RSS

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

8 Jun 2026 16:24 UTC
21 points
0 comments3 min readLW link