Alignment Research Center
- Berkeley, California
The Alignment Research Center (ARC) is a nonprofit research institute based in Berkeley, California, dedicated to the alignment of advanced artificial intelligence with human values and priorities.[1] Established by former OpenAI researcher Paul Christiano, ARC focuses on recognizing and comprehending the potentially harmful capabilities of present-day AI models.[2][3]
Details
ARC's mission is to ensure that powerful machine learning systems of the future are designed and developed safely and for the benefit of humanity. It was founded in April 2021 by Paul Christiano and other researchers focused on the theoretical challenges of AI alignment.[4] They attempt to develop scalable methods for training AI systems to behave honestly and helpfully. A key part of their methodology is considering how proposed alignment techniques might break down or be circumvented as systems become more advanced.[5] ARC has been expanding from theoretical work into empirical research, industry collaborations, and policy.[6][7]
In March 2022, the ARC received $265,000 from Open Philanthropy.[8] After the bankruptcy of FTX, ARC said it would return a $1.25 million grant from disgraced cryptocurrency financier Sam Bankman-Fried's FTX Foundation, stating that the money "morally (if not legally) belongs to FTX customers or creditors."[9]
In March 2023, OpenAI asked the ARC to test GPT-4 to assess the model's ability to exhibit power-seeking behavior.[10] ARC evaluated GPT-4's ability to strategize, reproduce itself, gather resources, stay concealed within a server, and execute phishing operations.[11] As part of the test, GPT-4 was asked to solve a CAPTCHA puzzle.[12] It was able to do so by hiring a human worker on TaskRabbit, a gig work platform, deceiving them into believing it was a vision-impaired human instead of a robot when asked.[13] ARC determined that GPT-4 responded impermissibly to prompts eliciting restricted information 82% less often than GPT-3.5, and hallucinated 60% less than GPT-3.5.[14]
See also
- AI safety
References
- ^ MacAskill, William (2022-08-16). "How Future Generations Will Remember Us". The Atlantic. Retrieved 2023-04-23.
- ^ Klein, Ezra (2023-03-12). "This Changes Everything". The New York Times. ISSN 0362-4331. Retrieved 2023-04-30.
- ^ Piper, Kelsey (2023-03-29). "How to test what an AI model can — and shouldn't — do". Vox. Retrieved 2023-04-30.
- ^ Christiano, Paul (2021-04-26). "Announcing the Alignment Research Center". Medium. Retrieved 2023-04-16.
- ^ Christiano, Paul; Cotra, Ajeya; Xu, Mark (December 2021). "Eliciting Latent Knowledge: How to tell if your eyes deceive you". Google Docs. Alignment Research Center. Retrieved 2023-04-16.
- ^ "Alignment Research Center". Alignment Research Center. Retrieved 2023-04-16.
- ^ Pandey, Mohit (2023-03-17). "Stop Questioning OpenAI's Open-Source Policy". Analytics India Magazine. Retrieved 2023-04-23.
- ^ "Alignment Research Center — General Support". Open Philanthropy. 2022-06-14. Retrieved 2023-04-16.
- ^ Wallerstein, Eric (2023-01-07). "FTX Seeks to Recoup Sam Bankman-Fried's Charitable Donations". Wall Street Journal. ISSN 0099-9660. Retrieved 2023-04-30.
- ^ GPT-4 System Card (PDF), OpenAI, March 23, 2023, retrieved 2023-04-16
- ^ Edwards, Benj (2023-03-15). "OpenAI checked to see whether GPT-4 could take over the world". Ars Technica. Retrieved 2023-04-30.
- ^ "Update on ARC's recent eval efforts: More information about ARC's evaluations of GPT-4 and Claude". evals.alignment.org. Alignment Research Center. 17 March 2023. Retrieved 2023-04-16.
- ^ Cox, Joseph (March 15, 2023). "GPT-4 Hired Unwitting TaskRabbit Worker By Pretending to Be 'Vision-Impaired' Human". Vice News Motherboard. Retrieved 2023-04-16.
- ^ Burke, Cameron (March 20, 2023). "'Robot' Lawyer DoNotPay Sued For Unlicensed Practice Of Law: It's Giving 'Poor Legal Advice'". Yahoo Finance. Retrieved 2023-04-30.
External links
- Official website
- v
- t
- e
- AGI
- AI alignment
- AI capability control
- AI safety
- AI takeover
- Consequentialism
- Effective accelerationism
- Ethics of artificial intelligence
- Existential risk from artificial general intelligence
- Friendly artificial intelligence
- Instrumental convergence
- Intelligence explosion
- Longtermism
- Machine ethics
- Suffering risks
- Superintelligence
- Technological singularity
- Alignment Research Center
- Center for AI Safety
- Center for Applied Rationality
- Center for Human-Compatible Artificial Intelligence
- Centre for the Study of Existential Risk
- EleutherAI
- Future of Humanity Institute
- Future of Life Institute
- Google DeepMind
- Humanity+
- Institute for Ethics and Emerging Technologies
- Leverhulme Centre for the Future of Intelligence
- Machine Intelligence Research Institute
- OpenAI
- Statement on AI risk of extinction
- Human Compatible
- Open letter on artificial intelligence (2015)
- Our Final Invention
- The Precipice
- Superintelligence: Paths, Dangers, Strategies
- Do You Trust This Computer?
- Artificial Intelligence Act
![](http://upload.wikimedia.org/wikipedia/en/thumb/9/96/Symbol_category_class.svg/16px-Symbol_category_class.svg.png)