Yes Re­quires the Pos­si­bil­ity of No

Scott Garrabrant17 May 2019 22:39 UTC
261 points
55 comments2 min readLW link2 reviews

Co­her­ent de­ci­sions im­ply con­sis­tent utilities

Eliezer Yudkowsky12 May 2019 21:33 UTC
148 points
81 comments26 min readLW link3 reviews

In­te­grat­ing dis­agree­ing subagents

Kaj_Sotala14 May 2019 14:06 UTC
141 points
15 comments21 min readLW link

The Re­la­tion­ship Between the Village and the Mission

Raemon12 May 2019 21:09 UTC
136 points
70 comments18 min readLW link

Say Wrong Things

Gordon Seidoh Worley24 May 2019 22:11 UTC
114 points
13 comments4 min readLW link

Com­plex Be­hav­ior from Sim­ple (Sub)Agents

moridinamael10 May 2019 21:44 UTC
112 points
13 comments9 min readLW link1 review

[Question] Where are peo­ple think­ing and talk­ing about global co­or­di­na­tion for AI safety?

Wei Dai22 May 2019 6:24 UTC
112 points
22 comments1 min readLW link

Quotes from Mo­ral Mazes

Zvi30 May 2019 11:50 UTC
109 points
27 comments53 min readLW link
(thezvi.wordpress.com)

Naked mole-rats: A case study in biolog­i­cal weirdness

eukaryote19 May 2019 18:40 UTC
95 points
14 comments3 min readLW link
(eukaryotewritesblog.com)

Dis­in­cen­tives for par­ti­ci­pat­ing on LW/​AF

Wei Dai10 May 2019 19:46 UTC
86 points
45 comments2 min readLW link

Offer of col­lab­o­ra­tion and/​or mentorship

Vanessa Kosoy16 May 2019 14:16 UTC
76 points
14 comments2 min readLW link

And the AI would have got away with it too, if...

Stuart_Armstrong22 May 2019 21:35 UTC
75 points
7 comments1 min readLW link

Eight Books To Read

Samo Burja14 May 2019 17:40 UTC
69 points
11 comments6 min readLW link
(medium.com)

Co­or­di­na­tion Sur­veys: why we should sur­vey to or­ga­nize re­spon­si­bil­ities, not just predictions

Academian7 May 2019 17:43 UTC
68 points
12 comments3 min readLW link3 reviews

In­ter­pre­ta­tions of “prob­a­bil­ity”

So8res9 May 2019 19:16 UTC
68 points
22 comments5 min readLW link

Sepa­ra­tion of Concerns

abramdemski23 May 2019 21:47 UTC
66 points
30 comments6 min readLW link

Tales From the Amer­i­can Med­i­cal System

Zvi10 May 2019 0:40 UTC
64 points
48 comments4 min readLW link
(thezvi.wordpress.com)

Ed Boy­den on the State of Science

Ben Pace13 May 2019 1:54 UTC
62 points
2 comments9 min readLW link

Dishon­est Up­date Reporting

Zvi4 May 2019 14:10 UTC
59 points
27 comments6 min readLW link2 reviews
(thezvi.wordpress.com)

Kevin Sim­ler’s “Go­ing Crit­i­cal”

habryka16 May 2019 4:36 UTC
56 points
1 comment1 min readLW link
(www.meltingasphalt.com)

Sim­ple Rules of Law

Zvi19 May 2019 0:10 UTC
55 points
24 comments28 min readLW link1 review
(thezvi.wordpress.com)

How to find a lost phone with dead bat­tery, us­ing Google Lo­ca­tion His­tory Takeout

Wei Dai30 May 2019 4:56 UTC
53 points
5 comments1 min readLW link

Towards op­ti­mal play as Villager in a mixed game

Benquo7 May 2019 5:29 UTC
51 points
40 comments3 min readLW link
(benjaminrosshoffman.com)

Micro feed­back loops and learning

Swimmer963 (Miranda Dixon-Luinenburg) 26 May 2019 0:50 UTC
50 points
12 comments6 min readLW link

“UDT2” and “against UD+ASSA”

Wei Dai12 May 2019 4:18 UTC
50 points
7 comments7 min readLW link

Claims & As­sump­tions made in Eter­nity in Six Hours

Ruby8 May 2019 23:11 UTC
50 points
7 comments3 min readLW link

MIRI Sum­mer Fel­lows Program

colm15 May 2019 0:28 UTC
49 points
3 comments2 min readLW link

Self-con­firm­ing pre­dic­tions can be ar­bi­trar­ily bad

Stuart_Armstrong3 May 2019 11:34 UTC
49 points
11 comments5 min readLW link

[Question] How long can peo­ple be pro­duc­tive in [time pe­riod]?

Elizabeth6 May 2019 22:35 UTC
47 points
17 comments1 min readLW link

Blame games

Benquo6 May 2019 2:38 UTC
45 points
13 comments7 min readLW link
(benjaminrosshoffman.com)

Cor­re­spon­dence vi­su­al­iza­tions for differ­ent in­ter­pre­ta­tions of “prob­a­bil­ity”

So8res10 May 2019 17:10 UTC
42 points
3 comments4 min readLW link

Con­straints & Slack­ness Rea­son­ing Exercises

johnswentworth21 May 2019 22:53 UTC
42 points
3 comments6 min readLW link

What Botswana Can Teach Us About Poli­ti­cal Stability

Samo Burja9 May 2019 18:30 UTC
40 points
4 comments1 min readLW link
(medium.com)

An­nounc­ing my YouTube channel

Samo Burja17 May 2019 17:50 UTC
40 points
1 comment3 min readLW link
(medium.com)

Kiss­ing Scars

Logan Riggs9 May 2019 16:00 UTC
39 points
1 comment1 min readLW link

[Question] Which sci­en­tific dis­cov­ery was most ahead of its time?

Richard_Ngo16 May 2019 12:58 UTC
38 points
14 comments1 min readLW link

Go Do Something

Davis_Kingsley21 May 2019 15:42 UTC
38 points
25 comments1 min readLW link

Author­i­tar­ian Empiricism

Benquo3 May 2019 19:34 UTC
38 points
10 comments10 min readLW link
(benjaminrosshoffman.com)

Euro­pean Com­mu­nity Week­end 2019

DreamFlasher16 May 2019 11:44 UTC
38 points
3 comments1 min readLW link

Prob­a­bil­ity in­ter­pre­ta­tions: Examples

So8res11 May 2019 20:32 UTC
38 points
23 comments5 min readLW link

345M ver­sion GPT-2 released

lifelonglearner5 May 2019 2:49 UTC
37 points
0 comments1 min readLW link
(openai.com)

A Map of the Less­wrong-O-Sphere of Interest

Elo4 May 2019 4:19 UTC
35 points
1 comment2 min readLW link

Nash equil­ibriums can be ar­bi­trar­ily bad

Stuart_Armstrong1 May 2019 14:58 UTC
35 points
24 comments2 min readLW link

More Notes on Sim­ple Rules

Zvi21 May 2019 14:50 UTC
34 points
1 comment6 min readLW link
(thezvi.wordpress.com)

“One Man’s Mo­dus Po­nens Is Another Man’s Mo­dus Tol­lens”

gwern17 May 2019 22:03 UTC
33 points
7 comments1 min readLW link
(www.gwern.net)

By de­fault, avoid am­bigu­ous dis­tant situations

Stuart_Armstrong21 May 2019 14:48 UTC
33 points
17 comments3 min readLW link

Crypto quant trad­ing: Naive Bayes

Alexei7 May 2019 19:29 UTC
33 points
13 comments4 min readLW link

To­tal­i­tar­ian eth­i­cal systems

Benquo3 May 2019 19:35 UTC
33 points
12 comments3 min readLW link
(benjaminrosshoffman.com)

The State of Affairs

Jacob Falkovich3 May 2019 16:18 UTC
33 points
0 comments14 min readLW link

The why and how of daily updates

VipulNaik5 May 2019 15:21 UTC
33 points
3 comments4 min readLW link