LESSWRONGTags
LW

Center for Human-Compatible AI (CHAI)

EditHistorySubscribe
Discussion (0)
Help improve this page (2 flags)
EditHistorySubscribe
Discussion (0)
Help improve this page (2 flags)
Random Tag
Contributors
2DanielFilan
2Ben Pace
1Amateur
1_will_

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:

Posts tagged Center for Human-Compatible AI (CHAI)
3
29Announcing the Alignment Newsletter
Rohin Shah
6y
3
2
221Debate on Instrumental Convergence between LeCun, Russell, Bengio, Zador, and More
Ω
Ben Pace
4y
Ω
61
2
1902018 AI Alignment Literature Review and Charity Comparison
Ω
Larks
5y
Ω
26
2
1302019 AI Alignment Literature Review and Charity Comparison
Ω
Larks
4y
Ω
18
2
112Our take on CHAI’s research agenda in under 1500 words
Ω
Alex Flint
4y
Ω
18
2
60[AN #69] Stuart Russell's new book on why we need to replace the standard model of AI
Ω
Rohin Shah
5y
Ω
12
2
57Human beats SOTA Go AI by learning an adversarial policy
Vanessa Kosoy
1y
32
2
55Stuart Russell: AI value alignment problem must be an "intrinsic part" of the field's mainstream agenda
Rob Bensinger
9y
38
2
34CHAI internship applications are open (due Nov 13)
Erik Jenner
6mo
0
2
24CHAI Internship applications are due by 12/15
martinfukui
4y
0
2
22AXRP Episode 8 - Assistance Games with Dylan Hadfield-Menell
Ω
DanielFilan
3y
Ω
1
2
14Rebuttal piece by Stuart Russell and FHI Research Associate Allan Dafoe: "Yes, the experts are worried about the existential risk of artificial intelligence."
crmflynn
7y
0
2
10Research internship position at CHAI
DanielFilan
6y
3
2
4Stuart Russell's Center for Human Compatible AI is looking for an Assistant Director
crmflynn
7y
0
1
76Swimming Upstream: A Case Study in Instrumental Rationality
TurnTrout
6y
7