Under Violet

Hide10 Jun 2026 1:30 UTC

5 points

0 comments10 min readLW link

(hidefromit.substack.com)

The Disutility of FDT: on Utility Functions and Voting, Insights from Behavioral Economics and Decision Theory

DanielW9 Jun 2026 23:13 UTC

7 points

3 comments8 min readLW link

“Self-Control” Is A (Neurological) Type Error

Elliot Callender9 Jun 2026 21:34 UTC

5 points

0 comments1 min readLW link

Towards a Formal Scientific Epistemology

Richard_Ngo9 Jun 2026 20:31 UTC

49 points

1 comment7 min readLW link

Some Interesting Papers on RLVR

CarolusRenniusVitellius9 Jun 2026 19:00 UTC

16 points

3 comments4 min readLW link

A Mike’s-Eye View of ARC’s Research

Mikewins9 Jun 2026 18:30 UTC

52 points

0 comments11 min readLW link

(www.alignment.org)

An LLM Flagged My Paper About LLMs Flagging Things.

Failfinder709 Jun 2026 18:00 UTC

4 points

0 comments2 min readLW link

The Skeptic, the Bayesian, Empiricism and Claims to Know:

DanielW9 Jun 2026 17:52 UTC

2 points

0 comments4 min readLW link

Claude Fable 5 and Mythos 5 [Linkpost]

fluxxrider9 Jun 2026 17:19 UTC

28 points

7 comments1 min readLW link

5 Things I Learned About People From Doing Stand-Up Comedy

Luise Woehlke9 Jun 2026 15:52 UTC

−4 points

5 comments2 min readLW link

(open.substack.com)

The Machines Lack Honour

Raymond Douglas9 Jun 2026 15:30 UTC

85 points

10 comments12 min readLW link

[Linkpost] Evals for “SPI-incompatible” behavior & reasoning: Guide to initial research

Anthony DiGiovanni9 Jun 2026 13:44 UTC

23 points

0 comments1 min readLW link

(docs.google.com)

Subversion-Resistance for Free from Formal Verification

Adam Chlipala9 Jun 2026 12:01 UTC

7 points

0 comments7 min readLW link

LLMs and almost good code

kqr9 Jun 2026 7:21 UTC

31 points

8 comments3 min readLW link

(entropicthoughts.com)

On Slop

Jan9 Jun 2026 1:08 UTC

32 points

2 comments7 min readLW link

(universalprior.substack.com)

How to build a cancer vaccine, and whether they will work this time

Abhishaike Mahajan8 Jun 2026 20:45 UTC

51 points

3 comments25 min readLW link

(www.owlposting.com)

Efficient tradeoffs and the safety-usefulness tradeoff model

Buck8 Jun 2026 20:28 UTC

44 points

0 comments8 min readLW link

Accelerated Skill Learning via Dream Engineering and Biofeedback

Elliot Callender8 Jun 2026 20:08 UTC

5 points

2 comments3 min readLW link

How valuable are weak AI safety regulations?

MichaelDickens8 Jun 2026 18:24 UTC

27 points

0 comments6 min readLW link

How to reduce capability degradation from off-model SFT

Dylan Xu, SebastianP and Alek Westover

8 Jun 2026 16:24 UTC

21 points

0 comments3 min readLW link