This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Home
All Posts
Concepts
Library
Best of LessWrong
Sequence Highlights
Rationality: A-Z
The Codex
HPMOR
Community Events
[Today]
June Meetup
[Tomorrow]
2nd Germany-wide ACX/LW event
[Yesterday]
AI Safety Thursdays: Towards a Connectome of Concepts for Deep Neural Networks
[Yesterday]
Research Party: ¡Afuera!
Subscribe (RSS/Email)
LW the Album
Leaderboard
About
FAQ
Top Questions
108
How do you feel about LessWrong these days? [Open feedback thread]
Q
Bird Concept
,
TurnTrout
2y
Q
286
160
Have LLMs Generated Novel Insights?
Q
Ω
abramdemski
,
Cole Wyeth
,
Kaj_Sotala
4mo
Q
Ω
41
118
What are your greatest one-shot life improvements?
Q
Mark Xu
,
blueanchovy
5y
Q
172
137
How Much Are LLMs Actually Boosting Real-World Programmer Productivity?
Q
Thane Ruthenis
,
Richard Horvath
4mo
Q
52
42
Does the Universal Geometry of Embeddings paper have big implications for interpretability?
Q
Evan R. Murphy
24d
Q
3
Recent Activity
1
How did you find out about AI Safety? Why and how did you get involved?
Q
Ana Lopez
11h
Q
0
3
When should you read a biography?
Q
CstineSublime
8d
Q
4
108
How do you feel about LessWrong these days? [Open feedback thread]
Q
Bird Concept
,
TurnTrout
2y
Q
286
12
Are superhuman savants real?
Q
Bunthut
3d
Q
1
3
Galaxy-Brain Hobo Antibiotics?
Q
Lorec
3d
Q
4
9
Why isn't there a LessWrong App? Is a "blog-app" sustainable/useful for a community?
Q
Osson4
5y
Q
19
4
Do multimodal LLMs (like 4o) use OCR under the hood to read dense text in images?
Q
2PuNCheeZ
5d
Q
1
9
How concerned are you about a fast takeoff due to a leap in hardware usage?
Q
MichaelDickens
6d
Q
7
11
How could I tell someone that consciousness is not the primary concern of AI Safety?
Q
Lysandre Terrisse
6d
Q
2
5
Under what conditions should humans stop pursuing technical AI safety careers?
Q
S. Alex Bradt
7d
Q
0
9
My friend wants a good book recommendation to understand AI, AI safety, and the field, and probably the drama. He’s smart but non-technical and not keeping up with trends. Any recs?
Q
JohnGreer
8d
Q
0
4
Which AI Safety techniques will be ineffective against diffusion models?
Q
Allen Thomas
1mo
Q
1