Page 1

Ar­bital postmortem

alexei
30 Jan 2018 13:48 UTC
327 points
107 commentsLW link

My at­tempt to ex­plain Look­ing, in­sight med­i­ta­tion, and en­light­en­ment in non-mys­te­ri­ous terms

Kaj_Sotala
8 Mar 2018 7:37 UTC
271 points
122 commentsLW link

An Un­trol­lable Math­e­mat­i­cian Illustrated

abramdemski
20 Mar 2018 0:00 UTC
260 points
35 commentsLW link

A LessWrong Crypto Autopsy

Scott Alexander
28 Jan 2018 9:01 UTC
259 points
116 commentsLW link

“Cheat to Win”: Eng­ineer­ing Pos­i­tive So­cial Feedback

sarahconstantin
5 Feb 2018 23:16 UTC
220 points
34 commentsLW link

A vot­ing the­ory primer for rationalists

Jameson Quinn
12 Apr 2018 15:15 UTC
206 points
66 commentsLW link

Notic­ing the Taste of Lotus

Valentine
27 Apr 2018 20:05 UTC
201 points
69 commentsLW link

Critch on ca­reer ad­vice for ju­nior AI-x-risk-con­cerned researchers

Rob Bensinger
12 May 2018 2:13 UTC
201 points
25 commentsLW link

Mak­ing your­self small

Helen
8 Mar 2018 14:26 UTC
190 points
50 commentsLW link

Toolbox-think­ing and Law-thinking

Eliezer Yudkowsky
31 May 2018 21:28 UTC
190 points
43 commentsLW link

Ex­pres­sive Vocabulary

Alicorn
24 May 2018 6:59 UTC
184 points
60 commentsLW link

The Costly Co­or­di­na­tion Mechanism of Com­mon Knowledge

Benito
15 Mar 2018 20:20 UTC
183 points
24 commentsLW link

Norms of Mem­ber­ship for Vol­un­tary Groups

sarahconstantin
11 Dec 2018 22:10 UTC
183 points
8 commentsLW link

2018 AI Align­ment Liter­a­ture Re­view and Char­ity Comparison

Larks
18 Dec 2018 4:46 UTC
183 points
23 commentsLW link

Anti-so­cial Punishment

Martin Sustrik
27 Sep 2018 7:08 UTC
177 points
58 commentsLW link

The Pavlov Strategy

sarahconstantin
20 Dec 2018 16:20 UTC
176 points
7 commentsLW link

Ra­tion­al­ist Com­mu­nity Hub in Moscow: 3 Years Retrospective

berekuk
25 Aug 2018 0:28 UTC
174 points
23 commentsLW link

Meta-tations on Moder­a­tion: Towards Public Archipelago

Raemon
25 Feb 2018 3:59 UTC
173 points
173 commentsLW link

“Tak­ing AI Risk Se­ri­ously” (thoughts by Critch)

Raemon
29 Jan 2018 9:27 UTC
171 points
68 commentsLW link

Ter­ror­ism, Tylenol, and dan­ger­ous information

Davis_Kingsley
12 May 2018 10:20 UTC
171 points
45 commentsLW link

Challenges to Chris­ti­ano’s ca­pa­bil­ity am­plifi­ca­tion proposal

Eliezer Yudkowsky
19 May 2018 18:18 UTC
170 points
38 commentsLW link

An­nounce­ment: AI al­ign­ment prize win­ners and next round

cousin_it
15 Jan 2018 14:33 UTC
166 points
68 commentsLW link

Ro­bust­ness to Scale

Scott Garrabrant
21 Feb 2018 22:55 UTC
163 points
15 commentsLW link

The In­tel­li­gent So­cial Web

Valentine
22 Feb 2018 18:55 UTC
163 points
87 commentsLW link

Pri­son­ers’ Dilemma with Costs to Modeling

Scott Garrabrant
5 Jun 2018 4:51 UTC
163 points
18 commentsLW link

Lo­cal Val­idity as a Key to San­ity and Civilization

Eliezer Yudkowsky
7 Apr 2018 4:25 UTC
161 points
52 commentsLW link

In­con­ve­nience Is Qual­i­ta­tively Bad

Alicorn
26 Feb 2018 23:27 UTC
157 points
50 commentsLW link

Un­rol­ling so­cial metacog­ni­tion: Three lev­els of meta are not enough.

Academian
25 Aug 2018 12:00 UTC
157 points
29 commentsLW link

The Loud­est Alarm Is Prob­a­bly False

orthonormal
2 Jan 2018 16:38 UTC
156 points
21 commentsLW link

Inad­e­quate Equil­ibria vs. Gover­nance of the Commons

Martin Sustrik
25 May 2018 13:17 UTC
155 points
14 commentsLW link

An­nounce­ment: AI al­ign­ment prize round 2 win­ners and next round

cousin_it
16 Apr 2018 3:08 UTC
153 points
29 commentsLW link

Sources of in­tu­itions and data on AGI

Scott Garrabrant
31 Jan 2018 23:30 UTC
152 points
26 commentsLW link

A Sketch of Good Communication

Benito
31 Mar 2018 22:48 UTC
150 points
28 commentsLW link

Embed­ded Agents

abramdemski
29 Oct 2018 19:53 UTC
150 points
29 commentsLW link

Affor­dance Widths

ialdabaoth
10 May 2018 23:37 UTC
148 points
22 commentsLW link

Oops on Com­mod­ity Prices

sarahconstantin
10 Jun 2018 15:40 UTC
148 points
8 commentsLW link

The Rocket Align­ment Problem

Eliezer Yudkowsky
4 Oct 2018 0:38 UTC
148 points
26 commentsLW link

Some cruxes on im­pact­ful al­ter­na­tives to AI policy work

ricraz
10 Oct 2018 13:35 UTC
146 points
13 commentsLW link

Act of Charity

jessicata
17 Nov 2018 5:19 UTC
142 points
45 commentsLW link

Write a Thou­sand Roads to Rome

Screwtape
8 Feb 2018 18:09 UTC
140 points
13 commentsLW link

Give praise

toonalfrink
29 Apr 2018 21:00 UTC
140 points
76 commentsLW link

Real­ism about rationality

ricraz
16 Sep 2018 10:46 UTC
140 points
69 commentsLW link
(thinkingcomplete.blogspot.com)

Leav­ing beta: Vot­ing on mov­ing to LessWrong.com

Vaniver
11 Mar 2018 22:53 UTC
139 points
65 commentsLW link

LW Mi­gra­tion Announcement

Vaniver
22 Mar 2018 2:18 UTC
139 points
14 commentsLW link

On ex­act math­e­mat­i­cal formulae

daozaich
22 Apr 2018 19:41 UTC
138 points
12 commentsLW link

Is Rhetoric Worth Learn­ing?

sarahconstantin
6 Apr 2018 22:03 UTC
137 points
54 commentsLW link

A model I use when mak­ing plans to re­duce AI x-risk

Benito
19 Jan 2018 0:21 UTC
136 points
40 commentsLW link

Of Two Minds

Valentine
17 May 2018 4:34 UTC
136 points
12 commentsLW link

Prize for prob­a­ble problems

paulfchristiano
8 Mar 2018 16:58 UTC
135 points
62 commentsLW link

Ra­tion­al­ity: Abridged

Quaerendo
6 Jan 2018 0:20 UTC
135 points
24 commentsLW link