Go Back
You can't go any further
You can't go any further
meritocratic
regular
democratic
hot
top
alive
2 posts
List of Links
26 posts
GPT
33
AI Alignment Writing Day Roundup #2
Ben Pace
3y
2
0
New(ish) AI control ideas
Stuart_Armstrong
5y
0
26
An exploration of GPT-2's embedding weights
Adam Scherlis
7d
2
60
By Default, GPTs Think In Plain Sight
Fabien Roger
1mo
16
31
[ASoT] Finetuning, RL, and GPT's world prior
Jozdien
18d
8
13
[LINK] - ChatGPT discussion
JanBrauner
19d
7
223
New Scaling Laws for Large Language Models
1a3orn
8mo
21
33
Recall and Regurgitation in GPT2
Megan Kinniment
2mo
1
187
The case for aligning narrowly superhuman models
Ajeya Cotra
1y
74
136
MIRI comments on Cotra's "Case for Aligning Narrowly Superhuman Models"
Rob Bensinger
1y
13
158
interpreting GPT: the logit lens
nostalgebraist
2y
32
140
Developmental Stages of GPTs
orthonormal
2y
74
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
89
Collection of GPT-3 results
Kaj_Sotala
2y
24
19
GPT-3 and concept extrapolation
Stuart_Armstrong
8mo
28