Jonathan Stray, CHAI Senior Scientist NEW: There’s also a video version of this post NEW: Our current research project to build political neutrality evaluations. There is an urgent need for a clear, consistent, and practical definition of p…
“The problem of control: how do we maintain power, forever, over entities that will eventually become more powerful than us?”In July 2023, Senate Committee on the Judiciary’s Subcommittee on Privacy, Technology, and the Law hosted the U.S.
On July 25, Stuart Russell gave a testimony on AI benefits, risks, and regulations at the U.S. Senate hearing titled “Oversight of A.I.: Principles for Regulation.” The following is his written testimony: Thank you, Chair Blumenthal, Rankin…
In March 2016, AlphaGo defeated the Go world champion Lee Sedol, winning four games to one. Machines had finally become superhuman at Go. Since then, Go-playing AI has only grown stronger. The supremacy of AI over humans seemed assured, wit…
by Luke Thorburn, Priyanjana Bengani, and Jonathan Stray A recommender system (or simply ‘recommender’) is an algorithm that takes a large set of items and determines which of those to display to a user—think the Facebook News Feed, the Twi…
The Center for Human-Compatible AI (CHAI) is multi-institution research group based at UC Berkeley. CHAI’s mission is to develop the conceptual and technical wherewithal to reorient the general thrust of AI research towards provably benefic…
Jonathan Stray 04 Feb 2025 NEW: Our current research project to build political neutrality evaluations. Stuart Russell 11 Sep 2023 On July 25, Stuart Russell gave a testimony on AI benefits, risks, and regulations at the U.S. Senate hearing…
Khanh Nguyen, Benjamin Plaut, Tu Trinh, and Mohamad Danesh introduce a fundamental coordination problem called Learning to Yield and Request Control (YRC), where the objective is to learn a strategy that determines when to act autonomously
Professor of EECS at UC Berkeley Director of Kavli Center for Ethics, Science, and the Public Professor of EECS at UC Berkeley Director of Kavli Center for Ethics, Science, and the Public Professor of EECS at UC Berkeley Professor of EECS a…
We seek to fill the following positions: If none of these positions are the right fit for you but you would still like to express an interest in working with us, please fill out this form. General enquiries about jobs at CHAI can be sent to…
Prof. Stuart J. Russell, CHAI Faculty Director, and staff This report describes the growth, outputs, and new program engagements of the Center for Human-Compatible AI in the year since the April 2022 CHAI progress report. The Center for Hum…
CHAI aims to reorient the foundations of AI research toward the development of provably beneficial systems. Currently, it is not possible to specify a formula for human values in any form that we know would provably benefit humanity, if tha…