Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
0 posts
Adversarial Collaboration
14 posts
Debate (AI safety technique)
25
Take 9: No, RLHF/IDA/debate doesn't solve outer alignment.
Charlie Steiner
8d
14
49
A Small Negative Result on Debate
Sam Bowman
8mo
11
78
Imitative Generalisation (AKA 'Learning the Prior')
Beth Barnes
1y
14
66
Why I'm excited about Debate
Richard_Ngo
1y
12
70
A guide to Iterated Amplification & Debate
Rafael Harth
2y
10
91
Writeup: Progress on AI Safety via Debate
Beth Barnes
2y
18
39
Looking for adversarial collaborators to test our Debate protocol
Beth Barnes
2y
5
37
How should AI debate be judged?
abramdemski
2y
27
27
Debate Minus Factored Cognition
abramdemski
1y
42
44
AI Safety Debate and Its Applications
VojtaKovarik
3y
5
29
New paper: (When) is Truth-telling Favored in AI debate?
VojtaKovarik
2y
7
18
Problems with AI debate
Stuart_Armstrong
3y
3
19
AI Safety via Debate
ESRogs
4y
13
8
Thoughts on "AI safety via debate"
Gordon Seidoh Worley
4y
4