chin­chilla’s wild implications

nostalgebraistJul 31, 2022, 1:18 AM
424 points
128 comments10 min readLW link1 review

How AI Takeover Might Hap­pen in 2 Years

joshcFeb 7, 2025, 5:10 PM
422 points
137 comments29 min readLW link
(x.com)

Failures in Kindness

silentbobMar 26, 2024, 9:30 PM
421 points
60 comments9 min readLW link

Trans­form­ers Rep­re­sent Belief State Geom­e­try in their Resi­d­ual Stream

Adam ShaiApr 16, 2024, 9:16 PM
419 points
100 comments12 min readLW link

Ugh fields

RokoApr 12, 2010, 5:06 PM
418 points
82 comments3 min readLW link

GPTs are Pre­dic­tors, not Imitators

Eliezer YudkowskyApr 8, 2023, 7:59 PM
416 points
100 comments3 min readLW link3 reviews

What We Learned from Briefing 70+ Law­mak­ers on the Threat from AI

leticiagarciaMay 27, 2025, 6:23 PM
415 points
10 comments16 min readLW link
(substack.com)

Ac­countabil­ity Sinks

Martin SustrikApr 22, 2025, 5:00 AM
415 points
57 comments15 min readLW link
(250bpm.substack.com)

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

Aug 29, 2022, 1:23 AM
413 points
90 comments37 min readLW link1 review

You Are Not Mea­sur­ing What You Think You Are Measuring

johnswentworthSep 20, 2022, 8:04 PM
411 points
45 comments8 min readLW link2 reviews

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

gwernMar 9, 2022, 4:35 PM
408 points
120 comments1 min readLW link1 review
(www.gwern.net)

That Alien Message

Eliezer YudkowskyMay 22, 2008, 5:55 AM
407 points
176 comments10 min readLW link

Bing Chat is blatantly, ag­gres­sively misaligned

evhubFeb 15, 2023, 5:29 AM
405 points
181 comments2 min readLW link1 review

Dy­ing Outside

HalFinneyOct 5, 2009, 2:45 AM
402 points
91 comments2 min readLW link

What Do We Mean By “Ra­tion­al­ity”?

Eliezer YudkowskyMar 16, 2009, 10:33 PM
396 points
19 comments6 min readLW link

Deep­Mind al­ign­ment team opinions on AGI ruin arguments

VikaAug 12, 2022, 9:06 PM
396 points
37 comments14 min readLW link1 review

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

Closed Limelike CurvesSep 3, 2024, 3:52 AM
395 points
36 comments1 min readLW link

Will Je­sus Christ re­turn in an elec­tion year?

Eric NeymanMar 24, 2025, 4:50 PM
394 points
54 comments4 min readLW link
(ericneyman.wordpress.com)

Ex­pect­ing Short In­fer­en­tial Distances

Eliezer YudkowskyOct 22, 2007, 11:42 PM
393 points
106 comments3 min readLW link

The Lens That Sees Its Flaws

Eliezer YudkowskySep 23, 2007, 12:10 AM
392 points
48 comments3 min readLW link

Reli­able Sources: The Story of David Gerard

TracingWoodgrainsJul 10, 2024, 7:50 PM
391 points
54 comments43 min readLW link

Reflec­tions on six months of fatherhood

jasoncrawfordJan 31, 2022, 5:28 AM
387 points
24 comments4 min readLW link1 review
(jasoncrawford.org)

The hos­tile telepaths problem

ValentineOct 27, 2024, 3:26 PM
383 points
89 comments15 min readLW link

State­ment on AI Ex­tinc­tion—Signed by AGI Labs, Top Aca­demics, and Many Other Notable Figures

Dan HMay 30, 2023, 9:05 AM
382 points
78 comments1 min readLW link1 review
(www.safe.ai)

Lies Told To Children

Eliezer YudkowskyApr 14, 2022, 11:25 AM
381 points
94 comments7 min readLW link1 review

Ap­plause Lights

Eliezer YudkowskySep 11, 2007, 6:31 PM
380 points
99 comments2 min readLW link

Play­ing in the Creek

HastingsApr 10, 2025, 5:39 PM
379 points
16 comments2 min readLW link
(hgreer.com)

In­tel­lec­tual Hip­sters and Meta-Contrarianism

Scott AlexanderSep 13, 2010, 9:36 PM
379 points
367 comments8 min readLW link

How to Ig­nore Your Emo­tions (while also think­ing you’re awe­some at emo­tions)

HazardJul 31, 2019, 1:34 PM
378 points
79 comments4 min readLW link4 reviews

There is way too much serendipity

MalmesburyJan 19, 2024, 7:37 PM
377 points
56 comments7 min readLW link

Re­ward is not the op­ti­miza­tion target

TurnTroutJul 25, 2022, 12:03 AM
376 points
123 comments10 min readLW link3 reviews

Anti-Aging: State of the Art

JackHDec 31, 2020, 7:07 PM
375 points
176 comments11 min readLW link1 review

Twelve Virtues of Rationality

Eliezer YudkowskyJan 1, 2006, 8:00 AM
375 points
13 comments7 min readLW link

Please don’t throw your mind away

TsviBTFeb 15, 2023, 9:41 PM
374 points
49 comments18 min readLW link1 review

A Mechanis­tic In­ter­pretabil­ity Anal­y­sis of Grokking

Aug 15, 2022, 2:41 AM
373 points
48 comments36 min readLW link1 review
(colab.research.google.com)

My hour of mem­o­ryless lucidity

Eric NeymanMay 4, 2024, 1:40 AM
373 points
35 comments5 min readLW link
(ericneyman.wordpress.com)

Coun­ter­ar­gu­ments to the ba­sic AI x-risk case

KatjaGraceOct 14, 2022, 1:00 PM
371 points
124 comments34 min readLW link1 review
(aiimpacts.org)

To listen well, get curious

benkuhnDec 13, 2020, 12:20 AM
369 points
37 comments4 min readLW link1 review
(www.benkuhn.net)

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 link1 review

How to have Poly­geni­cally Screened Children

GeneSmithMay 7, 2023, 4:01 PM
367 points
128 comments27 min readLW link1 review

Ac­count­ing For Col­lege Costs

johnswentworthApr 1, 2022, 5:28 PM
367 points
41 comments7 min readLW link

Sur­vival with­out dignity

L Rudolf LNov 4, 2024, 2:29 AM
367 points
29 comments15 min readLW link
(nosetgauge.substack.com)

How it feels to have your mind hacked by an AI

blakedJan 12, 2023, 12:33 AM
367 points
222 comments17 min readLW link

Not­ing an er­ror in Inad­e­quate Equilibria

Matthew BarnettFeb 8, 2023, 1:33 AM
366 points
60 comments2 min readLW link2 reviews

Work­ing hurts less than pro­cras­ti­nat­ing, we fear the twinge of starting

Eliezer YudkowskyJan 2, 2011, 12:15 AM
365 points
162 comments3 min readLW link

MIRI an­nounces new “Death With Dig­nity” strategy

Eliezer YudkowskyApr 2, 2022, 12:43 AM
363 points
546 comments18 min readLW link1 review

A Bear Case: My Pre­dic­tions Re­gard­ing AI Progress

Thane RuthenisMar 5, 2025, 4:41 PM
362 points
157 comments9 min readLW link

So­cial Dark Matter

Duncan Sabien (Inactive)Nov 16, 2023, 8:00 PM
362 points
127 comments34 min readLW link2 reviews

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 link1 review

Re­view: Planecrash

L Rudolf LDec 27, 2024, 2:18 PM
360 points
45 comments22 min readLW link
(nosetgauge.substack.com)