Se­quence Reread: Fake Beliefs [plus se­quence spotlight meta]

RaemonNov 2, 2022, 12:09 AM
27 points
3 comments1 min readLW link

Open Let­ter Against Reck­less Nu­clear Es­ca­la­tion and Use

Max TegmarkNov 3, 2022, 5:34 AM
27 points
25 comments1 min readLW link

Covid 11/​24/​22: Thanks for Good Health

ZviNov 24, 2022, 1:00 PM
26 points
4 comments8 min readLW link
(thezvi.wordpress.com)

Meme Dialects

jefftkNov 23, 2022, 9:30 PM
26 points
1 comment2 min readLW link
(www.jefftk.com)

Two New New­comb Variants

eva_Nov 14, 2022, 2:01 PM
26 points
24 comments3 min readLW link

(DIY) FMT for Anti-Aging & Biohacking

EternallyBlissfulNov 28, 2022, 3:49 PM
26 points
7 comments6 min readLW link

Recom­mend HAIST re­sources for as­sess­ing the value of RLHF-re­lated al­ign­ment research

Nov 5, 2022, 8:58 PM
26 points
9 comments3 min readLW link

[Question] Dumb and ill-posed ques­tion: Is con­cep­tual re­search like this MIRI pa­per on the shut­down prob­lem/​Cor­rigi­bil­ity “real”

joraineNov 24, 2022, 5:08 AM
26 points
11 comments1 min readLW link

Re­mem­ber to trans­late your thoughts back again

brookNov 1, 2022, 8:49 AM
25 points
11 comments3 min readLW link
(forum.effectivealtruism.org)

In Defence of Tem­po­ral Dis­count­ing in Longter­mist Ethics

DragonGodNov 13, 2022, 9:54 PM
25 points
4 commentsLW link

AI Safety Un­con­fer­ence NeurIPS 2022

OrpheusNov 7, 2022, 3:39 PM
25 points
0 commentsLW link
(aisafetyevents.org)

[Question] Is there some rea­son LLMs haven’t seen broader use?

tailcalledNov 16, 2022, 8:04 PM
25 points
27 comments1 min readLW link

Me­satrans­la­tion and Metatranslation

jdpNov 9, 2022, 6:46 PM
25 points
4 comments11 min readLW link

Distil­la­tion of “How Likely Is De­cep­tive Align­ment?”

NickGabsNov 18, 2022, 4:31 PM
24 points
4 comments10 min readLW link

Prevent­ing atheroscle­ro­sis, the eas­iest way to im­prove your life ex­pec­tancy?

Eli_Nov 29, 2022, 8:05 PM
24 points
9 comments15 min readLW link

In­ter­cept ar­ti­cle about lab accidents

ChristianKlNov 7, 2022, 9:10 PM
23 points
9 comments1 min readLW link
(theintercept.com)

Covid 11/​3/​22: Ask­ing Forgiveness

ZviNov 3, 2022, 1:50 PM
23 points
3 comments6 min readLW link
(thezvi.wordpress.com)

Solv­ing for the op­ti­mal work-life bal­ance with ge­o­met­ric rationality

Eric NeymanNov 28, 2022, 5:02 PM
23 points
1 comment8 min readLW link

[Question] Why don’t we have self driv­ing cars yet?

Linda LinseforsNov 14, 2022, 12:19 PM
22 points
16 comments1 min readLW link

AI Safety Micro­grant Round

Chris_LeongNov 14, 2022, 4:25 AM
22 points
1 commentLW link

[Question] EA (& AI Safety) has over­es­ti­mated its pro­jected fund­ing — which de­ci­sions must be re­vised?

Cleo NardoNov 11, 2022, 1:50 PM
22 points
7 comments1 min readLW link
(forum.effectivealtruism.org)

Ad­ver­sar­ial Pri­ors: Not Pay­ing Peo­ple to Lie to You

eva_Nov 10, 2022, 2:29 AM
22 points
9 comments3 min readLW link

Reflec­tive Consequentialism

Adam ZernerNov 18, 2022, 11:56 PM
21 points
14 comments4 min readLW link

[Question] When do you vi­su­al­ize (or not) while do­ing math?

Alex_AltairNov 23, 2022, 8:15 PM
21 points
9 comments1 min readLW link

EA & LW Fo­rums Weekly Sum­mary (14th Nov − 27th Nov 22′)

Zoe WilliamsNov 29, 2022, 11:00 PM
21 points
1 commentLW link

AI Fore­cast­ing Re­search Ideas

JsevillamolNov 17, 2022, 5:37 PM
21 points
2 commentsLW link

A Walk­through of In-Con­text Learn­ing and In­duc­tion Heads (w/​ Charles Frye) Part 1 of 2

Neel NandaNov 22, 2022, 5:12 PM
20 points
0 comments1 min readLW link
(www.youtube.com)

Austin LW meetup notes: The FTX Affair

jchanNov 22, 2022, 2:01 PM
20 points
3 comments16 min readLW link

En­tropy Scal­ing And In­trin­sic Me­mory

Nov 15, 2022, 6:11 PM
20 points
5 comments5 min readLW link

Mastodon Replies as Comments

jefftkNov 17, 2022, 8:10 PM
20 points
0 comments1 min readLW link
(www.jefftk.com)

Google Search as a Washed Up Ser­vice Dog: “I HALP!”

ShmiNov 7, 2022, 7:02 AM
20 points
8 comments1 min readLW link

Lazy Python Ar­gu­ment Parsing

jefftkNov 3, 2022, 2:20 AM
20 points
3 comments1 min readLW link
(www.jefftk.com)

4 Key As­sump­tions in AI Safety

PrometheusNov 7, 2022, 10:50 AM
20 points
5 comments7 min readLW link

Con­ver­sa­tions on Al­co­hol Consumption

AnnapurnaNov 1, 2022, 5:09 AM
20 points
6 comments9 min readLW link

Op­por­tu­ni­ties that sur­prised us dur­ing our Clearer Think­ing Re­grants program

spencergNov 7, 2022, 1:09 PM
20 points
0 commentsLW link

Science and Math

lsusrNov 27, 2022, 4:05 AM
19 points
6 comments1 min readLW link

Three Align­ment Schemas & Their Problems

Shoshannah TekofskyNov 26, 2022, 4:25 AM
19 points
1 comment6 min readLW link

The Fu­til­ity of Sta­tus and Signalling

Ape in the coatNov 13, 2022, 5:14 PM
19 points
4 comments3 min readLW link

[simu­la­tion] 4chan user claiming to be the at­tor­ney hired by Google’s sen­tient chat­bot LaMDA shares wild de­tails of encounter

janusNov 10, 2022, 9:39 PM
19 points
1 comment13 min readLW link
(generative.ink)

EA & LW Fo­rums Weekly Sum­mary (7th Nov − 13th Nov 22′)

Zoe WilliamsNov 16, 2022, 3:04 AM
19 points
0 commentsLW link

Why is fiber good for you?

bracesNov 2, 2022, 2:04 AM
18 points
2 comments2 min readLW link

di­v­ine carrot

Alok SinghNov 10, 2022, 8:50 PM
18 points
2 comments1 min readLW link
(alok.github.io)

Me­tac­u­lus is seek­ing Soft­ware Engineers

dschwarzNov 5, 2022, 12:42 AM
18 points
0 comments1 min readLW link
(apply.workable.com)

Mind is uncountable

Filip SondejNov 2, 2022, 11:51 AM
18 points
22 commentsLW link

Cor­rigi­bil­ity Via Thought-Pro­cess Deference

Thane RuthenisNov 24, 2022, 5:06 PM
18 points
5 comments9 min readLW link

[Question] Is there a good way to award a fixed prize in a pre­dic­tion con­test?

jchanNov 2, 2022, 9:37 PM
18 points
5 comments1 min readLW link

The two con­cep­tions of Ac­tive In­fer­ence: an in­tel­li­gence ar­chi­tec­ture and a the­ory of agency

Roman LeventovNov 16, 2022, 9:30 AM
18 points
0 comments4 min readLW link

[Question] Who holds all the USDT?

ChristianKlNov 25, 2022, 11:58 AM
17 points
6 comments1 min readLW link

[Book Re­view] “Sta­tion Eleven” by Emily St. John Mandel

lsusrNov 7, 2022, 5:56 AM
17 points
1 comment1 min readLW link

[Video] How hav­ing Fast Fourier Trans­forms sooner could have helped with Nu­clear Disar­ma­ment—Veritaserum

mako yassNov 3, 2022, 9:04 PM
17 points
1 commentLW link