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)
7
Alignment with argument-networks and assessment-predictions
Tor Økland Barstad
7d
3
16
Research request (alignment strategy): Deep dive on "making AI solve alignment for us"
JanBrauner
19d
3
92
Beliefs and Disagreements about Automating Alignment Research
Ian McKenzie
3mo
4
151
Godzilla Strategies
johnswentworth
6mo
65
47
A Library and Tutorial for Factored Cognition with Language Models
stuhlmueller
2mo
0
73
Rant on Problem Factorization for Alignment
johnswentworth
4mo
48
80
Air Conditioner Test Results & Discussion
johnswentworth
6mo
38
118
Supervise Process, not Outcomes
stuhlmueller
8mo
8
109
Preregistration: Air Conditioner Test
johnswentworth
8mo
64
35
Ought will host a factored cognition “Lab Meeting”
jungofthewon
3mo
1
10
Provably Honest - A First Step
Srijanak De
1mo
2
16
Discussion on utilizing AI for alignment
elifland
3mo
3
42
Scientific Wrestling: Beyond Passive Hypothesis-Testing
adamShimi
9mo
6
38
A bicycle for your memory
sortega
8mo
8
36
Take 9: No, RLHF/IDA/debate doesn't solve outer alignment.
Charlie Steiner
8d
14
20
Briefly thinking through some analogs of debate
Eli Tyre
3mo
3
42
A Small Negative Result on Debate
Sam Bowman
8mo
11
31
Learning the smooth prior
Geoffrey Irving
7mo
0
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
94
Writeup: Progress on AI Safety via Debate
Beth Barnes
2y
18
16
An AI-in-a-box success model
azsantosk
8mo
1
55
Three mental images from thinking about AGI debate & corrigibility
Steven Byrnes
2y
35
52
Looking for adversarial collaborators to test our Debate protocol
Beth Barnes
2y
5
49
How should AI debate be judged?
abramdemski
2y
27
37
Debate Minus Factored Cognition
abramdemski
1y
42
32
New paper: (When) is Truth-telling Favored in AI debate?
VojtaKovarik
2y
7