Feel­ing Old: Leav­ing your 20s in the 2020s

squidiousNov 22, 2022, 10:50 PM
37 points
3 comments1 min readLW link
(opalsandbonobos.blogspot.com)

Brute-forc­ing the uni­verse: a non-stan­dard shot at di­a­mond alignment

Martín SotoNov 22, 2022, 10:36 PM
9 points
2 comments20 min readLW link

An­nounc­ing AI Align­ment Awards: $100k re­search con­tests about goal mis­gen­er­al­iza­tion & corrigibility

Nov 22, 2022, 10:19 PM
73 points
20 comments4 min readLW link

ACX Zurich Novem­ber Meetup

MBNov 22, 2022, 9:41 PM
1 point
0 comments1 min readLW link

Hu­man-level Full-Press Di­plo­macy (some bare facts).

Cleo NardoNov 22, 2022, 8:59 PM
50 points
7 comments3 min readLW link

[Question] How does late-2022 COVID trans­mis­si­bil­ity drop over time?

Daniel DeweyNov 22, 2022, 7:54 PM
8 points
2 comments1 min readLW link

AI will change the world, but won’t take it over by play­ing “3-di­men­sional chess”.

Nov 22, 2022, 6:57 PM
134 points
97 comments24 min readLW link

Progress links and tweets, 2022-11-22

jasoncrawfordNov 22, 2022, 5:39 PM
17 points
0 comments1 min readLW link
(rootsofprogress.org)

Tyranny of the Epistemic Majority

Scott GarrabrantNov 22, 2022, 5:19 PM
192 points
13 comments9 min readLW link1 review

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)

Sim­ple Im­prove­ment to Col­lege Foot­ball Over­time Rules

ZviNov 22, 2022, 5:00 PM
10 points
0 comments1 min readLW link
(thezvi.wordpress.com)

Meta AI an­nounces Cicero: Hu­man-Level Di­plo­macy play (with di­alogue)

Jacy Reese AnthisNov 22, 2022, 4:50 PM
93 points
64 comments1 min readLW link
(www.science.org)

Austin LW meetup notes: The FTX Affair

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

Mo­ti­vated Cog­ni­tion and the Mul­ti­verse of Truth

Q HomeNov 22, 2022, 12:51 PM
8 points
16 comments24 min readLW link

LessWrong read­ers are in­vited to ap­ply to the Lurkshop

Nov 22, 2022, 9:19 AM
101 points
41 comments3 min readLW link

Gaox­ing Guy

Alok SinghNov 22, 2022, 1:50 AM
3 points
1 comment1 min readLW link
(alok.github.io)

Mis­cel­la­neous First-Pass Align­ment Thoughts

NickGabsNov 21, 2022, 9:23 PM
12 points
4 comments10 min readLW link

[Heb­bian Nat­u­ral Ab­strac­tions] Introduction

Nov 21, 2022, 8:34 PM
34 points
3 comments4 min readLW link
(www.snellessen.com)

Utili­tar­i­anism Meets Egalitarianism

Scott GarrabrantNov 21, 2022, 7:00 PM
121 points
16 comments6 min readLW link1 review

In­ter­view with Matt Freeman

EvenflairNov 21, 2022, 6:17 PM
15 points
0 comments1 min readLW link
(overcast.fm)

Here’s the exit.

ValentineNov 21, 2022, 6:07 PM
113 points
180 comments10 min readLW link5 reviews

Benefits/​Risks of Scott Aaron­son’s Ortho­dox/​Re­form Fram­ing for AI Alignment

JeremyyNov 21, 2022, 5:54 PM
2 points
1 commentLW link

[ASoT] Reflec­tivity in Nar­row AI

Ulisse MiniNov 21, 2022, 12:51 AM
6 points
1 comment1 min readLW link

Scott Aaron­son on “Re­form AI Align­ment”

ShmiNov 20, 2022, 10:20 PM
39 points
17 comments1 min readLW link
(scottaaronson.blog)

On Mo­ral­ity, Ethics, and all that Jazz

Delen HeismanNov 20, 2022, 8:00 PM
4 points
4 comments2 min readLW link
(delen.substack.com)

Limits to the Con­trol­la­bil­ity of AGI

Nov 20, 2022, 7:18 PM
10 points
2 comments9 min readLW link

Ca­reer Scout­ing: Dentistry

koratkarNov 20, 2022, 3:55 PM
69 points
5 comments5 min readLW link
(careerscouting.substack.com)

De­ci­sion The­ory but also Ghosts

eva_Nov 20, 2022, 1:24 PM
17 points
21 comments10 min readLW link

ARC pa­per: For­mal­iz­ing the pre­sump­tion of independence

Erik JennerNov 20, 2022, 1:22 AM
97 points
2 comments2 min readLW link
(arxiv.org)

Up­date to Mys­ter­ies of mode col­lapse: text-davinci-002 not RLHF

janusNov 19, 2022, 11:51 PM
71 points
8 comments2 min readLW link

Make the Drought Eva­po­rate!

AnthonyRepettoNov 19, 2022, 11:41 PM
32 points
25 comments3 min readLW link

Elas­tic Pro­duc­tivity Tools

Simon BerensNov 19, 2022, 9:59 PM
76 points
8 comments2 min readLW link
(simonberens.me)

A Short Dialogue on the Mean­ing of Re­ward Functions

Nov 19, 2022, 9:04 PM
45 points
0 comments3 min readLW link

By De­fault, GPTs Think In Plain Sight

Fabien RogerNov 19, 2022, 7:15 PM
88 points
36 comments9 min readLW link

Re­view: Bayesian Statis­tics the Fun Way by Will Kurt

mattoNov 19, 2022, 6:52 PM
4 points
2 comments2 min readLW link

[Question] How does acausal trade work in a de­ter­minis­tic mul­ti­verse?

sisyphusNov 19, 2022, 1:50 AM
2 points
13 comments1 min readLW link

Choos­ing the right dish

Adam ZernerNov 19, 2022, 1:38 AM
38 points
7 comments8 min readLW link

Reflec­tive Consequentialism

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

Value Created vs. Value Extracted

SableNov 18, 2022, 9:34 PM
8 points
6 comments6 min readLW link
(affablyevil.substack.com)

The Disas­trously Con­fi­dent And Inac­cu­rate AI

Sharat Jacob JacobNov 18, 2022, 7:06 PM
13 points
0 comments13 min readLW link

How AI Fails Us: A non-tech­ni­cal view of the Align­ment Problem

testingthewatersNov 18, 2022, 7:02 PM
7 points
1 comment2 min readLW link
(ethics.harvard.edu)

[Question] Is there any policy for a fair treat­ment of AIs whose friendli­ness is in doubt?

nahojNov 18, 2022, 7:01 PM
15 points
10 comments1 min readLW link

Distil­la­tion of “How Likely Is De­cep­tive Align­ment?”

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

Con­tra Chords

jefftkNov 18, 2022, 4:20 PM
12 points
1 comment7 min readLW link
(www.jefftk.com)

[Question] Up­dates on scal­ing laws for foun­da­tion mod­els from ′ Tran­scend­ing Scal­ing Laws with 0.1% Ex­tra Com­pute’

Nick_GreigNov 18, 2022, 12:46 PM
15 points
2 comments1 min readLW link

Hal­i­fax, NS – Monthly Ra­tion­al­ist, EA, and ACX Meetup

IdeopunkNov 18, 2022, 11:45 AM
10 points
0 comments1 min readLW link

In­tro­duc­ing The Log­i­cal Foun­da­tion, A Plan to End Poverty With Guaran­teed Income

Michael SimmNov 18, 2022, 8:13 AM
9 points
23 commentsLW link

My Deon­tol­ogy Says Nar­row-Mind­ed­ness is Always Wrong

LVSNNov 18, 2022, 6:11 AM
6 points
2 comments1 min readLW link

AI Ethics != Ai Safety

DentinNov 18, 2022, 3:02 AM
2 points
0 comments1 min readLW link

Don’t de­sign agents which ex­ploit ad­ver­sar­ial inputs

Nov 18, 2022, 1:48 AM
72 points
64 comments12 min readLW link