All200520062007200820092010201120122013201420152016201720182019202020212022202320242025
AllJanFebMarAprMayJunJulAugSepOctNovDec
All12345678910111213141516171819202122232425262728293031

Com­par­i­son of de­ci­sion the­o­ries (with a fo­cus on log­i­cal-coun­ter­fac­tual de­ci­sion the­o­ries)

riceissaMar 16, 2019, 9:15 PM
78 points
11 comments10 min readLW link

Ter­ror­ism and Rus­sell’s love of excitement

CaiwitzAzariaMar 16, 2019, 6:53 AM
−9 points
0 comments1 min readLW link

Boe­ing 737 MAX MCAS as an agent cor­rigi­bil­ity failure

ShmiMar 16, 2019, 1:46 AM
60 points
3 comments1 min readLW link

Hu­mans aren’t agents—what then for value learn­ing?

Charlie SteinerMar 15, 2019, 10:01 PM
28 points
16 comments3 min readLW link

Privacy

ZviMar 15, 2019, 8:20 PM
79 points
78 comments6 min readLW link
(thezvi.wordpress.com)

Ac­tive Cu­ri­os­ity vs Open Curiosity

UnrealMar 15, 2019, 4:54 PM
76 points
24 comments3 min readLW link

IDA 5-8/​14: Ap­proval Directed Agents

RAISEMar 14, 2019, 11:58 PM
4 points
0 comments1 min readLW link
(app.grasple.com)

Nashville SSC March Meetup

Dude McDudeMar 14, 2019, 7:37 PM
1 point
0 comments1 min readLW link

Risk of Mass Hu­man Suffer­ing /​ Ex­tinc­tion due to Cli­mate Emer­gency

willfranksMar 14, 2019, 6:32 PM
4 points
3 comments1 min readLW link

Spec­u­la­tions on Duo Standard

ZviMar 14, 2019, 2:30 PM
9 points
2 comments8 min readLW link
(thezvi.wordpress.com)

Com­bin­ing in­di­vi­d­ual prefer­ence util­ity functions

Stuart_ArmstrongMar 14, 2019, 2:14 PM
13 points
2 comments1 min readLW link

Mys­ter­ies, iden­tity, and prefer­ences over non-rewards

Stuart_ArmstrongMar 14, 2019, 1:52 PM
14 points
1 comment1 min readLW link

Black­mailers are pri­va­teers in the war on hypocrisy

BenquoMar 14, 2019, 8:13 AM
25 points
23 comments5 min readLW link
(benjaminrosshoffman.com)

AI Safety Pr­ereq­ui­sites Course: Ba­sic ab­stract rep­re­sen­ta­tions of computation

RAISEMar 13, 2019, 7:38 PM
28 points
2 comments1 min readLW link

Ques­tion: MIRI Cor­rig­bil­ity Agenda

algon33Mar 13, 2019, 7:38 PM
15 points
11 comments1 min readLW link

A the­ory of hu­man values

Stuart_ArmstrongMar 13, 2019, 3:22 PM
28 points
13 comments7 min readLW link

[Question] For­mal­is­ing con­tin­u­ous info cas­cades? [Info-cas­cade se­ries]

Ben Pace and Bird Concept
Mar 13, 2019, 10:55 AM
16 points
5 comments1 min readLW link

[Question] How large is the harm from info-cas­cades? [Info-cas­cade se­ries]

Bird Concept and Ben Pace
Mar 13, 2019, 10:55 AM
22 points
2 comments1 min readLW link

[Question] How can we re­spond to info-cas­cades? [Info-cas­cade se­ries]

Bird Concept and Ben Pace
Mar 13, 2019, 10:55 AM
14 points
12 comments1 min readLW link

[Question] Distri­bu­tion of info-cas­cades across fields? [Info-cas­cade se­ries]

Bird Concept and Ben Pace
Mar 13, 2019, 10:55 AM
14 points
2 comments1 min readLW link

[Question] Un­der­stand­ing in­for­ma­tion cascades

Bird Concept and Ben Pace
Mar 13, 2019, 10:55 AM
50 points
42 comments3 min readLW link

Ver­ify­ing vNM-ra­tio­nal­ity re­quires an ontology

jeyoorMar 13, 2019, 12:03 AM
25 points
5 comments1 min readLW link

[Link] OpenAI LP

AlexeiMar 12, 2019, 11:22 PM
13 points
0 comments1 min readLW link

DATE CHANGE: Mar 18: Lex­ing­ton, KY, US

nathanhellerMar 12, 2019, 10:01 PM
1 point
0 comments1 min readLW link

LW Up­date 2019-03-12 -- Bugfixes, small features

jimrandomhMar 12, 2019, 9:56 PM
17 points
7 comments1 min readLW link

You Get About Five Words

RaemonMar 12, 2019, 8:30 PM
250 points
81 comments1 min readLW link6 reviews

[Old] Wayfind­ing series

Gordon Seidoh WorleyMar 12, 2019, 5:54 PM
8 points
0 comments15 min readLW link

[Old] Map­mak­ing Series

Gordon Seidoh WorleyMar 12, 2019, 5:32 PM
8 points
0 comments12 min readLW link

[Question] The tech left behind

LeafcraftMar 12, 2019, 2:47 PM
25 points
22 comments1 min readLW link

New York Res­tau­rants I Love: Pizza

ZviMar 12, 2019, 12:10 PM
10 points
0 comments9 min readLW link
(thezvi.wordpress.com)

How to Un­der­stand and Miti­gate Risk

Matt GoldenbergMar 12, 2019, 10:14 AM
55 points
30 comments16 min readLW link

[Question] If you wrote a let­ter to your fu­ture self ev­ery day, what would you put in it?

Pee DoomMar 12, 2019, 9:42 AM
17 points
3 comments1 min readLW link

Align­ment Newslet­ter #48

Rohin ShahMar 11, 2019, 9:10 PM
29 points
14 comments9 min readLW link
(mailchi.mp)

De­sign­ing agent in­cen­tives to avoid side effects

Vika and TurnTrout
Mar 11, 2019, 8:55 PM
29 points
0 comments2 min readLW link
(medium.com)

What Vibing Feels Like

Matt GoldenbergMar 11, 2019, 8:10 PM
19 points
17 comments2 min readLW link

Ex­am­ple pop­u­la­tion ethics: or­dered dis­counted utility

Stuart_ArmstrongMar 11, 2019, 4:10 PM
19 points
15 comments1 min readLW link

Call for Con­tri­bu­tions: Im­plied Marginal Value of Time from Good/​Services

skinnersboxyMar 11, 2019, 3:59 PM
8 points
3 comments1 min readLW link

Blegg Mode

Zack_M_DavisMar 11, 2019, 3:04 PM
18 points
68 comments1 min readLW link
(unremediatedgender.space)

IRL 2/​8: Miti­gat­ing de­gen­er­acy: mul­ti­ple experimentation

RAISEMar 11, 2019, 1:33 PM
13 points
0 comments1 min readLW link
(app.grasple.com)

Meta-Dooms­day Ar­gu­ment: Uncer­tainty About the Val­idity of the Prob­a­bil­is­tic Pre­dic­tion of the End of the World

avturchinMar 11, 2019, 10:30 AM
8 points
3 comments1 min readLW link
(philpapers.org)

This is Why Your Hard Work Sits on the Shelf — and Here’s What to Do About It

Ian David MossMar 11, 2019, 1:09 AM
2 points
0 comments5 min readLW link
(medium.com)

[Fic­tion] IO.SYS

DataPacRatMar 10, 2019, 9:23 PM
40 points
4 comments22 min readLW link

Muqaata’a by Fa­had Himsi (I.)

Martin SustrikMar 10, 2019, 3:10 PM
15 points
4 comments3 min readLW link
(250bpm.com)

Plans are Re­cur­sive & Why This is Important

Ruby10 Mar 2019 1:58 UTC
81 points
11 comments10 min readLW link

Show LW: Fallacyfiles

CaiwitzAzaria10 Mar 2019 0:16 UTC
7 points
0 comments1 min readLW link

On the Reg­u­la­tion of Perception

lionhearted (Sebastian Marshall)9 Mar 2019 16:28 UTC
16 points
8 comments4 min readLW link

Sleep­ing Beauty Prob­lem, An­thropic Prin­ci­ple and Per­spec­tive Reasoning

dadadarren9 Mar 2019 15:21 UTC
5 points
22 comments8 min readLW link

Lyubarsky intro

Mary Chernyshenko9 Mar 2019 11:13 UTC
6 points
7 comments1 min readLW link

How dan­ger­ous is it to ride a bi­cy­cle with­out a helmet?

habryka9 Mar 2019 2:58 UTC
34 points
30 comments4 min readLW link

Re­nam­ing “Front­page”

Raemon9 Mar 2019 1:23 UTC
41 points
16 comments4 min readLW link