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)
118
Godzilla Strategies
johnswentworth
6mo
65
116
Supervise Process, not Outcomes
stuhlmueller
8mo
8
107
Solving Math Problems by Relay
bgold
2y
26
106
Preregistration: Air Conditioner Test
johnswentworth
8mo
64
84
Rant on Problem Factorization for Alignment
johnswentworth
4mo
48
80
Air Conditioner Test Results & Discussion
johnswentworth
6mo
38
79
Beliefs and Disagreements about Automating Alignment Research
Ian McKenzie
3mo
4
76
Ought: why it matters and ways to help
paulfchristiano
3y
7
67
Experiment: a good researcher is hard to find
gwern
10y
21
63
Vaniver's View on Factored Cognition
Vaniver
3y
4
58
The Majority Is Always Wrong
Eliezer Yudkowsky
15y
54
45
Scientific Wrestling: Beyond Passive Hypothesis-Testing
adamShimi
9mo
6
44
Preface to the Sequence on Factored Cognition
Rafael Harth
2y
7
41
Idealized Factored Cognition
Rafael Harth
2y
6
102
Imitative Generalisation (AKA 'Learning the Prior')
Beth Barnes
1y
14
91
Writeup: Progress on AI Safety via Debate
Beth Barnes
2y
18
77
Why I'm excited about Debate
Richard_Ngo
1y
12
66
Three mental images from thinking about AGI debate & corrigibility
Steven Byrnes
2y
35
63
Looking for adversarial collaborators to test our Debate protocol
Beth Barnes
2y
5
62
A guide to Iterated Amplification & Debate
Rafael Harth
2y
10
59
How should AI debate be judged?
abramdemski
2y
27
49
Thoughts on AI Safety via Debate
Vaniver
4y
12
46
Take 9: No, RLHF/IDA/debate doesn't solve outer alignment.
Charlie Steiner
8d
14
46
Debate Minus Factored Cognition
abramdemski
1y
42
41
Can there be an indescribable hellworld?
Stuart_Armstrong
3y
19
34
New paper: (When) is Truth-telling Favored in AI debate?
VojtaKovarik
2y
7
34
AI Safety via Debate
ESRogs
4y
13
32
A Small Negative Result on Debate
Sam Bowman
8mo
11