The Parable of Pre­dict-O-Matic

abramdemski15 Oct 2019 0:49 UTC
245 points
41 comments14 min readLW link5 nominations4 reviews

What failure looks like

paulfchristiano17 Mar 2019 20:18 UTC
240 points
48 comments8 min readLW link2 nominations2 reviews

Heads I Win, Tails?—Never Heard of Her; Or, Selec­tive Re­port­ing and the Tragedy of the Green Rationalists

Zack_M_Davis24 Sep 2019 4:12 UTC
223 points
37 comments8 min readLW link2 nominations2 reviews

Book sum­mary: Un­lock­ing the Emo­tional Brain

Kaj_Sotala8 Oct 2019 19:11 UTC
222 points
32 comments21 min readLW link2 nominations3 reviews

Wel­come to LessWrong!

14 Jun 2019 19:42 UTC
209 points
21 comments4 min readLW link

Be­ing the (Pareto) Best in the World

johnswentworth24 Jun 2019 18:36 UTC
208 points
46 comments3 min readLW link3 nominations3 reviews

Is Ra­tion­al­ist Self-Im­prove­ment Real?

Jacob Falkovich9 Dec 2019 17:11 UTC
203 points
73 comments11 min readLW link2 nominations3 reviews

Per­son­al­ized Medicine For Real

sarahconstantin4 Mar 2019 22:40 UTC
201 points
16 comments5 min readLW link
(srconstantin.wordpress.com)

How to Ig­nore Your Emo­tions (while also think­ing you’re awe­some at emo­tions)

Hazard31 Jul 2019 13:34 UTC
200 points
67 comments4 min readLW link2 nominations4 reviews

“Other peo­ple are wrong” vs “I am right”

Buck22 Feb 2019 20:01 UTC
199 points
19 comments9 min readLW link2 nominations2 reviews

Align­ment Re­search Field Guide

abramdemski8 Mar 2019 19:57 UTC
199 points
9 comments17 min readLW link2 nominations2 reviews

The Zet­telkas­ten Method

abramdemski20 Sep 2019 13:15 UTC
193 points
77 comments42 min readLW link2 nominations3 reviews

De­bate on In­stru­men­tal Con­ver­gence be­tween LeCun, Rus­sell, Ben­gio, Zador, and More

Ben Pace4 Oct 2019 4:08 UTC
176 points
54 comments15 min readLW link2 nominations2 reviews

Build­ing up to an In­ter­nal Fam­ily Sys­tems model

Kaj_Sotala26 Jan 2019 12:25 UTC
174 points
84 comments28 min readLW link2 nominations2 reviews

The 3 Books Tech­nique for Learn­ing a New Skilll

Matt Goldenberg9 Jan 2019 12:45 UTC
172 points
48 comments2 min readLW link

Asym­met­ric Justice

Zvi25 Apr 2019 16:00 UTC
169 points
96 comments5 min readLW link3 nominations2 reviews
(thezvi.wordpress.com)

Steel­man­ning Divination

Vaniver5 Jun 2019 22:53 UTC
164 points
47 comments6 min readLW link2 nominations2 reviews

Mis­takes with Con­ser­va­tion of Ex­pected Evidence

abramdemski8 Jun 2019 23:07 UTC
159 points
21 comments12 min readLW link2 nominations1 review

Hu­mans Who Are Not Con­cen­trat­ing Are Not Gen­eral Intelligences

sarahconstantin25 Feb 2019 20:40 UTC
156 points
34 comments6 min readLW link4 nominations1 review
(srconstantin.wordpress.com)

Jeff Hawk­ins on neu­ro­mor­phic AGI within 20 years

Steven Byrnes15 Jul 2019 19:16 UTC
155 points
24 comments12 min readLW link1 nomination

Yes Re­quires the Pos­si­bil­ity of No

Scott Garrabrant17 May 2019 22:39 UTC
153 points
49 comments2 min readLW link6 nominations2 reviews

Rest Days vs Re­cov­ery Days

Unreal19 Mar 2019 22:37 UTC
150 points
33 comments6 min readLW link2 nominations1 review

Power Buys You Dis­tance From The Crime

Elizabeth2 Aug 2019 20:50 UTC
148 points
75 comments7 min readLW link2 nominations1 review
(acesounderglass.com)

Notic­ing Frame Differences

Raemon30 Sep 2019 1:24 UTC
148 points
35 comments8 min readLW link3 nominations2 reviews

Book Re­view: De­sign Prin­ci­ples of Biolog­i­cal Circuits

johnswentworth5 Nov 2019 6:49 UTC
147 points
22 comments12 min readLW link2 nominations1 review

Some Thoughts on My Psy­chi­a­try Practice

Laura B16 Jan 2019 23:16 UTC
144 points
43 comments4 min readLW link2 nominations2 reviews

Book Re­view: The Se­cret Of Our Success

Scott Alexander5 Jun 2019 6:50 UTC
144 points
17 comments25 min readLW link3 nominations2 reviews
(slatestarcodex.com)

RAISE post-mortem

toonalfrink24 Nov 2019 16:19 UTC
144 points
12 comments4 min readLW link

Rule Thinkers In, Not Out

Scott Alexander27 Feb 2019 2:40 UTC
142 points
59 comments4 min readLW link3 nominations4 reviews
(slatestarcodex.com)

Risks from Learned Op­ti­miza­tion: Introduction

31 May 2019 23:44 UTC
140 points
40 comments12 min readLW link3 nominations3 reviews

Make more land

jefftk16 Oct 2019 11:20 UTC
140 points
32 comments2 min readLW link2 nominations5 reviews
(www.jefftk.com)

Chris Olah’s views on AGI safety

evhub1 Nov 2019 20:13 UTC
140 points
38 comments12 min readLW link2 nominations2 reviews

The Costs of Reliability

sarahconstantin20 Jul 2019 1:20 UTC
139 points
12 comments3 min readLW link2 nominations2 reviews
(srconstantin.wordpress.com)

Moloch Hasn’t Won

Zvi28 Dec 2019 16:30 UTC
138 points
37 comments7 min readLW link3 nominations1 review
(thezvi.wordpress.com)

In­tegrity and ac­countabil­ity are core parts of rationality

habryka15 Jul 2019 20:22 UTC
136 points
66 comments6 min readLW link2 nominations1 review

Honor­ing Petrov Day on LessWrong, in 2019

Ben Pace26 Sep 2019 9:10 UTC
136 points
169 comments4 min readLW link

The un­ex­pected difficulty of com­par­ing AlphaS­tar to humans

Richard Korzekwa 18 Sep 2019 2:20 UTC
133 points
34 comments26 min readLW link2 nominations
(aiimpacts.org)

Seek­ing Power is Often Ro­bustly In­stru­men­tal in MDPs

5 Dec 2019 2:33 UTC
133 points
34 comments17 min readLW link2 nominations2 reviews
(arxiv.org)

Rea­son isn’t magic

Benquo18 Jun 2019 4:04 UTC
130 points
18 comments2 min readLW link2 nominations3 reviews
(benjaminrosshoffman.com)

Un­der­stand­ing “Deep Dou­ble Des­cent”

evhub6 Dec 2019 0:00 UTC
130 points
40 comments5 min readLW link3 nominations4 reviews

The Amish, and Strate­gic Norms around Technology

Raemon24 Mar 2019 22:16 UTC
129 points
18 comments3 min readLW link2 nominations2 reviews

2019 AI Align­ment Liter­a­ture Re­view and Char­ity Comparison

Larks19 Dec 2019 3:00 UTC
129 points
18 comments62 min readLW link

From Per­sonal to Pri­son Gangs: En­forc­ing Proso­cial Behavior

johnswentworth24 Jan 2019 18:07 UTC
127 points
24 comments5 min readLW link2 nominations2 reviews

The Re­la­tion­ship Between the Village and the Mission

Raemon12 May 2019 21:09 UTC
126 points
68 comments18 min readLW link

Paper-Read­ing for Gears

johnswentworth4 Dec 2019 21:02 UTC
126 points
6 comments4 min readLW link2 nominations1 review

The Schel­ling Choice is “Rab­bit”, not “Stag”

Raemon8 Jun 2019 0:24 UTC
125 points
53 comments12 min readLW link2 nominations3 reviews

The Forces of Bland­ness and the Disagree­able Majority

sarahconstantin28 Apr 2019 19:44 UTC
124 points
27 comments3 min readLW link2 nominations2 reviews
(srconstantin.wordpress.com)

Disen­tan­gling ar­gu­ments for the im­por­tance of AI safety

Richard_Ngo21 Jan 2019 12:41 UTC
123 points
23 comments8 min readLW link

Co­her­ent de­ci­sions im­ply con­sis­tent utilities

Eliezer Yudkowsky12 May 2019 21:33 UTC
123 points
80 comments26 min readLW link3 nominations3 reviews

Evolu­tion of Modularity

johnswentworth14 Nov 2019 6:49 UTC
123 points
9 comments2 min readLW link2 nominations1 review