Go Back
Choose this branch
You can't go any further
meritocratic
regular
democratic
hot
top
alive
46 posts
Factored Cognition
Experiments
Ought
AI-assisted Alignment
Memory and Mnemonics
Air Conditioning
23 posts
Debate (AI safety technique)
184
Godzilla Strategies
johnswentworth
6mo
65
120
Supervise Process, not Outcomes
stuhlmueller
8mo
8
112
Preregistration: Air Conditioner Test
johnswentworth
8mo
64
105
Beliefs and Disagreements about Automating Alignment Research
Ian McKenzie
3mo
4
98
Ought: why it matters and ways to help
paulfchristiano
3y
7
89
Solving Math Problems by Relay
bgold
2y
26
80
Air Conditioner Test Results & Discussion
johnswentworth
6mo
38
66
A Library and Tutorial for Factored Cognition with Language Models
stuhlmueller
2mo
0
62
Rant on Problem Factorization for Alignment
johnswentworth
4mo
48
52
Ought will host a factored cognition “Lab Meeting”
jungofthewon
3mo
1
52
Factored Cognition
stuhlmueller
4y
6
46
A bicycle for your memory
sortega
8mo
8
39
Scientific Wrestling: Beyond Passive Hypothesis-Testing
adamShimi
9mo
6
35
Participating in a Covid-19 Vaccine Trial
ejacob
1y
14
97
Writeup: Progress on AI Safety via Debate
Beth Barnes
2y
18
82
Imitative Generalisation (AKA 'Learning the Prior')
Beth Barnes
1y
14
74
A guide to Iterated Amplification & Debate
Rafael Harth
2y
10
69
Why I'm excited about Debate
Richard_Ngo
1y
12
52
A Small Negative Result on Debate
Sam Bowman
8mo
11
46
AI Safety Debate and Its Applications
VojtaKovarik
3y
5
44
Three mental images from thinking about AGI debate & corrigibility
Steven Byrnes
2y
35
41
Looking for adversarial collaborators to test our Debate protocol
Beth Barnes
2y
5
39
How should AI debate be judged?
abramdemski
2y
27
32
Learning the smooth prior
Geoffrey Irving
7mo
0
30
New paper: (When) is Truth-telling Favored in AI debate?
VojtaKovarik
2y
7
29
Can there be an indescribable hellworld?
Stuart_Armstrong
3y
19
28
Debate Minus Factored Cognition
abramdemski
1y
42
26
Take 9: No, RLHF/IDA/debate doesn't solve outer alignment.
Charlie Steiner
8d
14