LESSWRONG
LW

HomeAll PostsConceptsLibrary

Best of LessWrong

Sequence Highlights

Rationality: A-Z

Community Events

Subscribe (RSS/Email)

Top Questions

Recent Activity

AI Safety Thursdays: Are LLMs aware of their learned behaviors?

Thu Jul 10•Toronto

LessWrong Community Weekend 2025

Fri Aug 29•Berlin

AGI Forum @ Purdue University

Thu Jul 10•West Lafayette

Take the Grill Pill

Thu Jul 10•Waterloo

108How do you feel about LessWrong these days? [Open feedback thread]

Bird Concept, TurnTrout

2y

286

161Have LLMs Generated Novel Insights?

abramdemski, Cole Wyeth, Kaj_Sotala

4mo

41

118What are your greatest one-shot life improvements?

Mark Xu, blueanchovy

5y

172

139How Much Are LLMs Actually Boosting Real-World Programmer Productivity?

Thane Ruthenis, Richard Horvath

4mo

52

43Does the Universal Geometry of Embeddings paper have big implications for interpretability?

1mo

3

Load MoreView All Top Questions

8Can a pre-commitment to not give in to blackmail be "countered" by a pre-commitment to ignore such pre-commitments?

5d

11

1How did you first understand cognitive biases? Looking for community experiences

Vladimir Loginov

3d

3

14Is a near-term, self-sustaining Mars colony impossible?

5y

18

4Question of the Week #1 – With Great Power:

5d

0

18What was so great about Move 37?

1mo

2

6Are LLMs being trained using LessWrong text?

8d

4

9RSS feed for 1 LW user?

Commander Zander

7d

1

4Can AIs be shown their messages aren't tampered with?

8d

10

15Any Trump Supporters Want to Dialogue?

k64, Shankar Sivarajan

9mo

92

3What nation did Trump prevent from going to war (Feb. 2025)?

4mo

5

3Galaxy-Brain Hobo Antibiotics?

23d

8

13How does the LessWrong team generate the website illustrations?

Nina Panickssery, RobertM

17d

1

Load MoreView All Questions