A de­scrip­tive, not pre­scrip­tive, overview of cur­rent AI Align­ment Research

Jun 6, 2022, 9:59 PM
139 points
21 comments7 min readLW link

Ra­tion­al­ist Meetup—Lyn­gby Den­mark 2022-07-03

Carl DybdahlJun 6, 2022, 8:35 PM
6 points
1 comment1 min readLW link

Micro­phone on Elec­tric Man­dolin II

jefftkJun 6, 2022, 8:30 PM
9 points
0 comments2 min readLW link
(www.jefftk.com)

We haven’t quit evolu­tion [short]

the gears to ascensionJun 6, 2022, 7:07 PM
5 points
3 comments2 min readLW link

Grokking “Fore­cast­ing TAI with biolog­i­cal an­chors”

anson.hoJun 6, 2022, 6:58 PM
38 points
0 comments14 min readLW link

DALL-E 2 - Unoffi­cial Nat­u­ral Lan­guage Image Edit­ing, Art Cri­tique Survey

bakztfutureJun 6, 2022, 6:27 PM
0 points
0 comments1 min readLW link
(bakztfuture.substack.com)

We Should Break Up Elite Colleges

sahajshardaJun 6, 2022, 6:15 PM
−1 points
0 comments1 min readLW link
(sahajsharda.substack.com)

[Question] What board games would you recom­mend?

Yair HalberstadtJun 6, 2022, 4:38 PM
16 points
32 comments1 min readLW link

[Question] Health & Lifestyle In­ter­ven­tions With Heavy-Tailed Out­comes?

MondSemmelJun 6, 2022, 4:26 PM
12 points
9 comments1 min readLW link

Read­ing the ethi­cists 2: Hunt­ing for AI al­ign­ment papers

Charlie SteinerJun 6, 2022, 3:49 PM
24 points
2 comments7 min readLW link

Tran­script of a Twit­ter Dis­cus­sion on EA from June 2022

ZviJun 6, 2022, 1:50 PM
85 points
4 comments1 min readLW link
(thezvi.wordpress.com)

Some ideas for fol­low-up pro­jects to Red­wood Re­search’s re­cent paper

JanBJun 6, 2022, 1:29 PM
10 points
0 comments7 min readLW link

Give the model a model-builder

Adam JermynJun 6, 2022, 12:21 PM
3 points
0 comments5 min readLW link

[Question] What jour­nal­ing prompts do you use?

ChristianKlJun 6, 2022, 11:35 AM
13 points
5 comments1 min readLW link

Why do some peo­ple try to make AGI?

TekhneMakreJun 6, 2022, 9:14 AM
14 points
7 comments3 min readLW link

Miriam Ye­vick on why both sym­bols and net­works are nec­es­sary for ar­tifi­cial minds

Bill BenzonJun 6, 2022, 8:34 AM
1 point
0 comments4 min readLW link

Op­ti­miza­tion and Ad­e­quacy in Five Bullets

james.lucassenJun 6, 2022, 5:48 AM
35 points
2 comments4 min readLW link
(jlucassen.com)

Why agents are powerful

Daniel KokotajloJun 6, 2022, 1:37 AM
37 points
7 comments7 min readLW link

Episte­molog­i­cal Vigilance for Alignment

adamShimiJun 6, 2022, 12:27 AM
66 points
11 comments10 min readLW link

AGI Ruin: A List of Lethalities

Eliezer YudkowskyJun 5, 2022, 10:05 PM
940 points
708 comments30 min readLW link3 reviews

Teach­ing all things to all peo­ple in all ways

AnonymousJun 5, 2022, 9:38 PM
1 point
2 comments10 min readLW link

Noisy en­vi­ron­ment reg­u­late util­ity maximizers

Niclas KupperJun 5, 2022, 6:48 PM
4 points
0 comments7 min readLW link

Ex­pected Value vs. Ex­pected Growth

tom-pollakJun 5, 2022, 6:48 PM
3 points
1 comment2 min readLW link

North­boro Air Qual­ity Measurement

jefftkJun 5, 2022, 5:50 PM
9 points
0 comments1 min readLW link
(www.jefftk.com)

New co­op­er­a­tion mechanism—quadratic fund­ing with­out a match­ing pool

Filip SondejJun 5, 2022, 1:55 PM
11 points
0 comments5 min readLW link

The Fourth Arena 2: New be­ings in time

Bill BenzonJun 5, 2022, 1:30 PM
1 point
0 comments2 min readLW link

Rus­sian x-risks newslet­ter May 2022 + short his­tory of “method­ol­o­gists”

avturchinJun 5, 2022, 11:50 AM
23 points
4 comments2 min readLW link

Some ques­tions I’ve been pon­der­ing...

Dalton MaberyJun 5, 2022, 4:21 AM
1 point
3 comments1 min readLW link

Rein­vent­ing the wheel

jasoncrawfordJun 4, 2022, 10:39 PM
78 points
13 comments2 min readLW link
(rootsofprogress.org)

What do you do to de­liber­ately prac­tice?

hathJun 4, 2022, 10:20 PM
26 points
9 comments2 min readLW link

Quick Look: Asymp­tomatic Her­pes Shedding

ElizabethJun 4, 2022, 9:40 PM
37 points
4 comments2 min readLW link
(acesounderglass.com)

Meetup in SF, June 11: Progress Stud­ies + Effec­tive Altruism

Jun 4, 2022, 9:30 PM
7 points
0 comments1 min readLW link

How to pur­sue a ca­reer in tech­ni­cal AI alignment

Charlie Rogers-SmithJun 4, 2022, 9:11 PM
69 points
1 comment39 min readLW link

Open & Wel­come Thread—June 2022

MondSemmelJun 4, 2022, 7:27 PM
8 points
30 comments1 min readLW link

The Fourth Arena: What’s Up in the world these days? We’re mov­ing to a new, a new what?

Bill BenzonJun 4, 2022, 7:07 PM
2 points
0 comments3 min readLW link

Towards a For­mal­i­sa­tion of Re­turns on Cog­ni­tive Rein­vest­ment (Part 1)

DragonGodJun 4, 2022, 6:42 PM
17 points
11 comments13 min readLW link

[Question] Does quan­tum me­chan­ics pre­dict all the effects of rel­a­tivity ex­cept grav­ity?

EniScienJun 4, 2022, 1:52 PM
4 points
2 comments1 min readLW link

Deep Learn­ing Sys­tems Are Not Less In­ter­pretable Than Logic/​Prob­a­bil­ity/​Etc

johnswentworthJun 4, 2022, 5:41 AM
160 points
55 comments2 min readLW link1 review

An­nounc­ing the Align­ment of Com­plex Sys­tems Re­search Group

Jun 4, 2022, 4:10 AM
91 points
20 comments5 min readLW link

Eter­nal youth as eter­nal suffering

ShmiJun 4, 2022, 1:48 AM
7 points
2 comments1 min readLW link

D&D.Sci June 2022: A God­dess Tried To Rein­car­nate Me Into A Fan­tasy World, But I In­sisted On Us­ing Data Science To Select An Op­ti­mal Com­bi­na­tion Of Cheat Skills!

abstractapplicJun 4, 2022, 1:28 AM
40 points
22 comments3 min readLW link

The Bur­den of Worldbuilding

lsusrJun 4, 2022, 1:15 AM
27 points
12 comments1 min readLW link

[Question] Longter­mist Con­se­quences of a New Dark Age?

David UdellJun 3, 2022, 11:00 PM
7 points
3 comments1 min readLW link

Just Say No to Utilitarianism

Arjun PanicksseryJun 3, 2022, 10:59 PM
3 points
0 comments1 min readLW link
(arjunpanickssery.substack.com)

The STEM Attractor

David UdellJun 3, 2022, 10:21 PM
12 points
0 comments2 min readLW link

Book Re­view: Talent

ZviJun 3, 2022, 8:10 PM
70 points
19 comments79 min readLW link
(thezvi.wordpress.com)

On The Spec­trum, On The Guest List: (iii) Etiquette

party girlJun 3, 2022, 6:44 PM
7 points
1 comment8 min readLW link
(onthespectrumontheguestlist.substack.com)

Give the AI safe tools

Adam JermynJun 3, 2022, 5:04 PM
3 points
0 comments4 min readLW link

Ra­tion­al­ity camps in Oxford for 16-20 yo: Ap­ply by June 12th

Anna GajdovaJun 3, 2022, 3:22 PM
25 points
0 comments1 min readLW link

I’m try­ing out “as­ter­oid mind­set”

Alex_AltairJun 3, 2022, 1:35 PM
90 points
5 comments4 min readLW link