All 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 202120222023 2024 2025

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

AGI Ruin: A List of Lethalities

Eliezer YudkowskyJun 5, 2022, 10:05 PM

929 points

708 comments30 min readLW link 3 reviews

Where I agree and disagree with Eliezer

paulfchristianoJun 19, 2022, 7:15 PM

898 points

223 comments18 min readLW link 2 reviews

What an actually pessimistic containment strategy looks like

lcApr 5, 2022, 12:19 AM

679 points

138 comments6 min readLW link 2 reviews

Simulators

janusSep 2, 2022, 12:45 PM

631 points

168 comments41 min readLW link 8 reviews

(generative.ink)

Let’s think about slowing down AI

KatjaGraceDec 22, 2022, 5:40 PM

551 points

182 comments38 min readLW link 3 reviews

(aiimpacts.org)

The Redaction Machine

BenSep 20, 2022, 10:03 PM

503 points

48 comments27 min readLW link 1 review

Luck based medicine: my resentful story of becoming a medical miracle

ElizabethOct 16, 2022, 5:40 PM

488 points

121 comments12 min readLW link 3 reviews

(acesounderglass.com)

Losing the root for the tree

Adam ZernerSep 20, 2022, 4:53 AM

480 points

31 comments9 min readLW link 1 review

Counter-theses on Sleep

NatáliaMar 21, 2022, 11:21 PM

447 points

135 comments15 min readLW link 1 review

It’s Probably Not Lithium

NatáliaJun 28, 2022, 9:24 PM

442 points

187 comments28 min readLW link 1 review

chinchilla’s wild implications

nostalgebraistJul 31, 2022, 1:18 AM

424 points

128 comments10 min readLW link 1 review

(My understanding of) What Everyone in Technical Alignment is Doing and Why

Thomas Larsen and elifland

Aug 29, 2022, 1:23 AM

413 points

90 comments37 min readLW link 1 review

You Are Not Measuring What You Think You Are Measuring

johnswentworthSep 20, 2022, 8:04 PM

407 points

44 comments8 min readLW link 2 reviews

It Looks Like You’re Trying To Take Over The World

gwernMar 9, 2022, 4:35 PM

407 points

120 comments1 min readLW link 1 review

(www.gwern.net)

DeepMind alignment team opinions on AGI ruin arguments

VikaAug 12, 2022, 9:06 PM

395 points

37 comments14 min readLW link 1 review

Reflections on six months of fatherhood

jasoncrawfordJan 31, 2022, 5:28 AM

387 points

24 comments4 min readLW link 1 review

(jasoncrawford.org)

Lies Told To Children

Eliezer YudkowskyApr 14, 2022, 11:25 AM

381 points

94 comments7 min readLW link 1 review

Reward is not the optimization target

TurnTroutJul 25, 2022, 12:03 AM

375 points

123 comments10 min readLW link 3 reviews

A Mechanistic Interpretability Analysis of Grokking

Neel Nanda and Tom Lieberum

Aug 15, 2022, 2:41 AM

373 points

48 comments36 min readLW link 1 review

(colab.research.google.com)

Counterarguments to the basic AI x-risk case

KatjaGraceOct 14, 2022, 1:00 PM

371 points

124 comments34 min readLW link 1 review

(aiimpacts.org)

Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover

Ajeya CotraJul 18, 2022, 7:06 PM

368 points

95 comments75 min readLW link 1 review

Accounting For College Costs

johnswentworthApr 1, 2022, 5:28 PM

366 points

41 comments7 min readLW link

Security Mindset: Lessons from 20+ years of Software Security Failures Relevant to AGI Alignment

elspoodJun 21, 2022, 11:55 PM

362 points

42 comments7 min readLW link 1 review

Staring into the abyss as a core life skill

benkuhnDec 22, 2022, 3:30 PM

354 points

22 comments12 min readLW link 1 review

(www.benkuhn.net)

MIRI announces new “Death With Dignity” strategy

Eliezer YudkowskyApr 2, 2022, 12:43 AM

354 points

546 comments18 min readLW link 1 review

What DALL-E 2 can and cannot do

Swimmer963 (Miranda Dixon-Luinenburg) May 1, 2022, 11:51 PM

353 points

303 comments9 min readLW link

Beware boasting about non-existent forecasting track records

Jotto999May 20, 2022, 7:20 PM

338 points

112 comments5 min readLW link 1 review

What should you change in response to an “emergency”? And AI risk

AnnaSalamonJul 18, 2022, 1:11 AM

337 points

60 comments6 min readLW link 1 review

Why I think strong general AI is coming soon

porbySep 28, 2022, 5:40 AM

336 points

141 comments34 min readLW link 1 review

Looking back on my alignment PhD

TurnTroutJul 1, 2022, 3:19 AM

334 points

66 comments11 min readLW link

Optimality is the tiger, and agents are its teeth

VeedracApr 2, 2022, 12:46 AM

327 points

44 comments16 min readLW link 1 review

Models Don’t “Get Reward”

Sam RingerDec 30, 2022, 10:37 AM

313 points

61 comments5 min readLW link 1 review

On how various plans miss the hard bits of the alignment challenge

So8resJul 12, 2022, 2:49 AM

313 points

89 comments29 min readLW link 3 reviews

Six Dimensions of Operational Adequacy in AGI Projects

Eliezer YudkowskyMay 30, 2022, 5:00 PM

310 points

66 comments13 min readLW link 1 review

Epistemic Legibility

ElizabethFeb 9, 2022, 6:10 PM

309 points

30 comments20 min readLW link 1 review

(acesounderglass.com)

Why Agent Foundations? An Overly Abstract Explanation

johnswentworthMar 25, 2022, 11:17 PM

302 points

58 comments8 min readLW link 1 review

A challenge for AGI organizations, and a challenge for readers

Rob Bensinger and Eliezer Yudkowsky

Dec 1, 2022, 11:11 PM

302 points

33 comments2 min readLW link

Two-year update on my personal AI timelines

Ajeya CotraAug 2, 2022, 11:07 PM

293 points

60 comments16 min readLW link

What Are You Tracking In Your Head?

johnswentworthJun 28, 2022, 7:30 PM

287 points

83 comments4 min readLW link 1 review

Mysteries of mode collapse

janusNov 8, 2022, 10:37 AM

284 points

57 comments14 min readLW link 1 review

Sazen

Duncan Sabien (Deactivated)Dec 21, 2022, 7:54 AM

281 points

83 comments12 min readLW link 2 reviews

We Choose To Align AI

johnswentworthJan 1, 2022, 8:06 PM

280 points

16 comments3 min readLW link 1 review

Don’t die with dignity; instead play to your outs

Jeffrey LadishApr 6, 2022, 7:53 AM

280 points

60 comments5 min readLW link

Is AI Progress Impossible To Predict?

alyssavanceMay 15, 2022, 6:30 PM

277 points

39 comments2 min readLW link

A central AI alignment problem: capabilities generalization, and the sharp left turn

So8resJun 15, 2022, 1:10 PM

272 points

55 comments10 min readLW link 1 review

Toni Kurz and the Insanity of Climbing Mountains

GeneSmithJul 3, 2022, 8:51 PM

271 points

67 comments11 min readLW link 2 reviews

Humans are very reliable agents

alyssavanceJun 16, 2022, 10:02 PM

269 points

35 comments3 min readLW link

12 interesting things I learned studying the discovery of nature’s laws

Ben PaceFeb 19, 2022, 11:39 PM

268 points

40 comments9 min readLW link 1 review

Comment reply: my low-quality thoughts on why CFAR didn’t get farther with a “real/efficacious art of rationality”

AnnaSalamonJun 9, 2022, 2:12 AM

261 points

63 comments17 min readLW link 1 review

Changing the world through slack & hobbies

Steven ByrnesJul 21, 2022, 6:11 PM

261 points

13 comments10 min readLW link