All200520062007200820092010201120122013201420152016201720182019202020212022202320242025
AllJanFebMarAprMayJunJulAugSepOctNovDec
All12345678910111213141516171819202122232425262728293031

[Pre­dic­tion] The Con­se­quences of Rad­i­cal Reform

lsusrMar 9, 2021, 11:05 PM
36 points
16 comments5 min readLW link

Defend­ing the non-cen­tral fallacy

Matthew BarnettMar 9, 2021, 9:42 PM
140 points
38 comments6 min readLW link

De-con­fus­ing my­self about Pas­cal’s Mug­ging and New­comb’s Problem

DirectedEvolutionMar 9, 2021, 8:45 PM
7 points
1 comment3 min readLW link

Towards a Mechanis­tic Un­der­stand­ing of Goal-Directedness

Mark XuMar 9, 2021, 8:17 PM
46 points
1 comment5 min readLW link

Why does Ap­plied Div­inity Stud­ies think EA hasn’t grown since 2015?

KatjaGraceMar 9, 2021, 10:10 AM
51 points
1 comment3 min readLW link
(worldspiritsockpuppet.com)

Will Mar­tian G be enough to make healthy baseline ba­bies?

Randomized, ControlledMar 9, 2021, 3:30 AM
4 points
8 comments1 min readLW link

CLR’s re­cent work on multi-agent systems

JesseCliftonMar 9, 2021, 2:28 AM
54 points
2 comments13 min readLW link

Why Hasn’t Effec­tive Altru­ism Grown Since 2015?

AppliedDivinityStudiesMar 9, 2021, 1:43 AM
64 points
28 comments9 min readLW link

D&D.Sci III Eval­u­a­tion and Ruleset

abstractapplicMar 8, 2021, 11:01 PM
16 points
4 comments3 min readLW link

Episte­molog­i­cal Fram­ing for AI Align­ment Research

adamShimiMar 8, 2021, 10:05 PM
58 points
7 comments9 min readLW link

What I’d change about differ­ent philos­o­phy fields

Rob BensingerMar 8, 2021, 6:25 PM
56 points
52 comments4 min readLW link

[Lec­ture Club] Awak­en­ing from the Mean­ing Crisis

VaniverMar 8, 2021, 3:22 PM
72 points
207 comments2 min readLW link

If you’ve learned from the best, you’re do­ing it wrong

George3d6Mar 8, 2021, 1:14 PM
36 points
18 comments6 min readLW link
(cerebralab.com)

Sim­ple Tricks to Im­prove KN95 Masks

dawangyMar 8, 2021, 8:59 AM
25 points
6 comments2 min readLW link

Care and demandingness

Joe CarlsmithMar 8, 2021, 7:03 AM
25 points
10 comments11 min readLW link

Ir­ra­tional ar­gu­ments or valuable heuris­tics?

Hauntology Ph.D.Mar 8, 2021, 5:34 AM
8 points
0 comments8 min readLW link

How I Meditate

Gordon Seidoh WorleyMar 8, 2021, 3:34 AM
18 points
4 comments2 min readLW link

The Case for Log­i­cal Fallacies

Aaron BergmanMar 8, 2021, 3:04 AM
14 points
0 comments7 min readLW link
(aaronbergman.substack.com)

A sim­ple way to make GPT-3 fol­low instructions

Quintin PopeMar 8, 2021, 2:57 AM
11 points
5 comments4 min readLW link

Sleep math: red clay blue clay

KatjaGraceMar 8, 2021, 12:30 AM
23 points
9 comments1 min readLW link
(worldspiritsockpuppet.com)

See­ing Sta­tus Quo Bias

LironMar 8, 2021, 12:24 AM
27 points
4 comments5 min readLW link

PhD stu­dent mu­tual line-man­ager invitation

Tim LiptrotMar 7, 2021, 11:06 PM
11 points
0 comments1 min readLW link

[Question] What are the biggest cur­rent im­pacts of AI?

Sam ClarkeMar 7, 2021, 9:44 PM
15 points
5 comments1 min readLW link

Car Thoughts

jefftkMar 7, 2021, 9:30 PM
8 points
8 comments3 min readLW link
(www.jefftk.com)

Book Notes: Scal­ing, Why is An­i­mal Size so Im­por­tant?

ketchupduckMar 7, 2021, 8:16 PM
19 points
5 comments7 min readLW link

An­nounce­ment: Real-time dis­cus­sions in a new Club­house com­mu­nity.

gianlucatrudaMar 7, 2021, 7:38 PM
16 points
11 comments2 min readLW link

In­tro­duc­ing Metafore­cast: A Fore­cast Ag­gre­ga­tor and Search Tool

NunoSempere and ozziegooen
Mar 7, 2021, 7:03 PM
83 points
6 comments4 min readLW link

Thoughts on the Repug­nant Conclusion

Tomás B.Mar 7, 2021, 7:00 PM
9 points
4 comments1 min readLW link

Prag­matic Cut­offs

BoraskoMar 7, 2021, 6:35 PM
4 points
1 comment3 min readLW link

The three ex­ist­ing ways of ex­plain­ing the three char­ac­ter­is­tics of existence

Kaj_SotalaMar 7, 2021, 6:20 PM
40 points
1 comment13 min readLW link

Un­con­ve­nient con­se­quences of the logic be­hind the sec­ond law of thermodynamics

Marco DiscendentiMar 7, 2021, 6:14 PM
8 points
44 comments2 min readLW link

The av­er­age North Korean mathematician

MalmesburyMar 7, 2021, 5:28 PM
67 points
19 comments8 min readLW link
(www.telescopic-turnip.net)

Teach­ing to Compromise

Martin SustrikMar 7, 2021, 1:57 PM
16 points
5 comments2 min readLW link

Bakeoff

jefftkMar 7, 2021, 1:30 AM
26 points
4 comments1 min readLW link
(www.jefftk.com)

Con­trar­ian Writ­ing Advice

lsusrMar 7, 2021, 12:23 AM
54 points
13 comments1 min readLW link

Notic­ing and Over­com­ing Bias

Neel NandaMar 6, 2021, 9:06 PM
14 points
1 comment7 min readLW link

[Question] What eth­i­cal thought ex­per­i­ments can be re­versed?

Mati_RoyMar 6, 2021, 3:12 PM
16 points
19 comments1 min readLW link

[Question] What (fea­si­ble) aug­mented senses would be use­ful or in­ter­est­ing?

AprilSRMar 6, 2021, 4:28 AM
8 points
9 comments1 min readLW link

Check OK, bab­ble-read, op­ti­mize (how I read text­books)

DirectedEvolutionMar 6, 2021, 3:17 AM
25 points
3 comments5 min readLW link

MIRI com­ments on Co­tra’s “Case for Align­ing Nar­rowly Su­per­hu­man Models”

Rob BensingerMar 5, 2021, 11:43 PM
142 points
13 comments26 min readLW link

The case for al­ign­ing nar­rowly su­per­hu­man models

Ajeya CotraMar 5, 2021, 10:29 PM
186 points
75 comments38 min readLW link1 review

D&D.Sci III: Mancer Matchups

abstractapplicMar 5, 2021, 7:07 PM
21 points
22 comments3 min readLW link

GPT-3 and the fu­ture of knowl­edge work

fowlertmMar 5, 2021, 5:40 PM
16 points
0 comments2 min readLW link

Take­aways from the In­tel­li­gence Ris­ing RPG

Quinn and Viktor Rehnberg
Mar 5, 2021, 10:27 AM
51 points
7 comments12 min readLW link

Mul­ti­modal Neu­rons in Ar­tifi­cial Neu­ral Networks

Kaj_SotalaMar 5, 2021, 9:01 AM
57 points
2 comments2 min readLW link
(distill.pub)

Does mak­ing un­steady in­cre­men­tal progress work?

peterbarnettMar 5, 2021, 7:23 AM
8 points
4 comments1 min readLW link
(peterbarnett.org)

Why Selec­tive Breed­ing is a Bad Way to do Ge­netic Engineering

GeneSmithMar 5, 2021, 2:30 AM
13 points
14 comments2 min readLW link

Par­ti­ci­pat­ing in a Covid-19 Vac­cine Trial #3: I Hope I feel Worse Tomorrow

ejacobMar 5, 2021, 12:02 AM
8 points
2 comments5 min readLW link

[AN #140]: The­o­ret­i­cal mod­els that pre­dict scal­ing laws

Rohin ShahMar 4, 2021, 6:10 PM
46 points
8 comments10 min readLW link
(mailchi.mp)

A Semitech­ni­cal In­tro­duc­tory Dialogue on Solomonoff Induction

Eliezer YudkowskyMar 4, 2021, 5:27 PM
143 points
33 comments54 min readLW link