“You’re the most beautiful girl in the world” and Wittgensteinian Language Games

Chris_Leong20 Apr 2024 14:54 UTC

6 points

17 comments1 min readLW link

Searching for Search

NicholasKees and janus

28 Nov 2022 15:31 UTC

91 points

8 comments14 min readLW link 1 review

So What’s Up With PUFAs Chemically?

J Bostock27 Apr 2024 13:32 UTC

35 points

16 comments6 min readLW link

Refusal in LLMs is mediated by a single direction

Andy Arditi, Oscar Obeso, Aaquib111, wesg and Neel Nanda

27 Apr 2024 11:13 UTC

111 points

24 comments9 min readLW link

Mercy to the Machine: Thoughts & Rights

False Name27 Apr 2024 16:36 UTC

8 points

5 comments17 min readLW link

D&D.Sci

abstractapplic5 Dec 2020 23:26 UTC

54 points

46 comments1 min readLW link

ChatGPT understands language

philosophybear27 Jan 2023 7:14 UTC

26 points

4 comments6 min readLW link

(philosophybear.substack.com)

Magic by forgetting

avturchin24 Apr 2024 14:32 UTC

18 points

19 comments4 min readLW link

Transformers Represent Belief State Geometry in their Residual Stream

Adam Shai16 Apr 2024 21:16 UTC

304 points

64 comments12 min readLW link

[Question] Examples of Highly Counterfactual Discoveries?

johnswentworth23 Apr 2024 22:19 UTC

156 points

83 comments1 min readLW link

Losing Faith In Contrarianism

omnizoid25 Apr 2024 20:53 UTC

30 points

36 comments5 min readLW link

D&D.Sci Long War: Defender of Data-mocracy

aphyer26 Apr 2024 22:30 UTC

38 points

8 comments3 min readLW link

Sparsify: A mechanistic interpretability research agenda

Lee Sharkey3 Apr 2024 12:34 UTC

85 points

22 comments22 min readLW link

Voting Theory Introduction

Scott Garrabrant17 Oct 2022 8:48 UTC

81 points

8 comments6 min readLW link

A list of core AI safety problems and how I hope to solve them

davidad26 Aug 2023 15:12 UTC

161 points

24 comments5 min readLW link

Propagating Facts into Aesthetics

Raemon19 Dec 2019 4:09 UTC

115 points

36 comments11 min readLW link 1 review

Changes in College Admissions

Zvi24 Apr 2024 13:50 UTC

54 points

10 comments39 min readLW link

(thezvi.wordpress.com)

On Not Pulling The Ladder Up Behind You

Screwtape26 Apr 2024 21:58 UTC

95 points

5 comments9 min readLW link

D&D.Sci Evaluation and Ruleset

abstractapplic12 Dec 2020 15:00 UTC

46 points

12 comments3 min readLW link

This is Water by David Foster Wallace

Nathan Young24 Apr 2024 21:21 UTC

53 points

15 comments13 min readLW link

(fs.blog)