All200520062007200820092010201120122013201420152016201720182019202020212022202320242025
AllJanFebMarAprMayJunJulAugSepOctNovDec

(The) Light­cone is noth­ing with­out its peo­ple: LW + Lighthaven’s big fundraiser

habryka30 Nov 2024 2:55 UTC
611 points
273 comments42 min readLW link

LessWrong’s (first) album: I Have Been A Good Bing

habryka and kave
1 Apr 2024 7:33 UTC
576 points
183 comments11 min readLW link

OpenAI Email Archives (from Musk v. Alt­man and OpenAI blog)

habryka16 Nov 2024 6:38 UTC
538 points
81 comments51 min readLW link

Align­ment Fak­ing in Large Lan­guage Models

ryan_greenblatt, evhub, Carson Denison, Benjamin Wright, Fabien Roger, Monte M, Sam Marks, Johannes Treutlein, Sam Bowman and Buck
18 Dec 2024 17:19 UTC
493 points
78 comments10 min readLW link1 review

I would have shit in that alley, too

Mr. Keating18 Jun 2024 4:41 UTC
485 points
142 comments4 min readLW link1 review

The Best Tacit Knowl­edge Videos on Every Subject

Parker Conley31 Mar 2024 17:14 UTC
450 points
175 comments21 min readLW link

Trans­form­ers Rep­re­sent Belief State Geom­e­try in their Resi­d­ual Stream

Adam Shai16 Apr 2024 21:16 UTC
429 points
101 comments12 min readLW link1 review

Failures in Kindness

silentbob26 Mar 2024 21:30 UTC
427 points
60 comments9 min readLW link

The hos­tile telepaths problem

Valentine27 Oct 2024 15:26 UTC
418 points
101 comments15 min readLW link5 reviews

How I got 4.2M YouTube views with­out mak­ing a sin­gle video

Closed Limelike Curves3 Sep 2024 3:52 UTC
409 points
36 comments1 min readLW link

Reli­able Sources: The Story of David Gerard

TracingWoodgrains10 Jul 2024 19:50 UTC
401 points
56 comments43 min readLW link2 reviews

Sur­vival with­out dignity

L Rudolf L4 Nov 2024 2:29 UTC
387 points
29 comments15 min readLW link
(nosetgauge.substack.com)

There is way too much serendipity

Malmesbury19 Jan 2024 19:37 UTC
386 points
58 comments7 min readLW link1 review

My hour of mem­o­ryless lucidity

Eric Neyman4 May 2024 1:40 UTC
377 points
37 comments5 min readLW link
(ericneyman.wordpress.com)

No­tifi­ca­tions Re­ceived in 30 Minutes of Class

tanagrabeast26 May 2024 17:02 UTC
372 points
17 comments8 min readLW link1 review

Re­view: Planecrash

L Rudolf L27 Dec 2024 14:18 UTC
363 points
46 comments22 min readLW link
(nosetgauge.substack.com)

Safety isn’t safety with­out a so­cial model (or: dis­pel­ling the myth of per se tech­ni­cal safety)

Andrew_Critch14 Jun 2024 0:16 UTC
362 points
41 comments4 min readLW link3 reviews

Thoughts on seed oil

dynomight20 Apr 2024 12:29 UTC
360 points
131 comments17 min readLW link1 review
(dynomight.net)

You don’t know how bad most things are nor pre­cisely how they’re bad.

Solenoid_Entity4 Aug 2024 14:12 UTC
354 points
52 comments5 min readLW link1 review

[April Fools’ Day] In­tro­duc­ing Open As­teroid Impact

Linch1 Apr 2024 8:14 UTC
349 points
32 comments1 min readLW link2 reviews
(openasteroidimpact.org)

Univer­sal Ba­sic In­come and Poverty

Eliezer Yudkowsky26 Jul 2024 7:23 UTC
348 points
147 comments9 min readLW link

What Goes Without Saying

sarahconstantin20 Dec 2024 18:00 UTC
345 points
29 comments5 min readLW link1 review
(sarahconstantin.substack.com)

Biolog­i­cal risk from the mir­ror world

jasoncrawford12 Dec 2024 19:07 UTC
334 points
38 comments7 min readLW link
(newsletter.rootsofprogress.org)

MIRI 2024 Com­mu­ni­ca­tions Strategy

Gretta Duleba29 May 2024 19:33 UTC
325 points
218 comments7 min readLW link

I got dysen­tery so you don’t have to

eukaryote22 Oct 2024 4:55 UTC
325 points
7 comments17 min readLW link1 review
(eukaryotewritesblog.com)

The Field of AI Align­ment: A Post­mortem, and What To Do About It

johnswentworth26 Dec 2024 18:48 UTC
321 points
174 comments8 min readLW link1 review

Would catch­ing your AIs try­ing to es­cape con­vince AI de­vel­op­ers to slow down or un­de­ploy?

Buck26 Aug 2024 16:46 UTC
319 points
78 comments4 min readLW link1 review

Gentle­ness and the ar­tifi­cial Other

Joe Carlsmith2 Jan 2024 18:21 UTC
314 points
33 comments11 min readLW link

Sleeper Agents: Train­ing De­cep­tive LLMs that Per­sist Through Safety Training

evhub, Carson Denison, Meg, Monte M, David Duvenaud, Nicholas Schiefer and Ethan Perez
12 Jan 2024 19:51 UTC
310 points
95 comments3 min readLW link
(arxiv.org)

By de­fault, cap­i­tal will mat­ter more than ever af­ter AGI

L Rudolf L28 Dec 2024 17:52 UTC
306 points
106 comments16 min readLW link
(nosetgauge.substack.com)

Laz­i­ness death spirals

PatrickDFarley19 Sep 2024 15:58 UTC
299 points
41 comments8 min readLW link

Ori­ent­ing to 3 year AGI timelines

Nikola Jurkovic22 Dec 2024 1:15 UTC
298 points
63 comments8 min readLW link2 reviews

Scale Was All We Needed, At First

Gabe M14 Feb 2024 1:49 UTC
297 points
35 comments8 min readLW link
(aiacumen.substack.com)

Overview of strong hu­man in­tel­li­gence am­plifi­ca­tion methods

TsviBT8 Oct 2024 8:37 UTC
294 points
162 comments10 min readLW link1 review

My AI Model Delta Com­pared To Yudkowsky

johnswentworth10 Jun 2024 16:12 UTC
291 points
103 comments4 min readLW link

Non-Dis­par­age­ment Ca­naries for OpenAI

aysja and Adam Scholl
30 May 2024 19:20 UTC
290 points
51 comments2 min readLW link

On green

Joe Carlsmith21 Mar 2024 17:38 UTC
290 points
36 comments31 min readLW link1 review

The On­line Sports Gam­bling Ex­per­i­ment Has Failed

Zvi11 Nov 2024 14:30 UTC
289 points
60 comments11 min readLW link
(thezvi.wordpress.com)

“No-one in my org puts money in their pen­sion”

Tobes16 Feb 2024 18:33 UTC
285 points
17 comments9 min readLW link1 review
(seekingtobejolly.substack.com)

Rais­ing chil­dren on the eve of AI

juliawise15 Feb 2024 21:28 UTC
283 points
47 comments5 min readLW link

The Great Data In­te­gra­tion Schlep

sarahconstantin13 Sep 2024 15:40 UTC
279 points
19 comments9 min readLW link
(sarahconstantin.substack.com)

80,000 hours should re­move OpenAI from the Job Board (and similar EA orgs should do similarly)

Raemon3 Jul 2024 20:34 UTC
274 points
71 comments3 min readLW link

the case for CoT un­faith­ful­ness is overstated

nostalgebraist29 Sep 2024 22:07 UTC
269 points
44 comments11 min readLW link1 review

Ex­press in­ter­est in an “FHI of the West”

habryka18 Apr 2024 3:32 UTC
268 points
41 comments3 min readLW link

The case for en­sur­ing that pow­er­ful AIs are controlled

ryan_greenblatt and Buck
24 Jan 2024 16:11 UTC
268 points
74 comments28 min readLW link1 review

Leav­ing MIRI, Seek­ing Funding

abramdemski8 Aug 2024 18:32 UTC
264 points
19 comments2 min readLW link

Truth­seek­ing is the ground in which other prin­ci­ples grow

Elizabeth27 May 2024 1:09 UTC
264 points
16 comments16 min readLW link

Get­ting 50% (SoTA) on ARC-AGI with GPT-4o

ryan_greenblatt17 Jun 2024 18:44 UTC
263 points
50 comments13 min readLW link

The Best Lay Ar­gu­ment is not a Sim­ple English Yud Essay

J Bostock10 Sep 2024 17:34 UTC
262 points
17 comments5 min readLW link1 review

My PhD the­sis: Al­gorith­mic Bayesian Epistemology

Eric Neyman16 Mar 2024 22:56 UTC
262 points
14 comments7 min readLW link
(arxiv.org)