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
22
AI Alignment Writing Day Roundup #2
Ben Pace
3y
2
0
New(ish) AI control ideas
Stuart_Armstrong
5y
0
34
An exploration of GPT-2's embedding weights
Adam Scherlis
7d
2
62
[ASoT] Finetuning, RL, and GPT's world prior
Jozdien
18d
8
75
By Default, GPTs Think In Plain Sight
Fabien Roger
1mo
16
14
[LINK] - ChatGPT discussion
JanBrauner
19d
7
255
New Scaling Laws for Large Language Models
1a3orn
8mo
21
43
Recall and Regurgitation in GPT2
Megan Kinniment
2mo
1
170
The case for aligning narrowly superhuman models
Ajeya Cotra
1y
74
171
interpreting GPT: the logit lens
nostalgebraist
2y
32
155
Developmental Stages of GPTs
orthonormal
2y
74
108
MIRI comments on Cotra's "Case for Aligning Narrowly Superhuman Models"
Rob Bensinger
1y
13
132
Can you get AGI from a Transformer?
Steven Byrnes
2y
39
117
Alignment As A Bottleneck To Usefulness Of GPT-3
johnswentworth
2y
57
82
Collection of GPT-3 results
Kaj_Sotala
2y
24
73
To what extent is GPT-3 capable of reasoning?
TurnTrout
2y
74