Stan­ford En­cy­clo­pe­dia of Philos­o­phy on AI ethics and superintelligence

Kaj_SotalaMay 2, 2020, 7:35 AM
43 points
19 comments7 min readLW link
(plato.stanford.edu)

[Question] How does pub­lish­ing a pa­per work?

LironMay 21, 2020, 12:14 PM
42 points
5 comments1 min readLW link

In­di­vi­d­ual Ra­tion­al­ity Needn’t Gen­er­al­ize to Ra­tional Consensus

Akshat MahajanMay 4, 2020, 10:53 PM
42 points
17 comments4 min readLW link

Covid-19: Comorbidity

ZviMay 10, 2020, 9:30 PM
42 points
7 comments7 min readLW link
(thezvi.wordpress.com)

Plague in As­sas­sin’s Creed Odyssey

ZviMay 24, 2020, 12:00 PM
41 points
3 comments1 min readLW link
(thezvi.wordpress.com)

162 benefits of coronavirus

bfinnMay 12, 2020, 11:19 AM
41 points
20 comments8 min readLW link

Maths writer/​cowrit­ter needed: how you can’t dis­t­in­guish early ex­po­nen­tial from early sigmoid

Stuart_ArmstrongMay 6, 2020, 9:41 AM
41 points
13 comments1 min readLW link

Learn­ing and ma­nipu­lat­ing learning

Stuart_ArmstrongMay 19, 2020, 1:02 PM
39 points
5 comments10 min readLW link

Trust-Build­ing: The New Ra­tion­al­ity Project

DirectedEvolutionMay 28, 2020, 10:53 PM
39 points
15 comments2 min readLW link

Book re­port: The­ory of Games and Eco­nomic Be­hav­ior (von Neu­mann & Mor­gen­stern)

NisanMay 11, 2020, 9:47 AM
38 points
4 comments6 min readLW link

Com­pet­i­tive safety via gra­dated curricula

Richard_NgoMay 5, 2020, 6:11 PM
38 points
5 comments5 min readLW link

How can In­ter­pretabil­ity help Align­ment?

May 23, 2020, 4:16 PM
37 points
3 comments9 min readLW link

How can non­prof­its gain the ad­van­tages of the for-profit model?

jasoncrawfordMay 6, 2020, 1:15 AM
37 points
0 comments2 min readLW link
(rootsofprogress.org)

Reflec­tive Complaints

RaemonMay 21, 2020, 9:11 PM
37 points
20 comments1 min readLW link

Evolu­tion is sam­pling error

willbradshawMay 23, 2020, 4:21 PM
37 points
2 comments6 min readLW link
(apomorphic.com)

Learn­ing to build conviction

benkuhnMay 16, 2020, 11:30 PM
36 points
1 comment5 min readLW link
(www.benkuhn.net)

Cor­rigi­bil­ity as out­side view

TurnTroutMay 8, 2020, 9:56 PM
36 points
11 comments4 min readLW link

Spec­u­la­tions on the Fu­ture of Fic­tion Writing

johnswentworthMay 28, 2020, 4:34 PM
35 points
14 comments2 min readLW link

Con­jec­ture Workshop

johnswentworthMay 15, 2020, 10:41 PM
35 points
2 comments2 min readLW link

Reopen Protest Sign Survey

jefftkMay 1, 2020, 3:40 AM
34 points
4 comments3 min readLW link
(www.jefftk.com)

English Bread Regulations

jefftkMay 18, 2020, 1:20 PM
33 points
12 comments6 min readLW link
(www.jefftk.com)

[AN #100]: What might go wrong if you learn a re­ward func­tion while acting

Rohin ShahMay 20, 2020, 5:30 PM
33 points
2 comments12 min readLW link
(mailchi.mp)

The Great­est Host

trentbrickMay 10, 2020, 8:28 PM
33 points
8 comments14 min readLW link

Med­i­ta­tion: the screen-and-watcher model of the hu­man mind, and how to use it

femtogrammarMay 1, 2020, 10:36 PM
32 points
12 comments6 min readLW link

Our Need for Need

eapacheMay 29, 2020, 11:12 AM
32 points
1 comment4 min readLW link

Multi-agent safety

Richard_NgoMay 16, 2020, 1:59 AM
31 points
8 comments5 min readLW link

[Question] Isn’t Tesla stock highly un­der­val­ued?

LironMay 18, 2020, 1:56 AM
31 points
41 comments2 min readLW link

Kids and Time

jefftkMay 12, 2020, 11:40 AM
30 points
2 comments2 min readLW link
(www.jefftk.com)

Kids and Mo­ral Agency

jefftkMay 8, 2020, 12:50 PM
30 points
9 comments1 min readLW link
(www.jefftk.com)

Utility need not be bounded

Richard_KennawayMay 14, 2020, 6:10 PM
30 points
34 comments2 min readLW link

[Question] What are ob­jects that have made your life bet­ter?

Mark XuMay 21, 2020, 8:59 PM
30 points
54 comments1 min readLW link

[Question] How to avoid Schel­ling points?

cwg1g16May 14, 2020, 7:37 PM
29 points
9 comments1 min readLW link

[AN #99]: Dou­bling times for the effi­ciency of AI algorithms

Rohin ShahMay 13, 2020, 5:20 PM
29 points
0 comments10 min readLW link
(mailchi.mp)

Shared House Setup

jefftkMay 9, 2020, 11:30 AM
28 points
0 comments2 min readLW link
(www.jefftk.com)

[Question] What is a de­ci­sion the­ory as a math­e­mat­i­cal ob­ject?

Erik JennerMay 25, 2020, 1:44 PM
28 points
4 comments1 min readLW link

[Question] What would flour­ish­ing look like in Con­way’s Game of Life?

sudhanshu_kasewaMay 12, 2020, 11:22 AM
27 points
20 comments1 min readLW link

Covid-19 5/​7: Fight­ing Limbo

ZviMay 7, 2020, 7:00 PM
27 points
7 comments10 min readLW link
(thezvi.wordpress.com)

Small Data

lsusrMay 14, 2020, 4:29 AM
27 points
13 comments4 min readLW link

The prin­ci­ple of no non-Apologies

agentydragonMay 28, 2020, 7:58 PM
26 points
8 comments2 min readLW link

Scott Garrabrant’s prob­lem on re­cov­er­ing Brouwer as a corol­lary of Lawvere

RupertMay 4, 2020, 10:01 AM
26 points
2 comments2 min readLW link

Really Fresh Baking

jefftkMay 10, 2020, 11:40 AM
26 points
9 comments1 min readLW link
(www.jefftk.com)

The Mind: Board Game Review

AlexeiMay 10, 2020, 12:45 AM
26 points
16 comments2 min readLW link

Covid-19 5/​29: Dumb Reopening

ZviMay 29, 2020, 9:00 PM
26 points
0 comments2 min readLW link
(thezvi.wordpress.com)

Mak­ing a Crow­dac­tion platform

B JacobsMay 16, 2020, 4:08 PM
25 points
9 comments5 min readLW link

Your ab­strac­tion isn’t wrong, it’s just re­ally bad

George3d6May 26, 2020, 8:14 PM
25 points
17 comments17 min readLW link
(blog.cerebralab.com)

[Question] Why aren’t we test­ing gen­eral in­tel­li­gence dis­tri­bu­tion?

B JacobsMay 26, 2020, 4:07 PM
25 points
7 comments1 min readLW link

How to do re­mote co-working

SoerenMindMay 8, 2020, 7:38 PM
25 points
11 comments1 min readLW link

AGIs as collectives

Richard_NgoMay 22, 2020, 8:36 PM
24 points
23 comments4 min readLW link

Dist­in­guish­ing lo­gis­tic curves

Stuart_ArmstrongMay 15, 2020, 11:38 AM
24 points
0 comments7 min readLW link

[AN #98]: Un­der­stand­ing neu­ral net train­ing by see­ing which gra­di­ents were helpful

Rohin ShahMay 6, 2020, 5:10 PM
22 points
3 comments9 min readLW link
(mailchi.mp)