The Center for Human-Compatible Artificial Intelligence (CHAI) is a research center at

University of California, Berkeley The University of California, Berkeley (UC Berkeley, Berkeley, Cal, or California) is a public land-grant research university in Berkeley, California. Established in 1868 as the University of California, it is the state's first land-grant u ...

(UC Berkeley) focusing on advanced

artificial intelligence Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by animals and humans. Example tasks in which this is done include speech re ...

(AI) safety methods. CHAI was founded in 2016 by a group of academics led by UC Berkeley computer science professor and AI author

Stuart J. Russell Stuart Jonathan Russell (born 1962) is a British computer scientist known for his contributions to artificial intelligence (AI). He is a professor of computer science at the University of California, Berkeley and was from 2008 to 2011 an adjunct ...

. Russell is known for co-authoring the widely used AI textbook '' Artificial Intelligence: A Modern Approach''. CHAI's faculty membership includes

Bart Selman Bart Selman is a Dutch-American professor of computer science at Cornell University. He has previously worked at AT&T Bell Laboratories. He is also co-founder and principal investigator of the Center for Human-Compatible Artificial Intelligence ( ...

and

Joseph Halpern Joseph Yehuda Halpern (born 1953) is an Israeli-American professor of computer science at Cornell University. Most of his research is on reasoning about knowledge and uncertainty. Biography Halpern graduated in 1975 from University of Toronto wi ...

from Cornell University,

Pieter Abbeel Pieter Abbeel is a professor of electrical engineering and computer sciences, Director of the Berkeley Robot Learning Lab, and co-director of the Berkeley AI Research (BAIR) Lab at the University of California, Berkeley. He is also the co-founder ...

from UC Berkeley, and

Michael Wellman Michael Paul Wellman (born March 27, 1961) is the Richard H. Orenstein Division Chair of Computer Science and Engineering and Lynn A. Conway Collegiate Professor of Computer Science and Engineering at the University of Michigan, Ann Arbor. W ...

from the University of Michigan. In 2016, the

Open Philanthropy Project Open Philanthropy is a research and grantmaking foundation that makes grants based on the doctrine of effective altruism. It was founded as a partnership between GiveWell and Good Ventures. Its current co-chief executive officers are Holde ...

(OpenPhil) recommended a grant of $5,555,550 over five years to support CHAI. CHAI received an additional grant of $200,000 from OpenPhil in 2019.

Research

CHAI's approach to AI safety research focuses on value alignment strategies, particularly

inverse reinforcement learning Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine ...

, in which the AI infers human values from observing human behavior. It has also worked on modeling human-machine interaction in scenarios where intelligent machines have an "off-switch" that they are capable of overriding.

References

External links

* Artificial intelligence associations Existential risk from artificial general intelligence Existential risk organizations Organizations established in 2016 {{US-org-stub

Research

See also

References

External links