Thomas Kwa’s MIRI research experience

Thomas Kwa, peterbarnett, Vivek Hebbar, Jeremy Gillen, jacobjacob and Raemon

2 Oct 2023 16:42 UTC

142 points

39 comments1 min readLW link

When to Get the Booster?

jefftk3 Oct 2023 21:00 UTC

32 points

2 comments2 min readLW link

(www.jefftk.com)

AXRP Episode 25 - Cooperative AI with Caspar Oesterheld

DanielFilan3 Oct 2023 21:50 UTC

27 points

0 comments92 min readLW link

The 99% principle for personal problems

Kaj_Sotala2 Oct 2023 8:20 UTC

101 points

6 comments2 min readLW link

(kajsotala.fi)

Linkpost: They Studied Dishonesty. Was Their Work a Lie?

Linch2 Oct 2023 8:10 UTC

88 points

7 comments2 min readLW link

(www.newyorker.com)

[Question] Potential alignment targets for a sovereign superintelligent AI

Paul Colognese3 Oct 2023 15:09 UTC

26 points

4 comments1 min readLW link

[Question] Current AI safety techniques?

Zach Stein-Perlman3 Oct 2023 19:30 UTC

13 points

1 comment2 min readLW link

What would it mean to understand how a large language model (LLM) works? Some quick notes.

Bill Benzon3 Oct 2023 15:11 UTC

18 points

2 comments8 min readLW link

Dall-E 3

p.b.2 Oct 2023 20:33 UTC

35 points

4 comments1 min readLW link

(openai.com)

How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions

JanBrauner, Owain_Evans and SoerenMind

28 Sep 2023 18:53 UTC

162 points

28 comments3 min readLW link

“Diamondoid bacteria” nanobots: deadly threat or dead-end? A nanotech investigation

titotal29 Sep 2023 14:01 UTC

135 points

49 comments1 min readLW link

(titotal.substack.com)

My Effortless Weightloss Story: A Quick Runthrough

CuoreDiVetro30 Sep 2023 23:02 UTC

89 points

36 comments9 min readLW link

Some Quick Follow-Up Experiments to “Taken out of context: On measuring situational awareness in LLMs”

miles3 Oct 2023 2:22 UTC

24 points

0 comments9 min readLW link

energy landscapes of experts

bhauth2 Oct 2023 14:08 UTC

37 points

2 comments3 min readLW link

(www.bhauth.com)

Inside Views, Impostor Syndrome, and the Great LARP

johnswentworth25 Sep 2023 16:08 UTC

239 points

40 comments5 min readLW link

My Mid-Career Transition into Biosecurity

jefftk2 Oct 2023 21:20 UTC

25 points

4 comments2 min readLW link

(www.jefftk.com)

The Talk: a brief explanation of sexual dimorphism

Malmesbury18 Sep 2023 16:23 UTC

423 points

69 comments16 min readLW link

Mech Interp Challenge: October—Deciphering the Sorted List Model

TheMcDouglas3 Oct 2023 10:57 UTC

10 points

0 comments3 min readLW link

Early Experiments in Reward Model Interpretation Using Sparse Autoencoders

marc/er, Amirali Abdullah, Rauno Arike, Fazl and nothoughtsheadempty

3 Oct 2023 7:45 UTC

11 points

0 comments5 min readLW link

Arguments for moral indefinability

Richard_Ngo30 Sep 2023 22:40 UTC

47 points

15 comments7 min readLW link

(www.thinkingcomplete.com)