Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
128 posts
GPT
Bounties & Prizes (active)
QURI
AI Safety Public Materials
Squiggle
Generativity
112 posts
Conjecture (org)
Language Models
Refine
Project Announcement
Anthropic
Exploratory Engineering
Encultured AI (org)
Transformer Circuits
Transformers
91
Bad at Arithmetic, Promising at Math
cohenmacaulay
2d
17
45
Next Level Seinfeld
Zvi
1d
6
237
Jailbreaking ChatGPT on Release Day
Zvi
18d
74
23
A crisis for online communication: bots and bot users will overrun the Internet?
Mitchell_Porter
9d
11
13
Does ChatGPT’s performance warrant working on a tutor for children? [It’s time to take it to the lab.]
Bill Benzon
1d
2
13
[LINK] - ChatGPT discussion
JanBrauner
19d
7
-12
Could an AI be Religious?
mk54
16d
14
18
Is the ChatGPT-simulated Linux virtual machine real?
Kenoubi
7d
7
5
ChatGPT: "An error occurred. If this issue persists..."
Bill Benzon
13d
11
13
What is the best article to introduce someone to AI safety for the first time?
Trevor1
28d
7
14
Best introductory overviews of AGI safety?
Jakub Kraus
7d
5
69
Announcing AI Alignment Awards: $100k research contests about goal misgeneralization & corrigibility
Akash
28d
20
17
ChatGPT is surprisingly and uncanningly good at pretending to be sentient
ZT5
17d
11
4
Trivial GPT-3.5 limitation workaround
Dave Lindbergh
8d
4
27
Discovering Language Model Behaviors with Model-Written Evaluations
evhub
4h
3
5
Will research in AI risk jinx it? Consequences of training AI on AI risk arguments
Yann Dubois
1d
6
123
Did ChatGPT just gaslight me?
ThomasW
19d
45
80
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
213
Mysteries of mode collapse
janus
1mo
35
472
Simulators
janus
3mo
103
19
Shh, don't tell the AI it's likely to be evil
naterush
14d
9
0
Simulators and Mindcrime
DragonGod
11d
4
16
Does a LLM have a utility function?
Dagon
11d
6
27
Gliders in Language Models
Alexandre Variengien
25d
11
46
A brainteaser for language models
Adam Scherlis
8d
3
164
Language models seem to be much better than humans at next-token prediction
Buck
4mo
56
183
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
123
Refine: An Incubator for Conceptual Alignment Research Bets
adamShimi
8mo
13