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)
11
Research request (alignment strategy): Deep dive on "making AI solve alignment for us"
JanBrauner
19d
3
79
Beliefs and Disagreements about Automating Alignment Research
Ian McKenzie
3mo
4
84
Rant on Problem Factorization for Alignment
johnswentworth
4mo
48
118
Godzilla Strategies
johnswentworth
6mo
65
3
Alignment with argument-networks and assessment-predictions
Tor Økland Barstad
7d
3
80
Air Conditioner Test Results & Discussion
johnswentworth
6mo
38
116
Supervise Process, not Outcomes
stuhlmueller
8mo
8
106
Preregistration: Air Conditioner Test
johnswentworth
8mo
64
28
A Library and Tutorial for Factored Cognition with Language Models
stuhlmueller
2mo
0
18
Ought will host a factored cognition “Lab Meeting”
jungofthewon
3mo
1
8
Infinite Possibility Space and the Shutdown Problem
magfrump
2mo
0
45
Scientific Wrestling: Beyond Passive Hypothesis-Testing
adamShimi
9mo
6
30
A bicycle for your memory
sortega
8mo
8
24
Ceiling Fan Air Filter
jefftk
7mo
9
46
Take 9: No, RLHF/IDA/debate doesn't solve outer alignment.
Charlie Steiner
8d
14
27
Briefly thinking through some analogs of debate
Eli Tyre
3mo
3
30
Learning the smooth prior
Geoffrey Irving
7mo
0
32
A Small Negative Result on Debate
Sam Bowman
8mo
11
102
Imitative Generalisation (AKA 'Learning the Prior')
Beth Barnes
1y
14
77
Why I'm excited about Debate
Richard_Ngo
1y
12
91
Writeup: Progress on AI Safety via Debate
Beth Barnes
2y
18
62
A guide to Iterated Amplification & Debate
Rafael Harth
2y
10
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
59
How should AI debate be judged?
abramdemski
2y
27
46
Debate Minus Factored Cognition
abramdemski
1y
42
8
An AI-in-a-box success model
azsantosk
8mo
1
34
New paper: (When) is Truth-telling Favored in AI debate?
VojtaKovarik
2y
7