AvE: As­sis­tance via Empowerment

FactorialCodeJun 30, 2020, 10:07 PM
12 points
1 comment1 min readLW link
(arxiv.org)

I am Bad at Flirt­ing; Real­iz­ing that by Notic­ing Confusion

snog toddgrassJun 30, 2020, 8:05 PM
8 points
7 comments4 min readLW link

Com­par­ing AI Align­ment Ap­proaches to Min­i­mize False Pos­i­tive Risk

Gordon Seidoh WorleyJun 30, 2020, 7:34 PM
5 points
0 comments9 min readLW link

[Question] How ought I spend time?

QuinnJun 30, 2020, 4:53 PM
10 points
11 comments1 min readLW link

Sick of struggling

dqups1Jun 30, 2020, 4:47 PM
2 points
7 comments1 min readLW link

Somerville Mask Usage

jefftkJun 30, 2020, 2:50 PM
17 points
4 comments1 min readLW link
(www.jefftk.com)

Web AI dis­cus­sion Groups

Donald HobsonJun 30, 2020, 11:22 AM
11 points
0 comments2 min readLW link

How do take­off speeds af­fect the prob­a­bil­ity of bad out­comes from AGI?

KRJun 29, 2020, 10:06 PM
15 points
2 comments8 min readLW link

AI Benefits Post 2: How AI Benefits Differs from AI Align­ment & AI for Good

CullenJun 29, 2020, 5:00 PM
8 points
7 comments2 min readLW link

Thoughts as open tabs

ryan wongJun 29, 2020, 12:13 PM
17 points
12 comments2 min readLW link

Op­ti­mized Pro­pa­ganda with Bayesian Net­works: Com­ment on “Ar­tic­u­lat­ing Lay The­o­ries Through Graph­i­cal Models”

Zack_M_DavisJun 29, 2020, 2:45 AM
105 points
10 comments4 min readLW link

Ab­strac­tions on In­con­sis­tent Data

eapacheJun 29, 2020, 12:30 AM
7 points
0 comments2 min readLW link

Gödel’s Le­gacy: A game with­out end

HazardJun 28, 2020, 6:50 PM
45 points
11 comments12 min readLW link

Gary Mar­cus vs Cor­ti­cal Uniformity

Steven ByrnesJun 28, 2020, 6:18 PM
18 points
0 comments8 min readLW link

Self-sac­ri­fice is a scarce resource

mingyuanJun 28, 2020, 5:08 AM
129 points
18 comments5 min readLW link

A re­ply to Agnes Callard

VaniverJun 28, 2020, 3:25 AM
91 points
36 comments3 min readLW link

Don’t Make Your Prob­lems Hide

orthonormalJun 27, 2020, 8:24 PM
61 points
5 comments2 min readLW link

Me­di­a­tors of History

johnswentworthJun 27, 2020, 7:55 PM
25 points
1 comment4 min readLW link

Five Ways To Pri­ori­tize Better

lynettebyeJun 27, 2020, 6:40 PM
136 points
7 comments20 min readLW link1 review

[Question] Have gen­eral de­com­posers been for­mal­ized?

QuinnJun 27, 2020, 6:09 PM
8 points
5 comments1 min readLW link

[Question] Why are all these do­mains called from Less Wrong?

ViliamJun 27, 2020, 1:46 PM
26 points
11 comments1 min readLW link

Life at Three Tails of the Bell Curve

lsusrJun 27, 2020, 8:49 AM
65 points
10 comments4 min readLW link

Map Er­rors: The Good, The Bad, and The Territory

orthonormalJun 27, 2020, 5:22 AM
29 points
4 comments2 min readLW link

Ne­go­ti­at­ing With Yourself

orthonormalJun 26, 2020, 11:55 PM
28 points
0 comments5 min readLW link

AI safety via mar­ket making

evhubJun 26, 2020, 11:07 PM
72 points
45 comments1 min readLW link

Public Po­si­tions and Pri­vate Guts

Jun 26, 2020, 11:00 PM
22 points
1 comment6 min readLW link

Rad­i­cal Prob­a­bil­ism [Tran­script]

Jun 26, 2020, 10:14 PM
48 points
12 comments6 min readLW link

Miss­ing dog reasoning

Jun 26, 2020, 9:30 PM
27 points
3 comments5 min readLW link

Atem­po­ral Eth­i­cal Obligations

eapacheJun 26, 2020, 7:52 PM
13 points
20 comments2 min readLW link

Sun­day June 28 – talks by john­swent­worth, Daniel koko­ta­jlo, Char­lie Steiner, TurnTrout

Jun 26, 2020, 7:13 PM
28 points
1 comment1 min readLW link

Black Death at the Golden Gate (book re­view)

PeterMcCluskeyJun 26, 2020, 4:09 PM
17 points
0 comments4 min readLW link
(www.bayesianinvestor.com)

In­sti­tu­tional Senescence

Martin SustrikJun 26, 2020, 4:40 AM
27 points
7 comments2 min readLW link
(250bpm.com)

In­dus­try and workers

smaslennikovJun 25, 2020, 8:03 PM
−3 points
12 comments4 min readLW link
(smaslennikov.com)

Covid 6/​25: The Dam Breaks

ZviJun 25, 2020, 6:30 PM
116 points
21 comments8 min readLW link
(thezvi.wordpress.com)

An ag­ile ap­proach to pre-research

DirectedEvolutionJun 25, 2020, 6:29 PM
15 points
0 comments4 min readLW link

A Per­sonal (In­terim) COVID-19 Postmortem

DavidmanheimJun 25, 2020, 6:10 PM
163 points
41 comments9 min readLW link1 review

GPT-3 Fic­tion Samples

gwernJun 25, 2020, 4:12 PM
63 points
15 commentsLW link
(www.gwern.net)

There’s an Awe­some AI Ethics List and it’s a lit­tle thin

AABoylesJun 25, 2020, 1:43 PM
13 points
1 comment1 min readLW link
(github.com)

Don­tDoxS­cot­tAlexan­der.com—A Petition

Jun 25, 2020, 5:44 AM
120 points
32 comments1 min readLW link
(DontDoxScottAlexander.com)

Pre­view On Hover

jefftkJun 24, 2020, 10:20 PM
20 points
22 comments2 min readLW link
(www.jefftk.com)

Don’t pun­ish your­self for bad luck

SherrinfordJun 24, 2020, 9:52 PM
16 points
9 comments3 min readLW link

Bet­ting with Manda­tory Post-Mortem

abramdemskiJun 24, 2020, 8:04 PM
105 points
14 comments1 min readLW link

Quick Look #1 Dio­phan­tus of Alexandria

SebastianG Jun 24, 2020, 7:12 PM
19 points
0 comments2 min readLW link

[Question] What’s the name for that plau­si­ble de­ni­a­bil­ity thing?

eapacheJun 24, 2020, 6:42 PM
11 points
3 comments1 min readLW link

[Question] Can I archive con­tent from less­wrong.com on the way­back ma­chine (in­ter­net archive, archive.org) ?

nick lacombeJun 24, 2020, 6:15 PM
14 points
3 comments1 min readLW link

Ab­strac­tion, Evolu­tion and Gears

johnswentworthJun 24, 2020, 5:39 PM
29 points
11 comments4 min readLW link

[AN #105]: The eco­nomic tra­jec­tory of hu­man­ity, and what we might mean by optimization

Rohin ShahJun 24, 2020, 5:30 PM
24 points
3 comments11 min readLW link
(mailchi.mp)

Linkpost: M21 Re­view: We Have Normality

ZviJun 24, 2020, 4:10 PM
10 points
0 comments1 min readLW link
(thezvi.wordpress.com)

Models, myths, dreams, and Cheshire cat grins

Stuart_ArmstrongJun 24, 2020, 10:50 AM
21 points
7 comments2 min readLW link

[Question] Does NYT have poli­cies?

Douglas_KnightJun 24, 2020, 4:06 AM
19 points
0 comments1 min readLW link