How cur­ing ag­ing could help progress

jasoncrawfordMay 22, 2022, 10:43 PM
52 points
19 comments1 min readLW link
(rootsofprogress.org)

[Question] Help! What do I say at my wed­ding?

Jonathan TaskMay 22, 2022, 8:08 PM
7 points
10 comments1 min readLW link

Ad­ver­sar­ial at­tacks and op­ti­mal control

JanMay 22, 2022, 6:22 PM
17 points
7 comments8 min readLW link
(universalprior.substack.com)

What kinds of al­gorithms do multi-hu­man imi­ta­tors learn?

May 22, 2022, 2:27 PM
20 points
0 comments3 min readLW link

Are hu­man imi­ta­tors su­per­hu­man mod­els with ex­plicit con­straints on ca­pa­bil­ities?

Chris van MerwijkMay 22, 2022, 12:46 PM
41 points
3 comments1 min readLW link

The value of x-risk reduction

NathanBarnardMay 22, 2022, 7:44 AM
4 points
0 comments4 min readLW link

On The Spec­trum, On The Guest List

party girlMay 22, 2022, 3:31 AM
24 points
6 comments1 min readLW link
(onthespectrumontheguestlist.substack.com)

An Agent Based Con­scious­ness Model (un­for­tu­nately it’s not com­putable)

Logan ZoellnerMay 21, 2022, 11:00 PM
6 points
2 comments8 min readLW link

Wormy the Worm

River LewisMay 21, 2022, 3:34 PM
3 points
23 comments5 min readLW link
(heytraveler.substack.com)

Philo­soph­i­cal con­sid­er­a­tions of ces­sa­tion of brain activity

clockworkMay 21, 2022, 3:18 PM
9 points
6 comments1 min readLW link

How Big Are Covid Par­ti­cles?

jefftkMay 21, 2022, 2:00 PM
29 points
5 comments3 min readLW link
(www.jefftk.com)

[Short ver­sion] In­for­ma­tion Loss --> Basin flatness

Vivek HebbarMay 21, 2022, 12:59 PM
12 points
0 comments1 min readLW link

In­for­ma­tion Loss --> Basin flatness

Vivek HebbarMay 21, 2022, 12:58 PM
62 points
31 comments7 min readLW link

The Fu­ture of Nu­clear War

avturchinMay 21, 2022, 7:52 AM
33 points
1 comment34 min readLW link

Clar­ify­ing what ELK is try­ing to achieve

Towards_KeeperhoodMay 21, 2022, 7:34 AM
22 points
1 comment5 min readLW link

[re­tracted] A re­ally sim­plis­tic ex­per­i­ment for LessWrong and /​r/​SneerClub

Nicholas / Heather KrossMay 21, 2022, 5:52 AM
−1 points
32 comments1 min readLW link

[Question] Who is available for con­tract work? (A la the Hacker News “Who Wants To Be Hired” threads)

nonzerosumMay 20, 2022, 11:59 PM
12 points
1 comment1 min readLW link

[Question] Why does gra­di­ent de­scent always work on neu­ral net­works?

MichaelDickensMay 20, 2022, 9:13 PM
15 points
11 comments1 min readLW link

Be­ware boast­ing about non-ex­is­tent fore­cast­ing track records

Jotto999May 20, 2022, 7:20 PM
338 points
112 comments5 min readLW link1 review

How RL Agents Be­have When Their Ac­tions Are Mod­ified? [Distil­la­tion post]

PabloAMCMay 20, 2022, 6:47 PM
22 points
0 comments8 min readLW link

Over-digi­tal­iza­tion: A Pre­lude to Analo­gia (Chap­ter 6)

Justin BullockMay 20, 2022, 4:39 PM
3 points
0 comments13 min readLW link

Pod­cast: Spencer Green­berg talks to me about deal­ing with our group­struck­ness and boundedness

KatjaGraceMay 20, 2022, 4:20 AM
28 points
0 comments1 min readLW link
(worldspiritsockpuppet.com)

For­mula for a Shortage

ZviMay 19, 2022, 7:30 PM
57 points
9 comments24 min readLW link
(thezvi.wordpress.com)

Procla­ma­tion of game-the­o­retic emergence

dr_diagorasMay 19, 2022, 6:09 PM
−4 points
2 comments1 min readLW link

[Question] How has the to­tal amount of gain-of-func­tion re­search wor­ld­wide grown/​shrunk over time?

johnswentworthMay 19, 2022, 3:57 PM
29 points
7 comments1 min readLW link

14 Tech­niques to Ac­cel­er­ate Your Learning

May 19, 2022, 1:59 PM
66 points
10 comments11 min readLW link

Covid 5/​19/​22: The Law of Five

ZviMay 19, 2022, 12:20 PM
53 points
2 comments11 min readLW link
(thezvi.wordpress.com)

[Question] Should you kiss it bet­ter?

Yair HalberstadtMay 19, 2022, 3:58 AM
9 points
14 comments1 min readLW link

Look­ing for AI /​ Ap­pli­ca­tion Eng­ineer @ OpenPrin­ci­ples—Help peo­ple al­ign ac­tions with principles

ti_guoMay 19, 2022, 3:23 AM
1 point
0 comments1 min readLW link

Fem­i­nism and Femininity

NathanBarnardMay 18, 2022, 10:53 PM
4 points
8 comments6 min readLW link

[Question] What’s up with the re­cent mon­key­pox cases?

johnswentworthMay 18, 2022, 10:06 PM
61 points
27 comments1 min readLW link

We have achieved Noob Gains in AI

phdeadMay 18, 2022, 8:56 PM
118 points
20 comments7 min readLW link

A pos­si­ble check against mo­ti­vated rea­son­ing us­ing elicit.org

david reinsteinMay 18, 2022, 8:52 PM
3 points
0 comments1 min readLW link

Read­ing the ethi­cists: A re­view of ar­ti­cles on AI in the jour­nal Science and Eng­ineer­ing Ethics

Charlie SteinerMay 18, 2022, 8:52 PM
50 points
8 comments14 min readLW link

Max­ent and Ab­strac­tions: Cur­rent Best Arguments

johnswentworthMay 18, 2022, 7:54 PM
33 points
2 comments3 min readLW link

Fram­ing Practicum: Dy­namic Programming

aysajanMay 18, 2022, 6:16 PM
10 points
5 comments5 min readLW link

How to get into AI safety research

Stuart_ArmstrongMay 18, 2022, 6:05 PM
44 points
7 comments1 min readLW link

A bridge to Dath Ilan? Im­proved gov­er­nance on the crit­i­cal path to AI al­ign­ment.

Jackson WagnerMay 18, 2022, 3:51 PM
24 points
0 comments12 min readLW link

Un­der­stand­ing Gato’s Su­per­vised Re­in­force­ment Learning

lorepieriMay 18, 2022, 11:08 AM
3 points
5 comments1 min readLW link
(lorenzopieri.com)

Gato’s Gen­er­al­i­sa­tion: Pre­dic­tions and Ex­per­i­ments I’d Like to See

Oliver SourbutMay 18, 2022, 7:15 AM
43 points
3 comments10 min readLW link

I just watched the Open C3 Sub­com­mit­tee Hear­ing on Uniden­ti­fied Ae­rial Phenom­ena (UFOs). Here’s a suc­cinct sum­mary and com­men­tary + some background

mako yassMay 18, 2022, 4:15 AM
27 points
22 comments4 min readLW link

Den­ver, CO City Park Meetup

paleboneMay 18, 2022, 3:54 AM
2 points
0 comments1 min readLW link

Work­day Air Qual­ity Measurements

jefftkMay 18, 2022, 2:10 AM
18 points
1 comment1 min readLW link
(www.jefftk.com)

Fea­ture re­quest: draft comments

DirectedEvolutionMay 17, 2022, 9:21 PM
9 points
3 comments1 min readLW link

Pop­u­lar ed­u­ca­tion in Swe­den: much more than you wanted to know

Henrik KarlssonMay 17, 2022, 8:07 PM
118 points
3 comments11 min readLW link
(escapingflatland.substack.com)

On sav­ing one’s world

Rob BensingerMay 17, 2022, 7:53 PM
192 points
4 comments1 min readLW link

Pro­posal: Twit­ter dis­like button

KatjaGraceMay 17, 2022, 7:40 PM
13 points
7 comments1 min readLW link
(worldspiritsockpuppet.com)

BERI is seek­ing new col­lab­o­ra­tors (2022)

sawyerMay 17, 2022, 5:33 PM
1 point
0 comments1 min readLW link

For­mula for Dy­ing Babies

ZviMay 17, 2022, 4:50 PM
88 points
12 comments6 min readLW link
(thezvi.wordpress.com)

Ac­tion­able-guidance and roadmap recom­men­da­tions for the NIST AI Risk Man­age­ment Framework

May 17, 2022, 3:26 PM
26 points
0 comments3 min readLW link