 | |
| Formation | 2016; 9 years ago (2016) |
|---|---|
| Headquarters | Berkeley, California |
Director | Stuart J. Russell |
Executive director | Mark Nitzberg |
Parent organization | University of California, Berkeley |
| Website | humancompatible |
TheCenter for Human-Compatible Artificial Intelligence (CHAI) is a research center at theUniversity of California, Berkeley focusing on advancedartificial intelligence (AI)safety methods. The center was founded in 2016 by a group of academics led byBerkeley computer science professor and AI expertStuart J. Russell.[1][2] Russell is known for co-authoring the widely used AI textbookArtificial Intelligence: A Modern Approach.
CHAI's faculty membership includesRussell,Pieter Abbeel and Anca Dragan fromBerkeley,Bart Selman andJoseph Halpern fromCornell,[3]Michael Wellman and Satinder Singh Baveja from theUniversity of Michigan, andTom Griffiths andTania Lombrozo fromPrinceton.[4] In 2016, theOpen Philanthropy Project (OpenPhil) recommended thatGood Ventures provide CHAI support of $5,555,550 over five years.[5] CHAI has since received additional grants fromOpenPhil and Good Ventures of over $12,000,000, including for collaborations with theWorld Economic Forum and Global AI Council.[6][7][8]
CHAI's approach to AI safety research focuses on value alignment strategies, particularlyinverse reinforcement learning, in which the AI infers human values from observing human behavior.[9] It has also worked on modeling human-machine interaction in scenarios where intelligent machines have an "off-switch" that they are capable of overriding.[10]
 | This article about an organization in the United States is astub. You can help Wikipedia byexpanding it. |
