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
73 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

AI Align­ment as Equil­ibrium Design

Elad Hazan10 May 2026 18:56 UTC
19 points
4 comments5 min readLW link

Claude Does Not Ac­tu­ally Taste Bananas: Po­tas­sium-Based Syn­thetic Phenomenol­ogy In Lan­guage Models

Noah Weinberger10 May 2026 17:13 UTC
8 points
2 comments10 min readLW link
(huggingface.co)

The Dar­wi­nian Honey­moon—Why I am not as im­pressed by hu­man progress as I used to be

Elias Schmied10 May 2026 15:55 UTC
138 points
23 comments4 min readLW link

Re­in­force­ment learn­ing scal­ing might in­cen­tivise hid­den rea­son­ing ar­chi­tec­tures for AI

Oliver Sourbut10 May 2026 15:30 UTC
19 points
5 comments6 min readLW link
(www.oliversourbut.net)

Asym­me­try Between Defen­sive and Ac­quisi­tive In­stru­men­tal Deception

keith_wynroe10 May 2026 12:33 UTC
17 points
1 comment5 min readLW link

Con­text Mod­ifi­ca­tion as a Nega­tive Align­ment Tax

Florian_Dietz10 May 2026 11:32 UTC
7 points
0 comments4 min readLW link

‘Who Let The Docs Out’ Is Award­ing Up To $50K For 6 Doc Film­mak­ers Dur­ing A LIVE Pitch Com­pe­ti­tion In LA! Ap­pli­ca­tion Dead­line: May 19th

Max Hellier10 May 2026 11:08 UTC
1 point
0 comments1 min readLW link
(docsout.org)

[Question] Best In­tro AI X-Risk Re­source?

XelaP10 May 2026 11:03 UTC
12 points
3 comments2 min readLW link

Stock­holm ACX Fika

Ave Mariekex10 May 2026 5:46 UTC
1 point
0 comments1 min readLW link

Con­trol Debt

Ida Caspary10 May 2026 5:07 UTC
11 points
0 comments7 min readLW link

Saw­tooth Problems

Alexander Slugworth10 May 2026 5:01 UTC
54 points
14 comments21 min readLW link

Could Fron­tier AI Re­searchers Col­lec­tively Slow the Race? A Con­di­tional Pledge Mechanism

Cassandra Threshold10 May 2026 3:22 UTC
21 points
2 comments7 min readLW link

Somerville Porch­fest 2026

jefftk10 May 2026 1:20 UTC
10 points
0 comments3 min readLW link
(www.jefftk.com)

The AI In­dus­trial Ex­plo­sion — Part 2: Tran­si­tion Dynamics

djbinder10 May 2026 1:02 UTC
23 points
0 comments12 min readLW link
(defensesindepth.bio)

The Goblins Are the Paperclips

Hisku9 May 2026 22:51 UTC
12 points
0 comments3 min readLW link