ArchiveSequencesAbout
QuestionsEventsShortformAlignment ForumAF Comments
HomeFeaturedAllTagsRecent Comments
RSS
NewHotActiveOld
Page 1

Guardian An­gels: LLM Per­son­al­iza­tion for Pro­duc­tivity and Security

gwern17 Jun 2026 3:21 UTC
157 points
34 comments2 min readLW link
(gwern.net)

Es­ti­mat­ing No-CoT Task-Com­ple­tion Time Hori­zons of Fron­tier AI Models

Anders Cairns Woodruff, Francis Rhys Ward, Dewi Gould, Rauno Arike, Jason R Brown, Jo Jiao, wlanderson, ariana_azarbal, harrymayne, Patrick Leask, Twm Stone, Josh Hills, Ida Caspary, Shubhorup Biswas and Julian Stastny
10 Jun 2026 17:58 UTC
265 points
23 comments4 min readLW link

Trees are mostly made of air and a gen­er­al­iz­able les­son for AI safety

Zephaniah Roe29 May 2026 4:08 UTC
261 points
55 comments4 min readLW link

Mnemonic por­traits for 19,023 hu­man genes

Brinedew28 May 2026 22:16 UTC
346 points
28 comments15 min readLW link

Models find­ing soft­ware vuln­er­a­bil­ities is not the pri­mary source of cy­ber­se­cu­rity risk

lc14 May 2026 3:39 UTC
311 points
24 comments2 min readLW link

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

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

Bad Prob­lems Don’t Stop Be­ing Bad Be­cause Some­body’s Wrong About Fault Analysis

Linch9 May 2026 1:30 UTC
264 points
75 comments3 min readLW link

x-risk-themed

kave6 May 2026 15:16 UTC
246 points
24 comments3 min readLW link
(kaverennedy.substack.com)

Ir­re­triev­abil­ity; or, Mur­phy’s Curse of Oneshot­ness upon ASI

Eliezer Yudkowsky4 May 2026 22:11 UTC
367 points
132 comments22 min readLW link

How Go Play­ers Disem­power Them­selves to AI

Ashe Vazquez Nuñez1 May 2026 23:24 UTC
708 points
78 comments8 min readLW link

llm as­sis­tant per­sonas seem in­creas­ingly in­co­her­ent (some sub­jec­tive ob­ser­va­tions)

nostalgebraist29 Apr 2026 3:53 UTC
345 points
84 comments9 min readLW link

Do not con­quer what you can­not defend

habryka16 Apr 2026 4:13 UTC
424 points
73 comments6 min readLW link

Cur­rent AIs seem pretty mis­al­igned to me

ryan_greenblatt15 Apr 2026 15:14 UTC
710 points
81 comments27 min readLW link

An­noy­ingly Prin­ci­pled Peo­ple, and what be­falls them

Raemon13 Apr 2026 17:35 UTC
306 points
71 comments5 min readLW link

What I did in the he­do­nium shock­wave, by Emma, age six and a half

ozymandias13 Apr 2026 16:47 UTC
445 points
45 comments5 min readLW link
(ozybrennan.substack.com)

Morale

J Bostock12 Apr 2026 20:15 UTC
312 points
47 comments2 min readLW link

The Prac­ti­cal Guide to Superbabies

GeneSmith2 Apr 2026 17:02 UTC
214 points
67 comments54 min readLW link

In­tel­li­gence Dis­solves Privacy

Vaniver2 Apr 2026 3:50 UTC
164 points
80 comments6 min readLW link

My hobby: run­ning de­ranged surveys

leogao27 Mar 2026 0:41 UTC
312 points
65 comments9 min readLW link

The Terrarium

Caleb Biddulph26 Mar 2026 18:08 UTC
585 points
52 comments21 min readLW link
Back to topNext