Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
14 posts
Factored Cognition
Ought
14 posts
Debate (AI safety technique)
Adversarial Collaboration
118
Supervise Process, not Outcomes
stuhlmueller
8mo
8
87
Ought: why it matters and ways to help
paulfchristiano
3y
7
73
Rant on Problem Factorization for Alignment
johnswentworth
4mo
48
48
Vaniver's View on Factored Cognition
Vaniver
3y
4
47
A Library and Tutorial for Factored Cognition with Language Models
stuhlmueller
2mo
0
45
Factored Cognition
stuhlmueller
4y
6
35
Ought will host a factored cognition “Lab Meeting”
jungofthewon
3mo
1
35
Preface to the Sequence on Factored Cognition
Rafael Harth
2y
7
34
Idealized Factored Cognition
Rafael Harth
2y
6
29
Update on Ought's experiments on factored evaluation of arguments
Owain_Evans
2y
0
23
Clarifying Factored Cognition
Rafael Harth
2y
2
21
Alignment Newsletter #36
Rohin Shah
4y
0
16
Traversing a Cognition Space
Rafael Harth
2y
5
14
[AN #86]: Improving debate and factored cognition through human experiments
Rohin Shah
2y
0
94
Writeup: Progress on AI Safety via Debate
Beth Barnes
2y
18
92
Imitative Generalisation (AKA 'Learning the Prior')
Beth Barnes
1y
14
73
Why I'm excited about Debate
Richard_Ngo
1y
12
68
A guide to Iterated Amplification & Debate
Rafael Harth
2y
10
52
Looking for adversarial collaborators to test our Debate protocol
Beth Barnes
2y
5
49
How should AI debate be judged?
abramdemski
2y
27
42
A Small Negative Result on Debate
Sam Bowman
8mo
11
37
Debate Minus Factored Cognition
abramdemski
1y
42
36
AI Safety Debate and Its Applications
VojtaKovarik
3y
5
36
Take 9: No, RLHF/IDA/debate doesn't solve outer alignment.
Charlie Steiner
8d
14
32
New paper: (When) is Truth-telling Favored in AI debate?
VojtaKovarik
2y
7
27
AI Safety via Debate
ESRogs
4y
13
21
Problems with AI debate
Stuart_Armstrong
3y
3
12
Thoughts on "AI safety via debate"
Gordon Seidoh Worley
4y
4