AI ALIGNMENT FORUMTags
AF

Center for Human-Compatible AI (CHAI)

EditHistorySubscribe
Discussion (0)
Help improve this page (2 flags)
EditHistorySubscribe
Discussion (0)
Help improve this page (2 flags)
Center for Human-Compatible AI (CHAI)
Random Tag
Contributors
2Ben Pace
2DanielFilan
1Amateur
1Will Aldred

The Center for Human-Compatible AI is a research institute at UC Berkeley, founded and led by Stuart Russell. Its stated objective is to prevent building unfriendly AI by focusing research on provably beneficial behaviour.

External links:

  • Homepage of the Center for Human-Compatible AI
Posts tagged Center for Human-Compatible AI (CHAI)
Most Relevant
1
60Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
3y
17
1
402018 AI Alignment Literature Review and Charity Comparison
Larks
4y
4
1
392019 AI Alignment Literature Review and Charity Comparison
Larks
3y
8
1
36Our take on CHAI’s research agenda in under 1500 words
Alex Flint
3y
13
1
25[AN #69] Stuart Russell's new book on why we need to replace the standard model of AI
Rohin Shah
3y
10
1
14AXRP Episode 8 - Assistance Games with Dylan Hadfield-Menell
DanielFilan
2y
1
0
18Learning preferences by looking at the world
Rohin Shah
4y
4
0
15Rohin Shah on reasons for AI optimism
abergal
3y
24
0
9CHAI Internship Application
martinfukui
2y
0
1
5CHAI, Assistance Games, And Fully-Updated Deference [Scott Alexander]
Lukas Berglund
6mo
0
Add Posts