, and simply checking a ban notice misses this history. I have also worked with some sock pages/content, and restored sock content without change. I don't think this means admins should be encouraged to undelete G5 pages they would not currently want to undelete, which the RfC prompts discussion on. CMD (talk) 04:08, 3 March 2023 (UTC)[reply]
Isn't the easiest way to deal with that to just add it to the REFUND requirements? Any requester of a G5 undeletion must include in the request the reason why the banned editor was banned and how this doesn't conflict with the undeletion request and article requirements. Make the requester do the work. SilverserenC05:01, 3 March 2023 (UTC)[reply]
To clarify, in the opening statement of the RfC, I stated that: this assumes that there are no other issues with the pages. If there is a chance the article can be speedily deleted under G3 and G12, then per my opening statement, it should not be restored. Why? I Ask (talk) 03:51, 3 March 2023 (UTC)[reply]
For clarification about A11, I decided to include it as it is one of the few CSD criteria where it is not actively harmful (such as G3, which are pure hoaxes) or completely futile (such as A3, an article that is empty) to restore. I believe these are the four CSD criteria where there exists some form of potentially useable content. For example, some scientist (for some reason) summarizes their findings here before later being published in a peer-reviewed journal. This is purely hypothetical, of course, but (as you said) I can not find a particular downside to prevent including A11 alongside A7 and A9. Why? I Ask (talk) 03:37, 3 March 2023 (UTC)[reply]
Editors can already ask for restoration to userspace of content deleted under these criteria, so I'm not sure what the policy question is here. I would oppose anything that encourages people to challenge G5 deletions (and an undeleted G5 is still a G5, no matter in which space it sits; it requires substantial input by others to stop being deleteable). —Kusma (talk) 10:05, 3 March 2023 (UTC)[reply]
Technically, the policy is WP:UDP which is vague in what some of the applicable speedy deletion criteria are. Currently, the page WP:REFUND (while not itself a policy) says that A7, A9, and A11 should not be requested to be undeleted, so it does not seem like they currently are able to request restoration through this venue. This RfC attempts to amend that wording (and potentially some at either WP:UDP or WP:CSD) to formally establish that editors are allowed back these articles if they feel they could help in their editing. Would you support A7, A9, and A11 in that case? Why? I Ask (talk) 10:21, 3 March 2023 (UTC)[reply]
Support. I don't see any downsides to allowing (not requiring) refunds of potentially useful content if someone wants it. If the requester abuses this, then that's a behavioural issue that can and should be dealt with as per any other behavioural issue. Thryduulf (talk) 10:07, 3 March 2023 (UTC)[reply]
Support for A7/A9; oppose for A11: There is no need to maintain unnecessary administrative hurdles to restoring material that could form the basis of something useful in the hands of the right editor willing to take custodianship of the content - especially so if the restoration is restricted to draft space or user space. Also support for G5 G4 in line with the rationale provided by Filelakeshoe below. Iskandar323 (talk) 10:50, 3 March 2023 (UTC)[reply]
Yes, I would suggest to remove the G5 part from the proposal as it has been rejected elsewhere and shouldn't just be forum shopped here. —Kusma (talk) 11:02, 3 March 2023 (UTC)[reply]
That has to do with the wording of G5 which seems to be opposed (and it never specified user or draftspace as opposed to mainspace). There was also differences in opinion on why it should not be added, with some basing it on the fact they oppose G5 restoration and some opposing because they simply did not like how it singled out this specific CSD. And there was also support at the deletion review which is why a centralized discussion to formally decide this for future articles is better. You can not just try to invalidate this discussion that stands on its own merits because you personally oppose it. The current half of the votes above that support show there is a discussion to be had. Why? I Ask (talk) 11:03, 3 March 2023 (UTC)[reply]
I don't oppose the discussion, but I would oppose the discussion being WP:FORUMSHOPPED. As mentioned, I did not participate in the previous two discussions, and upon finding them I see that my time was taken up by something which seems to be already trending towards consensus against in two existing locations. If you want to bring more attention to ongoing discussions, the correct course of action is to leave a neutral note here pointing towards that discussion. CMD (talk) 11:20, 3 March 2023 (UTC)[reply]
That you have supporters for your cause here does not change the fact that this is textbook WP:FORUMSHOPping, especially as you have failed to mention the other discussions that CMD has now linked to, which should be taken into account by the closer of this discussion. —Kusma (talk) 11:21, 3 March 2023 (UTC)[reply]
CMD and Kusma, these two (I guess three) discussions have different scopes. The DRV determines if G5 was applied correctly (and it was). The discussion at CSD determines if text is added to G5 that says that editors may request undeletion (and there is no consensus to add the text there). This is a separate issue involving four CSD criteria where it is asking if there consensus to support the general restoration of content deleted to non-mainspace venues to work on. Why? I Ask (talk) 11:30, 3 March 2023 (UTC)[reply]
This proposal, if I can call it that, seems to be about WP:REFUND, and removing "A7, A9, A11" from the list which says "Please do not request that pages deleted under speedy deletion criteria F7, F9, F11, U5, A7, A9, A11, G3, G4, G10, G11 or G12 be undeleted here". Although it's obvious you want G5 involved somehow, I'm unclear what changes you actually want. The page already says, at least implies through its current structure, that you can already request a G5 undeletion. What changes are you looking for? -- zzuuzz(talk)11:28, 3 March 2023 (UTC)[reply]
Through the other discussion you have been a part of, some editors have opposed the notion that you should be able to request a G5 deletion or held that it should never be restored no matter what (rendering the ability to request moot). This RfC attempts to formally establish whether or not that is the case. Why? I Ask (talk) 11:31, 3 March 2023 (UTC)[reply]
I find it painfully clear through the whole of policy that a G5 restoration can be both requested and fulfilled. Though I also understand there is no obligation. Thus I still don't understand what's being proposed. -- zzuuzz(talk)11:37, 3 March 2023 (UTC)[reply]
So you support that users can appeal a G5 deletion and have the content userfied or drafted? Aside from that, it also asks whether or not administrators have the full right to deny such a request purely and systematically on the basis of it being deleted by the four criteria. (This is how most G5 requests for undeletion end up as some administrators believe that no material by editors who were banned should ever be restored without necessarily weighing in on the content of the deleted article in question.) Why? I Ask (talk) 11:51, 3 March 2023 (UTC)[reply]
You can tell me all about that one day. We're all volunteers and (pretty much) don't have to do anything. We have more than one admin for many reasons and many occasions. This is one of them. -- zzuuzz(talk)12:16, 3 March 2023 (UTC)[reply]
As I said above, there's nothing prohibiting a request for G5'd content. If you find an admin who says no they won't do something, find another admin who will, if you can. There's a lot of stuff I won't do but it doesn't mean it can't be done. -- zzuuzz(talk)12:52, 3 March 2023 (UTC)[reply]
That seems strange to be able to get userfication of articles deleted by G5 by raising the issue at multiple admin talk pages to see which one is willing to do so. Why? I Ask (talk) 16:01, 3 March 2023 (UTC)[reply]
Not a clear RFC proposal, but as a frequent refunder I will comment. When someone requests a G5 overturn, there is a high chance that they are a sock of the banned user. I like to refer the request to the deleter or blocker of the banned user to make a more informed decision about whether to block the requestor. When it comes to things that were deleted for invalid reasons, I may restore (eg if the file was deleted as a copyvio, but the copy was of a Wikipedia mirror). Even a G5 may be inappropriate if it was edited significantly by someone else. If the deleter is still active, then notifying them of the erroneous delete is a good idea so they can rectify it. Other situations where the circumstances have changed would require a good reason to be given by the requestor. Eg if an A7ed topic is now notable. Graeme Bartlett (talk) 12:07, 3 March 2023 (UTC)[reply]
This proposal specifies user and draft spaces where notability does not apply. Do you still think a reason should have to always be given for A7, A9, and A11 requests? Why? I Ask (talk) 12:14, 3 March 2023 (UTC)[reply]
Support for A7, A9, and A11. But Oppose /conditional support for G5. Conditional in the sense that we should have some guidance about how to handle those requests. It depends what the user was blocked for. Someone blocked for chronic copyright violations shouldn't have anything restored to public view without a thorough check first. That probably means emailing a draft to the requesting user with a warning rather than a userfication/draftification. Someone blocked for egregious harassment and personal attacks shouldn't have their material restored under any circumstance, because we need to prioritize the health of our community. What's unclear are the other cases. If someone's a chronic edit warrior, did some stupid sock puppetry, couldn't stop making cosmetic edits, or blocked for any of the other more IMO trivial offenses, I don't see a reason why a refund shouldn't be granted. In other words, a refund can be requested, but if we're going down that road we should have some documentation for admins outlining the conditions when it is or isn't ok. — Rhododendritestalk \\ 12:18, 3 March 2023 (UTC)[reply]
So you would support an edit or proposal that documents when G5 restorations should be allowed? I think there is room to explore that idea, but that may be a different RfC. Why? I Ask (talk) 12:28, 3 March 2023 (UTC)[reply]
I've struck "conditional support" for now, as I'd prefer to err on the side of not refunding banned users' content, but think that there are exceptions to that rule that could conceivably be documented in a way that would add it to the list. — Rhododendritestalk \\ 13:57, 3 March 2023 (UTC)[reply]
Nothing in this proposal would require anybody to refund anything, it would simply explicitly permit them to do so if they wished. Obviously some content should not be restored (copyvios, attacks, etc), some content that should be cleaned before being put in mainspace (very promotional, highly POV, etc), some content that can be cleaned in mainspace (occasional POV problems, suboptimal formatting, globalisation needed, etc) and some content that was deleted solely because some admins believe that "banned means banned" is of greater importance than providing (even occasionally GA or FA-standard) encyclopaedic content to readers (I vehemently disagree with this, but recognise that it is widely held view). There examples of every type that are deleted per G5. Thryduulf (talk) 13:12, 3 March 2023 (UTC)[reply]
Nothing in this proposal would require anybody to refund anything - But, as with some admins believe that "banned means banned", there's disagreement about when it should apply. G5 isn't an area I'd feel comfortable just leaving open to individual discretion because some feel that the immediate availability of decent content trumps anything else. While there are absolutely exceptions, I'd want us to err on the side of excluding the content. believe that "banned means banned" is of greater importance than providing (even occasionally GA or FA-standard) encyclopaedic content to readers - You've provided one extreme interpretation of the dispute you're referencing. Here's the other extreme: some admins believe there's no abuse, harassment, or sockpuppetry that's too severe to salvage content because "it's all about the readers", as though encouraging sockpuppetry by toxic personalities doesn't do immeasurable damage to specific individuals/groups or the greater community, doesn't discourage people from contributing, or doesn't dissuade people from participating in the first place. Some believe that damage is just too abstract, so why bother with uncountable hypothetical articles and other contributions from uncountable discouraged/put off users in the future when we can have one more decent article "for the readers" today. A bit stronger than I'd typically use it, but it seemed like a fitting counterpart to a reduction to "solely believe that banned means banned". — Rhododendritestalk \\ 13:57, 3 March 2023 (UTC)[reply]
Support A7/A9/A11, Oppose G5 as worded, per Rhododendrites and Galobtter - particularly, I think that G5 merits a separate discussion. casualdejekyll14:15, 3 March 2023 (UTC)[reply]
Support A7/A9/A11. I'm less enthusiastic about A11, but whatever. Oppose G5. Recreating content previously created by a known sock is itself prima-facie evidence of socking. We're already losing the sock battle, no need to give them additional assistance. -- RoySmith(talk)14:32, 3 March 2023 (UTC)[reply]
I'm honestly surprised you would make this argument, RoySmith, considering your block of User:Lettler as a sockpuppet when they weren't one. And it appears it likely drove them from the project. A bunch of their articles were also deleted under G5 during the period of your block and you appear to have made no effort to rectify that (I got around to fixing it myself today). SilverserenC21:52, 4 March 2023 (UTC)[reply]
@Silver seren there's very little I can say publicly about that case other than to note that it was an extraordinary situation and policy should not be driven by extraordinary events. If there were pages created by Lettler which were deleted under G5, I have no objection to those specific pages being refunded. Looking over Deleted user contributions for Lettler right now, I don't see any such entries. -- RoySmith(talk)23:08, 4 March 2023 (UTC)[reply]
Because I had them undeleted just now. I think policy discussions should however include cases where prior policy and methods failed and were harmful to editors on the project. In this case, why isn't there a system for someone's articles to be undeleted if they were deleted under false pretenses? We can argue all we want of deletion review or anything else, but the fact of the matter is that it's been over a month and there was no action taken to fix this issue until I noticed it and happened to make the effort to correct it. When it's something that should have been done immediately after Lettler was unblocked. SilverserenC23:11, 4 March 2023 (UTC)[reply]
Support A7/A9/A11. As with the above, I Oppose G5, but I'm willing to be convinced in a separate discussion; G5 carries too many other issues to be bundled with the others. --Jayron3215:04, 3 March 2023 (UTC)[reply]
I see! I believe most administrators are usually willing to userfy such content. I've never seen a request for that get opposed. I would be willing to add G4 to the RfC, as well. Why? I Ask (talk) 15:47, 3 March 2023 (UTC)[reply]
Support for the A-series criteria: these are meant to apply to articles; the deletion concern is addressed by moving the page out of article space. Oppose for G5 per WP:BMB; as I said in the parallel discussion happening at WT:CSD (*cough* WP:FORUMSHOPPING *cough*), I'll gladly provide email copies of G5-deleted articles to any editor in good standing who asks so that they can write an article in their own words, but I won't restore them. I intend to continue this practice regardless of the outcome of these two discussions. Ivanvector (Talk/Edits) 15:52, 3 March 2023 (UTC)[reply]
Just a small request: Undeletion policy should provide enough flexibility to provide list of citations and references. So some who wishes to take stalk of earlier used references in deleted article while working fresh should be possible in most circumstances. Also some flexibility when some one wants to use deleted article just for retaining article history for credits but will be writing article almost afresh.Sorry for not being able to visit RFC proposal in detail and commenting for minimal expectation. I hope my comment is relevant enough and would make some sense. Bookku (talk) 12:33, 4 March 2023 (UTC)[reply]
Yes, the main reason this is so important is because of WP:RUD. If a user wishes to use deleted content, it must be restored for attribution per the legal policy. Why? I Ask (talk) 12:38, 4 March 2023 (UTC)[reply]
Oppose allowing restoration of G5ed articles at REFUND, per WP:BMB, and because REFUND is only intended for uncontroversial cases (which does not include G5). I don't think we actually need this language at all, it's only really there to stop new users making requests which are very unlikely to be granted, and if you request that an article deleted under the A criteria be moved to draftspace for improvement then it will very likely be granted already unless there's something else wrong with the content. This is only being proposed here because the OP's attempt at WT:CSD to add a right to get G5ed pages restored didn't go well. Hut 8.519:38, 6 March 2023 (UTC)[reply]
Can you point out the policy that says G5 is considered "controversial". From my understanding, everything deleted without a discussion (e.g., PRODs) is considered uncontroversial. If what you are saying is true, then the text at WP:REFUND needs to update to clarify what is considered "controversial". Also, looking through the archives, there are multiple instances of some experienced editors having their request for pages deleted under A7–11 criteria restored denied. The text may need to be more explicit in how such cases can be restored to non-mainspace venues if that is the case already. Why? I Ask (talk) 21:24, 6 March 2023 (UTC)[reply]
The question is literally the name of topic of the discussion. It starts with a capital letter and ends with a question mark. --Jayron3218:25, 9 March 2023 (UTC)[reply]
Support yes they can even be restored straight to mainspace if requested. Contributions are under the CC BY-SA 3.0 License so even if banned anyone uninvolved in good standing should be free to request undeletion and in most cases it should be accepted though we shouldn't ignore the fact this may encorage users to evade bans though so maybe not in all cases but I'd say if uninvolved and in good standing its generally fine. Crouch, Swale (talk) 19:42, 10 March 2023 (UTC)[reply]
Oppose detail restrictive / prescriptive instructions at WP:REFUND. It is the right place for a newcomer’s first request. The responsibility for refunding lies with the admin. If an admin doesn’t know when it’s appropriate to refund a G5, either they shouldn’t be an admin, or should be undeletion G5 deletions. —SmokeyJoe (talk) 20:49, 10 March 2023 (UTC)[reply]
As others have said, I don't think it makes sense to bundle these questions together. Support A7 and A9; they should clearly be restorable because they are about simple, straightforward flaws that may in fact be easy to correct, sometimes with nothing more than a single sentence cited to sources already in the article or with the addition of an easily-found source or to. A11, definitely no, not ever - unless someone completely screwed up there is nothing of value to the project in an A11 undeletion; and if someone screwed up we have proper channels for that. When people post made-up stuff in article space we want them to stop it and either work on not-made-up stuff or go away, we don't want them to move it to userspace; and unlike A7/A9 the flaw that got the article deleted is not fixable. G5 is more complex in that we have to weigh the desire to discourage block-evasion with the potential to recover stuff of value, but I'd say no to G5 because making it too easy for blocked users to leave meaningful impacts on Wikipedia encourages block-evasion. This is especially true for editors who were blocked for tendentious / POV editing; assuming their POV is a widespread one and therefore inevitably well-represented among editors, they could almost always count on an editor who shares their beliefs recovering their deleted articles, which would defeat the whole purpose of blocking them in the first place. --Aquillion (talk) 21:20, 10 March 2023 (UTC)[reply]
Support as an option for A7, A9, and G5; making it clear that "yes an admin can do this", not "yes someone must do this". I think there should also be an option in these cases of "restore / provide the list of sources" (or provide confirmation that there were no sources), leaving the article text deleted. DavidLeeLambert (talk) 19:23, 18 March 2023 (UTC)[reply]
In the last few weeks there has been a flood of deletion of sports templates at Wikipedia:Templates for discussion with several thousand being deleted. Typically they only get one or two votes from the same handful of TfD regulars who vote delete for everything. Many times users subst a template and then send it to TfD as unused, which seems like WP:GAMING. I believe a larger community review is needed to root out such dubious practices among TfD regulars who have been conducting large scale deletions virtually unchecked. A lot of templates are being deleted by replacing it with WP:LST. LST is a recent technology and not widely understood by most users yet, while templates have been around for a long time and are easy to use. There should be explicit community consensus if we are going to do a large scale replacement of templates with LST. So I would like a hear what the larger community outside TfD regulars have to say about this. 2409:408C:AD8D:273D:0:0:43C8:AC0B (talk) 17:39, 10 March 2023 (UTC)[reply]
I am an old fart who finds even the use of templates confusing. That said, I took a look at the LST page, and I am lost. It seems to be written for coders by coders - and not for the average user. I have no clue what WP:LST is saying or what I would use it for. If I needed to edit a page that used LST - I simply couldn’t.I am increasingly thinking that WP is no longer “an encyclopedia that anyone can edit”… since the amount of technical knowledge required to do so is growing beyond my abilities. Sad. Blueboar (talk) 18:03, 10 March 2023 (UTC)[reply]
Labeled section transclusion introduces a dependency between the source article and the articles transcluding the sections in question. The source article needs to preserve the labels being used to identify the transcluded text, whether those are the section headers or special transclusion labels. You didn't specify how they were being used for the content you were referring to, but I'm guessing for sports templates, it was tabular data. Tables are generally maintainable as standalone entities and so are well-suited for being placed on a separate template page. Personally I feel even if the table is only being used in a small number of places (or even one), it can be desirable to keep a frequently updated table on a separate page. In theory if the updates end (say, at the end of a season), the template could be substituted onto the one page it was used, but I don't see much benefit at that point. (It would shorten any applicable lists of template categories, but I don't think that will have much practical effect.)
Labeled section transclusion in mainspace is an interesting possibility for reusing a section of text between related articles. Text is generally not as easy to maintain in a standalone template, though, as the surrounding context plays a role crafting the text appropriately. Labeled section transclusion allows context for one location to be immediately visible, but not the context for the other places where it is used. Comments can be used to point to the other places (which would also help avoid the labels being changed inadvertently). Given the additional technical complexity, though, it might be preferable to just use comments to point to other places that should be updated, and rely on them being updated manually instead of automatically through transclusion. Labeled section transclusion for text sections is, I feel, a better fit for some content in the Wikipedia namespace, in specific cases where dealing with possible breakage is more manageable.
On a side note, labeled section transclusion isn't new; it's been around for a decade (I'm not sure how long the feature to include text based on the headings has been around, but based on the help page history, at least nine years). isaacl (talk) 18:34, 10 March 2023 (UTC)[reply]
It sounds interesting and possibly useful, but I would agree with Blueboar that WP:LST is nearly incomprehensible to someone not already well versed in the nuances. Even looking at the few pages listed there as examples wasn't helpful in trying to understand how the tables/text interact, where to update information, or generally how/when to use LST. I'd agree with the original poster that more consensus (and probably explanation/education) is needed before LST is used as a replacement for templates. —Carter (Tcr25) (talk) 19:32, 10 March 2023 (UTC)[reply]
@Blueboar and Tcr25: The WP:LST page is complicated, because it's trying to describe all of the possible syntactical forms. Basically, if you have two articles, Foo and Bar, and you want some content to appear identically in both, you would first choose which one is to actually have this as editable content. Let's say that it's Foo - in this article, you would have:
... content that is only relevant to Foo. <section begin=MySection />This content is relevant to both articles.<section end=MySection /> More content that is only relevant to Foo ...
and this displays as
... content that is only relevant to Foo. This content is relevant to both articles. More content that is only relevant to Foo ...
Then in the article Bar, you would have:
... content that is only relevant to Bar. {{#lst:Foo|MySection}} More content that is only relevant to Bar ...
and this would display as
... content that is only relevant to Bar. This content is relevant to both articles. More content that is only relevant to Bar ...
Then when at some future point you edit that part of Foo that is between the two <section /> tags, the change will propagate to Bar exactly like an edit to a template would. --Redrose64 🌹 (talk) 23:36, 10 March 2023 (UTC)[reply]
It looks like there are several things that need to be made more comprehensible. WP:LST needs to be improved, TfD discussions that invoke it need to be improved, and the post here needs to be improved to give us some examples of what the problem is. Phil Bridger (talk) 20:49, 10 March 2023 (UTC)[reply]
@Phil Bridger: in Wikipedia:Templates for discussion/Log/2023 March 10, User:Frietjes has nominated over 120 templates for deletion after replacing it with LST. She and others at TFD never follow the approach of "I propose deleting these templates after replacing it with LST for this reason", it is always "I have replaced these templates with LST and should be deleted". This is presenting a WP:FAITACCOMPLI to voters. There ought to be clear consensus from the larger community about the necessity of this before doing such large scale deletion for questionable benefit. Many of these templates have been around for over a decade and present in hundreds of old revisions of articles. This kind of deletion of harmless templates shows a mass of red links in old article versions. I have not seen any clear argument as to what advantage LST has over templates. In fact in my experience LST content is harder to edit than templates, harder than even Wikidata. At least for templates you have "V. T. E" buttons and pencil icon for wikidata items that take you to the page that needs to be edited. This is not always present in LST, you have to see page source to try and figure out where it is coming from, which is not easy. Many times I have just given up instead of going through such hassle for updating Cricket stats. Tables from LST cannot be edited using visual editor, with no indication that it is coming from some other page. All of these are barriers for editing Wikipedia. 2409:408C:AE10:FC75:0:0:4348:8811 (talk) 06:12, 11 March 2023 (UTC)[reply]
I'm sure there was an explicit rule against orphaning templates before sending them to TfD as "unused". All I can find for now is WP:TFD#Discussion which does say Templates are rarely orphaned—that is, removed from pages that transclude them—before the discussion is closed. I unfortunately didn't supply a link in this post or this post eight years ago. --Redrose64 🌹 (talk) 10:21, 11 March 2023 (UTC)[reply]
I think those who are maintaining the content should be able to decide for themselves the mechanism that works best for them. Thus I disagree with the example of changing a list of athletes from a template to labeled section transclusion if those who are interested in maintaining the content prefer using a template. I appreciate that the content may be complete in terms of membership, but in addition to monitoring for vandalism, it could undergo future revisions in formatting or associated information. Let those interested in doing the work manage how they want to do it. isaacl (talk) 17:26, 11 March 2023 (UTC)[reply]
A collaborative project shouldn't decide to hand an ongoing bill to a group of people working on a task and say, here, keep paying this bill for something I bought. That's one group of people taking ownership of a decision but not paying for it. isaacl (talk) 21:40, 11 March 2023 (UTC)[reply]
I agree with you, but on the other side, do you remember the jokes about the coder who couldn't be fired, because he made the payroll system such a mess of spaghetti code, and if he left, nobody else could get paid? We don't want to interfere with the people who are doing the work, but we also don't want to be left with a system that nobody else can use. WhatamIdoing (talk) 21:42, 17 March 2023 (UTC)[reply]
Yes, as I mentioned in another comment, I agree there is a longer-term issue with generational turnover of page watchers. However it's not clear to me that deleting these particular nominated templates will make much difference. isaacl (talk) 20:04, 18 March 2023 (UTC)[reply]
I am familiar with LST. I've used it recently for selective table row transclusion. Templates should not consist of article content that needs verification, even if the content is in tabular form. I support pivoting from templates to LST in this set of cases, despite the fact that some maintainers will have difficulty adapting for a certain period. It's worth it. I support Frietjes nominations and actions taken at TFD. Whenever transcluding, it is important to point editors to the source page where they can edit the content. Sometimes, custom hatnotes are needed for this. Editing transcluded content is not more complicated than editing a templated table with no edit button. —Alalch E.19:48, 11 March 2023 (UTC)[reply]
Is the crux of the issue that LST content may contain sourcing information when a template doesn't? I'm trying to understand the benefit of LST over templates and while some editors may prefer LST over templates for a table (for example) no usability or reliability benefits are readily evident to me. —Carter (Tcr25) (talk) 20:29, 11 March 2023 (UTC)[reply]
Templates with such content get vandalized and subjected to disruptive editing (changes that fail WP:V), but this often goes unnoticed because these changes may be subtle and editors don't put such templates in their watchlist. —Alalch E.20:33, 11 March 2023 (UTC)[reply]
Same for an article transcluding parts of a less-watched article. "Templates might get vandalized" is a rather weak argument for making it harder to learn to edit articles. —Kusma (talk) 22:07, 11 March 2023 (UTC)[reply]
Are there examples of this happening that can be pointed to? How widespread is it? Vandalism and bad-faith edits can happen in all sorts of places. —Carter (Tcr25) (talk) 14:32, 12 March 2023 (UTC)[reply]
The example given above by OP does seem like a very explicit case of WP:GAMING. It's similar to someone removing a category from all its relevant articles and then nominating the category for deletion with the argument that it's empty and un-used. A blatant gaming situation that appears to be conducted by an echo chamber of editors trying to push LST into usage on their own, without actually gathering input from the community as a whole. SilverserenC22:30, 11 March 2023 (UTC)[reply]
To me, LSTs do like they will offer improvements over at least some uses for templates. But I don't feel they should be used to replace templates until there's both (1) community awareness of LSTs and (2) documentation that's intelligible to less technical people.—S MarshallT/C23:48, 11 March 2023 (UTC)[reply]
LST (labeled section transclusion) is a can of worms. It requires incomprehensible wikitext in the source article (where the content comes from) and the target (where the copy is displayed). No amount of all-caps hidden comments will make the system resist the ravages of time when gnomes nibble away either at the source or target articles. Also, what is the point of duplicating article text? Phrases that work in the source article should probably be altered and abbreviated in the target. Johnuniq (talk) 00:01, 12 March 2023 (UTC)[reply]
A couple years ago when LST usage was new even to more technical editors I was considering different ways to make the LST system more robust and comprehensible. The main thing was introducing a bot that kept track of LST being broken fixing it or notifying the editor that broke it depending on context, but that would be a lot of work. Making the Wikitext more comprehensible was also a part of it introducing templates like {{Section transclusion}} to better track LST usage, possibly highlight LST portions in preview mode and avoid using parser function syntax which most users aren't familiar with. I also feel like LST as a term should be abandoned in favor of just section transclusion which would be a lot less intimidating since "labeled section" isn't a term used anywhere else and people probably wouldn't use an obscure abbreviation as much. And there should of course be a rewrite of Help:LST. All of this is still relevant today, but I really don't feel excited about working on it. Currently I feel the practice of deploying more LST is slightly positive, like most template work, but isn't near it's full potential. As a TfD regular I will also say that I highly doubt this is intended as gaming at all, but rather just making it more convenient to implement after having seen similar nominations going through hundreds of times. If the LST is already implemented the template can just be deleted after the discussion is over instead of placing it in the holding cell and await that someone returns to all these templates and implement it. It is a bit of gray zone, but I have a hard time believing this isn't done in good faith and I feel the WP:BURO argument is quite strong here given the number of previous nominations. --Trialpears (talk) 02:48, 12 March 2023 (UTC)[reply]
If the LST is already implemented the template can just be deleted after the discussion is over
But is the implementation even something being discussed or are the editors involved unilaterally implementing it without discussion with anyone, let alone the community at large? Because I can certainly say that I oppose any implementation of LST as is currently being done. The actual usefulness for Wikipedia and especially for editors trying to improve articles having to deal with LST coding is severely lacking in evidence right now. SilverserenC03:06, 12 March 2023 (UTC)[reply]
TfD regularly discuss implementation details and is generally quite good at soliciting input from a lot of non-template editors for large discussions through the TfD notices displayed everywhere the template is used. That can result in a TfD being advertised on literally millions of pages at times. It appears however that LST nominations are somewhat of a perfect storm for forming a local consensus anyway since each individual nomination is only advertised on a handful of pages which always leads to TfD regulars being in a majority even though there is occasional opposition. Since lots of nominations have occurred the nominators and closers feel like there significant precedent and large scale consensus even though that may not be true. Nothing malicious is going on, but rather the structure of the discussion has lead to this type of nomination being under advertised. After seeing the page count at Category:Pages transcluding nonexistent sections just now I'm also feeling that something has to be done to improve the situation. --Trialpears (talk) 04:07, 12 March 2023 (UTC)[reply]
There was an old bug that caused some pages which shouldn't be in the category to be in it, which was fixed a few weeks ago, but it appears some pages are still in the category due to bad caching. I WP:NULLEDITed the page, and it's no longer in the category. * Pppery *it has begun...16:01, 12 March 2023 (UTC)[reply]
Oh god, that's even worse than I thought. I still think a bot should be used as well since it can notify editors who accidentally broke it or in some cases fix it automatically. --Trialpears (talk) 03:51, 12 March 2023 (UTC)[reply]
I've created User:Trialpears/Section Transclusion now which is a vision on roughly how WP:LST could read in the future if the improvements suggest above are implemented. If someone who thought the current help page was overly complicated wants to read this and see if this makes the feature seem more manageable that would be appreciated! Everything but the bot should be manageable for me to get done in a week if this is something we want. --Trialpears (talk) 06:51, 12 March 2023 (UTC)[reply]
Replacing templated tables by LST seems to have no upsides that I can see, only considerable downsides (in some TfDs a year ago or so, I have seen many non-arguments such as "templates should have more than X transclusions"). If an editorial decision is made to replace the table in the "source" article by something else, all uses in other articles will break. There should be no pressure to revert such an edit: editors should use their best judgement to make the article they are working on as good as possible. If that breaks other articles, fix it at the target (it is the target article editors'responsibility to watch everything they transclude and to make sure it is what they want). Editing is hard enough as it is without the kind of interdependency introduced by LST. Unlike section anchors (another interdependence), it does not fail gracefully. —Kusma (talk) 07:40, 12 March 2023 (UTC)[reply]
This section has the wrong title. It sounds as if someone is trying to abolish templates and replace them with LST across Wikipedia. No, the starter of this discussion talks specifically about certain sports templates which bear article content (so they are non-standard templates) and are used usually in two articles (a comprehensive list and an article that benefits from the inclusion of a portion of that list), and which were, and some still are, nominated and TfD, and have generally been deleted there. In this, relevant, context, it's unconceivable that there could be a reasonable editorial decision to replace, say, a country's men's team roster in Basketball at the 2016 Summer Olympics – Men's team rosters with something else. Just unconceivable. If such a change were made, editors who have this page on their watchlist would revert it. The same can not be said for individual templates, which have underwent undesirable and undetected changes historically. LST is sometimes a bad idea for the reasons you state, but not always. Editorial judgement is required, and here it was properly excercised. —Alalch E.14:55, 12 March 2023 (UTC)[reply]
Here is an upside you missed - templates always have less watchers than articles. Moving the tables into the parent article means that there are many more eyes watching for changes. Gonnym (talk) 15:19, 12 March 2023 (UTC)[reply]
I am not convinced that this makes a substantial difference in practice for our less popular articles. Five barely active watchers of an article isn't better than one person actively looking out for the template. —Kusma (talk) 18:07, 12 March 2023 (UTC)[reply]
I do not have a clear enough understanding of LST and its downsides at the moment. IMO, Sports "data" (win-loss/scores etc), specially after an event is complete should preferably be in articles, while any "styling" should be templated out. But that aside, I do think @Frietjes: should have first gotten a consensus, preferably a full RFC, before starting this work. There's 1000+ articles and templates affected, probably more, and changing/deleting that many pages ought to involve some larger discussions. So far I can find no such RFCs, and so would recomment Frietjes to stop this conversion until consensus is obtained. Soni (talk) 18:39, 12 March 2023 (UTC)[reply]
The part that concerns me is presenting to TfD as empty templates. That circumvents the widespread notice the system is meant to provide. There should either be community wide consensus to implement LST or the TfD should be nominated before any attempt to use LST and the rationale should include using LST as replacement. There is often more than one way to do something and it is rare the community has mandated a specific way (Engvar, citation styles, etc.)Slywriter (talk) 21:19, 13 March 2023 (UTC)[reply]
The actual text used on TfD pages is unused after being merged with the parent article with attribution and transcluding articles update to use WP:LST. That makes it clear what happend and that it wasn't unused before. That the LST convertion happend before the page is nominated for deletion isn't necessarily a notification problem since it causes an edit that shows up in watchlists instead of being visible if you visit the article. The problem I see is that edits like this has a summary like update template syntax rather than something like convert template to LST template nominated for deletion at TfD. It also appears like there will now be a bit of a pause for these nominations and Category:Pages transcluding nonexistent sections are being activley dealt with by @Frietjes and Plasticspork: who have been involved with implementing LST. --Trialpears (talk) 21:36, 13 March 2023 (UTC)[reply]
I have used both LST as well as Templates, and have authored both. But to my mind, no one has elucidated a common thread that I hear running through many of the comments above, which I believe is key, and that is this: editors are becoming enslaved to the technology, instead of the technology serving our editors (and through them, our readers). That is completely backwards. In my mind, it is the height of absurdity to argue that we must use LST instead of Templates, because LST text exists in namespace zero (articles) where sourcing is required, and Templates exist in namespace ten, where sourcing is not required, or is excluded. If we made these rules, we can change them. First, we must see what user needs are, and then we must mold the technology to serve them/us, not vice versa. Is there consensus to make Template content sourceable and subject to WP:V under some conditions, perhaps via a naming convention? "Make it so." Is there agreement to create namespace 16, "Content", intended for template-style transclusion into one or more articles, and falling under the requirements of WP:Verifiability and other P&G, in order to provide a (conceptually) simple resolution to this type of problem? Make it so. Finally, if you see someone changing transclusion of a template in an article you have a stake in to LST and it's getting in your way, just revert it and change it right back again to using the template. There's nothing to stop you from doing so, and perhaps you'll end up living in the last house standing, that is blocking the bulldozers from flattening everything in order to build that supermall parking lot, but I think you'll find a lot of people tend to support that when they see it, and may even start pushing back and helping you. I live on both sides of this, as I do truly enjoy and appreciate the technology and use it to the max, delighting in every new useful-but-maybe-obscure tecchie gadget that I can find, and I also love writing content and finding sourcing for it, and doing both at once is double the pleasure; however, and this is a *big* however: it is very clear to me where the priority lies, and that is that the technology must serve our needs, full stop, no exceptions. Anything else, is completely wrong-headed. If the technology isn't doing what it should, or is getting in your way, discuss it here, or raise a ticket on Phabricator. Mathglot (talk) 09:01, 15 March 2023 (UTC)[reply]
No one's made an argument that content in templates doesn't have to be sourced. If it appears in mainspace, whether through transclusion or not, then it must be verifiable. Many editors have commented on letting those creating the content use the wikitext features that suit their workflow best (including both creation and later maintenance), rather than have someone else decide on their behalf that they must use a specific feature and watch a certain page. In the long run, as generations of editors turn over, we will need a way to ensure pages remain monitored. Given the existing amount of resuse of content through templates, though, it's not clear to me that eliminating the ones being proposed for deletion will have a significant effect on this problem. isaacl (talk) 18:01, 15 March 2023 (UTC)[reply]
I suspect that @Mathglot is responding to comments like the one above that says Templates should not consist of article content that needs verification, even if the content is in tabular form.
A quick check indicates that there are already 70K pages in the Template: namespace with ref tags, so that's not a problem; it's already possible to source anything that you want to transclude from the Template: namespace. WhatamIdoing (talk) 21:49, 17 March 2023 (UTC)[reply]
Automatically restrict the editing on the pages of political parties
I recently had the chance to see some controversies develop in the talk pages of a few political parties of my country, where some users complain that the articles are heavily patrolled by sympathizers if not outright party members, in effect turning what's supposed to factual encyclopedic articles into propaganda pages since nothing that might be even remotely inconvenient usually stays for very long no matter how factual or how well sourced it is. And suggestions like "just discuss with them bro!", strike me as completely inadequate.
I don't know what debate if any there is around this issue, but increasing the minimum requirements to edit on political parties might limit the flow of users whose sole reason to edit is to peddle their ideologies and nothing else, with no regards to facts, even if it doesn't solve it completely. Wareno (talk) 19:32, 14 March 2023 (UTC)[reply]
When it comes articles (about individual people) in the English Wikipedia, should one make the article name from the Russian transliteration or given minority language version? Especially with Tatar names, since there also exists a Latin Alphabet version of their language, albeit in limited use. I can think of arguments for both; the version in the minority language is sort of more "authentic since that is the native language of given people, but at the same time, the Russian version is the official version that is also in the passports. It also usually tends to be more approachable to English speakers. Xәkim (talk) 15:02, 16 March 2023 (UTC)[reply]
There is no “one-size-fits-all” rule for this. Per WP:COMMONNAME the article title should use whatever name is most commonly used in English language sources that discuss the subject (as that will be the most recognizable to our readers).
In the article text, we have a bit more flexibility. We would normally default to the COMMONNAME as well… however, it is appropriate to (briefly) mention any other variants. This is often done as a parenthetical in the opening sentences or paragraph. Blueboar (talk) 15:33, 16 March 2023 (UTC)[reply]
To expand on the above, while it's a case-by-case assessment, variants should typically be included if there is a reasonable chance that an English-speaking reader could encounter the variants somewhere off-Wikipedia, but we should not be inventing plausible variants if we do not previously have evidence of them being used. signed, Rosguilltalk15:43, 16 March 2023 (UTC)[reply]
The following discussion is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.
Maps are used as references in 32,000+ articles. From time to time questions about their use are raised in venues such as WP:GAC,WP:AFD and WT:OR. Policy and guidelines about sourcing and verifiability do not directly address nontextual sources. This RFC was started to answer some of those questions. I feel the Wikipedia community would benefit if we have some codified guidelines about their use to avoid having to continually revisit these topics.Dave (talk) 05:29, 19 March 2023 (UTC)[reply]
The discussion above is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.
Both shortcuts are within the bot policy and suggest that they apply for permission for their edits here. I suggest that the top 20 of the article creators are included in the denomination of masscreating editors and they should apply for permission there. In a RFC of 2009, (also at the village pump (policy)), the article number that classifies for masscreation was not really defined, but 25-50 was not opposed. Yet also the ones who created more than 25-50 didn't apply for permission, with one of the prominent cases being Lugnuts, which in my opinion is a deplorable loss, because his investment of time to wikipedia was huge. If his and also of others energy could have been guided to a calmer area, they'd likely still edit (under their original accounts).
They could anyway have been requested to apply for permission per WP:MEATBOT (about bot-like editing), but that policy doesn't seem to have been observed or enforced when the several discussions on masscreation began. Many of the masscreating editors are lost to Wikipedia, and I'd say it is not only their fault, but in part also our fault because we were not able not guide them to a more cooperative way of editing.
In order to prevent further very long discussions, I believe it would be good to just enforce WP:MEATBOT and amend WP:MASSCREATE to the top 20 article creators of the month. If one enters the top 20, they must apply per MASSCREATE, if one edits bot-like and is able to create several articles within a few minutes or two hours they shall apply per MEATBOT.Paradise Chronicle (talk) 09:08, 21 March 2023 (UTC)[reply]
You are conflicting a few things here. WP:MEATBOT doesn't mean we treat all fast edits and lots of changes as being a bot. It talks of disruptive editing, and if it's done quickly, it makes no difference if done by a bot or by hand, and WP:MASSCREATE is talking about specifically using automated or semi-automated tools. If someone is making lots of articles with the use of tools, then they need to fill out at BRFA. If they are creating poor or disruptive articles, then they need to be raised at ANI or another noticeboard. We don't simply create policy to penalise good faith article creation, see WP:NOTBUROLee Vilenski(talk • contribs)09:29, 21 March 2023 (UTC)[reply]
To prevent long discussions as we had with Carlossuarez and Lugnuts? Future examples might become Adamtt9 or Pvmoutside, both editors who are in the top 20. Adamtt9 creates articles contrary to
Regarding the species in danger comment, I reviewed the three articles referenced. The first two are referenced properly and according to the IUCN are categorized as least concern, so I'm not sure what the editor is trying to say, the third article I did not create...Pvmoutside
You sure also created the third one, just check here. And least concern... ok and? they are still on the red list and the infobox should be a summary of the article in which you usually do not mention the red list as far as I have noticed.Paradise Chronicle (talk) 21:49, 22 March 2023 (UTC)[reply]
Uhhh, I want to correct myself. I didn't know that least concern means no concern as I figured that if they are included in the red list for threatened species they are in danger. Apparently it's not like that and I apologize. I still see those articles as taggable, let's say for too technical as they are full of latin names and acronyms and would support the removal of autopatrolled from Pvmoutside. Paradise Chronicle (talk) 07:47, 23 March 2023 (UTC)[reply]
No? Where do we state a figure for how much one can create? MASSCREATE talks about using tools. If someone wants to create hundreds of articles that are all well cited, there is no issue. Lee Vilenski(talk • contribs)14:23, 21 March 2023 (UTC)[reply]
Tools for semi-automation would include things like boilerplate text - a necessity for anyone who is creating dozens of articles per day. WP:MEATBOT would also apply, which doesn't require any tools to have been used.
However, I agree that this proposal isn't the route forward; defining mass creation solely in terms of the most prolific editors is too inflexible and will likely exclude many mass creators, and may include a couple of editors who don't engage in mass creation. BilledMammal (talk) 15:35, 21 March 2023 (UTC)[reply]
At Masscreate it says any large-scale automated or semi-automated content page creation task must be approved by the BRFA. It is the first phrase. Since no-one seems to have been approved, no-one seems to have applied for the rights even though they surpassed the mentioned unopposed threshold and we are having very long discussions on stub creations, I thought it might help narrowing it down to the 20 most prolific ones. But if not even they can be included, who will, and then also what's the sense of having such a policy? To be included in the top 20, doesn't have to be seen as a punishment, and it is also not meant as a punishment, the amendment is meant to regulate the masscreation of articles, so the ones that are good at it, can be shown as the examples to follow to the ones who are not yet so good at it, and this before having created hundreds or even thousands of articles. Paradise Chronicle (talk) 20:10, 21 March 2023 (UTC)[reply]
What are the actual problems with the individual articles that these editors are creating (ignoring how, when and by whom they were created)? If you cannot identify any specific problems that apply to at least the majority of the articles created, and explain how classifying them as mass-created would address those problems, then all this is a waste of time.
It specifically says "automated". You are trying to make any user who creates a lot of articles need to fill out a BRFA, giving examples of people who create poor articles. All this policy is designed to do is make more work for someone actually making non-automated articles - and if they are making them badly, they'd hardly put in enough time to do a bot request form. Lee Vilenski(talk • contribs)22:15, 21 March 2023 (UTC)[reply]
@Lee Vilenski. It says semi-automated and underneath comes
That simply isn't true. MEATBOT talks about disruptive bot like editing. It DOES NOT suggest that all edits that are done quickly are bot edits, nor that they are disruptive However, merely editing quickly, particularly for a short time, is not by itself disruptive. That is the bit where this falls down. This proposal suggests that all users who create lots of articles (regardless of quality) should in fact be treated like a bot, and made to fill in a form.
This is also something that is already easy to deal with with existing policy. Is the user using tools? Yes - get them to fill out the form. No? Well, are the articles disruptive, or of poor quality? Yes - report to ANI, other noticeboard, or their talk. They'll soon stop, or gain a block. No? Well, I don't really see the issue. If I wanted to create 30 articles tomorrow that were all well sourced? I don't really see what the issue is, nor would I expect someone to come along and tell me that I need to put in paperwork and become a bot.
Yeah I am not sure if that was a personal attack or a personal point of view. I'd be glad to learn what was you see as a personal attack. You are an admin and like a politician public figure you should be receptive to criticism.
Anyway, while you are right that it is mentioned that for a short while it is not disruptive some of the Masscreators edit high speed on long term. Some like Pvmoutside are editing high speed since years. And if the short term is the one where my suggestion fails, the opposite which would be long term is where I should have your support.
Then I'll also copy paste this part of WP:MEATBOT and then all can decide for themselves.
Editors who choose to use semi-automated tools to assist their editing should be aware that processes which operate at higher speeds, with a higher volume of edits, or with less human involvement are more likely to be treated as bots. If there is any doubt, you should make a bot approval request. In such cases, the Bot Approvals Group will determine whether the full approval process and a separate bot account are necessary.
It doesn't say the edits have to be disruptive in order to apply, just that they have to be high speed enough and their edits can be treated as bot-like editing which applies to several of the top 20 article creators. The title of the shortcut MEATBOT is Bot-like editing and that it is mainly focused on disruptive editing can be a point of view, but one I do not share.
You may want to peruse the recent WP:ACAS. Yes, our current rules don't address mass creation without problems and without the use of tools, and that's not ideal. A big problem seems to be some fundamental disagreements about what, exactly, the problems are when it comes to mass creation and how to define it... — Rhododendritestalk \\ 16:48, 21 March 2023 (UTC)[reply]
That was pointed out on my talk page, yes. I assumed you didn't see it because you referenced a 2009 RfC but not the one we just had on this topic (a long one that took a lot of time with, as you point out, no real solution). Not saying that should be the end of it -- it just seemed worth mentioning is all. NBD. — Rhododendritestalk \\ 22:16, 21 March 2023 (UTC)[reply]
I don't know that it does, except insofar as there have been a lot of people who claim the existing guidance does apply, should apply in spirit, or otherwise operate as though we have rules that we do not have. My "not ideal" is just about clarity/common understanding. — Rhododendritestalk \\ 22:16, 21 March 2023 (UTC)[reply]
The number one editor on this list produced an average of just over four articles per day. Any of us could sit down and spend 15-20 minutes sketching out a reasonable rudimentary article on a missing notable figure, and thereby create four articles in a day, with nothing even close to resembling mass-editing. BD2412T22:53, 21 March 2023 (UTC)[reply]
Then if the two admins here stonewall my suggestions, how can we apply those policies? If it's not the top 20 or editors who perform semiautomated edits, then who? You are the admins, you should know. Or are you all hoping to block the next one instead of finding solution for them? Be a bit constructive here.Paradise Chronicle (talk) 23:54, 21 March 2023 (UTC)[reply]
I don't know if this adds to the discussion, but a few years ago the Tree of Life Project had a bot called Polbot which created many species pages, but was ended when many of those pages needed corrections....Pvmoutside (talk) 00:24, 22 March 2023 (UTC)[reply]
The following question was proposed previously, but a discussion on it was never opened due to the cancellation of the ArbCom mandated RfC. It might be worth revisiting?
Which proposed definition of mass creation should we adopt? Please rank your choices by listing them in order of preference from most preferred to least preferred. Preferences, weighted by strength of argument, will be resolved through IRV. A: A single editor creating a large number of articles based on boilerplate text and referenced to the same small group of sources. B: A single editor creating more than 100 articles based on boilerplate text and referenced to the same small group of sources. C: A single editor, creating more than 10 articles per day, 20 articles per week or 50 articles per month, based on boilerplate text and referenced only to the same small group of sources. D: None of the above
In B 100 articles are meant in total or per minute? If this is not clarified the ones who prefer not to apply will find any excuse. And I doubt if boiler plate should be mentioned as then a possible answer would be that they edit micro stubs manually for days and then publish all at once within a few minutes like I already read before. Paradise Chronicle (talk) 02:38, 22 March 2023 (UTC)[reply]
100 means in total; previous discussion has suggested that boilerplate is necessary, both because it can be determined by reviewing the articles, and because there is agreement that mass creation isn't simply due to the rate of creation but what is created. BilledMammal (talk) 02:43, 22 March 2023 (UTC)[reply]
@Paradise Chronicle you still haven't explained what problem you want to solve. Until you can do that everything else is pointless. What do you want to achieve by applying MASSCREATE? What benefit will doing so bring to the encyclopaedia? It's worth noting that as far as I can tell from a quick glance, none of the suggested definitions BilledMammal would apply to Lord Cornwallis' articles because they are not based on boilerplate text. Thryduulf (talk) 00:50, 22 March 2023 (UTC)[reply]
I have explained above, but you probably didn't read. The aim is to prevent long discussions in the future as we had in the past with Lugnuts and other editors. I believe if editors apply at BRFA, we can show examples to the ones who create deficient stubs. I'd say Lord Cornwallis and I believe also Moonswimmer and Esculenta for sure (articles are rather good) could serve as examples to show to editors who also want to masscreate articles. But since no-one is interested in that I thought it would be interesting to know how the policies on masscreate and meatbot can be applied. If no-one knows we can also just abolish them, then also no-one will have the idea to bring them up. Either show a way how to apply it or abolish it. Paradise Chronicle (talk) 02:16, 22 March 2023 (UTC)[reply]
@Thryduulf, I think the motivation is "drama prevention" rather than anything about the articles or the creation – like if we were to write down that "Mass creation applies to the creation of six or more articles per hour, except during a new moon, when the rate is lowered to one article per hour, unless you have reviewed five extra DYKs during the last 90 days, in which case the usual rate limits apply", and another rule that says "If someone claims mass creation when the creation rate is approved by this tool, then the first three editors who notice this are entitled to post 'Liar, liar, pants on fire' on the editor's talk page", then we won't have l-o-o-o-n-g discussions about whether creating two articles that I dislike is "mass creation" instead of "a violation of all that is right and decent".
However, given that I see editors who persist in claim "original research" for material that is both verifiable and cited, I am not convinced. Maybe if we give them another badname they'd switch to that eventually.
Paradise, the problem with "top 20" is that if editor #20 has created 1,000 articles ever, then:
I can do whatever I want for the first 999 articles, including flooding the review queues with 999 articles in the space of 999 minutes, but
if I create just one article per week, then after ~20 years, I'm going to have to get permission from the bot folks to do something that is obviously not bot-like editing.
@WhatamIdoing, the Top 20 are only for 2022, not for the last 20 years. And also, Wikipedia can develop towards quality, as it happened in many areas of Wikipedia. I believe this development will also come to article creation but maybe I am just a bit ahead of time. Paradise Chronicle (talk) 07:01, 24 March 2023 (UTC)[reply]
Based on a rolling 12-month period or on the previous calendar year?
It doesn't make sense to tell someone that they were in the top 20 last time, so creating even one article now requires extra permission. And it might not make sense anyway, because what if I create hundreds or thousands of redirects, but someone expands those into real articles? Our tools detect that as being a real article (now), so it would count someone else's article creation "against" my limit, unless you did a manual review, which is not really helping.
And it doesn't address the practical problem with mass creation, which is flooding the review queues. It does not matter what the overall limit is, if you say I can do whatever I want for the first ____ articles, including flooding the review queues with ____ articles in the space of ____ minutes will always be a problem unless ____ is a sufficiently low number that the reviewers can handle the burst of activity (generally accepted as 25 to 50 per day). WhatamIdoing (talk) 18:34, 25 March 2023 (UTC)[reply]
Then let's turn it around. What kind of editor would have to apply at BRFA as suggested by MASSCREATE and MEATBOT? So far none seems to have applied for and none was given the rights even though they have created more than 25-50 articles per day or used semiautomated tools for their article creations. I have asked this already before but no answer so far. Paradise Chronicle (talk) 19:04, 25 March 2023 (UTC)[reply]
Paradise Chronicle, I think the rule should be that you apply at BRFA if your future plans will produce a level of articles that the community expects to cause problems for the Wikipedia:New pages patrol. That level has been set at 25 to 50 articles per day for many years. I would personally reduce it slightly, to say something like "25 to 50 articles per day day, or a total of more than 300 articles per month", but other editors would probably choose other numbers. WhatamIdoing (talk) 23:26, 28 March 2023 (UTC)[reply]
Just came here to mention that a similar discussion was held here, where some standards were purposed for articles specific to the Dams. I think at the end, it boils down to the quality of article , not the quantity of article. Each project's articles should be discussed on the specific project group because you can find the concerned experts there and can decide on the quality, standards and overall assessment. After all one cannot be an expert in everything. Best regards!nirmal (talk) 02:11, 23 March 2023 (UTC)[reply]
My opinion is that the problem could be mitigated by banning the creation of stubs. If an article on a subject doesn't have at least, say, 250 words or an equivalent number of bytes then it doesn't belong in the encyclopedia. Maybe stubs should be relegated to the wiki dictionary or some other site. Smallchief (talk) 16:21, 24 March 2023 (UTC)[reply]
An encyclopaedic stub and a dictionary entry are not at all similar, and suggest you have a fundamental misunderstanding of the purposes of Wikipedia and/or Wiktionary. That does not lend favour to your proposal. Thryduulf (talk) 16:59, 24 March 2023 (UTC)[reply]
@Smallchief Great idea the one with the wiktionary. I have/had a similar idea. I thought that if one is not able to word out 10 phrases on a subject, it's not notable enough for wikipedia. As for me it's not enough to add a source, but also the information to the article that is in the source. Paradise Chronicle (talk) 17:43, 24 March 2023 (UTC)[reply]
No, there was not any clear outcome. Please read the discussion properly. Anyway, in the dam related article, one guy hijacked the process and I left on him to move forward.nirmal (talk) 01:28, 25 March 2023 (UTC)[reply]
I agree with you that there was no proper closure, but as to me the replies with the strongest arguments were the ones that supported List of Dams articles (comparable to the Lists of Dams in the USA). And your suggestion of a certain professional criteria per ICOLD is good as well, but not one of your dams created on the 1 of March I checked fulfills your own criteria of 1 Million Cubic capacity. Or maybe you can explain how lower numbers still fit in the ICOLD criteria?Paradise Chronicle (talk) 02:31, 25 March 2023 (UTC)[reply]
RfC on clarifying whether commonality or ties should be preferred when choosing terminology
A: Universally accepted terms should always be used, even for topics where TIES applies, unless the national variety is contextually important to the topic.
B: Universally accepted terms should only be used when TIES does not apply.
Using the examples from MOS:COMMONALITY, under proposal A topics with ties to Britain and America will use glasses rather than spectacles and eyeglasses respectively, and topics with ties to India will use ten million rather than one crore. An example of an exception where national varieties should be used due to being contextually important to the topic would be 100 Crore Club.
Under proposal B topics with ties to Britain and America will always use spectacles and eyeglasses respectively, while topics with ties to India will use one crore.
If there is a consensus for either option then MOS:ENGVAR will be updated to reflect this. 03:48, 25 March 2023 (UTC)
A. Our goal is to write a global encyclopedia, accessible to all English readers, and using universally accepted terms contributes to this goal. We want a reader in India to be able to read an article about a Canadian topic and not be confused by the words used, and we want a reader in Canada to be able to read an article about an Indian topic and not be confused by the words used.
Sometimes, confusion is unavoidable; there is not always a universally used term. For example, a car's trunk or boot. In such circumstances we need to compromise, and MOS:TIES and MOS:RETAIN is a good method to do so, but in circumstances we don't need to compromise, when we can use a word that all readers will understand without us needing to gloss it or without them needing to read another article, then we should use that word. BilledMammal (talk) 03:48, 25 March 2023 (UTC)[reply]
B, but explain - while I absolutely appreciate the desire to have articles all use consistent language, I can't reconcile that with the consequence that option A would mean we're treating certain varieties of English as "more English" than others. The "common" language will almost inevitably be either British or American in origin, while other varieties of English get progressively overwritten even when on articles which have a strong tie to that particular language. I think the best compromise here is to have MOS:TIES take precedent, with the caveat that when using a term specific to the relevant variety of English it should be explained at first mention, such as "Tramping (hiking) is a popular activity..." or "₹70 crore (₹700 million)" as suggested below. Turnagra (talk) 08:41, 25 March 2023 (UTC)[reply]
I disagree we would be treating it as less English, any more than we treat informal English (given our preference for formal English) as "less English" - instead, we would be treating it as less useful for writing a global Encylopedia. However, even if it did treat it that way, I don't see an issue with that; is not English used by 100% of English speakers more English than English used by less than 100% of English speakers?
This applies to words from all parts of the English speaking world; for example, the word we use for Soft drink is the most commonly used word only in Australia and New Zealand, with alternatives like fizzy drink (most common in Britain), pop (most common in the United States and Canada), and cold drink (most common in South Africa and India) rejected for lack of commonality. BilledMammal (talk) 23:29, 27 March 2023 (UTC)[reply]
BilledMammal, you are not entirely correct about the usage of "pop" in the United States, where that is a highly regionalized usage. "Pop" is the most common usage in Western New York, Ohio, Michigan, Minnesota and the upper Great Plains and upper Rocky Mountains states. I grew up in Michigan where everyone said "pop", and then I moved to California, by far the most populous state, where nobody says "pop" but instead everyone says "soda" or "soft drink". Otherwise, Michigan English and mainstream California English are quite similar to me. But even half a century after I left Michigan, occasionally someone will say that I sound like I am from Michigan. Take a look at the map in this article. Cullen328 (talk) 06:04, 28 March 2023 (UTC)[reply]
As am I, BilledMammal. But I have never spent an extended period of time in the Deep South. I have driven through and jetted into the area, staying briefly in hotels and motels. But I am like a tourist from Sydney or Paris when I am in that part of the U.S. Cullen328 (talk) 07:25, 28 March 2023 (UTC)[reply]
Oppose both. Both A and B are too extreme. It depends: How commonly understood is the supposedly universally accepted term? How strong is the tie? How confusing is a term to the readers who didn't get their most familiar term? These vary case by case. They're factors to be weighed as guidance, not rules with an absolute order of priority. For example, "filling station" is arguably a commonality, yet also few people's first choice. Even when there are weak ties, we should usually just pick gas station or petrol station, and even when there are no ties, we should retain gas/petrol/filling station as opposed to forcing "filling" everywhere. Similarly for the commonality "controlled-access highway". On the other hand, "glasses" is very widely understood; even in an article with clear ties we should ordinarily write "glasses". Still other cases will have their own unique considerations. Adumbrativus (talk) 10:01, 25 March 2023 (UTC)[reply]
A wouldn't require us to use terms like "filling station", because as you point out a good argument can be made against it being a word that is a commonality. It would only compel us to use words where there is a consensus that the proposed word is actually a commonality. BilledMammal (talk) 23:33, 27 March 2023 (UTC)[reply]
Oppose both A and B - Our goal is to serve [English-reading] users, not force everyone to accept one single format. While it is true that English is not a native language in many regions, it remains widely spoken and probably the most common language the populace can speak if they're multi-lingual (India, in this instance). As such, we have the MOS:TIES to incorporate the respective variety of English. MOS:COMMONALITY is a guideline and as the section header suggests "opportunities" not that "we must and should at all costs" as the proposals say. As such, I don't have any objection to use "100,000 xyz" instead of "1 lakh xyz" or "ten million" instead of "one crore" - non-currency figures (see my comment in Discussion for currency figures; 100 Crore Club is currency-related) - which is where the opportunity for a commonality lie. But we shouldn't force the wording in MOS to "should". — DaxServer (t · m · c) 12:24, 25 March 2023 (UTC)[reply]
Oppose the premise - It is a mistake to think that there is a conflict between TIES and COMMONALITY - a well written article will find a way to achieve both at the same time. On those rare occasions where we must choose, we need to examine the options on a case by case basis. Blueboar (talk) 13:28, 25 March 2023 (UTC)[reply]
A/false dichotomy. glasses is a British English word as well as spectacles, so it is not a TIES issue to use glasses. Universally accepted terms should be used if they exist. This is what COMMONALITY says. TIES puts forwards no contradiction. — Bilorv (talk) 16:36, 25 March 2023 (UTC)[reply]
Neither This is a false dichotomy. Editorial discretion should be used to determine which is more relevant. The one place that I find TIES most annoying—the use of crore/lakh—is easily solved by a number of templates on point, or by good old fashioned typing out of both numbers. Editors are smart, I trust folks to make sensible editing decisions. CaptainEekEdits Ho Cap'n!⚓23:50, 25 March 2023 (UTC)[reply]
Generally oppose as a false dichotomy, because we use editorial discretion and do not need a binary rule for everything. If I were pushed to pick a side, it would be A, because we are here to write a global encyclopedia, not pander to local dialect pecadilloes. — SMcCandlish☏¢ 😼 07:09, 27 March 2023 (UTC)[reply]
Neither Deal with matters on a case-by-case basis. There's no need for a universal rule here. Weigh the evidence and make a decision based on the particulars of each individual instance as to which of the two sets of guidance is more applicable. --Jayron3212:27, 27 March 2023 (UTC)[reply]
A in the general case, but for lakh/crore specifically, DaxServer points out below that "million" is legitimately harder to understand for them, which is enough to swing my viewpoint for that one case. Template:INRConvert seems like the way to go there. ℰmi1y⧼T·C⧽21:31, 27 March 2023 (UTC)[reply]
Neither A nor B - in most of the cases that this RfC seems likely to be used to officiate, the terms that are actually available are unlikely to be either truly universal or truly particular, but are rather situated on spectra or mixtures between these supposed pure forms. National varieties of English certainly do exist, but they do not each consist of a definitive assemblage of universal and particular language choices in the way this RfC seems to presuppose.
Selecting Option B would encourage TIES flag-planting and parochial deployments of local vernacular, while I expect Option A to be drawn upon by editors, often unintentionally, in service of language that seems universal to a particular editor in situations where the reality is more complex. There is no good reason to choose between these options as a policy matter, when the best practice will continue to consist in linguistic pragmatics carried on "on the ground".
By the way, the language with which the RfC options are actually described seems designed to prevent editors from supporting, for example, universal terms when they are judged equally appropriate when compared to language group-bounded terms in a specific context, without also supporting universal terms in any instance where they are available at all - this non-neutral presentation of a decision that more naturally falls into three preference zones may explain why so few editors to date have been able or willing actually to choose between A and B. Newimpartial (talk) 00:07, 28 March 2023 (UTC)[reply]
What would you propose as an "option C"? My intent with option A was for it to only apply to terms that there is a consensus are a "universal term", and not to other situations such as when language only seems universal to a particular editor, but the wording may have fallen short of the intent. BilledMammal (talk) 00:51, 28 March 2023 (UTC)[reply]
My understanding of the decision can't be added to the existing options IMO because of the way the terrain is already mapped in the first two.
My idea of a neutrality is better reflected in the following question and options:
hypothetical RfC
How should the choice between universal and Engvar-specific terms be decided:
1. Always use a universal term if a substantially-applicable one can be identified.
2. Prefer the use of universal terms where they can be identified, but not in cases where specific, nationally-important terms are relevant to the topic.
3. Use universal terms wherever they are equivalent to and comparably recognizable to nationally-specific terms, but prefer nationally-specific terms where they are more specific, more recognizable or decidedly more idiomatic.
4. Prefer the use of nationally-specific terms for articles where the scope of the topic is bound (by definition or by the preponderance of sourcing) to the variety of English selected for the article.
5. Always use nationally-specific terms where they exist for the variety of English selected for the article.
6. None of the above: follow local consensus whenever such issues arise.
(edit conflict) The current Option A seems equivalent to my 2., and your option B seems equivalent to my 5. From my point of view, then, not only NOTA (6) but also the middle option (3) are missing, and you have offered a more moderate A against a more extreme B (sitting at 2/5 and 5/5 if you imagine my options as a Likert scale). (And no, I am not actially proposing a 5-option RfC; I'm just trying to articulate why I see A and B as non-neutral in the spectrum of possible opinions.) Newimpartial (talk) 01:17, 28 March 2023 (UTC)[reply]
For three, if I have understood it correctly that was the intent of my proposal; a term with recognizably issues under a specific ENGVAR is not, in my opinion, compatible with the requirements of COMMONALITY. However, it seems that this opinion may not be universal, which would explain some of the objections to this proposal.
B is equivalent to your 4; it doesn't apply to articles where the ENGVAR is there under MOS:RETAIN rather than MOS:TIES.
(And no, I am not actially proposing a 5-option RfC; I'm just trying to articulate why I see A and B as non-neutral in the spectrum of possible opinions.) If I understand you correctly, you would support #3 and would have proposed a 3-option RfC with the current two options plus that one? BilledMammal (talk) 01:28, 28 March 2023 (UTC)[reply]
In this hypothetical I would be torn (as I believe would other editors, based in their !votes) between 3 and 6. Also, in an RFCBEFORE I would have tried to reach one option combining my 1-2 and one for 4-5, perhaps through the use of "require/prefer". I get that both of your options are "always", but I think the instrument needs to be sensitive to preferences away from the "centre" of the distribution, so I would avoid "always" in a 3-option format. (Also, I still see your A as closer to 2 than 3, given the use of "always", but if you see it as closer to 3 then you are making my point for me about A representing a moderate option favoring COMMONALITY AND B being a more drastic option favoring TIES.)
digression about my option 4 vs. 5
Also, while I see now that my 5 points to RETAIN whereas your option B points to TIES, I think your option B is still closer to my 5 in key respects: not only in using "always", but more importantly because my 4 requires that that the engvar be bound to the scope of the topic to establish a preference. A topic covering North America, for example, could have strong ties to the US engvar without being bound/limited to it. I have a half-baked example: it might be appropriate to incorporate the US-specific terms used by Major League Soccer and RS about it to describe its own activities, but that topic is not so US-bound that it would make sense to me to follow US syntax where it is not widely understood in Canada, if for example terms about employment or citizenship differ between those two countries and the article makes reference to these aspects.
Oppose both as being too extreme and lacking in nuance per Newimpartial and lacking any evidence of need for a universal rule. Thryduulf (talk) 16:28, 28 March 2023 (UTC)[reply]
Oppose both - Both options lack nuance. The current ambiguity allows editors to decide what makes the most sense in a given context. If the term with the closest MOS:TIES to a subject lacks MOS:COMMONALITY it can be perfectly acceptable to just explain what the term means, in the same way that articles will usually say "the building is 20 metres (66 ft) tall" it is also perfectly acceptable to say "there are estimated to be 10 crore (100 million) of these plants growing in India" or "the company also produces potato chips (crisps)". It's also worth noting that even where commonality does exist, the implication of a term in the context of a different variety of English may be different. For example, in an article written in British English, saying "the cargo was carried by truck" would generally imply the use of a smaller vehicle than "the cargo was carried by lorry", and in that case the best way to achieve commonality might be to say "the cargo was transported by road using a lorry" or something to that effect. HumanBodyPiloter5 (talk) 00:13, 29 March 2023 (UTC)[reply]
A query, using Chennai Express as an example, as it seems the lakh/crore issue is at the heart of this. This article states in the infobox that the budget was ₹70 crore; wouldn't it be more intuitive and simpler to just do "₹70 crore (₹700 million)"? Curbon7 (talk) 06:04, 25 March 2023 (UTC)[reply]
In the context of currency, if we're going to add explanation, we might as well say "₹70 crore (US$12 million)", or whatever the conversion rate was at the relevant time. If a reader doesn't know what ₹70 crore means, then that reader (presumably not from India) probably has a better sense of what ₹700 million means, but in the end probably not a very good sense of that either. Adumbrativus (talk) 10:38, 25 March 2023 (UTC)[reply]
I gather this is ultimately about lakh/crore. I would discourage a blanket change to ENGVAR; if we have to, add a note clarifying preferred approaches for that specific case.
Going to broad overall changes like this can have unforseen consequences - "B" assumes that all local contexts would use the local term if not for standardisation, but in the example given, 'glasses' is probably more common than 'spectacles' in BrEng. The result would end up mandating an unrelated change that probably no-one actually wants, in order to settle a single specific dispute. Andrew Gray (talk) 10:28, 25 March 2023 (UTC)[reply]
An example from the earlier discussion regarding school terms that went unresolved: Should a page with U.S. ties be using freshman and sophomore instead of the understandable, but less common and more verbose, first-year and second-year student?—Bagumba (talk) 11:00, 25 March 2023 (UTC)[reply]
Re the Indian currency numbering system, ~1.3 billion people - 1/7th of the global population - uses it. If I were to read "₹700 million" because it is "universally accepted term", I'm lost and absolutely cannot comprehend. I've to mentally convert the figure to "₹70 crore" to understand the meaning. To alleviate the lakh/crore problem, we use {{INRConvert}} - example: ₹70 crore (US$8.4 million) or ₹70 lakhcrore (equivalent to ₹290 trillion or US$3.5 trillion in 2023). And not the "₹70 crore (₹700 million)". The world we live in uses USD as the global base currency. If I were to read an article with ¥10,000 - I've no clue of the value, however using a {{YENConvert}} or a similar one, I'd have a reference point to USD (despite not being a currency I use except paying for international purchases - true for majority of the population). — DaxServer (t · m · c) 12:37, 25 March 2023 (UTC)[reply]
The issue with INRConvert is that it still doesn't tell the reader how many rupees that it; the equivalent in dollars is useful, but it still leaves the reader lacking information. A MOS:COMMONALITY compromise could be to always type the full number out (₹700,000,000), at least for topics with MOS:TIES to India and Pakistan? BilledMammal (talk) 23:17, 27 March 2023 (UTC)[reply]
INRConvert is just a template that we can customize to whatever usefulness we determine it would provide. Or another template. But not a cover-all rule — DaxServer (t · m · c) 07:38, 28 March 2023 (UTC)[reply]
Ties is to establish which variety of English is appropriate to the article. Commonality directs that, so long as it is sensible and reasonable, non-type specific terminology is (and subject to those provisos, always) preferred over type-specific. I don’t see the issue here? MapReader (talk) 14:43, 25 March 2023 (UTC)[reply]
@MapReader: The issue is that it isn't seen as subject to those provisos, always preferred over type-specific, with some editors arguing that TIES should be preferred - see above, where an editor argues for the use of "tramping" over "hiking" in relation to New Zealand topics, a position which reflects current use in articles - I haven't looked into the subject, but I suspect that hiking meets all those provisos for New Zealand topics. BilledMammal (talk) 23:53, 27 March 2023 (UTC)[reply]
There is nothing in TIES that ‘requires’ variety-specific terminology if a commonly understood alternative exists; that would both be a nonsense and a direct contradiction of COMMONALITY. Nevertheless, in your example, if “hiking” (despite being clearly common to UK and US English) genuinely isn’t used as a word in New Zealand, the editor would have a point as it doesn’t meet the criteria for Commonality. Accepting that a word we might use every day really isn’t widely understood in another English-speaking country is sometimes difficult, but there are plenty of examples both ways between the UK and US that make the point. MapReader (talk) 05:11, 28 March 2023 (UTC)[reply]
Then clearly they are wrong, since TIES relates to the generic style of an article whereas COMMONALITY directs toward the word to be used in a particular sentence. MapReader (talk) 05:59, 28 March 2023 (UTC)[reply]
@MapReader: The issue is that editors holding that position can and do argue that it is aligned with policy, and in the process block proposals to use commonality compliant words; this proposal is intended to address that problem. BilledMammal (talk) 06:30, 28 March 2023 (UTC)[reply]
You talk about a proposal, but looking back at the options referred to in previous discussion, A is essentially current practice and B clearly unhelpful and probably unworkable. In any event, COMMONALITY (and hence A) needs to be used sensibly and is generally a question of re-wording the whole sentence, since there aren't too many cases where are both single words particular to individual varieties of English and another word with the same meaning that is common to both. MapReader (talk) 06:48, 28 March 2023 (UTC)[reply]
I think it's worth noting that many cases where there can seem to be a conflict between MOS:COMMONALITY and MOS:TIES are actually cases where MOS:JARGON is more relevant. For example, the solution to Americans not knowing what a saloon car is and Brits not knowing what a sedan is is to say "it is a four-door saloon car" or "the car is a four-door sedan", which is generally clear enough for most purposes, especially if the mildly-technical terms "saloon car" or "sedan" are wikilinked. HumanBodyPiloter5 (talk) 00:36, 29 March 2023 (UTC)HumanBodyPiloter5 (talk) 00:39, 29 March 2023 (UTC)[reply]
Discussion on disallowing use of the ʻokina in Chinese romanized article titles
I have noticed that there seems to be a marked left-wing orientation within Wikipedia (in the United States, it corresponds to the Democratic Party). I would like an explanation as to whether this is really the case, or whether it is just my impression; furthermore, I would like to know, with proof, whether Wikipedia, according to its own laws, can have political orientations, or must, by necessity, always be neutral. I repeat: it would seem, in my opinion, that there is a not inconsiderable left-wing political orientation here on Wikipedia. JackkBrown (talk) 13:45, 26 March 2023 (UTC)[reply]
You are not the first to make such an observation. Officially, we are supposed to maintain a WP:Neutral point of view. Whether we achieve this (or not) often depends on the reader’s own neutrality… those on the right complain that we don’t give their view enough coverage, while those on the left complain that we give it too much coverage. Blueboar (talk) 13:59, 26 March 2023 (UTC)[reply]
@Blueboar: so (not Wikipedia's fault in any case), is there really a predominantly left-wing orientation on Wikipedia? Even on en.wiki? I would be very sorry if that were indeed the case, because the information itself would suffer greatly. JackkBrown (talk) 14:09, 26 March 2023 (UTC)[reply]
I would say there is a slight left wing orientation, but not a predominant one. Part of the issue is that we require reliable sources, and reliable sources tend to skew left wing. This is especially true with academic sources. Since academics tend to be left of center, this will impact our coverage a bit. Meanwhile, right wing sources tend to be considered unreliable (often for good reasons). As one experienced Wikipedian put it: “The fact is, Reality skews left of center… thus, so does WP.” Blueboar (talk) 14:35, 26 March 2023 (UTC)[reply]
"Left wing" - "right wing" is only one dimension of the political space. Note that Jimmy Wales, principal founder of Wikipedia, and under whom Wikipedia's core policies were developed, has described himself at various times as an objectivist and a libertarian, strongly influenced by Ayn Rand's The Fountainhead; and more recently as "center-right" and "centrist". The culture of Wikipedia is more libertarian than authoritarian (a political dimension that is orthogonal to left/right), and is very much bedded in building an encyclopedia free for all to read and edit, requiring all content to be verifiable from reliable sources, and presenting all content with a neutral point of view. Editing Wikipedia is open to all, with no political test, as long as an editor remains civil and abides with our policies and guidelines. Many editors have some sort of inherent political bias, but many of us, no matter what our political leanings, are dedicated to keeping Wikipeida based on reliable sources and presented with a neutral point of view. Donald Albury16:22, 26 March 2023 (UTC)[reply]
As well as everything that has been said above, I would point out that this is a global encyclopedia, not just a United States one. Certain goods, such as universal healthcare, are accepted in nearly all of the world as beneficial (even by those on the right of politics), but not in the US. Even, and probably more so than in much of the world, universal education is considered to be a public good by right-wingers in the United States. Phil Bridger (talk) 19:01, 26 March 2023 (UTC)[reply]
In a Poli Sci class twenty plus years ago, the professor drew a line on the board and then placed one in the center and wrote Dem on left, Rep on Right. At that time, US politics was considered centrist and two sides of the same coin when it came to global politics. The 21st century has brought significant divergence from those positions and I wonder how the professor would define them now. As to Wikipedia, personalities play a far bigger part in being a productive editor and those who believe Wikipedia is hopelessly flawed are of no use to the project and generally fail to abide by civility and verifiability. In short, much of the US "far-right" winds up self-excluding themselves from the project through behavioral activites incompatible with the project as they mistake this for social media where unsourced debate is welcome.Slywriter (talk) 19:36, 26 March 2023 (UTC)[reply]
Do you JackkBrown have any specific example where wikipedia is supposed to be left leaning towards the Democratic Party? That there exist certain Republicans who believe conspiracy theories like Qanon or that Obama is not an US citizen doesn't make Wikipedia left-wing but much more academic.Paradise Chronicle (talk) 22:43, 26 March 2023 (UTC)[reply]
Using the US definition of left and right I think it clearly has a left bias on articles related to US politics, and I could come up with various slam dunk examples of that. I tend to not worry about that unless it gets so bad that it harms the informativeness of the article, which does sometimes happen. I think that the cause is a combination of systemic issues combined with people who want it that way. It would be good to fix the systemic issues enough to meet the lower bar of fixing those where it harms the informativeness of the articles. Those fixes would help in many other areas besides bias. Sincerely, North8000 (talk) 23:25, 26 March 2023 (UTC)[reply]
It would be much more helpful for the OP and any other concerned people to provide a couple of examples—it's impossible to hold a meaningful discussion without something concrete. Johnuniq (talk) 05:15, 27 March 2023 (UTC)[reply]
Wikipedia presents the facts as understood by the scholarly consensus in the democratic global west, because of our rules. This makes it "left wing" by US standards, but not particularly left wing by the standards of other advanced democracies. The "alternative facts" of the US right are unwelcome here.—S MarshallT/C07:47, 27 March 2023 (UTC)[reply]
From the UK perspective, the Democrats are to the right of our Conservative party. And the Republicans off the chart. There is no equivalent of our left or even centre in mainstream US politics. So your view of left/right bias reflects a US idea of where the "middle" is. But to emphasise S Marshall's point, current political parties and commentators that lie on the right of wherever your spectrum is have adopted a "the facts are unimportant/inconvenient" playbook that is very much at odds with Wikipedia's values. A populist, reckless-with-the-truth, "strong man" political approach isn't necessarily right wing, it just seems to be the current fashion. This, and not economic beliefs, is I think the source of most of the complaints by right wing politicians and commentators about bias on Wikipedia. Why there should be this correlation between economic beliefs and honesty I don't know, and future generations of politicians might change. -- Colin°Talk10:43, 27 March 2023 (UTC)[reply]
To add to and emphasize something in my previous post, I don't think that overall left/right bias can even be defined much less measured and so I don't think that one can say that such exists. I think that you have to get more specific / granular to really say anything about it. My post was about US politics specifically using the US definitions of the two sides. By saying "US definition", I wasn't talking about where it sits in some large right/left measurement, I meant that even the metrics of the scale are different. For example, in some areas, "liberal" has a very different meaning in the US compared to Europe. Also, in the US the existence of the two "teams" dominates everything; even ideology and viewpoints are often subservient to / determined by team membership instead of the reverse. Also, the types of media where each side predominates in the US are different. Once side is stronger in the legacy media, the other on the internet and talk radio and Fox. Internet and radio are inherently less filtered which means the whackiest stuff comes from there. Also structurally, they are less likely to have an internal review layer which wikipedia policies lean towards. Which in turn, enables people to point to those things and with a broad overgeneralization brush deprecate or de-emphasize those sources. BTW, this isn't just about trustworthiness for wp:verifiability, more importantly here is that deprecation or de-emphasis snowballs into wp:weight which has large impacts. In that realm, it's not about verifiability, it's about which totally verifiable things and views do and don't get covered and get emphasized/de-emphasized IMO the bias in in areas like which aspects get emphasized / de-emphasized/ covered / not covered, existence/non-existence and titles of articles. For example, an article about a conservative figure or organization will be very heavy on what their opponents said about them. North8000 (talk) 12:08, 27 March 2023 (UTC)[reply]
With very few (unusually erudite) exceptions, people perceiving and commenting on a supposed political bias of enwiki in general are providing much stronger evidence about their own political standpoints than they are about enwiki and its culture. On specific topics, on the other hand, articles may indeed reflect various kinds of biases including left/right political ones, though outside of recent U.S. politics, political spectrum bias is seldom the most prominent among these, IMO. Newimpartial (talk) 13:27, 27 March 2023 (UTC)[reply]
Worldwide density of geotagged Wikipedia entries as of 2013 Wikipedia tries to be neutral, but due to its reliance on published sources, it picks up some of their bias. It might be true that there is a left bias in certain topic areas, probably inherited from the sources that are useful for them. But the biases on here that are really significant IMO are the ones described at wp:systemic bias. None of these are about the left vs right debate, but about the general lack of coverage of topics in non-western nations, disproportionate lack of female biographies, the way articles are written to suit a certain demographic which isn't representative of wikipedia's overall readership, etc.. Compared to these issues, worries about subtle political biases are just a distraction. small jarstc22:05, 28 March 2023 (UTC)[reply]
For example, many (most?) people believe in ghosts, and Ghost does not say what our overall readers believe. But as you say, that has nothing to do with a right–left political bias. WhatamIdoing (talk) 23:47, 28 March 2023 (UTC)[reply]
My personal opinion is that there certainly are some pages that do have a bias, but not too many have an extreme one. I think that we should further our efforts to inform newer users about the POV noticeboard for the most extreme cases. I've been a registered user on the site since 2018 and have read Wikipedia since I was 7; I haven't heard about it since January of this year. Maybe include noticeboards on some of the Welcome templates? InvadingInvader (userpage, talk) 22:45, 29 March 2023 (UTC)[reply]
Pointless edits
Is there a WP:PAG or even an essay that addresses editors who engage in pointless edits where all they're removing is white-space that has no effect on how the article appears? I swear there is (I wanna say there was even an ARBCOM thing related to that type of editing), but can't find it. —Locke Cole • t • c16:23, 28 March 2023 (UTC)[reply]
(edit conflict) There is WP:COSMETIC in the context of bots, but that's the only one I can think of/find. I too remember something about this at arbcom, I don't think it wasn't the focus of the case but probably in the context of bots and/or MOS issues. Thryduulf (talk) 16:34, 28 March 2023 (UTC)[reply]
Some concerns here. What is the definition of "too detailed"? That seems rather ambiguous. If it is decided that we should ease up on the detail, we are going to need specific guidelines to keep things within the range of what is considered reasonable. If the main issue is too much emphasis on "fluff" like tiny rural communities that even locals haven't heard of, and listing essentially every minor road the tornado crosses, I would say there is legitimacy to that, and I can work with it. However, if I'm being asked to do away with genuinely interesting, relevant tidbits of information, including contextual damage such as scouring and how far vehicles were thrown, debris patterns, debarking severity, names or types of businesses destroyed, and that kind of thing, I don't know how I can contribute meaningfully, and I don't know how I will be able to accurately portray the type and intensity of damage left behind by tornadoes. That is my main concern. I don't want any details regarding the damage itself left out. My other concern is, what about long-trackers like Mayfield? If we have a non-flexible cap on summary length, important info will basically be forced to me omitted, and don't think that's ok. While I do think we can cut down on informational fluff, I think summary length should be a case by case basis based on track length. Thoughts? I don't have anything else to add and will likely take a break after this. Ya'll can hash the rest of this out. TornadoInformation12 (talk) 06:05, 29 March 2023 (UTC)TornadoInformation12[reply]
I always thought all this detail was unnecessary. My only comment is that the longer these summaries are the less inclined most people will be to read any of it. This isn’t the place to preserve every minute detail of the storm. United States Man (talk) 14:22, 29 March 2023 (UTC)[reply]
I agree. I don't like article summaries having to rely on the Damage Assessment Toolkit, which often has minor errors (especially just following events), is difficult to archive, and is unintuitive for people trying to check citations. Rarely, if ever, should the summaries be as detailed as the actual survey narrative (though they usually are). Penitentes (talk) 14:57, 29 March 2023 (UTC)[reply]
...this just makes me sad, because I was just trying to mirror what I saw in the past as well as the NWS summary as well. Maybe I did put too much information in this case, but the other ones I don't understand because those were tornadoes that did vast amounts of various levels destructions along long-tracks. In other words, the section in question can be a little shorter if need be, but I don't see the need to shorten any of the other ones. ChessEric16:03, 29 March 2023 (UTC)[reply]
Meh. I read the article at the center of the controversy, and I don't particularly mind the length. The source being used appears to be scrupulously reliable, and there's no requirement that multiple sources be used. As long as we don't run afoul of WP:LENGTH, I see no problem with the level of detail here. The language is not overly technical, there is, of course, some room for editing and tightening up of the language (perhaps by cutting out, for example, geographic references that are unlikely to be recognizable outside of the immediate neighborhood), but that's part of the normal editing process, and we don't need to set policy to handle that. One person writes something, later on someone comes and edits it a bit, we get to better writing overall that way. It's not really a length or detail issue for me, and we certainly don't need to create some kind of "one-size-fits-all" standard. Let people write, let other people write more, let still other people edit as needed. It's how the process works. --Jayron3216:09, 29 March 2023 (UTC)[reply]
Hey I'm not gonna be editing for about a week while I work on my mental health, but I still have some input after sleeping on it last night. How about these ideas? The Mayfield tornado summary was made easier to read because somebody broke it down section by section. It's a lot easier on the eyes, and not as overwhelming. How about doing that rather than putting a hard cap on summary length? I mean some day we are going to have another crazy multi-state long tracker, and a hard cap would create issues. OR another option is making stand-alone articles for particularly major tornadoes, so that if people want a short summary, they can just look at the brief version in the "Confirmed Tornadoes" section below the table, and if they want the full summary, they can click on the article above the paragraph that will take them to the page for that specific tornado (like Mayfield). I also do think we can cut down on the street by street SUPER-detailed analysis, or mentioning every tiny ghost town or rural community the tornado passes near. Like rather than explaining the damage in each neighborhood, just reigning it in to "neighborhoods in the eastern part of town sustained major damage, ranging from EF2 to EF3", plus maybe an extra detail if there is one particularly intersting damage point within that area. I'm willing to reign things in within reason, as long as no actual info gets sacrificed, and I think there's a way to appease both sides. What do you guys think? TornadoInformation12 (talk) 20:52, 29 March 2023 (UTC)TornadoInformation12[reply]
Comment – It would be difficult to prescribe a precise level of detail for descriptions for tornado damage, but I think that these sections can be curtailed based on the nature of the data itself. Usage of the National Weather Service's damage survey viewer – a database of sorts – as a reliable source for tornado information is probably a valid use, though the ongoing RfC regarding the usage of maps as sources might be consequential here. Although there isn't necessarily a requirement to use multiple sources for information, the use of multiple sources would provide more context as WP:INDISCRIMINATE recommends. These would I imagine often be local news sources, which would provide context to the businesses and neighborhoods being impacted beyond a perhaps overly detailed play-by-play of street-level impacts. The motivating section for this RfC, however, has other issues with regard to its usage of the source. Many statements are not supported at all by the data available on the tool (e.g. the database, which only lists point by point damage severity, has nothing to say about the tornado being rain-wrapped wedge tornado [...] observed by multiple storm chasers). The section also makes judgements about the tornado weakening or strengthening or changing in size when the source does not indicate anything about the tornado's strength or size at a point. It also appears that the source is being used to reach conclusions that the source does not make. For example, the section states an old barn was structurally compromised when the source says nothing about an old barn, only that a structure was surveyed that falls into a category of small barns and farm outbuildings. The source often uses canned descriptions of damage and type of structure, providing no insight to exactly what businesses and neighborhoods were impacted. I'm worried that the source is being used to tell a story that, while possibly accurate, is not verifiable and may be more descriptive than what the source actually offers. It is also important to note that the survey tool only lists points of damage that the National Weather Service has decided to survey/upload, and should not be used to enumerate or describe the spatial extent of damage. —TheAustinMan(Talk ⬩ Edits)20:58, 29 March 2023 (UTC)[reply]
NWS often specifically says it is increasing strength or decreasing strength. Also per WP:CALC (even more specifically, an ongoing separate and un-related clarification RfC) basically says editors can do routine calculations. The clarification RfC seems to say the same general thing where it is routine still for editors to say 1 number is larger than another. So based on that, when NWS says EF3 damage points occurred here, but 1 mile away, EF2 damage points occurred, editors are able to say the EF3 damage was stronger than the EF2 damage, which means the tornado wasn't as strong (aka weakened). So that aspect will still be protected and the clarification RfC is heavily leaning that way it appears. Elijahandskip (talk) 21:29, 29 March 2023 (UTC)[reply]
The "rain-wrapped wedge tornado" statement being inferred is understandable because I just left it there, although there are several videos and pictures that confirm that it was such. However, I do take issue with some of the other statements, which I will list below:
"tornado weakening or strengthening or changing in size"
This text is in the NWS Jackson survey:
"The tornado continued northeastward, producing tree damage as it crossed the Steele Bayou Canal then into Sharkey County. At this point, the tornado began to increase in size and intensity, and there was evidence of multiple vortices at multiple points along the path in Sharkey County."
"The first indications of EF3 to EF4 damage occurred along Pinkins Rd, where each structure along the dead end road, including several manufactured homes and a site built home, was demolished."
"As the tornado moved into the western side of Rolling Fork, the tornadic wind field was broad, encompassing the area from Race St where exterior damage occurred to the Sharkey Issaquena Hospital to Bear Lake Rd on the south end. The corridor of greatest damage on the west side of the city, up to EF3, extended from 7th St between Martin Ave and Joor Ave to 3rd St between Southern Ave and Lewis Ave to S 1st St near Wright Ave."
"After the tornado crossed Deer Creek into the eastern side of Rolling Fork, some intensification occurred, with additional EF4 damage noted. Two homes, one along Sharkey St and one along Collette Ave, had all walls collapsed."
"Another area of EF4 damage was along Mulberry St and Hunt St, where additional homes and businesses had all walls collapsed, Several other structures had roofs removed and some walls collapsed as far north as Lindsay St and Magnolia St. As the tornado approached US 61, several businesses were impacted, especially in the area between Walnut St and Rosenwald Ave. Several of these businesses were metal building systems that were nearly or completely destroyed."
"Around 30 mobile or manufactured homes at the Chuck's Dairy Bar property were destroyed."
"old barn was structurally compromised":
On the DAT, there is an EF0 point along Grant Road at latitude 32.84 longitude -90.99. This point says, "damage_txt Small Barns or Farm Outbuildings (SBO)" followed by "dod_txt Uplift or collapse of roof structure." The "comments" given were "much of roof removed and structure compromised - old structure." This is verification of that.
"canned descriptions of damage and type of structure, providing no insight to exactly what businesses and neighborhoods were impacted:"
See above comment on the NWS Jackson survey. As far as the specific businesses impacted other than Chuck's Dairy Bar, they were already in the summary, so I left them there.
I should also note that on the DAT, the NWS Jackson has no info about what the tornado did after it hit Rolling Fork. Therefore, the damage points is what I used beyond that point and the only thing I noted besides that was changes in strength. Whether this is insightful or not is up for debate, but I just wanted to explain where in the information came from. ChessEric23:18, 29 March 2023 (UTC)[reply]
@ChessEric: I appreciate the commentary provided on some of the examples. I see the statements are backed by the survey report published by the Jackson weather service office, but given that's the case, it should be made clear what's being sourced. Since those statements are not explicitly verified on the interactive data toolkit, then the <ref> should be near the relevant information. The frequent, consecutive use of citing the damage toolkit makes it seem as that information is coming from the tool when it is not. As for the old barn example, that's not necessarily verified by the source: it's an "old structure" and has been classed as a small barn or farm outbuilding, but that doesn't necessarily imply it's a barn. @Elijahandskip:WP:CALC would be relevant if the NWS listed the intensity of the tornado along its path, but that's not what they're doing. They are only indicating the degree of damage experienced by structures, which can vary based on the sturdiness of the structure or the density of structures independent of tornado intensity. For instance, a tornado doing EF5-rated damage moving over a rural area and striking a small chicken coop has not necessarily "weakened" simply on the basis that damage to the chicken coop could only be rated as EF2 at highest. —TheAustinMan(Talk ⬩ Edits)00:24, 30 March 2023 (UTC)[reply]
Decide on a case by case basis, but base such case by caseness on the severity of a tornado. I believe that some tornadoes should have longer article leads, but not all of them. For example, a minor tornado that maybe killed one or two people shouldn't get a longer lead section than a stronger tornado which almost cost as much as some hurricanes. I think that our articles on mass shootings do a good job of exemplifying what should happen to tornadoes. Articles on major mass shootings like the Stoneman Douglas High School shooting have clearly longer and more detailed leads than the Mayfair Mall shooting, which killed zero people and injured only eight others. Case by case is the best action pace. InvadingInvader (userpage, talk) 22:51, 29 March 2023 (UTC)[reply]
Meh. I don’t think the length is an issue here, and think it misguided to be “looking for guidance on how to best adhere to WP:MOS and WP:NOTEVERYTHING regarding what information is not insignificant” here. There seems a valid concern about mostly single source, but that would be to comply with WP:WEIGHT and to avoid WP:NOTMIRROR. Otherwise I think length might mean an issue with WP:INDISCRIMINATE, but not in this case because it has a connected narrative. Level of detail guidance seems more a WP:DETAIL topic than length per se. I would perhaps offer guidance that level of detail should harmonize with WP:WEIGHT, that greater WEIGHT should be given greater prominence of position and length, and items not present in multiple sources or in major sources should have little or no mention. Cheers Markbassett (talk) 01:59, 30 March 2023 (UTC)[reply]
So what's the consensus here? Case by case? If so, before we make a summary, each time we'll have to agree an a length limit. That's fine with me as long as it keeps everyone happy. Thoughts? TornadoInformation12 (talk) 03:56, 30 March 2023 (UTC)TornadoInformation12[reply]
For me, my thoughts are do what you're best at. Some people are good at writing, but not at editing, which is to say some people may write and reference things great, but when deciding among the plethora of information on a topic, they aren't great at deciding which bits of information are vital, and which can be omitted without losing meaning for the reader. That's perfectly okay. We don't expect every contributor to be perfect at every aspect of good writing. If you're good at writing, but not at editing, it's okay to leave that task for someone else; so long as you understand that sometimes people will remove sourced information if its presence doesn't improve the article in question. That's a normal part of editing, and if you're okay with people editing your work down, no one should feel obligated to hold back on what they are good at. We shouldn't be setting policy saying ahead to try to stop you from contributing by your own means, so long as you also understand that people will make improvements to your writing, and sometimes removal is improvement. That's my whole point above. Writing too much isn't a problem at all. People can come along later and tighten things up. It's fine, so long as we're all obeying WP:CITE and WP:V and WP:NPOV and all the rest. --Jayron3212:16, 30 March 2023 (UTC)[reply]
Agree with Jayron… trimming long articles is all part of the process, but we would rather have something to trim than not have enough. So… if you are not sure whether to include some bit of verifiable information… go ahead and include it. And if it subsequently gets trimmed out, no big deal.
Finally, don’t take it personally. Remember that the goal is to improve the article… and improvement involves both adding and removing (or rewriting). Blueboar (talk) 13:00, 30 March 2023 (UTC)[reply]
It sounds like the decision is this; if you're working on the summary, put the information that you think is important and let other people come in and make the necessary changes. Now I've trimmed a lot of the Rolling Fork section (mostly removing DAT inferences), but I wouldn't mind it becoming longer again. Now someone tried to make an article for this tornado, and that was not necessary, but I see why there was an RfC for this topic. ChessEric16:10, 30 March 2023 (UTC)[reply]
Google Gboard's microphone icon support speech recognition for iOS and Android devices. For devices with different operating systems there exist free software and free add-ons for Google Chrome (full list available at the following link: [11]: Dictation and TalkTyper, Voicein and Lipsurf). 151.82.234.22 (talk) 20:20, 30 March 2023 (UTC)[reply]
— The Transhumanist 11:18, 13 February 2023 (UTC)
But this contradicts the title of the first source provided (the second source is behind a registration wall):
Moved from Wikipedia:Village pump (proposals)#Make Wikipedia:Requested moves/Closing instructions a guideline
This is a failed proposal
There is currently a discussion that may interest you. Wikipedia talk:Manual of Style#Disallowing use of the ʻokina in Chinese romanized article titles proposes that the ʻokina gennerally be prohibited from article titles derived from Chinese whenever it does not adhere to the English Wikipedia policy to use commonly recognizable names. Plese join the discussion. Thank you. Peaceray (talk) 17:12, 25 March 2023 (UTC)
