Page 1

What failure looks like

paulfchristiano
17 Mar 2019 20:18 UTC
208 points
42 comments8 min readLW link

Per­son­al­ized Medicine For Real

sarahconstantin
4 Mar 2019 22:40 UTC
199 points
15 comments5 min readLW link
(srconstantin.wordpress.com)

Align­ment Re­search Field Guide

abramdemski
8 Mar 2019 19:57 UTC
197 points
5 comments17 min readLW link

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

Buck
22 Feb 2019 20:01 UTC
195 points
15 comments9 min readLW link

Be­ing the (Pareto) Best in the World

johnswentworth
24 Jun 2019 18:36 UTC
169 points
35 comments3 min readLW link

Jeff Hawk­ins on neu­ro­mor­phic AGI within 20 years

steve2152
15 Jul 2019 19:16 UTC
153 points
11 comments12 min readLW link

Build­ing up to an In­ter­nal Fam­ily Sys­tems model

Kaj_Sotala
26 Jan 2019 12:25 UTC
152 points
30 comments28 min readLW link

Asym­met­ric Justice

Zvi
25 Apr 2019 16:00 UTC
148 points
86 comments5 min readLW link
(thezvi.wordpress.com)

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

Hazard
31 Jul 2019 13:34 UTC
142 points
56 comments4 min readLW link

Steel­man­ning Divination

Vaniver
5 Jun 2019 22:53 UTC
141 points
36 comments6 min readLW link

The Re­la­tion­ship Between the Village and the Mission

Raemon
12 May 2019 21:09 UTC
139 points
67 comments18 min readLW link

The 3 Books Tech­nique for Learn­ing a New Skilll

mr-hire
9 Jan 2019 12:45 UTC
137 points
45 comments2 min readLW link

Mis­takes with Con­ser­va­tion of Ex­pected Evidence

abramdemski
8 Jun 2019 23:07 UTC
135 points
15 comments12 min readLW link

Book Re­view: The Se­cret Of Our Success

Scott Alexander
5 Jun 2019 6:50 UTC
132 points
8 comments25 min readLW link
(slatestarcodex.com)

In­tegrity and ac­countabil­ity are core parts of rationality

habryka
15 Jul 2019 20:22 UTC
132 points
61 comments6 min readLW link

Yes Re­quires the Pos­si­bil­ity of No

Scott Garrabrant
17 May 2019 22:39 UTC
126 points
39 comments2 min readLW link

Thoughts on Hu­man Models

xrchz
21 Feb 2019 9:10 UTC
123 points
21 comments10 min readLW link

Disen­tan­gling ar­gu­ments for the im­por­tance of AI safety

ricraz
21 Jan 2019 12:41 UTC
120 points
21 comments8 min readLW link

Hu­mans Who Are Not Con­cen­trat­ing Are Not Gen­eral Intelligences

sarahconstantin
25 Feb 2019 20:40 UTC
120 points
29 comments6 min readLW link
(srconstantin.wordpress.com)

Co­her­ent de­ci­sions im­ply con­sis­tent utilities

Eliezer Yudkowsky
12 May 2019 21:33 UTC
119 points
53 comments26 min readLW link

The Amish, and Strate­gic Norms around Technology

Raemon
24 Mar 2019 22:16 UTC
116 points
11 comments3 min readLW link

Rest Days vs Re­cov­ery Days

Unreal
19 Mar 2019 22:37 UTC
115 points
20 comments6 min readLW link

Rea­son isn’t magic

Benquo
18 Jun 2019 4:04 UTC
115 points
11 comments2 min readLW link
(benjaminrosshoffman.com)

Power Buys You Dis­tance From The Crime

Elizabeth
2 Aug 2019 20:50 UTC
114 points
64 comments7 min readLW link
(acesounderglass.com)

Some Thoughts on My Psy­chi­a­try Practice

Laura B
16 Jan 2019 23:16 UTC
113 points
31 comments4 min readLW link

Risks from Learned Op­ti­miza­tion: Introduction

evhub
31 May 2019 23:44 UTC
112 points
31 comments12 min readLW link

The Costs of Reliability

sarahconstantin
20 Jul 2019 1:20 UTC
111 points
3 comments3 min readLW link
(srconstantin.wordpress.com)

Fo­rum par­ti­ci­pa­tion as a re­search strategy

Wei_Dai
30 Jul 2019 18:09 UTC
111 points
32 comments3 min readLW link

Writ­ing chil­dren’s pic­ture books

jessicata
25 Jun 2019 21:43 UTC
110 points
20 comments5 min readLW link
(unstableontology.com)

Soft take­off can still lead to de­ci­sive strate­gic advantage

Daniel Kokotajlo
23 Aug 2019 16:39 UTC
110 points
27 comments8 min readLW link

Offer of col­lab­o­ra­tion and/​or mentorship

Vanessa Kosoy
16 May 2019 14:16 UTC
109 points
12 comments2 min readLW link

An­nounc­ing the Cen­ter for Ap­plied Postrationality

DonyChristie
2 Apr 2019 1:17 UTC
108 points
14 comments1 min readLW link

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

Raemon
8 Jun 2019 0:24 UTC
107 points
27 comments12 min readLW link

A Key Power of the Pres­i­dent is to Co­or­di­nate the Ex­e­cu­tion of Ex­ist­ing Con­crete Plans

Ben Pace
16 Jul 2019 5:06 UTC
105 points
13 comments10 min readLW link

De­grees of Freedom

sarahconstantin
2 Apr 2019 21:10 UTC
103 points
27 comments11 min readLW link
(srconstantin.wordpress.com)

Selec­tion vs Control

abramdemski
2 Jun 2019 7:01 UTC
102 points
16 comments11 min readLW link

Rule Thinkers In, Not Out

Scott Alexander
27 Feb 2019 2:40 UTC
101 points
43 comments4 min readLW link
(slatestarcodex.com)

The Real Rules Have No Exceptions

Said Achmiz
23 Jul 2019 3:38 UTC
101 points
42 comments1 min readLW link

S-Curves for Trend Forecasting

mr-hire
23 Jan 2019 18:17 UTC
100 points
14 comments3 min readLW link

Say Wrong Things

G Gordon Worley III
24 May 2019 22:11 UTC
99 points
11 comments4 min readLW link

Liter­a­ture Re­view: Distributed Teams

Elizabeth
16 Apr 2019 1:19 UTC
98 points
34 comments6 min readLW link

Ar­bital scrape

emmab
6 Jun 2019 23:11 UTC
96 points
23 comments1 min readLW link

Karma-Change Notifications

jimrandomh
2 Mar 2019 2:52 UTC
95 points
44 comments1 min readLW link

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

Wei_Dai
22 May 2019 6:24 UTC
94 points
20 comments1 min readLW link

Why Subagents?

johnswentworth
1 Aug 2019 22:17 UTC
94 points
18 comments7 min readLW link

Refram­ing Su­per­in­tel­li­gence: Com­pre­hen­sive AI Ser­vices as Gen­eral Intelligence

rohinmshah
8 Jan 2019 7:12 UTC
93 points
69 comments5 min readLW link
(www.fhi.ox.ac.uk)

Book Sum­mary: Con­scious­ness and the Brain

Kaj_Sotala
16 Jan 2019 14:43 UTC
93 points
14 comments26 min readLW link

Align­ment Newslet­ter One Year Retrospective

rohinmshah
10 Apr 2019 6:58 UTC
93 points
31 comments21 min readLW link

Com­plex Be­hav­ior from Sim­ple (Sub)Agents

moridinamael
10 May 2019 21:44 UTC
92 points
8 comments9 min readLW link

Counterspells

Virgil Kurkjian
27 Apr 2019 23:37 UTC
91 points
24 comments10 min readLW link