Where I agree and dis­agree with Eliezer

paulfchristiano19 Jun 2022 19:15 UTC
684 points
191 comments20 min readLW link

AGI Ruin: A List of Lethalities

Eliezer Yudkowsky5 Jun 2022 22:05 UTC
666 points
629 comments30 min readLW link

What an ac­tu­ally pes­simistic con­tain­ment strat­egy looks like

lc5 Apr 2022 0:19 UTC
510 points
133 comments6 min readLW link

Counter-the­ses on Sleep

Natália Coelho Mendonça21 Mar 2022 23:21 UTC
401 points
131 comments15 min readLW link

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

gwern9 Mar 2022 16:35 UTC
376 points
124 comments1 min readLW link
(www.gwern.net)

It’s Prob­a­bly Not Lithium

Natália Coelho Mendonça28 Jun 2022 21:24 UTC
347 points
112 comments27 min readLW link

What DALL-E 2 can and can­not do

Swimmer9631 May 2022 23:51 UTC
336 points
297 comments9 min readLW link

MIRI an­nounces new “Death With Dig­nity” strategy

Eliezer Yudkowsky2 Apr 2022 0:43 UTC
324 points
518 comments18 min readLW link

Reflec­tions on six months of fatherhood

jasoncrawford31 Jan 2022 5:28 UTC
321 points
21 comments4 min readLW link
(jasoncrawford.org)

Ac­count­ing For Col­lege Costs

johnswentworth1 Apr 2022 17:28 UTC
318 points
40 comments7 min readLW link

Lies Told To Children

Eliezer Yudkowsky14 Apr 2022 11:25 UTC
306 points
94 comments7 min readLW link

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

elspood21 Jun 2022 23:55 UTC
294 points
34 comments7 min readLW link

Epistemic Legibility

Elizabeth9 Feb 2022 18:10 UTC
280 points
28 comments20 min readLW link
(acesounderglass.com)

Is AI Progress Im­pos­si­ble To Pre­dict?

alyssavance15 May 2022 18:30 UTC
263 points
38 comments2 min readLW link

Six Di­men­sions of Oper­a­tional Ad­e­quacy in AGI Projects

Eliezer Yudkowsky30 May 2022 17:00 UTC
255 points
65 comments13 min readLW link

We Choose To Align AI

johnswentworth1 Jan 2022 20:06 UTC
247 points
15 comments3 min readLW link

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

Ben Pace19 Feb 2022 23:39 UTC
245 points
40 comments9 min readLW link

Be­ware boast­ing about non-ex­is­tent fore­cast­ing track records

Jotto99920 May 2022 19:20 UTC
241 points
109 comments5 min readLW link

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

Jeffrey Ladish6 Apr 2022 7:53 UTC
235 points
58 comments5 min readLW link

Why Agent Foun­da­tions? An Overly Ab­stract Explanation

johnswentworth25 Mar 2022 23:17 UTC
231 points
51 comments8 min readLW link

(briefly) RaDVaC and SMTM, two things we should be doing

Eliezer Yudkowsky12 Jan 2022 6:20 UTC
230 points
78 comments3 min readLW link

A Quick Guide to Con­fronting Doom

Ruby13 Apr 2022 19:30 UTC
222 points
36 comments2 min readLW link

Con­tra Hofs­tadter on GPT-3 Nonsense

rictic15 Jun 2022 21:53 UTC
222 points
18 comments2 min readLW link

An Ob­ser­va­tion of Vav­ilov Day

Elizabeth3 Jan 2022 21:10 UTC
219 points
42 comments3 min readLW link
(acesounderglass.com)

Edit­ing Ad­vice for LessWrong Users

JustisMills11 Apr 2022 16:32 UTC
215 points
13 comments6 min readLW link

AGI Safety FAQ /​ all-dumb-ques­tions-al­lowed thread

Aryeh Englander7 Jun 2022 5:47 UTC
215 points
488 comments4 min readLW link

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

AnnaSalamon9 Jun 2022 2:12 UTC
215 points
59 comments17 min readLW link

Re­plac­ing Karma with Good Heart To­kens (Worth $1!)

1 Apr 2022 9:31 UTC
211 points
191 comments4 min readLW link

Hu­mans are very re­li­able agents

alyssavance16 Jun 2022 22:02 UTC
206 points
27 comments3 min readLW link

New Scal­ing Laws for Large Lan­guage Models

1a3orn1 Apr 2022 20:41 UTC
205 points
20 comments5 min readLW link

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

So8res15 Jun 2022 13:10 UTC
200 points
36 comments10 min readLW link

Visi­ble Home­less­ness in SF: A Quick Break­down of Causes

alyssavance25 May 2022 1:40 UTC
193 points
40 comments2 min readLW link

Slow mo­tion videos as AI risk in­tu­ition pumps

Andrew_Critch14 Jun 2022 19:31 UTC
193 points
35 comments2 min readLW link

On sav­ing one’s world

Rob Bensinger17 May 2022 19:53 UTC
189 points
5 comments1 min readLW link

Moses and the Class Struggle

lsusr1 Apr 2022 11:55 UTC
188 points
24 comments5 min readLW link

Call For Distillers

johnswentworth4 Apr 2022 18:25 UTC
186 points
36 comments3 min readLW link

Pro­jec­tLawful.com: Eliezer’s lat­est story, past 1M words

Eliezer Yudkowsky11 May 2022 6:18 UTC
185 points
93 comments1 min readLW link

A con­crete bet offer to those with short AI timelines

9 Apr 2022 21:41 UTC
184 points
93 comments4 min readLW link

Benign Boundary Violations

Duncan_Sabien26 May 2022 6:48 UTC
184 points
83 comments18 min readLW link

dalle2 comments

nostalgebraist26 Apr 2022 5:30 UTC
183 points
13 comments13 min readLW link
(nostalgebraist.tumblr.com)

Post­mortem on DIY Re­com­bi­nant Covid Vaccine

caffemacchiavelli22 Jan 2022 14:12 UTC
177 points
27 comments5 min readLW link

Do a cost-benefit anal­y­sis of your tech­nol­ogy usage

TurnTrout27 Mar 2022 23:09 UTC
173 points
53 comments13 min readLW link

Op­ti­mal­ity is the tiger, and agents are its teeth

Veedrac2 Apr 2022 0:46 UTC
172 points
28 comments16 min readLW link

Have You Tried Hiring Peo­ple?

rank-biserial2 Mar 2022 2:06 UTC
172 points
120 comments8 min readLW link

We Are Con­jec­ture, A New Align­ment Re­search Startup

Connor Leahy8 Apr 2022 11:40 UTC
171 points
24 comments4 min readLW link

Look­ing back on my al­ign­ment PhD

TurnTrout1 Jul 2022 3:19 UTC
171 points
8 comments11 min readLW link

Rus­sia has In­vaded Ukraine

lsusr24 Feb 2022 7:52 UTC
165 points
270 comments3 min readLW link

What’s Up With Con­fus­ingly Per­va­sive Con­se­quen­tial­ism?

Raemon20 Jan 2022 19:22 UTC
164 points
88 comments4 min readLW link

Play­ing with DALL·E 2

Dave Orr7 Apr 2022 18:49 UTC
164 points
116 comments6 min readLW link

AI Could Defeat All Of Us Combined

HoldenKarnofsky9 Jun 2022 15:50 UTC
163 points
28 comments17 min readLW link
(www.cold-takes.com)