Center for Human-Compatible Artificial Intelligence
Formation | 2016 |
---|---|
Headquarters | Berkeley, California |
Leader | Stuart J. Russell |
Parent organization | University of California, Berkeley |
Website | humancompatible |
The Center for Human-Compatible Artificial Intelligence (CHAI) is a research center at University of California, Berkeley (UC Berkeley) focusing on advanced artificial intelligence (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.[1][2] Russell is known for co-authoring the widely used AI textbook Artificial Intelligence: A Modern Approach.
CHAI's faculty membership includes Bart Selman and Joseph Halpern from Cornell University,[3] Pieter Abbeel from UC Berkeley, and Michael Wellman from the University of Michigan.[4] In 2016, the Open Philanthropy Project (OpenPhil) recommended a grant of $5,555,550 over five years to support CHAI.[5] CHAI received an additional grant of $200,000 from OpenPhil in 2019.[6]
Research[]
CHAI's approach to AI safety research focuses on value alignment strategies, particularly inverse reinforcement learning, in which the AI infers human values from observing human behavior.[7] It has also worked on modeling human-machine interaction in scenarios where intelligent machines have an "off-switch" that they are capable of overriding.[8]
See also[]
- Existential risk from artificial general intelligence
- Future of Humanity Institute
- Future of Life Institute
- Human Compatible
- Machine Intelligence Research Institute
References[]
- ^ Norris, Jeffrey (Aug 29, 2016). "UC Berkeley launches Center for Human-Compatible Artificial Intelligence". Retrieved Dec 27, 2019.
- ^ Solon, Olivia (Aug 30, 2016). "The rise of robots: forget evil AI – the real risk is far more insidious". The Guardian. Retrieved Dec 27, 2019.
- ^ Cornell University. "Human-Compatible AI". Retrieved Dec 27, 2019.
- ^ Center for Human-Compatible Artificial Intelligence. "People". Retrieved Dec 27, 2019.
- ^ Open Philanthropy Project (Aug 2016). "UC Berkeley — Center for Human-Compatible AI (2016)". Retrieved Dec 27, 2019.
- ^ Open Philanthropy Project (Nov 2019). "UC Berkeley — Center for Human-Compatible AI (2019)". Retrieved Dec 27, 2019.
- ^ Conn, Ariel (Aug 31, 2016). "New Center for Human-Compatible AI". Future of Life Institute. Retrieved Dec 27, 2019.
- ^ Bridge, Mark (June 10, 2017). "Making robots less confident could prevent them taking over".
External links[]
- Artificial intelligence associations
- Existential risk from artificial general intelligence
- Existential risk organizations
- Organizations established in 2016
- United States organization stubs