AI ALIGNMENT FORUM
Wikitags
AF

Subscribe
Discussion0

Center for Human-Compatible AI (CHAI)

Subscribe
Discussion0
Written by Amateur, Ben Pace, Will Aldred, et al. last updated 30th Dec 2024

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.

Posts tagged Center for Human-Compatible AI (CHAI)
63Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ben Pace
6y
17
402018 AI Alignment Literature Review and Charity Comparison
Larks
6y
4
392019 AI Alignment Literature Review and Charity Comparison
Larks
5y
8
36Our take on CHAI’s research agenda in under 1500 words
Alex Flint
5y
14
25[AN #69] Stuart Russell's new book on why we need to replace the standard model of AI
Rohin Shah
6y
10
14AXRP Episode 8 - Assistance Games with Dylan Hadfield-Menell
DanielFilan
4y
1
18Learning preferences by looking at the world
Rohin Shah
6y
4
15Rohin Shah on reasons for AI optimism
abergal
6y
38
9CHAI Internship Application
martinfukui
5y
0
10Tensor Trust: An online game to uncover prompt injection vulnerabilities
Luke Bailey, qxcv
2y
0
Add Posts