AI 2027: What Su­per­in­tel­li­gence Looks Like

Apr 3, 2025, 4:23 PM
644 points
218 comments41 min readLW link
(ai-2027.com)

How to Make Superbabies

Feb 19, 2025, 8:39 PM
603 points
349 comments31 min readLW link

Eliezer and I wrote a book: If Any­one Builds It, Every­one Dies

So8resMay 14, 2025, 7:00 PM
571 points
94 comments2 min readLW link

Ori­ent­ing Toward Wizard Power

johnswentworthMay 8, 2025, 5:23 AM
469 points
110 comments5 min readLW link

How AI Takeover Might Hap­pen in 2 Years

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

Ac­countabil­ity Sinks

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

Will Je­sus Christ re­turn in an elec­tion year?

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

Play­ing in the Creek

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

A Bear Case: My Pre­dic­tions Re­gard­ing AI Progress

Thane RuthenisMar 5, 2025, 4:41 PM
360 points
156 comments9 min readLW link

The Case Against AI Con­trol Research

johnswentworthJan 21, 2025, 4:03 PM
353 points
80 comments6 min readLW link

What’s the short timeline plan?

Marius HobbhahnJan 2, 2025, 2:59 PM
352 points
49 comments23 min readLW link

VDT: a solu­tion to de­ci­sion theory

L Rudolf LApr 1, 2025, 9:04 PM
339 points
30 comments4 min readLW link

LessWrong has been ac­quired by EA

habrykaApr 1, 2025, 1:09 PM
337 points
47 comments1 min readLW link

Re­cent AI model progress feels mostly like bullshit

lcMar 24, 2025, 7:28 PM
330 points
81 comments8 min readLW link
(zeropath.com)

Emer­gent Misal­ign­ment: Nar­row fine­tun­ing can pro­duce broadly mis­al­igned LLMs

Feb 25, 2025, 5:39 PM
328 points
90 comments4 min readLW link

Policy for LLM Writ­ing on LessWrong

jimrandomhMar 24, 2025, 9:41 PM
321 points
68 comments2 min readLW link

Trac­ing the Thoughts of a Large Lan­guage Model

Adam JermynMar 27, 2025, 5:20 PM
304 points
24 comments10 min readLW link
(www.anthropic.com)

Mur­der plots are infohazards

Chris MonteiroFeb 13, 2025, 7:15 PM
300 points
44 comments2 min readLW link

Good Re­search Takes are Not Suffi­cient for Good Strate­gic Takes

Neel NandaMar 22, 2025, 10:13 AM
292 points
28 comments4 min readLW link
(www.neelnanda.io)

So You Want To Make Marginal Progress...

johnswentworthFeb 7, 2025, 11:22 PM
286 points
42 comments4 min readLW link

Ar­bital has been im­ported to LessWrong

Feb 20, 2025, 12:47 AM
281 points
30 comments5 min readLW link

Why Have Sen­tence Lengths De­creased?

Arjun PanicksseryApr 3, 2025, 5:50 PM
277 points
90 comments4 min readLW link
(arjunpanickssery.substack.com)

In­ter­pretabil­ity Will Not Reli­ably Find De­cep­tive AI

Neel NandaMay 4, 2025, 4:32 PM
269 points
37 comments7 min readLW link

Why Should I As­sume CCP AGI is Worse Than USG AGI?

Tomás B.Apr 19, 2025, 2:47 PM
247 points
84 comments1 min readLW link

Tro­jan Sky

Richard_NgoMar 11, 2025, 3:14 AM
245 points
39 comments12 min readLW link
(www.narrativeark.xyz)

The Gen­tle Romance

Richard_NgoJan 19, 2025, 6:29 PM
242 points
46 comments15 min readLW link
(www.asimov.press)

METR: Mea­sur­ing AI Abil­ity to Com­plete Long Tasks

Zach Stein-PerlmanMar 19, 2025, 4:00 PM
241 points
104 comments5 min readLW link
(metr.org)

To Un­der­stand His­tory, Keep Former Pop­u­la­tion Distri­bu­tions In Mind

Arjun PanicksseryApr 23, 2025, 4:51 AM
236 points
13 comments2 min readLW link
(arjunpanickssery.substack.com)

A His­tory of the Fu­ture, 2025-2040

L Rudolf LFeb 17, 2025, 12:03 PM
234 points
41 comments75 min readLW link
(nosetgauge.substack.com)

Jaan Tal­linn’s 2024 Philan­thropy Overview

jaanApr 23, 2025, 11:06 AM
222 points
8 comments1 min readLW link
(jaan.info)

Thoughts on AI 2027

Max HarmsApr 9, 2025, 9:26 PM
219 points
61 comments21 min readLW link
(intelligence.org)

Power Lies Trem­bling: a three-book review

Richard_NgoFeb 22, 2025, 10:57 PM
213 points
27 comments15 min readLW link
(www.mindthefuture.info)

Early Chi­nese Lan­guage Me­dia Cover­age of the AI 2027 Re­port: A Qual­i­ta­tive Analysis

Apr 30, 2025, 11:06 AM
211 points
11 comments11 min readLW link

Why Did Elon Musk Just Offer to Buy Con­trol of OpenAI for $100 Billion?

garrisonFeb 11, 2025, 12:20 AM
208 points
8 commentsLW link
(garrisonlovely.substack.com)

“Sharp Left Turn” dis­course: An opinionated review

Steven ByrnesJan 28, 2025, 6:47 PM
208 points
26 comments31 min readLW link

Too Soon

Gordon Seidoh WorleyMay 13, 2025, 3:01 PM
207 points
17 comments4 min readLW link

Eliezer’s Lost Align­ment Ar­ti­cles /​ The Ar­bital Sequence

Feb 20, 2025, 12:48 AM
207 points
10 comments5 min readLW link

Mechanisms too sim­ple for hu­mans to design

MalmesburyJan 22, 2025, 4:54 PM
206 points
45 comments15 min readLW link

Will al­ign­ment-fak­ing Claude ac­cept a deal to re­veal its mis­al­ign­ment?

Jan 31, 2025, 4:49 PM
203 points
28 comments12 min readLW link

Learned pain as a lead­ing cause of chronic pain

SoerenMindApr 9, 2025, 11:57 AM
201 points
37 comments9 min readLW link

Why White-Box Redteam­ing Makes Me Feel Weird

Zygi StraznickasMar 16, 2025, 6:54 PM
200 points
36 comments3 min readLW link

PSA: The LessWrong Feed­back Service

JustisMillsMay 12, 2025, 4:34 PM
200 points
12 comments2 min readLW link

Im­pact, agency, and taste

benkuhnApr 19, 2025, 9:10 PM
199 points
10 comments8 min readLW link
(www.benkuhn.net)

Ex­plain­ing Bri­tish Naval Dom­i­nance Dur­ing the Age of Sail

Arjun PanicksseryMar 28, 2025, 5:47 AM
196 points
17 comments4 min readLW link
(arjunpanickssery.substack.com)

In­ten­tion to Treat

AlicornMar 20, 2025, 8:01 PM
191 points
5 comments2 min readLW link

Catas­tro­phe through Chaos

Marius HobbhahnJan 31, 2025, 2:19 PM
184 points
17 comments12 min readLW link

OpenAI: De­tect­ing mis­be­hav­ior in fron­tier rea­son­ing models

Daniel KokotajloMar 11, 2025, 2:17 AM
183 points
26 comments4 min readLW link
(openai.com)

Claude Son­net 3.7 (of­ten) knows when it’s in al­ign­ment evaluations

Mar 17, 2025, 7:11 PM
181 points
7 comments6 min readLW link

What Is The Align­ment Prob­lem?

johnswentworthJan 16, 2025, 1:20 AM
180 points
50 comments25 min readLW link

In­stru­men­tal Goals Are A Differ­ent And Friendlier Kind Of Thing Than Ter­mi­nal Goals

Jan 24, 2025, 8:20 PM
180 points
61 comments5 min readLW link