Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
2595 posts
AI
AI Timelines
AI Takeoff
Interpretability (ML & AI)
Careers
Instrumental Convergence
Iterated Amplification
Corrigibility
Audio
Debate (AI safety technique)
Infra-Bayesianism
DeepMind
488 posts
GPT
Conjecture (org)
Art
Music
Machine Learning (ML)
Bounties & Prizes (active)
OpenAI
QURI
Language Models
Project Announcement
DALL-E
Meta-Humor
84
Towards Hodge-podge Alignment
Cleo Nardo
1d
20
41
The "Minimal Latents" Approach to Natural Abstractions
johnswentworth
22h
6
5
Podcast: Tamera Lanham on AI risk, threat models, alignment proposals, externalized reasoning oversight, and working at Anthropic
Akash
2h
0
16
An Open Agency Architecture for Safe Transformative AI
davidad
11h
11
198
The next decades might be wild
Marius Hobbhahn
5d
21
265
AI alignment is distinct from its near-term applications
paulfchristiano
7d
5
140
How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme
Collin
5d
18
6
I believe some AI doomers are overconfident
FTPickle
6h
4
5
Career Scouting: Housing Coordination
koratkar
5h
0
13
Take 12: RLHF's use is evidence that orgs will jam RL at real-world problems.
Charlie Steiner
19h
0
6
(Extremely) Naive Gradient Hacking Doesn't Work
ojorgensen
9h
0
71
Proper scoring rules don’t guarantee predicting fixed points
Johannes_Treutlein
4d
2
19
Why mechanistic interpretability does not and cannot contribute to long-term AGI safety (from messages with a friend)
Remmelt
1d
6
323
A challenge for AGI organizations, and a challenge for readers
Rob Bensinger
19d
30
27
Discovering Language Model Behaviors with Model-Written Evaluations
evhub
4h
3
112
Bad at Arithmetic, Promising at Math
cohenmacaulay
2d
17
47
Next Level Seinfeld
Zvi
1d
6
32
Take 11: "Aligning language models" should be weirder.
Charlie Steiner
2d
0
314
Jailbreaking ChatGPT on Release Day
Zvi
18d
74
101
[Interim research report] Taking features out of superposition with sparse autoencoders
Lee Sharkey
7d
10
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
7
Will research in AI risk jinx it? Consequences of training AI on AI risk arguments
Yann Dubois
1d
6
52
Discovering Latent Knowledge in Language Models Without Supervision
Xodarap
6d
1
234
Conjecture: a retrospective after 8 months of work
Connor Leahy
27d
9
148
Did ChatGPT just gaslight me?
ThomasW
19d
45
808
Simulators
janus
3mo
103
262
Mysteries of mode collapse
janus
1mo
35
36
An exploration of GPT-2's embedding weights
Adam Scherlis
7d
2