Arusha Per­pet­ual Chicken—an un­likely iter­ated game

James Stephen BrownApr 6, 2025, 10:56 PM
15 points
1 comment5 min readLW link
(nonzerosum.games)

How Gay is the Vat­i­can?

rbaApr 6, 2025, 9:27 PM
58 points
32 comments7 min readLW link

RFC: a tool to cre­ate a ranked list of pro­jects in ex­plain­able AI

eamagApr 6, 2025, 9:18 PM
2 points
0 comments1 min readLW link
(eamag.me)

Aus­tralia’s AI Cross­roads: Elec­tion 2025 Town Hall

Peter HorniakApr 6, 2025, 9:17 PM
1 point
0 comments1 min readLW link

The Lizard­man and the Black Hat Bobcat

ScrewtapeApr 6, 2025, 7:02 PM
108 points
15 comments9 min readLW link

Would this solve the (outer) al­ign­ment prob­lem, or at least help?

Wes RApr 6, 2025, 6:49 PM
−2 points
1 comment13 min readLW link

[Question] What are the fun­da­men­tal differ­ences be­tween teach­ing the AIs and hu­mans?

StanislavKrymApr 6, 2025, 6:17 PM
3 points
0 comments1 min readLW link

An “Op­ti­mistic” 2027 Timeline

YitzApr 6, 2025, 4:39 PM
13 points
16 comments9 min readLW link

Thoughts on Creat­ing a Good Language

Towards_KeeperhoodApr 6, 2025, 3:57 PM
1 point
2 comments7 min readLW link

The REPHRASE Cir­cuit: How Fine-Tun­ing En­hances LLMs to REPHRASE Text

Karthik ViswanathanApr 6, 2025, 3:02 PM
4 points
0 comments5 min readLW link

[Re­search sprint] Sin­gle-model cross­coder fea­ture ab­la­tion and steering

Thomas ReadApr 6, 2025, 2:42 PM
8 points
0 comments12 min readLW link

Fer­rer, Pilar, and Me

AskwhoApr 6, 2025, 11:22 AM
21 points
1 comment4 min readLW link
(open.substack.com)

FlexChunk: En­abling 100M×100M Out-of-Core SpMV (~1.8 min, ~1.7 GB RAM) with Near-Lin­ear Scaling

Daniil StrizhovApr 6, 2025, 5:27 AM
1 point
0 comments7 min readLW link

A col­lec­tion of ap­proaches to con­fronting doom, and my thoughts on them

RubyApr 6, 2025, 2:11 AM
48 points
18 comments12 min readLW link

A Slow Guide to Con­fronting Doom

RubyApr 6, 2025, 2:10 AM
84 points
20 comments14 min readLW link

[Linkpost] Vi­sual roadmap to strong hu­man germline engineering

TsviBTApr 5, 2025, 10:22 PM
30 points
0 comments1 min readLW link

Google Deep­Mind: An Ap­proach to Tech­ni­cal AGI Safety and Security

Rohin ShahApr 5, 2025, 10:00 PM
73 points
12 comments18 min readLW link
(arxiv.org)

In­tro­duc­tion to Rep­re­sent­ing Sen­tences as Log­i­cal Statements

Towards_KeeperhoodApr 5, 2025, 8:35 PM
22 points
9 comments16 min readLW link

Me­mory De­cod­ing Jour­nal Club: A col­lab­o­ra­tion of the Car­bon­copies Foun­da­tion and BPF Aspira­tional Neuroscience

Devin WardApr 5, 2025, 8:27 PM
1 point
0 comments1 min readLW link

Meta re­leases Llama-4 herd of models

winstonBosanApr 5, 2025, 7:51 PM
14 points
5 comments1 min readLW link

Against podcasts

Adam ZernerApr 5, 2025, 7:20 PM
33 points
19 comments4 min readLW link

What are Re­spon­si­ble Scal­ing Poli­cies (RSPs)?

Apr 5, 2025, 4:01 PM
3 points
0 comments1 min readLW link
(aisafety.info)

What does Yann LeCun think about AGI? A sum­mary of his talk, “Math­e­mat­i­cal Ob­sta­cles on the Way to Hu­man-Level AI”

Adam JonesApr 5, 2025, 12:21 PM
13 points
0 comments2 min readLW link

I Have No Mouth but I Must Speak

JackApr 5, 2025, 7:42 AM
7 points
8 comments8 min readLW link

Pre­dic­tion Mar­kets Are Mediocre

Ape in the coatApr 5, 2025, 6:54 AM
3 points
13 comments3 min readLW link

Among Us: A Sand­box for Agen­tic Deception

Apr 5, 2025, 6:24 AM
110 points
7 comments7 min readLW link

Ai Cone of Prob­a­bilties—what aren’t we talk­ing about?

MarzipanApr 5, 2025, 5:51 AM
−10 points
5 comments2 min readLW link

Quar­ter Inch Cables are Devious

jefftkApr 5, 2025, 2:40 AM
13 points
4 comments1 min readLW link
(www.jefftk.com)

Most Ques­tion­able De­tails in ‘AI 2027’

Commander ZanderApr 5, 2025, 12:32 AM
32 points
4 comments6 min readLW link

Karel Čapek’s ‘War with the Newts’ 1936 review

Petr 'Margot' AndreevApr 4, 2025, 11:12 PM
−10 points
1 comment1 min readLW link

How much progress ac­tu­ally hap­pens in the­o­ret­i­cal physics?

ChristianKlApr 4, 2025, 11:08 PM
32 points
32 comments1 min readLW link

Self-Repli­ca­tion: AI already can do it

Andrey SeryakovApr 4, 2025, 10:37 PM
4 points
0 comments5 min readLW link

Join Vi­tal­ist Bay: An 8-Week Longevity and Rad­i­cal Life Ex­ten­sion Event Series in Berkeley (April-May 2025)

VitaranApr 4, 2025, 9:03 PM
6 points
0 comments1 min readLW link

Sleep peace­fully: no hid­den rea­son­ing de­tected in LLMs. Well, at least in small ones.

Apr 4, 2025, 8:49 PM
16 points
2 comments7 min readLW link

AI com­pa­nies’ un­mon­i­tored in­ter­nal AI use poses se­ri­ous risks

sjadlerApr 4, 2025, 6:17 PM
13 points
2 comments1 min readLW link
(stevenadler.substack.com)

Will com­pute bot­tle­necks pre­vent a soft­ware in­tel­li­gence ex­plo­sion?

Tom DavidsonApr 4, 2025, 5:41 PM
77 points
24 comments12 min readLW link

Join Us for the Me­mory De­cod­ing Jour­nal Club!

Devin WardApr 4, 2025, 5:13 PM
1 point
0 comments1 min readLW link

Align­ment fak­ing CTFs: Ap­ply to my MATS stream

joshcApr 4, 2025, 4:29 PM
61 points
0 comments4 min readLW link

LLM AGI will have mem­ory, and mem­ory changes alignment

Seth HerdApr 4, 2025, 2:59 PM
73 points
15 comments9 min readLW link

A Bunch of Ma­tryoshka SAEs

Apr 4, 2025, 2:53 PM
25 points
0 comments8 min readLW link

AI CoT Rea­son­ing Is Often Unfaithful

ZviApr 4, 2025, 2:50 PM
66 points
4 comments7 min readLW link
(thezvi.wordpress.com)

Med­i­ta­tion and Re­duced Sleep Need

niplavApr 4, 2025, 2:42 PM
36 points
8 comments3 min readLW link

Su­ing OpenAI Won’t Save the Arts

E.G. Blee-GoldmanApr 4, 2025, 1:42 PM
2 points
0 comments5 min readLW link

For Policy’s Sake: Why We Must Dist­in­guish AI Safety from AI Se­cu­rity in Reg­u­la­tory Governance

Katalina HernandezApr 4, 2025, 9:16 AM
6 points
11 comments6 min readLW link

Ex­plain­ing the Joke: Paus­ing is The Way

WillPetilloApr 4, 2025, 9:04 AM
24 points
2 comments10 min readLW link

ACX/​EA Hy­der­abad Meetup

Apr 4, 2025, 8:12 AM
3 points
2 comments1 min readLW link

Tools for de­ci­sion-sup­port, de­liber­a­tion, sense-mak­ing, reasoning

David JamesApr 4, 2025, 2:27 AM
3 points
0 comments1 min readLW link

Cheese­cake Frosting

jefftkApr 4, 2025, 2:10 AM
10 points
9 comments1 min readLW link
(www.jefftk.com)

Chang­ing my mind about Chris­ti­ano’s ma­lign prior argument

Cole WyethApr 4, 2025, 12:54 AM
27 points
34 comments7 min readLW link

POTUS Pre­dic­tions Tournament

ChristianWilliamsApr 3, 2025, 10:48 PM
15 points
0 comments1 min readLW link
(www.metaculus.com)