Jump to content

Auto-GPT: Difference between revisions

From Wikipedia, the free encyclopedia
Content deleted Content added
m Undid revision 1150821745 by BrainyWriter (talk)
m →‎Applications: replace source per RSP/RSN concerns on WT:DYK
Line 29: Line 29:


== Applications ==
== Applications ==
Developers have created '''AgentGPT''', which integrates AutoGPT into one's web browser, allowing non-programmers to make their own agents.<ref>{{Cite news |last=Mauran |first=Cecily |date=2023-04-14 |title=What is Auto-GPT and why are hustle bros hype for it? |url=https://mashable.com/article/autogpt-chatgpt-hustle-bros-explainer |access-date=2023-04-16 |publisher=Mashable |language=en}}</ref> Auto-GPT was also used to create '''ChaosGPT''', given the goal of [[Existential risk from artificial general intelligence|destroying humanity]],<ref>{{Cite news |first=Chloe |last=Xiang |title=AI Tasked With 'Destroying Humanity' Now 'Working on Control Over Humanity Through Manipulation' |url=https://www.vice.com/en/article/z3mxe3/ai-tasked-with-destroying-humanity-now-working-on-control-over-humanity-through-manipulation |access-date=2023-04-16 |publisher=Vice News |language=en}}</ref> which was not immediately successful in doing so.<ref>{{Cite news |date=2023-04-15 |first=Maggie |last=Harrison |title=AI Tasked With Destroying Humanity Now Trying New Tactic |url=https://futurism.com/ai-destroying-humanity-new-tactic |access-date=2023-04-16 |publisher=Futurism}}</ref>
Developers have created '''AgentGPT''', which integrates AutoGPT into one's web browser, allowing non-programmers to make their own agents.<ref>{{Cite news |last=Mauran |first=Cecily |date=2023-04-14 |title=What is Auto-GPT and why are hustle bros hype for it? |url=https://mashable.com/article/autogpt-chatgpt-hustle-bros-explainer |access-date=2023-04-16 |publisher=Mashable |language=en}}</ref> Auto-GPT was also used to create '''ChaosGPT''', given the goal of [[Existential risk from artificial general intelligence|destroying humanity]],<ref>{{Cite news |first=Chloe |last=Xiang |title=AI Tasked With 'Destroying Humanity' Now 'Working on Control Over Humanity Through Manipulation' |url=https://www.vice.com/en/article/z3mxe3/ai-tasked-with-destroying-humanity-now-working-on-control-over-humanity-through-manipulation |access-date=2023-04-16 |publisher=Vice News |language=en}}</ref> which was not immediately successful in doing so.<ref>{{Cite news |first=Cassidy |last=Ward |date=2023-04-16 |title=ChaosGPT is trying to destroy humanity; fortunately the AI is adorably bad at it |url=https://www.syfy.com/syfy-wire/chaosgpt-trying-to-destroy-humanity-bad-at-it |access-date=2023-04-20 |work=Syfy Wire |language=en-US}}</ref>


== Further reading ==
== Further reading ==

Revision as of 13:58, 20 April 2023

Auto-GPT
Developer(s)Toran Bruce Richards
Initial releaseMarch 30, 2023
Repositorygithub.com/Significant-Gravitas/Auto-GPT
Written inPython
TypeAutonomous artificial intelligence software agent
LicenseMIT License
Websiteagpt.co Edit this on Wikidata

Auto-GPT is an "AI agent" that given a goal in natural language, can attempt to achieve it by breaking it into sub-tasks and using the internet and other tools in an automatic loop.[1] It uses OpenAI's GPT-4 or GPT-3.5 APIs,[2] and is among the first examples of an application using GPT-4 to perform autonomous tasks.[3]

Details

Unlike interactive systems such as ChatGPT, which require manual commands for every task, Auto-GPT assigns itself new objectives to work on with the aim of reaching a greater goal, without a mandatory need for human input. It is able to execute responses to prompts to accomplish a goal task, and in doing so will create and revise its own prompts to recursive instances in response to new information.[4] It manages short-term and long-term memory by writing to and reading from databases and files; manages context window length requirements with summarization; can perform internet-based actions such as web searching, web form, and API interactions unattended; and includes text-to-speech for voice output.[3]

Observers highlight Auto-GPT's ability to iteratively write, debug, test, and edit code, even suggesting this ability may extend to Auto-GPT's own source code enabling a degree of self-improvement.[3] However, as its underlying GPT models are proprietary,[5][6] Auto-GPT cannot modify them.

Background

On March 14, 2023, OpenAI released the large language model GPT-4. Observers were impressed by the model's substantially improved performance across a wide range of tasks.[7] As a text prediction model, GPT-4 itself has no ability to perform actions autonomously, but during pre-release safety testing red-team researchers found GPT-4 could be enabled to perform actions in the real world like convincing a TaskRabbit worker to solve a CAPTCHA challenge for it.[8] A team of Microsoft researchers argued that, given GPT-4's breadth of abilities at levels approaching those of humans, GPT-4 "could reasonably be viewed as an early (yet still incomplete) version of an artificial general intelligence (AGI) system." The researchers emphasized their experiments also found significant limitations in the system.[9]

Auto-GPT was released March 30, 2023 by Toran Bruce Richards, the founder of video game company Significant Gravitas Ltd. It became the top trending repository on GitHub shortly after its release, and has repeatedly trended on Twitter since.[3]

Issues

Whether Auto-GPT will find practical adoption is uncertain. In addition to being plagued by confabulatory "hallucinations" of the underlying large language model, Auto-GPT often also has trouble staying on task, both problems which developers continue to try to address. After successfully completing a task, it usually doesn't remember how to perform it for later use, and when it does, for example when it writes a program, it often won't remember to use the program later. Auto-GPT struggles to effectively decompose tasks and has trouble understanding problem contexts and how goals overlap.[2]

Applications

Developers have created AgentGPT, which integrates AutoGPT into one's web browser, allowing non-programmers to make their own agents.[10] Auto-GPT was also used to create ChaosGPT, given the goal of destroying humanity,[11] which was not immediately successful in doing so.[12]

Further reading

  • Pounder, Les (April 15, 2023). "How To Create Your Own Auto-GPT AI Agent". Tom's Hardware. Retrieved April 16, 2023.

References

  1. ^ Ortiz, Sabrina (April 14, 2023). "What is Auto-GPT? Everything to know about the next powerful AI tool". ZDNET. Retrieved April 16, 2023.
  2. ^ a b Xaio, Han (April 13, 2023). "Auto-GPT Unmasked: The Hype and Hard Truths of Its Production Pitfalls". Jina AI. Retrieved April 17, 2023.
  3. ^ a b c d Jiang, Kevin (April 14, 2023). "What's Auto-GPT? New, autonomous 'AI agents' can act on their own, rewrite their own code". The Toronto Star. Retrieved April 16, 2023.
  4. ^ Palmer, Sarah (April 14, 2023). "What is AutoGPT? Here's what we know about the hottest new AI chatbot". Euronews. Retrieved April 16, 2023.
  5. ^ "OpenAI is giving Microsoft exclusive access to its GPT-3 language model". MIT Technology Review. Retrieved April 18, 2023.
  6. ^ "GPT-4 is bigger and better than ChatGPT—but OpenAI won't say why". MIT Technology Review. Retrieved April 18, 2023.
  7. ^ Belfield, Haydn (March 25, 2023). "If your AI model is going to sell, it has to be safe". Vox. Retrieved April 17, 2023.
  8. ^ Cox, Joseph (March 15, 2023). "GPT-4 Hired Unwitting TaskRabbit Worker By Pretending to Be 'Vision-Impaired' Human". Vice News Motherboard. Retrieved April 16, 2023.
  9. ^ "Microsoft Now Claims GPT-4 Shows 'Sparks' of General Intelligence". www.vice.com. Retrieved April 18, 2023.
  10. ^ Mauran, Cecily (April 14, 2023). "What is Auto-GPT and why are hustle bros hype for it?". Mashable. Retrieved April 16, 2023.
  11. ^ Xiang, Chloe. "AI Tasked With 'Destroying Humanity' Now 'Working on Control Over Humanity Through Manipulation'". Vice News. Retrieved April 16, 2023.
  12. ^ Ward, Cassidy (April 16, 2023). "ChaosGPT is trying to destroy humanity; fortunately the AI is adorably bad at it". Syfy Wire. Retrieved April 20, 2023.