Book re­view: The Check­list Manifesto

Swimmer963 (Miranda Dixon-Luinenburg) 17 Sep 2021 23:09 UTC
122 points
13 comments5 min readLW link

The the­ory-prac­tice gap

Buck17 Sep 2021 22:51 UTC
138 points
15 comments6 min readLW link

Truth + Rea­son = The True Reli­gion?

David Gross17 Sep 2021 22:14 UTC
34 points
2 comments19 min readLW link

[Question] What should one’s policy re­gard­ing den­tal xrays be?

Randomized, Controlled17 Sep 2021 20:55 UTC
12 points
15 comments1 min readLW link

In­ves­ti­gat­ing AI Takeover Scenarios

Sammy Martin17 Sep 2021 18:47 UTC
27 points
1 comment27 min readLW link

A simu­la­tion basilisk

andrew sauer17 Sep 2021 17:44 UTC
3 points
1 comment1 min readLW link

Good­hart Ethology

Charlie Steiner17 Sep 2021 17:31 UTC
19 points
4 comments14 min readLW link

A Fight is a Faster Tax on Bullshit

Ray Doraisamy17 Sep 2021 16:26 UTC
2 points
8 comments3 min readLW link

Im­mo­bile AI makes a move: anti-wire­head­ing, on­tol­ogy change, and model splintering

Stuart_Armstrong17 Sep 2021 15:24 UTC
32 points
3 comments2 min readLW link

Great Power Conflict

Zach Stein-Perlman17 Sep 2021 15:00 UTC
11 points
6 comments4 min readLW link

Born Again: Dis­con­nected Psy­chol­ogy, Mar­tian Science, and the Order of the Phoenix

rogersbacon17 Sep 2021 14:23 UTC
4 points
0 comments17 min readLW link

Covid 9/​17: Done Bi­den His Time

Zvi17 Sep 2021 12:00 UTC
63 points
14 comments29 min readLW link
(thezvi.wordpress.com)

How feel­ing more se­cure feels differ­ent than I expected

Kaj_Sotala17 Sep 2021 9:20 UTC
79 points
15 comments3 min readLW link
(kajsotala.fi)

Re­search speedruns

drossbucket17 Sep 2021 6:54 UTC
40 points
6 comments3 min readLW link

Les­sons from covid pre­dic­tions: Always use mul­ti­ple models

pku17 Sep 2021 3:19 UTC
8 points
2 comments3 min readLW link

Let Us Do Our Work As Well

jsteinhardt17 Sep 2021 0:40 UTC
7 points
2 comments2 min readLW link
(bounded-regret.ghost.io)

Writ­ing On The Pareto Frontier

johnswentworth17 Sep 2021 0:05 UTC
70 points
12 comments3 min readLW link

Jit­ters No Ev­i­dence of Stu­pidity in RL

1a3orn16 Sep 2021 22:43 UTC
96 points
18 comments3 min readLW link

Com­ments on Ja­cob Falkovich on loneliness

Alex Flint16 Sep 2021 22:04 UTC
29 points
9 comments16 min readLW link

Eco­nomic AI Safety

jsteinhardt16 Sep 2021 20:50 UTC
35 points
3 comments5 min readLW link

The Me­taethics and Nor­ma­tive Ethics of AGI Value Align­ment: Many Ques­tions, Some Implications

Eleos Arete Citrini16 Sep 2021 16:13 UTC
6 points
0 comments8 min readLW link

Dat­ing Minefield vs. Dat­ing Playground

Vlad Loweren16 Sep 2021 16:13 UTC
23 points
4 comments4 min readLW link

Coun­ter­fac­tual Contracts

harsimony16 Sep 2021 15:20 UTC
10 points
4 comments9 min readLW link
(harsimony.wordpress.com)

[Question] ‘Good enough’ way to clean an O2 Curve res­pi­ra­tor?

Kenny16 Sep 2021 14:51 UTC
5 points
2 comments1 min readLW link

How truth­ful is GPT-3? A bench­mark for lan­guage models

Owain_Evans16 Sep 2021 10:09 UTC
58 points
24 comments6 min readLW link

I wanted to in­ter­view Eliezer Yud­kowsky but he’s busy so I simu­lated him instead

lsusr16 Sep 2021 7:34 UTC
111 points
33 comments5 min readLW link

“Who’s In Charge? Free Will and the Science of the Brain”

David Gross16 Sep 2021 2:38 UTC
10 points
6 comments4 min readLW link

Op­ti­miz­ing Mul­ti­ple Im­perfect Filters

johnswentworth15 Sep 2021 22:57 UTC
50 points
4 comments6 min readLW link

[in­ac­tive] £2000 bounty—con­tra­cep­tives (and UTI) liter­a­ture review

Chi Nguyen15 Sep 2021 22:37 UTC
70 points
14 comments2 min readLW link

Ed­mon­ton Meetup

JS15 Sep 2021 19:16 UTC
1 point
0 comments1 min readLW link

His­tory of count­ing to three?

jefftk15 Sep 2021 18:10 UTC
12 points
3 comments1 min readLW link
(www.jefftk.com)

Austin Petrov Day and Potluck

SilasBarta15 Sep 2021 17:38 UTC
10 points
3 comments1 min readLW link

[AN #164]: How well can lan­guage mod­els write code?

Rohin Shah15 Sep 2021 17:20 UTC
13 points
7 comments9 min readLW link
(mailchi.mp)

Harry Pot­ter and the Meth­ods of Psy­chomagic | Chap­ter 1: Affect

Henry Prowbell15 Sep 2021 17:03 UTC
64 points
5 comments7 min readLW link

[Question] How to deal with prob­a­bil­ities in the pres­ence of clones?

depressurize15 Sep 2021 17:01 UTC
4 points
6 comments1 min readLW link

Effec­tive Altru­ism Vir­tual Pro­grams Oct-Nov 2021

Yi-Yang15 Sep 2021 13:00 UTC
2 points
0 comments1 min readLW link

Or­a­cle pre­dic­tions don’t ap­ply to non-ex­is­tent worlds

Chris_Leong15 Sep 2021 9:44 UTC
10 points
25 comments3 min readLW link

The Mo­ti­vated Rea­son­ing Cri­tique of Effec­tive Altruism

Linch15 Sep 2021 1:43 UTC
26 points
0 comments23 min readLW link
(forum.effectivealtruism.org)

Film Study for Research

jsteinhardt14 Sep 2021 18:53 UTC
50 points
7 comments6 min readLW link

[Question] Why didn’t we find katas for ra­tio­nal­ity?

ChristianKl14 Sep 2021 16:43 UTC
9 points
35 comments1 min readLW link

GPT-Aug­mented Blogging

lsusr14 Sep 2021 11:55 UTC
52 points
18 comments13 min readLW link

[Question] Is there a bee­minder with­out the pun­ish­ment?

warrenjordan14 Sep 2021 2:51 UTC
16 points
10 comments1 min readLW link

LessWrong is pay­ing $500 for Book Reviews

Ruby14 Sep 2021 0:24 UTC
133 points
25 comments4 min readLW link

[Linkpost] Par­tial Deriva­tives and Par­tial Narratives

mike_hawke13 Sep 2021 21:02 UTC
17 points
0 comments1 min readLW link
(everythingstudies.com)

Digi­tal Peo­ple FAQ

HoldenKarnofsky13 Sep 2021 15:24 UTC
28 points
13 comments16 min readLW link

Digi­tal Peo­ple Would Be An Even Big­ger Deal

HoldenKarnofsky13 Sep 2021 15:23 UTC
34 points
14 comments13 min readLW link

[linkpost] The Psy­cholog­i­cal Econ­omy of In­ac­tion by William Gillis

Quinn12 Sep 2021 22:04 UTC
12 points
1 comment1 min readLW link
(humaniterations.net)

EA Fo­rum Creative Writ­ing Con­test: $10,000 in prizes for good stories

aarongertler12 Sep 2021 21:25 UTC
32 points
0 comments1 min readLW link
(forum.effectivealtruism.org)

Pivot!

Carlos Ramirez12 Sep 2021 20:39 UTC
−18 points
5 comments1 min readLW link

How fac­to­ries were made safe

jasoncrawford12 Sep 2021 19:58 UTC
181 points
46 comments18 min readLW link1 review
(rootsofprogress.org)