Sum­maries: Align­ment Fun­da­men­tals Curriculum

Leon LangSep 18, 2022, 1:08 PM
44 points
3 comments1 min readLW link
(docs.google.com)

Bay Sols­tice 2022 Call For Volunteers

Scott AlexanderSep 4, 2022, 6:44 AM
43 points
2 comments1 min readLW link

A Starter-kit for Ra­tion­al­ity Space

Jesse HooglandSep 1, 2022, 1:04 PM
43 points
0 comments1 min readLW link
(github.com)

Ge­or­gism in Space

harsimonySep 28, 2022, 4:05 PM
42 points
12 comments4 min readLW link
(harsimony.wordpress.com)

FDT is not di­rectly com­pa­rable to CDT and EDT

SMKSep 29, 2022, 2:42 PM
42 points
8 comments11 min readLW link

AI Gover­nance Needs Tech­ni­cal Work

MauSep 5, 2022, 10:28 PM
41 points
1 comment8 min readLW link

Covid 9/​1/​22: Meet the New Booster

ZviSep 1, 2022, 2:00 PM
41 points
6 comments14 min readLW link
(thezvi.wordpress.com)

The Defen­der’s Ad­van­tage of Interpretability

Marius HobbhahnSep 14, 2022, 2:05 PM
41 points
4 comments6 min readLW link

Tran­shu­man­ism, ge­netic en­g­ineer­ing, and the biolog­i­cal ba­sis of in­tel­li­gence.

fowlertmSep 14, 2022, 3:55 PM
41 points
23 comments1 min readLW link

Ap­pendix: How to run a suc­cess­ful Ham­ming circle

CFAR!DuncanSep 2, 2022, 12:22 AM
41 points
6 comments7 min readLW link

Over­ton Gym­nas­tics: An Ex­er­cise in Discomfort

Sep 5, 2022, 7:20 PM
40 points
15 comments4 min readLW link

When is in­tent al­ign­ment suffi­cient or nec­es­sary to re­duce AGI con­flict?

Sep 14, 2022, 7:39 PM
40 points
0 comments9 min readLW link

Katja Grace on Slow­ing Down AI, AI Ex­pert Sur­veys And Es­ti­mat­ing AI Risk

Michaël TrazziSep 16, 2022, 5:45 PM
40 points
2 comments3 min readLW link
(theinsideview.ai)

Sticky goals: a con­crete ex­per­i­ment for un­der­stand­ing de­cep­tive alignment

evhubSep 2, 2022, 9:57 PM
39 points
13 comments3 min readLW link

What are you for?

lsusrSep 6, 2022, 3:32 AM
39 points
5 comments1 min readLW link

Thoughts on AGI con­scious­ness /​ sentience

Steven ByrnesSep 8, 2022, 4:40 PM
38 points
37 comments6 min readLW link

There are no rules

unoptimalSep 23, 2022, 8:47 PM
38 points
2 comments5 min readLW link

FDT defects in a re­al­is­tic Twin Pri­son­ers’ Dilemma

SMKSep 15, 2022, 8:55 AM
38 points
1 comment26 min readLW link

Put Dirty Dishes in the Dishwasher

jefftkSep 10, 2022, 1:10 PM
37 points
16 comments1 min readLW link
(www.jefftk.com)

Fram­ing AI Childhoods

David UdellSep 6, 2022, 11:40 PM
37 points
8 comments4 min readLW link

Safety timelines: How long will it take to solve al­ign­ment?

Sep 19, 2022, 12:53 PM
37 points
7 comments6 min readLW link
(forum.effectivealtruism.org)

Ought will host a fac­tored cog­ni­tion “Lab Meet­ing”

Sep 9, 2022, 11:46 PM
35 points
1 comment1 min readLW link

How should Deep­Mind’s Chin­chilla re­vise our AI fore­casts?

Cleo NardoSep 15, 2022, 5:54 PM
35 points
12 comments13 min readLW link

Be­havi­our Man­i­folds and the Hes­sian of the To­tal Loss—Notes and Criticism

carboniferous_umbraculum Sep 3, 2022, 12:15 AM
35 points
5 comments6 min readLW link

D&D.Sci Septem­ber 2022: The Allo­ca­tion Helm

abstractapplicSep 16, 2022, 11:10 PM
34 points
34 comments1 min readLW link

Covid 9/​8/​22: Booster Boosting

ZviSep 8, 2022, 1:50 PM
34 points
9 comments24 min readLW link
(thezvi.wordpress.com)

[Question] Fore­cast­ing thread: How does AI risk level vary based on timelines?

eliflandSep 14, 2022, 11:56 PM
34 points
7 comments1 min readLW link

Bi­den should be ap­plauded for ap­point­ing Re­nee We­grzyn for ARPA-H

ChristianKlSep 18, 2022, 7:57 PM
34 points
0 comments2 min readLW link

Math­e­mat­i­cal Cir­cuits in Neu­ral Networks

Sean OsierSep 22, 2022, 3:48 AM
34 points
4 comments1 min readLW link
(www.youtube.com)

[Question] Why doesn’t China (or didn’t any­one) en­courage/​man­date elas­tomeric res­pi­ra­tors to con­trol COVID?

Wei DaiSep 17, 2022, 3:07 AM
34 points
15 comments1 min readLW link

Twit­ter Polls: Ev­i­dence is Evidence

ZviSep 20, 2022, 12:30 PM
34 points
8 comments7 min readLW link
(thezvi.wordpress.com)

Emer­gency Res­i­den­tial So­lar Jury-Rigging

jefftkSep 17, 2022, 2:30 AM
34 points
0 comments3 min readLW link
(www.jefftk.com)

90% of any­thing should be bad (& the pre­ci­sion-re­call trade­off)

cartografieSep 8, 2022, 1:20 AM
33 points
22 comments6 min readLW link

[Question] What’s the longest a sen­tient ob­server could sur­vive in the Dark Era?

RaemonSep 15, 2022, 8:43 AM
33 points
15 comments1 min readLW link

A Pin and a Bal­loon: An­thropic Frag­ility In­creases Chances of Ru­n­away Global Warm­ing

avturchinSep 11, 2022, 10:25 AM
33 points
23 comments52 min readLW link

[Question] Can some­one ex­plain to me why most re­searchers think al­ign­ment is prob­a­bly some­thing that is hu­manly tractable?

iamthouthouartiSep 3, 2022, 1:12 AM
32 points
11 comments1 min readLW link

Covid 9/​15/​22: Per­ma­nent Normal

ZviSep 15, 2022, 4:00 PM
32 points
9 comments20 min readLW link
(thezvi.wordpress.com)

On oxy­tocin-sen­si­tive neu­rons in au­di­tory cortex

Steven ByrnesSep 6, 2022, 12:54 PM
32 points
6 comments12 min readLW link

Guidelines for Mad Entrepreneurs

David UdellSep 16, 2022, 6:33 AM
31 points
0 comments11 min readLW link

[Question] Why are we sure that AI will “want” some­thing?

ShmiSep 16, 2022, 8:35 PM
31 points
57 comments1 min readLW link

AI Safety Endgame Stories

Ivan VendrovSep 28, 2022, 4:58 PM
31 points
11 comments11 min readLW link

New tool for ex­plor­ing EA Fo­rum, LessWrong and Align­ment Fo­rum—Tree of Tags

Filip SondejSep 13, 2022, 5:33 PM
31 points
2 comments1 min readLW link

Sha­har Avin On How To Reg­u­late Ad­vanced AI Systems

Michaël TrazziSep 23, 2022, 3:46 PM
31 points
0 comments4 min readLW link
(theinsideview.ai)

I Tripped and Be­came GPT! (And How This Up­dated My Timelines)

FrankophoneSep 1, 2022, 5:56 PM
31 points
0 comments4 min readLW link

Strat­egy For Con­di­tion­ing Gen­er­a­tive Models

Sep 1, 2022, 4:34 AM
31 points
4 comments18 min readLW link

Short story spec­u­lat­ing on pos­si­ble ram­ifi­ca­tions of AI on the art world

YitzSep 1, 2022, 9:15 PM
30 points
8 comments3 min readLW link
(archiveofourown.org)

Im­pact Shares For Spec­u­la­tive Projects

ElizabethSep 5, 2022, 6:00 PM
30 points
8 comments7 min readLW link
(acesounderglass.com)

Rep­re­sen­ta­tional Tethers: Ty­ing AI La­tents To Hu­man Ones

Paul BricmanSep 16, 2022, 2:45 PM
30 points
0 comments16 min readLW link

Unit Test Everything

DirectedEvolutionSep 29, 2022, 6:12 PM
30 points
0 comments8 min readLW link

Renor­mal­iza­tion: Why Big­ger is Simpler

tailcalledSep 14, 2022, 5:52 PM
30 points
5 comments1 min readLW link
(www.youtube.com)