PSA: For Chronic In­fec­tions, Check Teeth

Algon20 Nov 2025 23:14 UTC
15 points
2 comments1 min readLW link

[Paper] Out­put Su­per­vi­sion Can Obfus­cate the CoT

20 Nov 2025 22:41 UTC
92 points
3 comments5 min readLW link
(arxiv.org)

The Bor­ing Part of Bell Labs

Elizabeth20 Nov 2025 22:40 UTC
133 points
0 comments15 min readLW link
(acesounderglass.com)

What the term “Mass Com­mu­ni­ca­tion” ges­tures at

TristanTrim20 Nov 2025 22:34 UTC
3 points
0 comments7 min readLW link

Dom­i­nance: The Stan­dard Every­day Solu­tion To Akrasia

johnswentworth20 Nov 2025 21:42 UTC
50 points
22 comments2 min readLW link

Do One Neat Thing vs. Get Work Done

Kaj_Sotala20 Nov 2025 21:33 UTC
23 points
0 comments7 min readLW link

Gem­ini 3 is Eval­u­a­tion-Para­noid and Contaminated

Alice Blair20 Nov 2025 21:02 UTC
180 points
42 comments7 min readLW link

Cur­rent LLM agents need strong pres­sure to en­gage in schem­ing behavior

20 Nov 2025 20:45 UTC
23 points
0 comments11 min readLW link

Try see­ing art

foodforthought20 Nov 2025 19:25 UTC
10 points
1 comment5 min readLW link

AI #143: Every­thing, Every­where, All At Once

Zvi20 Nov 2025 18:22 UTC
37 points
2 comments65 min readLW link
(thezvi.wordpress.com)

Think­ing about rea­son­ing mod­els made me less wor­ried about scheming

Fabien Roger20 Nov 2025 18:20 UTC
89 points
7 comments12 min readLW link

Defin­ing AI Truth-Seek­ing by What It Is Not

Tianyi (Alex) Qiu20 Nov 2025 16:45 UTC
21 points
1 comment10 min readLW link

Restrict­ing Danger­ous Re­search: Has It Worked Be­fore, and Could It Work for AI?

jleibowich20 Nov 2025 16:45 UTC
12 points
1 comment16 min readLW link
(samotsvety.com)

Per­sis­tence Ethics

Suspended Reason20 Nov 2025 16:27 UTC
7 points
2 comments5 min readLW link

Should we shun the leg­ibly evil?

Dentosal20 Nov 2025 13:22 UTC
5 points
2 comments2 min readLW link

Ru­mored Trump EO

Stephen Martin20 Nov 2025 13:07 UTC
10 points
0 comments4 min readLW link

The Moss Frac­tal: How Care Reg­u­lates Func­tional Aware­ness from Microbes to AI

Lcofa20 Nov 2025 11:33 UTC
1 point
0 comments14 min readLW link

What would adults in the room know about AI risk?

rosehadshar20 Nov 2025 9:11 UTC
18 points
2 comments3 min readLW link

10 Wrong and Dumb Gram­mar Rules

dreeves20 Nov 2025 7:56 UTC
15 points
3 comments3 min readLW link

My burnout journey

Aprillion20 Nov 2025 6:58 UTC
4 points
0 comments1 min readLW link
(peter.hozak.info)

One King Upon The Chessboard

Screwtape20 Nov 2025 6:06 UTC
49 points
7 comments6 min readLW link

Evrart Claire: A Case Study in Anti-Epistemology

Ben Pace20 Nov 2025 5:49 UTC
48 points
5 comments16 min readLW link

What Is The Basin Of Con­ver­gence For Kelly Bet­ting?

johnswentworth20 Nov 2025 4:36 UTC
33 points
3 comments3 min readLW link

Out-pa­ter­nal­iz­ing the gov­ern­ment (get­ting oxy­gen for my baby)

Ruby20 Nov 2025 4:01 UTC
50 points
12 comments7 min readLW link

On the Ra­tion­al­ity of Fractions

matthew allen20 Nov 2025 2:54 UTC
−6 points
0 comments1 min readLW link

Ex­clu­sive: Here’s the draft Trump ex­ec­u­tive or­der on AI preemption

Matrice Jacobine19 Nov 2025 23:21 UTC
9 points
0 comments1 min readLW link
(www.transformernews.ai)

How crit­i­cal is ASML to GPU progress?

Algon19 Nov 2025 23:15 UTC
10 points
0 comments3 min readLW link

In Defense of Goodness

abramdemski19 Nov 2025 23:03 UTC
33 points
7 comments3 min readLW link

Prevent­ing covert ASI de­vel­op­ment in coun­tries within our agreement

Aaron_Scher19 Nov 2025 22:21 UTC
39 points
2 comments12 min readLW link

A re­view of Red Heart, the new al­ign­ment novel by Max Harms

Alex_Altair19 Nov 2025 21:15 UTC
33 points
1 comment2 min readLW link
(namelessvirtue.com)

Monthly Roundup #36: Novem­ber 2025

Zvi19 Nov 2025 21:00 UTC
26 points
3 comments36 min readLW link
(thezvi.wordpress.com)

MLSN #17: Mea­sur­ing Gen­eral AI Abil­ities and Miti­gat­ing Deception

19 Nov 2025 20:11 UTC
5 points
0 comments6 min readLW link
(newsletter.mlsafety.org)

Re­view: The Most Danger­ous Writ­ing App

Dentosal19 Nov 2025 18:49 UTC
10 points
0 comments2 min readLW link

Se­ri­ous Flaws in CAST

Max Harms19 Nov 2025 17:27 UTC
110 points
10 comments8 min readLW link

Dense re­con­struc­tion is the scaf­fold of ma­chine learning

zef19 Nov 2025 17:21 UTC
3 points
0 comments4 min readLW link
(bloodsteel.substack.com)

Bet­ter Writ­ing Through Claude

Gordon Seidoh Worley19 Nov 2025 16:00 UTC
14 points
2 comments6 min readLW link
(www.uncertainupdates.com)

Cur­rent LLMs seem to rarely de­tect CoT tampering

19 Nov 2025 15:27 UTC
56 points
0 comments20 min readLW link

I give up.

breaker2519 Nov 2025 11:54 UTC
3 points
1 comment1 min readLW link

The Bughouse Effect

TsviBT19 Nov 2025 8:57 UTC
67 points
6 comments13 min readLW link

Me­mories of a Bri­tish Board­ing School #2

Ben Pace19 Nov 2025 7:57 UTC
36 points
0 comments7 min readLW link

On Wanting

Screwtape19 Nov 2025 7:20 UTC
16 points
0 comments3 min readLW link

Au­to­mate, au­to­mate it all

habryka19 Nov 2025 7:08 UTC
75 points
0 comments5 min readLW link

My Eth­i­cal Co­nun­drum Around Writ­ing About Meditation

eleweek19 Nov 2025 5:05 UTC
24 points
1 comment4 min readLW link
(psychotechnology.substack.com)

A day in the life of a LW developer

RobertM19 Nov 2025 4:54 UTC
46 points
3 comments6 min readLW link

An an­tibiotic for par­a­sitic AI

1358019 Nov 2025 4:41 UTC
2 points
2 comments2 min readLW link

Against Money Maximalism

abramdemski19 Nov 2025 4:41 UTC
30 points
0 comments6 min readLW link

How the aliens next door shower

Ruby19 Nov 2025 2:42 UTC
71 points
0 comments3 min readLW link

KPD is a weak obstruction

JustinSheek19 Nov 2025 0:34 UTC
21 points
4 comments13 min readLW link

An­thropic is (prob­a­bly) not meet­ing its RSP se­cu­rity commitments

habryka18 Nov 2025 23:34 UTC
129 points
22 comments5 min readLW link

Con­sid­er­a­tions for set­ting the FLOP thresh­olds in our ex­am­ple in­ter­na­tional AI agree­ment

18 Nov 2025 23:31 UTC
54 points
5 comments7 min readLW link