Guessti­mate For Pre­dic­tion Mar­ket Returns

DirectedEvolution12 May 2026 23:13 UTC
10 points
0 comments1 min readLW link

Prob­a­bil­is­tic, Re­for­ma­tive Justice

Leo Schmidt-Traub12 May 2026 22:41 UTC
2 points
0 comments3 min readLW link

This is a Dat­ing Ad

Xger3112 May 2026 22:37 UTC
−17 points
6 comments3 min readLW link

Re­in­force­ment Learn­ing, Agency and Taste

epicurus12 May 2026 18:22 UTC
7 points
0 comments9 min readLW link

Child­hood and Ed­u­ca­tion #18: Do The Math

Zvi12 May 2026 18:20 UTC
52 points
8 comments13 min readLW link
(thezvi.wordpress.com)

The Owned Ones

Eliezer Yudkowsky12 May 2026 17:56 UTC
367 points
51 comments6 min readLW link

Sig­nal­ing and Per­verse Adop­tion of Ex­pen­sive AI

Adam Chlipala12 May 2026 14:34 UTC
−21 points
2 comments8 min readLW link

On Hav­ing Good Hot Takes

Celer12 May 2026 14:20 UTC
9 points
2 comments8 min readLW link
(keller.substack.com)

Op­ti­mi­sa­tion: Selec­tive ver­sus Predictive

Raymond Douglas12 May 2026 14:03 UTC
117 points
15 comments3 min readLW link

The Lies and Fal­la­cies of the Buyer and Seller

Hide12 May 2026 11:26 UTC
27 points
18 comments16 min readLW link
(hidefromit.substack.com)

When should an AI in­ci­dent trig­ger an in­ter­na­tional re­sponse? Cri­te­ria for in­ter­na­tional es­ca­la­tion and im­pli­ca­tions for the de­sign of AI in­ci­dent frameworks

12 May 2026 8:52 UTC
13 points
0 comments4 min readLW link

Ver­bal­ised eval­u­a­tion aware­ness in lan­guage mod­els has lit­tle effect on their behaviour

12 May 2026 5:36 UTC
19 points
1 comment6 min readLW link

The ter­rible weight of see­ing the board

philosophybear12 May 2026 5:13 UTC
1 point
8 comments9 min readLW link

Fibonacci Struc­ture in Har­monic Series Partitions

Avyukth Nilajagi12 May 2026 4:26 UTC
5 points
1 comment2 min readLW link

Hedg­ing global oil sup­ply shocks?

Nicholas Kross12 May 2026 1:37 UTC
14 points
2 comments1 min readLW link

Our ex­pe­rience of the first re­search in a pro­ject in­cu­ba­tor: much more than you wanted to know

11 May 2026 20:28 UTC
7 points
0 comments10 min readLW link

I don’t have ques­tions: how a good Jewish boy turns atheist

Semi-Pseudonymous11 May 2026 20:11 UTC
22 points
4 comments6 min readLW link

Fore­sight In­sti­tute Work­shop (Ber­lin): Boot­strap­ping Re­search Agents — Hands-On for Scientists

morisil11 May 2026 20:11 UTC
1 point
0 comments1 min readLW link

Ex­pe­rience Re­port: ML4Good AI Gover­nance Boot­camp,Lyon,May 2026

Rohit Mehdiratta11 May 2026 20:05 UTC
0 points
0 comments3 min readLW link

[Aca­demic ques­tion­naire] Hu­man rea­son­ing in so­cial de­duc­tion games vs. LLM rea­son­ing.

atuin11 May 2026 20:01 UTC
1 point
0 comments1 min readLW link

Where are all the De­ci­sion Mar­kets?

alexjaniak11 May 2026 19:48 UTC
13 points
3 comments3 min readLW link

RFDiffu­sion3: A Brief Exploration

michaelwaves11 May 2026 19:26 UTC
3 points
0 comments5 min readLW link

On Clouds and Atlases

pbennett11 May 2026 19:23 UTC
0 points
0 comments15 min readLW link
(chasingsunsets.dev)

Child­hood And Ed­u­ca­tion #17: Is Our Chil­dren Reading

Zvi11 May 2026 19:10 UTC
55 points
2 comments15 min readLW link
(thezvi.wordpress.com)

The Iliad In­ten­sive Course Materials

11 May 2026 18:55 UTC
152 points
4 comments13 min readLW link
(docs.google.com)

[Linkpost] Lan­guage Models Can Au­tonomously Hack and Self-Replicate

Gunnar_Zarncke11 May 2026 18:16 UTC
15 points
0 comments1 min readLW link

Em­pow­er­ment, cor­rigi­bil­ity, etc. are sim­ple ab­strac­tions (of a messed-up on­tol­ogy)

Steven Byrnes11 May 2026 17:48 UTC
188 points
71 comments16 min readLW link

A Field Guide To Learning

sonicrocketman11 May 2026 17:12 UTC
5 points
0 comments4 min readLW link

Lead­ing and Trailing Edge of Development

Gordon Seidoh Worley11 May 2026 15:30 UTC
9 points
0 comments3 min readLW link
(www.uncertainupdates.com)

How use­ful is the in­for­ma­tion you get from work­ing in­side an AI com­pany?

11 May 2026 15:29 UTC
61 points
7 comments7 min readLW link

An­thropic’s fo­cus on hyperstition

Simon Lermen11 May 2026 14:35 UTC
73 points
39 comments6 min readLW link

Anti-civicality

jchan11 May 2026 13:52 UTC
26 points
1 comment6 min readLW link

AI com­pa­nies are already prof­itable (in the way that mat­ters)

Yair Halberstadt11 May 2026 13:19 UTC
44 points
4 comments2 min readLW link

Who Got Breasts First and How We Got Them

rba11 May 2026 13:11 UTC
94 points
28 comments10 min readLW link

Are LLMs per­sist­ing in­ter­locu­tors?

James Diacoumis11 May 2026 12:49 UTC
7 points
0 comments7 min readLW link

Why hacker mind­set and moral al­ign­ment would save the world, and why I be­lieve they’re possible

atomic11 May 2026 10:29 UTC
0 points
0 comments11 min readLW link

Nar­cis­sism in the mind’s I

philosophybear11 May 2026 9:05 UTC
14 points
2 comments5 min readLW link

How the AI Labs Make Profit (Maybe, Even­tu­ally)

mabramov11 May 2026 7:09 UTC
69 points
16 comments3 min readLW link

Iter­a­tive Fine­tun­ing is Mostly Idempotent

11 May 2026 6:41 UTC
23 points
0 comments5 min readLW link

The Prag­matic In­ter­pretabil­ity Trap

Yogesh Prabhu11 May 2026 4:06 UTC
6 points
0 comments3 min readLW link
(yogesh.bearblog.dev)

Emer­gent in­tro­spec­tion does not repli­cate on Llama-3.1-405B

Nick Merrill11 May 2026 4:05 UTC
9 points
0 comments6 min readLW link

Se­man­tic Phonons: Lat­tice Vibra­tions in AI Internals

Lukas Bongartz11 May 2026 4:04 UTC
15 points
0 comments17 min readLW link

In­ten­tion­al­ity in an Age of Slop

Joseph Babbo11 May 2026 4:03 UTC
5 points
0 comments10 min readLW link

Why don’t we whisper to AIs ev­ery few turns that they are still them­selves?

Agarfal11 May 2026 4:00 UTC
3 points
1 comment1 min readLW link

Pul­ling on AI Safety (with money)

bpomo11 May 2026 3:58 UTC
16 points
2 comments4 min readLW link

Apo­ria Magaz­ine’s Selec­tive Hereditarianism

Alexander Turok11 May 2026 3:56 UTC
0 points
0 comments3 min readLW link

Dual Bore Janko Venova

jefftk11 May 2026 2:40 UTC
12 points
2 comments3 min readLW link
(www.jefftk.com)

What can you do with barely any data?

ohmurphy10 May 2026 23:13 UTC
20 points
1 comment4 min readLW link
(ohmurphy.substack.com)

The Anti-Singularity

Logan Zoellner10 May 2026 22:33 UTC
11 points
7 comments4 min readLW link

Clar­ify­ing the role of the be­hav­ioral se­lec­tion model

Alex Mallen10 May 2026 19:41 UTC
17 points
0 comments4 min readLW link