All 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 20232024

AllJan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

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

habryka30 Nov 2024 2:55 UTC

567 points

194 comments41 min readLW link

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

habryka and kave

1 Apr 2024 7:33 UTC

564 points

174 comments11 min readLW link

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

habryka16 Nov 2024 6:38 UTC

517 points

80 comments51 min readLW link

I would have shit in that alley, too

Declan Molony18 Jun 2024 4:41 UTC

436 points

134 comments4 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

411 points

51 comments10 min readLW link

Transformers Represent Belief State Geometry in their Residual Stream

Adam Shai16 Apr 2024 21:16 UTC

411 points

100 comments12 min readLW link

Failures in Kindness

silentbob26 Mar 2024 21:30 UTC

409 points

60 comments9 min readLW link

Reliable Sources: The Story of David Gerard

TracingWoodgrains10 Jul 2024 19:50 UTC

381 points

53 comments43 min readLW link

The hostile telepaths problem

Valentine27 Oct 2024 15:26 UTC

378 points

83 comments15 min readLW link

The Best Tacit Knowledge Videos on Every Subject

Parker Conley31 Mar 2024 17:14 UTC

377 points

143 comments16 min readLW link

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

Closed Limelike Curves3 Sep 2024 3:52 UTC

376 points

36 comments1 min readLW link

There is way too much serendipity

Malmesbury19 Jan 2024 19:37 UTC

366 points

56 comments7 min readLW link

My hour of memoryless lucidity

Eric Neyman4 May 2024 1:40 UTC

358 points

35 comments5 min readLW link

(ericneyman.wordpress.com)

Notifications Received in 30 Minutes of Class

tanagrabeast26 May 2024 17:02 UTC

354 points

16 comments8 min readLW link

Thoughts on seed oil

dynomight20 Apr 2024 12:29 UTC

347 points

129 comments17 min readLW link

(dynomight.net)

Survival without dignity

L Rudolf L4 Nov 2024 2:29 UTC

345 points

28 comments15 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

344 points

38 comments4 min readLW link

[April Fools’ Day] Introducing Open Asteroid Impact

Linch1 Apr 2024 8:14 UTC

334 points

29 comments1 min readLW link

(openasteroidimpact.org)

MIRI 2024 Communications Strategy

Gretta Duleba29 May 2024 19:33 UTC

320 points

202 comments7 min readLW link

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

Solenoid_Entity4 Aug 2024 14:12 UTC

316 points

48 comments5 min readLW link

I got dysentery so you don’t have to

eukaryote22 Oct 2024 4:55 UTC

315 points

4 comments17 min readLW link

(eukaryotewritesblog.com)

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

305 points

95 comments3 min readLW link

(arxiv.org)

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

Buck26 Aug 2024 16:46 UTC

294 points

76 comments4 min readLW link

Gentleness and the artificial Other

Joe Carlsmith2 Jan 2024 18:21 UTC

292 points

33 comments11 min readLW link

Universal Basic Income and Poverty

Eliezer Yudkowsky26 Jul 2024 7:23 UTC

288 points

134 comments9 min readLW link

Non-Disparagement Canaries for OpenAI

aysja and Adam Scholl

30 May 2024 19:20 UTC

287 points

51 comments2 min readLW link

Scale Was All We Needed, At First

Gabe M14 Feb 2024 1:49 UTC

286 points

33 comments8 min readLW link

(aiacumen.substack.com)

Biological risk from the mirror world

jasoncrawford12 Dec 2024 19:07 UTC

283 points

24 comments7 min readLW link

(newsletter.rootsofprogress.org)

My AI Model Delta Compared To Yudkowsky

johnswentworth10 Jun 2024 16:12 UTC

277 points

102 comments4 min readLW link

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

Raemon3 Jul 2024 20:34 UTC

272 points

71 comments1 min readLW link

Overview of strong human intelligence amplification methods

TsviBT8 Oct 2024 8:37 UTC

270 points

141 comments10 min readLW link

Leaving MIRI, Seeking Funding

abramdemski8 Aug 2024 18:32 UTC

269 points

19 comments2 min readLW link

Express interest in an “FHI of the West”

habryka18 Apr 2024 3:32 UTC

268 points

41 comments3 min readLW link

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

Tobes16 Feb 2024 18:33 UTC

267 points

16 comments9 min readLW link

(seekingtobejolly.substack.com)

Raising children on the eve of AI

juliawise15 Feb 2024 21:28 UTC

266 points

47 comments5 min readLW link

On green

Joe Carlsmith21 Mar 2024 17:38 UTC

266 points

35 comments31 min readLW link

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

ryan_greenblatt17 Jun 2024 18:44 UTC

262 points

50 comments13 min readLW link

The case for ensuring that powerful AIs are controlled

ryan_greenblatt and Buck

24 Jan 2024 16:11 UTC

260 points

66 comments28 min readLW link

My PhD thesis: Algorithmic Bayesian Epistemology

Eric Neyman16 Mar 2024 22:56 UTC

259 points

14 comments7 min readLW link

(arxiv.org)

The Great Data Integration Schlep

sarahconstantin13 Sep 2024 15:40 UTC

258 points

16 comments9 min readLW link

(sarahconstantin.substack.com)

Paul Christiano named as US AI Safety Institute Head of AI Safety

Joel Burget16 Apr 2024 16:22 UTC

256 points

58 comments1 min readLW link

(www.commerce.gov)

My Clients, The Liars

ymeskhout5 Mar 2024 21:06 UTC

248 points

85 comments7 min readLW link

Truthseeking is the ground in which other principles grow

Elizabeth27 May 2024 1:09 UTC

247 points

16 comments16 min readLW link

Laziness death spirals

PatrickDFarley19 Sep 2024 15:58 UTC

247 points

35 comments8 min readLW link

The Best Lay Argument is not a Simple English Yud Essay

J Bostock10 Sep 2024 17:34 UTC

247 points

15 comments5 min readLW link

Ilya Sutskever and Jan Leike resign from OpenAI [updated]

Zach Stein-Perlman15 May 2024 0:45 UTC

246 points

95 comments2 min readLW link

Principles for the AGI Race

William_S30 Aug 2024 14:29 UTC

245 points

13 comments18 min readLW link

The Online Sports Gambling Experiment Has Failed

Zvi11 Nov 2024 14:30 UTC

244 points

28 comments11 min readLW link

(thezvi.wordpress.com)

the case for CoT unfaithfulness is overstated

nostalgebraist29 Sep 2024 22:07 UTC

244 points

40 comments11 min readLW link

AI companies aren’t really using external evaluators

Zach Stein-Perlman24 May 2024 16:01 UTC

240 points

15 comments4 min readLW link