Book Re­view: The Righ­teous Mind

Tornus20 Jan 2022 21:42 UTC
7 points
5 comments7 min readLW link

The Liar and the Scold

Tomás B.20 Jan 2022 20:31 UTC
118 points
13 comments12 min readLW link

What’s Up With Con­fus­ingly Per­va­sive Goal Direct­ed­ness?

Raemon20 Jan 2022 19:22 UTC
175 points
89 comments4 min readLW link

Emo­tions = Re­ward Functions

jpyykko20 Jan 2022 18:46 UTC
16 points
10 comments5 min readLW link

Risk and Safety in the age of COVID

Mike Harris20 Jan 2022 18:40 UTC
24 points
14 comments10 min readLW link

An­chor Weights for ML

jsteinhardt20 Jan 2022 16:20 UTC
17 points
2 comments2 min readLW link
(bounded-regret.ghost.io)

Covid 1/​20/​22: Peak Omicron

Zvi20 Jan 2022 16:20 UTC
56 points
21 comments27 min readLW link
(thezvi.wordpress.com)

Es­ti­mat­ing train­ing com­pute of Deep Learn­ing models

20 Jan 2022 16:12 UTC
37 points
4 comments1 min readLW link

Choos­ing bat­tles (on the In­ter­net)

PatrickDFarley20 Jan 2022 15:38 UTC
24 points
2 comments4 min readLW link

Land Ho!

Zvi20 Jan 2022 13:30 UTC
120 points
4 comments4 min readLW link
(thezvi.wordpress.com)

Too right to write

Solenoid_Entity20 Jan 2022 13:21 UTC
28 points
12 comments3 min readLW link

Harry Pot­ter and the Meth­ods of Psy­chomagic | Chap­ter 3: In­tel­li­gence Explosions

Henry Prowbell20 Jan 2022 13:11 UTC
27 points
6 comments8 min readLW link

Speed Pasta Bake

jefftk20 Jan 2022 2:50 UTC
11 points
7 comments1 min readLW link
(www.jefftk.com)

Ac­tion: Help ex­pand fund­ing for AI Safety by co­or­di­nat­ing on NSF response

Evan R. Murphy19 Jan 2022 22:47 UTC
23 points
8 comments3 min readLW link

NFTs Are Prob­a­bly Not Beanie Babies

parrhesia19 Jan 2022 22:14 UTC
−6 points
9 comments4 min readLW link

Seat­tle: The physics of dy­namism (and AI al­ign­ment)

Alex Flint19 Jan 2022 17:10 UTC
9 points
0 comments1 min readLW link

Bay Area Ra­tion­al­ist Field Day

SurvivalBias19 Jan 2022 16:40 UTC
3 points
0 comments1 min readLW link

Omicron Post #15

Zvi19 Jan 2022 14:40 UTC
52 points
10 comments5 min readLW link
(thezvi.wordpress.com)

You Can Get Fluvoxamine

AppliedDivinityStudies18 Jan 2022 23:48 UTC
60 points
18 comments3 min readLW link

[Question] How do you rea­son about how many COVID test kits to keep on hand?

nim18 Jan 2022 18:09 UTC
7 points
0 comments2 min readLW link

Thought Ex­per­i­ments Provide a Third Anchor

jsteinhardt18 Jan 2022 16:00 UTC
46 points
20 comments4 min readLW link
(bounded-regret.ghost.io)

Positly covid sur­vey: long covid

KatjaGrace18 Jan 2022 10:40 UTC
31 points
2 comments8 min readLW link
(worldspiritsockpuppet.com)

The ig­no­rance of nor­ma­tive re­al­ism bot

Joe Carlsmith18 Jan 2022 5:26 UTC
43 points
6 comments35 min readLW link1 review

How to Build New Coun­tries à la 1729?

jdcampolargo17 Jan 2022 22:53 UTC
−1 points
1 comment7 min readLW link

[Question] The un­falsifi­able be­lief in (dooms­day) su­per­in­tel­li­gence sce­nar­ios?

Hickey17 Jan 2022 21:02 UTC
−5 points
28 comments1 min readLW link

Scalar re­ward is not enough for al­igned AGI

Peter Vamplew17 Jan 2022 21:02 UTC
23 points
3 comments11 min readLW link

[Question] Is there a good way to read deep into LW com­ment his­to­ries on mo­bile?

Maxwell Peterson17 Jan 2022 19:02 UTC
6 points
4 comments1 min readLW link

[Question] Hedg­ing omicron im­pact to sup­ply chains

mukashi17 Jan 2022 18:49 UTC
29 points
1 comment1 min readLW link

Work­ing through D&D.Sci, prob­lem 2 (solu­tion)

Pablo Repetto17 Jan 2022 17:41 UTC
16 points
8 comments1 min readLW link
(pabloernesto.github.io)

How I’m think­ing about GPT-N

delton13717 Jan 2022 17:11 UTC
54 points
21 comments18 min readLW link

Truth­ful LMs as a warm-up for al­igned AGI

Jacob_Hilton17 Jan 2022 16:49 UTC
65 points
14 comments13 min readLW link

Differ­ent way clas­sifiers can be diverse

Stuart_Armstrong17 Jan 2022 16:30 UTC
10 points
5 comments2 min readLW link

PIBBSS Fel­low­ship: Bounty for Refer­rals & Dead­line Extension

Anna Gajdova17 Jan 2022 16:23 UTC
7 points
0 comments1 min readLW link

Poly­mar­ket Covid-19 1/​17/​2022

Zvi17 Jan 2022 16:10 UTC
38 points
10 comments9 min readLW link
(thezvi.wordpress.com)

Value No­tion—Ques­tions to Ask

aysajan17 Jan 2022 15:35 UTC
5 points
0 comments4 min readLW link

Guidelines for cold mes­sag­ing people

Severin T. Seehrich17 Jan 2022 12:07 UTC
35 points
21 comments1 min readLW link

Be­ing the Hero is hard with the void

Johannes C. Mayer17 Jan 2022 11:27 UTC
5 points
1 comment4 min readLW link

A de­ci­sion tree for vac­ci­nat­ing chil­dren against Covid-19, or how to wisely make a mon­u­men­tal decision

methree17 Jan 2022 11:23 UTC
7 points
12 comments9 min readLW link

Challenges with Break­ing into MIRI-Style Research

Chris_Leong17 Jan 2022 9:23 UTC
75 points
16 comments2 min readLW link

A con­nec­tomic study of a petas­cale frag­ment of hu­man cere­bral cortex

PointlessOne17 Jan 2022 8:49 UTC
4 points
0 comments1 min readLW link
(vcg.seas.harvard.edu)

En­tropy isn’t suffi­cient to mea­sure pass­word strength

benwr17 Jan 2022 6:41 UTC
36 points
30 comments2 min readLW link
(www.benwr.net)

Teach­ing Street Crossing

jefftk16 Jan 2022 20:20 UTC
38 points
11 comments2 min readLW link
(www.jefftk.com)

Notes on Rationality

David Gross16 Jan 2022 19:05 UTC
16 points
1 comment12 min readLW link

New Year Re­view Resources

lynettebye16 Jan 2022 18:21 UTC
24 points
1 comment9 min readLW link

Some thoughts on “The Na­ture of Coun­ter­fac­tu­als”

tailcalled16 Jan 2022 18:12 UTC
20 points
11 comments11 min readLW link

Long covid: prob­a­bly worth avoid­ing—some considerations

KatjaGrace16 Jan 2022 11:46 UTC
134 points
88 comments14 min readLW link
(worldspiritsockpuppet.com)

Try­ing to Keep the Gar­den Well

Tobias H16 Jan 2022 5:42 UTC
99 points
5 comments1 min readLW link

Tar­get for Tonight: A Drama In One Act

vernamcipher16 Jan 2022 4:29 UTC
4 points
0 comments14 min readLW link

Reflec­tions on Con­nect Developers

Adam Zerner16 Jan 2022 0:20 UTC
17 points
21 comments5 min readLW link

Nudg­ing My Way Out Of The In­tel­lec­tual Mosh Pit

Elizabeth15 Jan 2022 23:40 UTC
42 points
20 comments4 min readLW link
(acesounderglass.com)