Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
240 posts
GPT
Language Models
Conjecture (org)
Bounties & Prizes (active)
Refine
Project Announcement
QURI
AI Safety Public Materials
Anthropic
Squiggle
Exploratory Engineering
Encultured AI (org)
248 posts
Machine Learning (ML)
Art
Music
OpenAI
Scaling Laws
DALL-E
Symbol Grounding
Meta-Humor
Computing Overhang
GAN
27
Discovering Language Model Behaviors with Model-Written Evaluations
evhub
4h
3
43
Next Level Seinfeld
Zvi
1d
6
70
Bad at Arithmetic, Promising at Math
cohenmacaulay
2d
17
26
Take 11: "Aligning language models" should be weirder.
Charlie Steiner
2d
0
11
Does ChatGPT’s performance warrant working on a tutor for children? [It’s time to take it to the lab.]
Bill Benzon
1d
2
59
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
160
Jailbreaking ChatGPT on Release Day
Zvi
18d
74
55
A brainteaser for language models
Adam Scherlis
8d
3
38
Discovering Latent Knowledge in Language Models Without Supervision
Xodarap
6d
1
98
Did ChatGPT just gaslight me?
ThomasW
19d
45
132
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
3
Will research in AI risk jinx it? Consequences of training AI on AI risk arguments
Yann Dubois
1d
6
103
What I Learned Running Refine
adamShimi
26d
5
164
Mysteries of mode collapse
janus
1mo
35
57
Reframing inner alignment
davidad
9d
13
18
My thoughts on OpenAI's Alignment plan
Donald Hobson
10d
0
188
Common misconceptions about OpenAI
Jacob_Hilton
3mo
138
207
chinchilla's wild implications
nostalgebraist
4mo
114
11
Neural networks biased towards geometrically simple functions?
DavidHolmes
12d
2
14
ChatGPT seems overconfident to me
qbolec
16d
3
287
What DALL-E 2 can and cannot do
Swimmer963
7mo
305
13
Playing with Aerial Photos
jefftk
19d
0
27
Inverse scaling can become U-shaped
Edouard Harris
1mo
15
76
Survey of NLP Researchers: NLP is contributing to AGI progress; major catastrophe plausible
Sam Bowman
3mo
6
17
Contra Chords
jefftk
1mo
1
169
dalle2 comments
nostalgebraist
7mo
13
74
AI art isn't "about to shake things up". It's already here.
Davis_Kingsley
4mo
19
43
Smoke without fire is scary
Adam Jermyn
2mo
22