LESSWRONG
LW

1493
Wikitags

Center for Human-Compatible AI (CHAI)

Edited by Amateur, Ben Pace, _will_, 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.

Subscribe
Discussion
Subscribe
Discussion
Posts tagged Center for Human-Compatible AI (CHAI)
29Announcing the Alignment Newsletter
Rohin Shah
7y
3
221Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ω
Ben Pace
6y
Ω
61
1902018 AI Alignment Literature Review and Charity Comparison
Ω
Larks
7y
Ω
26
1302019 AI Alignment Literature Review and Charity Comparison
Ω
Larks
6y
Ω
18
113Our take on CHAI’s research agenda in under 1500 words
Ω
Alex Flint
5y
Ω
18
60[AN #69] Stuart Russell's new book on why we need to replace the standard model of AI
Ω
Rohin Shah
6y
Ω
12
59Human beats SOTA Go AI by learning an adversarial policy
Vanessa Kosoy
3y
29
55Stuart Russell: AI value alignment problem must be an "intrinsic part" of the field's mainstream agenda
Rob Bensinger
11y
38
34CHAI internship applications are open (due Nov 13)
Erik Jenner
2y
0
24CHAI Internship applications are due by 12/15
martinfukui
6y
0
22AXRP Episode 8 - Assistance Games with Dylan Hadfield-Menell
Ω
DanielFilan
4y
Ω
1
14Rebuttal piece by Stuart Russell and FHI Research Associate Allan Dafoe: "Yes, the experts are worried about the existential risk of artificial intelligence."
crmflynn
9y
0
10Research internship position at CHAI
DanielFilan
8y
3
4Stuart Russell's Center for Human Compatible AI is looking for an Assistant Director
crmflynn
8y
0
77Swimming Upstream: A Case Study in Instrumental Rationality
TurnTrout
7y
7
Load More (15/24)
Add Posts