Simple probes can catch sleeper agents

Monte M, Carson Denison, Zac Hatfield-Dodds, David Duvenaud, Sam Bowman, Ethan Perez and evhub

23 Apr 2024 21:10 UTC

72 points

2 comments1 min readLW link

(www.anthropic.com)

[Question] Examples of Highly Counterfactual Discoveries?

johnswentworth23 Apr 2024 22:19 UTC

50 points

3 comments1 min readLW link

On what research policymakers actually need

MondSemmel23 Apr 2024 19:50 UTC

26 points

0 comments3 min readLW link

(www.slowboring.com)

Book review: Deep Utopia

PeterMcCluskey23 Apr 2024 19:55 UTC

21 points

2 comments4 min readLW link

(bayesianinvestor.com)

[Question] (When) Should you work through the night when inspiration strikes you?

Chi Nguyen23 Apr 2024 21:07 UTC

14 points

2 comments1 min readLW link

Dequantifying first-order theories

jessicata23 Apr 2024 19:04 UTC

26 points

0 comments8 min readLW link

(unstableontology.com)

On Minicircle

Metacelsus23 Apr 2024 21:28 UTC

10 points

0 comments1 min readLW link

(docs.google.com)

[Question] Is there software to practice reading expressions?

lsusr23 Apr 2024 21:53 UTC

16 points

3 comments1 min readLW link

Funny Anecdote of Eliezer From His Sister

Daniel Birnbaum22 Apr 2024 22:05 UTC

122 points

2 comments2 min readLW link

Take the wheel, Shoggoth! (Lesswrong is trying out changes to the frontpage algorithm)

Ruby and RobertM

23 Apr 2024 3:58 UTC

57 points

3 comments4 min readLW link

Rejecting Television

Declan Molony23 Apr 2024 4:59 UTC

48 points

4 comments6 min readLW link

Thoughts on seed oil

dynomight20 Apr 2024 12:29 UTC

232 points

45 comments17 min readLW link

(dynomight.net)

WSJ: Inside Amazon’s Secret Operation to Gather Intel on Rivals

trevor23 Apr 2024 21:33 UTC

8 points

0 comments5 min readLW link

(www.wsj.com)

Priors and Prejudice

MathiasKB22 Apr 2024 15:00 UTC

72 points

13 comments7 min readLW link

Let’s Design A School, Part 1

Sable23 Apr 2024 21:50 UTC

5 points

0 comments11 min readLW link

(affablyevil.substack.com)

Thoughts on Zero Points

depressurize23 Apr 2024 2:22 UTC

28 points

0 comments4 min readLW link

(sexandchicago.substack.com)

Subjective Questions Require Subjective information

Ben23 Apr 2024 13:16 UTC

7 points

2 comments4 min readLW link

Manifold “exploring real cash prizes”

Rana Dexsin23 Apr 2024 21:07 UTC

5 points

0 comments1 min readLW link

(manifoldmarkets.notion.site)

Motivation gaps: Why so much EA criticism is hostile and lazy

titotal22 Apr 2024 11:49 UTC

59 points

5 comments1 min readLW link

(titotal.substack.com)

On Llama-3 and Dwarkesh Patel’s Podcast with Zuckerberg

Zvi22 Apr 2024 13:10 UTC

55 points

3 comments47 min readLW link

(thezvi.wordpress.com)