AGI Ruin: A List of Lethalities

Eliezer Yudkowsky5 Jun 2022 22:05 UTC
840 points
670 comments30 min readLW link

Where I agree and dis­agree with Eliezer

paulfchristiano19 Jun 2022 19:15 UTC
839 points
212 comments20 min readLW link

What an ac­tu­ally pes­simistic con­tain­ment strat­egy looks like

lc5 Apr 2022 0:19 UTC
611 points
134 comments6 min readLW link

Simulators

janus2 Sep 2022 12:45 UTC
602 points
114 comments41 min readLW link
(generative.ink)

Let’s think about slow­ing down AI

KatjaGrace22 Dec 2022 17:40 UTC
509 points
179 comments38 min readLW link
(aiimpacts.org)

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

Elizabeth16 Oct 2022 17:40 UTC
448 points
111 comments12 min readLW link
(acesounderglass.com)

It’s Prob­a­bly Not Lithium

Natália Coelho Mendonça28 Jun 2022 21:24 UTC
440 points
181 comments28 min readLW link

The Redac­tion Machine

Ben20 Sep 2022 22:03 UTC
436 points
41 comments27 min readLW link

Counter-the­ses on Sleep

Natália Coelho Mendonça21 Mar 2022 23:21 UTC
420 points
129 comments15 min readLW link

Los­ing the root for the tree

Adam Zerner20 Sep 2022 4:53 UTC
409 points
27 comments9 min readLW link

chin­chilla’s wild implications

nostalgebraist31 Jul 2022 1:18 UTC
401 points
124 comments11 min readLW link

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

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

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

29 Aug 2022 1:23 UTC
388 points
87 comments38 min readLW link

Deep­Mind al­ign­ment team opinions on AGI ruin arguments

Vika12 Aug 2022 21:06 UTC
375 points
36 comments14 min readLW link

Reflec­tions on six months of fatherhood

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

Coun­ter­ar­gu­ments to the ba­sic AI x-risk case

KatjaGrace14 Oct 2022 13:00 UTC
359 points
122 comments34 min readLW link
(aiimpacts.org)

A Mechanis­tic In­ter­pretabil­ity Anal­y­sis of Grokking

15 Aug 2022 2:41 UTC
357 points
45 comments36 min readLW link
(colab.research.google.com)

What DALL-E 2 can and can­not do

Swimmer963 (Miranda Dixon-Luinenburg) 1 May 2022 23:51 UTC
352 points
303 comments9 min readLW link

Ac­count­ing For Col­lege Costs

johnswentworth1 Apr 2022 17:28 UTC
350 points
41 comments7 min readLW link

Lies Told To Children

Eliezer Yudkowsky14 Apr 2022 11:25 UTC
348 points
89 comments7 min readLW link

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

Ajeya Cotra18 Jul 2022 19:06 UTC
343 points
92 comments84 min readLW link

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

elspood21 Jun 2022 23:55 UTC
342 points
41 comments7 min readLW link

MIRI an­nounces new “Death With Dig­nity” strategy

Eliezer Yudkowsky2 Apr 2022 0:43 UTC
331 points
532 comments18 min readLW link

You Are Not Mea­sur­ing What You Think You Are Measuring

johnswentworth20 Sep 2022 20:04 UTC
328 points
38 comments8 min readLW link

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

AnnaSalamon18 Jul 2022 1:11 UTC
324 points
59 comments6 min readLW link

Why I think strong gen­eral AI is com­ing soon

porby28 Sep 2022 5:40 UTC
312 points
138 comments34 min readLW link

Look­ing back on my al­ign­ment PhD

TurnTrout1 Jul 2022 3:19 UTC
308 points
63 comments11 min readLW link

A challenge for AGI or­ga­ni­za­tions, and a challenge for readers

1 Dec 2022 23:11 UTC
295 points
33 comments2 min readLW link

Re­ward is not the op­ti­miza­tion target

TurnTrout25 Jul 2022 0:03 UTC
291 points
109 comments10 min readLW link

Epistemic Legibility

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

Two-year up­date on my per­sonal AI timelines

Ajeya Cotra2 Aug 2022 23:07 UTC
287 points
60 comments16 min readLW link

Six Di­men­sions of Oper­a­tional Ad­e­quacy in AGI Projects

Eliezer Yudkowsky30 May 2022 17:00 UTC
286 points
64 comments13 min readLW link

Be­ware boast­ing about non-ex­is­tent fore­cast­ing track records

Jotto99920 May 2022 19:20 UTC
286 points
111 comments5 min readLW link

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

So8res12 Jul 2022 2:49 UTC
281 points
78 comments29 min readLW link

Is AI Progress Im­pos­si­ble To Pre­dict?

alyssavance15 May 2022 18:30 UTC
277 points
39 comments2 min readLW link

Why Agent Foun­da­tions? An Overly Ab­stract Explanation

johnswentworth25 Mar 2022 23:17 UTC
277 points
54 comments8 min readLW link

Models Don’t “Get Re­ward”

Sam Ringer30 Dec 2022 10:37 UTC
277 points
58 comments5 min readLW link

Op­ti­mal­ity is the tiger, and agents are its teeth

Veedrac2 Apr 2022 0:46 UTC
276 points
36 comments16 min readLW link

Star­ing into the abyss as a core life skill

benkuhn22 Dec 2022 15:30 UTC
273 points
15 comments12 min readLW link
(www.benkuhn.net)

We Choose To Align AI

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

Mys­ter­ies of mode collapse

janus8 Nov 2022 10:37 UTC
271 points
50 comments14 min readLW link

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

So8res15 Jun 2022 13:10 UTC
271 points
49 comments10 min readLW link

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

Jeffrey Ladish6 Apr 2022 7:53 UTC
266 points
59 comments5 min readLW link

Hu­mans are very re­li­able agents

alyssavance16 Jun 2022 22:02 UTC
258 points
35 comments3 min readLW link

AI al­ign­ment is dis­tinct from its near-term applications

paulfchristiano13 Dec 2022 7:10 UTC
253 points
21 comments2 min readLW link
(ai-alignment.com)

Chang­ing the world through slack & hobbies

Steven Byrnes21 Jul 2022 18:11 UTC
251 points
13 comments10 min readLW link

So, geez there’s a lot of AI con­tent these days

Raemon6 Oct 2022 21:32 UTC
250 points
140 comments6 min readLW link

What Are You Track­ing In Your Head?

johnswentworth28 Jun 2022 19:30 UTC
249 points
76 comments4 min readLW link

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

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

New Scal­ing Laws for Large Lan­guage Models

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