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
7
Will research in AI risk jinx it? Consequences of training AI on AI risk arguments
Yann Dubois
1d
6
112
Bad at Arithmetic, Promising at Math
cohenmacaulay
2d
17
47
Next Level Seinfeld
Zvi
1d
6
314
Jailbreaking ChatGPT on Release Day
Zvi
18d
74
148
Did ChatGPT just gaslight me?
ThomasW
19d
45
101
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
19
A crisis for online communication: bots and bot users will overrun the Internet?
Mitchell_Porter
9d
11
15
Does ChatGPT’s performance warrant working on a tutor for children? [It’s time to take it to the lab.]
Bill Benzon
1d
2
262
Mysteries of mode collapse
janus
1mo
35
15
[LINK] - ChatGPT discussion
JanBrauner
19d
7
-1
Could an AI be Religious?
mk54
16d
14
26
Is the ChatGPT-simulated Linux virtual machine real?
Kenoubi
7d
7
808
Simulators
janus
3mo
103
37
Reframing inner alignment
davidad
9d
13
264
Common misconceptions about OpenAI
Jacob_Hilton
3mo
138
44
Four usages of "loss" in AI
TurnTrout
2mo
18
521
chinchilla's wild implications
nostalgebraist
4mo
114
25
Why don't we have self driving cars yet?
Linda Linsefors
1mo
16
27
Inverse scaling can become U-shaped
Edouard Harris
1mo
15
46
love, not competition
carado
1mo
20
51
Smoke without fire is scary
Adam Jermyn
2mo
22
12
Massive Scaling Should be Frowned Upon
harsimony
1mo
6
21
The Slippery Slope from DALLE-2 to Deepfake Anarchy
scasper
1mo
9
24
ChatGPT seems overconfident to me
qbolec
16d
3
21
Neural networks biased towards geometrically simple functions?
DavidHolmes
12d
2
61
OpenAI's Alignment Plans
dkirmani
3mo
17
57
A Data limited future
Donald Hobson
4mo
25