Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
42 posts
GPT
Bounties & Prizes (active)
AI-assisted Alignment
AI Safety Public Materials
List of Links
8 posts
Moore's Law
Compute
Nanotechnology
Computer Science
Tripwire
Quantum Mechanics
223
New Scaling Laws for Large Language Models
1a3orn
8mo
21
187
The case for aligning narrowly superhuman models
Ajeya Cotra
1y
74
158
interpreting GPT: the logit lens
nostalgebraist
2y
32
151
Godzilla Strategies
johnswentworth
6mo
65
140
Developmental Stages of GPTs
orthonormal
2y
74
136
MIRI comments on Cotra's "Case for Aligning Narrowly Superhuman Models"
Rob Bensinger
1y
13
114
How much chess engine progress is about adapting to bigger computers?
paulfchristiano
1y
23
114
Can you get AGI from a Transformer?
Steven Byrnes
2y
39
111
Alignment As A Bottleneck To Usefulness Of GPT-3
johnswentworth
2y
57
93
[Link] Why I’m optimistic about OpenAI’s alignment approach
janleike
15d
13
92
Beliefs and Disagreements about Automating Alignment Research
Ian McKenzie
3mo
4
89
Collection of GPT-3 results
Kaj_Sotala
2y
24
74
[$20K in Prizes] AI Safety Arguments Competition
Dan H
7mo
543
72
How "honest" is GPT-3?
abramdemski
2y
18
120
Moore's Law, AI, and the pace of progress
Veedrac
1y
39
91
Compute Trends Across Three eras of Machine Learning
Jsevillamol
10mo
13
59
Predicting GPU performance
Marius Hobbhahn
6d
24
42
Reasons compute may not drive AI capabilities growth
Kythe
4y
10
34
Verification and Transparency
DanielFilan
3y
6
27
Algorithmic Similarity
LukasM
3y
10
24
Implications of Quantum Computing for Artificial Intelligence Alignment Research
Jsevillamol
3y
3
2
Corrigibility thoughts I: caring about multiple things
Stuart_Armstrong
5y
0