RSS

Best of LessWrong

TagLast edit: 30 Apr 2024 3:09 UTC by habryka

The Best of LessWrong tag is applied to all posts which were voted highly enough in the annual LessWrong review to make it onto the Best of LessWrong page.

ARC’s first tech­ni­cal re­port: Elic­it­ing La­tent Knowledge

paulfchristiano, Mark Xu and Ajeya Cotra
14 Dec 2021 20:09 UTC
225 points
90 comments1 min readLW link3 reviews
(docs.google.com)

Sav­ing Time

Scott Garrabrant18 May 2021 20:11 UTC
156 points
20 comments4 min readLW link1 review

Lars Doucet’s Ge­or­gism se­ries on As­tral Codex Ten

Sune4 Dec 2021 19:43 UTC
13 points
2 comments1 min readLW link1 review
(astralcodexten.substack.com)

Worst-case think­ing in AI alignment

Buck23 Dec 2021 1:29 UTC
162 points
18 comments6 min readLW link2 reviews

The Point of Trade

Eliezer Yudkowsky22 Jun 2021 17:56 UTC
171 points
76 comments4 min readLW link1 review

Spe­cial­iz­ing in Prob­lems We Don’t Understand

johnswentworth10 Apr 2021 22:40 UTC
159 points
29 comments8 min readLW link1 review

You are prob­a­bly un­der­es­ti­mat­ing how good self-love can be

Charlie Rogers-Smith14 Nov 2021 0:41 UTC
145 points
19 comments12 min readLW link1 review

Cup-Stack­ing Skills (or, Reflex­ive In­vol­un­tary Men­tal Mo­tions)

[DEACTIVATED] Duncan Sabien11 Oct 2021 7:16 UTC
117 points
36 comments7 min readLW link2 reviews

“PR” is cor­ro­sive; “rep­u­ta­tion” is not.

AnnaSalamon14 Feb 2021 3:32 UTC
307 points
93 comments2 min readLW link3 reviews

Nu­clear war is un­likely to cause hu­man extinction

Jeffrey Ladish7 Nov 2020 5:42 UTC
124 points
47 comments11 min readLW link3 reviews

Can crimes be dis­cussed liter­ally?

Benquo22 Mar 2020 20:17 UTC
102 points
38 comments2 min readLW link3 reviews
(benjaminrosshoffman.com)

The Road to Mazedom

Zvi18 Jan 2020 14:10 UTC
94 points
25 comments7 min readLW link2 reviews
(thezvi.wordpress.com)

Notes from “Don’t Shoot the Dog”

juliawise2 Apr 2021 16:34 UTC
244 points
11 comments12 min readLW link1 review

Strong Ev­i­dence is Common

Mark Xu13 Mar 2021 22:04 UTC
244 points
49 comments1 min readLW link4 reviews
(markxu.com)

The date of AI Takeover is not the day the AI takes over

Daniel Kokotajlo22 Oct 2020 10:41 UTC
145 points
32 comments2 min readLW link1 review

In­ner Align­ment: Ex­plain like I’m 12 Edition

Rafael Harth1 Aug 2020 15:24 UTC
179 points
46 comments13 min readLW link2 reviews

Frame Control

Aella27 Nov 2021 22:59 UTC
314 points
282 comments23 min readLW link2 reviews

What Do GDP Growth Curves Really Mean?

johnswentworth7 Oct 2021 21:58 UTC
219 points
64 comments8 min readLW link2 reviews

Anti-Aging: State of the Art

JackH31 Dec 2020 19:07 UTC
371 points
176 comments11 min readLW link1 review

Covid-19: My Cur­rent Model

Zvi31 May 2020 17:40 UTC
188 points
74 comments19 min readLW link1 review
(thezvi.wordpress.com)

Shoulder Ad­vi­sors 101

[DEACTIVATED] Duncan Sabien9 Oct 2021 5:30 UTC
193 points
124 comments14 min readLW link2 reviews

Utility Max­i­miza­tion = De­scrip­tion Length Minimization

johnswentworth18 Feb 2021 18:04 UTC
208 points
44 comments5 min readLW link

A non-mys­ti­cal ex­pla­na­tion of “no-self” (three char­ac­ter­is­tics se­ries)

Kaj_Sotala8 May 2020 10:37 UTC
105 points
65 comments20 min readLW link1 review

What Mul­tipo­lar Failure Looks Like, and Ro­bust Agent-Ag­nos­tic Pro­cesses (RAAPs)

Andrew_Critch31 Mar 2021 23:50 UTC
272 points
64 comments22 min readLW link1 review

Elephant seal 2

KatjaGrace2 Feb 2021 9:40 UTC
57 points
5 comments1 min readLW link2 reviews
(worldspiritsockpuppet.com)

The Poin­t­ers Prob­lem: Hu­man Values Are A Func­tion Of Hu­mans’ La­tent Variables

johnswentworth18 Nov 2020 17:47 UTC
124 points
49 comments11 min readLW link2 reviews

Stud­ies On Slack

Scott Alexander13 May 2020 5:00 UTC
151 points
34 comments24 min readLW link1 review
(slatestarcodex.com)

The Death of Be­hav­ioral Economics

habryka22 Aug 2021 22:39 UTC
154 points
24 comments1 min readLW link2 reviews
(www.thebehavioralscientist.com)

Fea­ture Selection

Zack_M_Davis1 Nov 2021 0:22 UTC
315 points
24 comments16 min readLW link1 review

Draft re­port on AI timelines

Ajeya Cotra18 Sep 2020 23:47 UTC
214 points
56 comments1 min readLW link1 review

Search ver­sus design

Alex Flint16 Aug 2020 16:53 UTC
100 points
40 comments36 min readLW link1 review

Rul­ing Out Every­thing Else

[DEACTIVATED] Duncan Sabien27 Oct 2021 21:50 UTC
190 points
51 comments21 min readLW link2 reviews

There’s no such thing as a tree (phy­lo­ge­net­i­cally)

eukaryote3 May 2021 3:47 UTC
333 points
58 comments8 min readLW link2 reviews
(eukaryotewritesblog.com)

Si­mu­lacrum 3 As Stag-Hunt Strategy

johnswentworth26 Jan 2021 19:40 UTC
179 points
37 comments4 min readLW link3 reviews

Lies, Damn Lies, and Fabri­cated Options

[DEACTIVATED] Duncan Sabien17 Oct 2021 2:47 UTC
288 points
132 comments14 min readLW link2 reviews

Catch­ing the Spark

LoganStrohl30 Jan 2021 23:23 UTC
111 points
21 comments36 min readLW link1 review

Is Suc­cess the Enemy of Free­dom? (Full)

alkjash26 Oct 2020 20:25 UTC
291 points
68 comments9 min readLW link1 review
(radimentary.wordpress.com)

What cog­ni­tive bi­ases feel like from the inside

chaosmage3 Jan 2020 14:24 UTC
249 points
32 comments4 min readLW link

Swiss Poli­ti­cal Sys­tem: More than You ever Wanted to Know (I.)

Martin Sustrik19 Jul 2020 1:11 UTC
171 points
39 comments24 min readLW link2 reviews

My re­search methodology

paulfchristiano22 Mar 2021 21:20 UTC
159 points
38 comments16 min readLW link1 review
(ai-alignment.com)

The Plan

johnswentworth10 Dec 2021 23:41 UTC
254 points
78 comments14 min readLW link1 review

Trapped Pri­ors As A Ba­sic Prob­lem Of Rationality

Scott Alexander12 Mar 2021 20:02 UTC
141 points
32 comments14 min readLW link3 reviews

The Align­ment Prob­lem: Ma­chine Learn­ing and Hu­man Values

Rohin Shah6 Oct 2020 17:41 UTC
120 points
7 comments6 min readLW link1 review
(www.amazon.com)

In­tro­duc­tion to Carte­sian Frames

Scott Garrabrant22 Oct 2020 13:00 UTC
153 points
32 comments22 min readLW link1 review

Fun with +12 OOMs of Compute

Daniel Kokotajlo1 Mar 2021 13:30 UTC
224 points
86 comments12 min readLW link2 reviews

AGI safety from first prin­ci­ples: Introduction

Richard_Ngo28 Sep 2020 19:53 UTC
121 points
18 comments2 min readLW link1 review

An overview of 11 pro­pos­als for build­ing safe ad­vanced AI

evhub29 May 2020 20:38 UTC
205 points
36 comments38 min readLW link2 reviews

Finite Fac­tored Sets

Scott Garrabrant23 May 2021 20:52 UTC
146 points
95 comments24 min readLW link1 review

Your Cheer­ful Price

Eliezer Yudkowsky13 Feb 2021 5:41 UTC
262 points
82 comments17 min readLW link6 reviews

In­tro­duc­tion To The In­fra-Bayesi­anism Sequence

Diffractor and Vanessa Kosoy
26 Aug 2020 20:31 UTC
109 points
62 comments14 min readLW link2 reviews

Jean Mon­net: The Guerilla Bureaucrat

Martin Sustrik20 Mar 2021 10:37 UTC
175 points
25 comments18 min readLW link1 review

Cry­on­ics signup guide #1: Overview

mingyuan6 Jan 2021 0:25 UTC
150 points
33 comments6 min readLW link1 review

The Solomonoff Prior is Malign

Mark Xu14 Oct 2020 1:33 UTC
168 points
52 comments16 min readLW link3 reviews

Si­mu­lacra Levels and their Interactions

Zvi15 Jun 2020 13:10 UTC
197 points
50 comments17 min readLW link1 review
(thezvi.wordpress.com)

Grokking the In­ten­tional Stance

jbkjr31 Aug 2021 15:49 UTC
43 points
22 comments20 min readLW link1 review

The Treach­er­ous Path to Rationality

Jacob Falkovich9 Oct 2020 15:34 UTC
204 points
115 comments11 min readLW link1 review

The ground of optimization

Alex Flint20 Jun 2020 0:38 UTC
245 points
80 comments27 min readLW link1 review

Real­ity-Re­veal­ing and Real­ity-Mask­ing Puzzles

AnnaSalamon16 Jan 2020 16:15 UTC
258 points
57 comments13 min readLW link1 review

What 2026 looks like

Daniel Kokotajlo6 Aug 2021 16:14 UTC
473 points
150 comments16 min readLW link1 review

Effi­cien­tZero: How It Works

1a3orn26 Nov 2021 15:17 UTC
292 points
50 comments29 min readLW link1 review

How fac­to­ries were made safe

jasoncrawford12 Sep 2021 19:58 UTC
181 points
46 comments18 min readLW link1 review
(rootsofprogress.org)

Ngo and Yud­kowsky on al­ign­ment difficulty

Eliezer Yudkowsky and Richard_Ngo
15 Nov 2021 20:31 UTC
250 points
148 comments99 min readLW link1 review

What Money Can­not Buy

johnswentworth1 Feb 2020 20:11 UTC
318 points
49 comments4 min readLW link1 review

Leaky Del­e­ga­tion: You are not a Commodity

Darmani25 Jan 2021 2:04 UTC
297 points
34 comments15 min readLW link1 review

Seven Years of Spaced Rep­e­ti­tion Soft­ware in the Classroom

tanagrabeast4 Mar 2021 2:42 UTC
265 points
38 comments34 min readLW link1 review

Some AI re­search ar­eas and their rele­vance to ex­is­ten­tial safety

Andrew_Critch19 Nov 2020 3:18 UTC
204 points
37 comments50 min readLW link2 reviews

Why haven’t we cel­e­brated any ma­jor achieve­ments lately?

jasoncrawford17 Aug 2020 20:34 UTC
194 points
69 comments12 min readLW link2 reviews
(rootsofprogress.org)

Co­or­di­na­tion as a Scarce Resource

johnswentworth25 Jan 2020 23:32 UTC
231 points
22 comments4 min readLW link2 reviews

Trans­porta­tion as a Constraint

johnswentworth6 Apr 2020 4:58 UTC
177 points
32 comments6 min readLW link1 review

Self-In­tegrity and the Drown­ing Child

Eliezer Yudkowsky24 Oct 2021 20:57 UTC
329 points
85 comments5 min readLW link1 review

The Ra­tion­al­ists of the 1950s (and be­fore) also called them­selves “Ra­tion­al­ists”

Owain_Evans28 Nov 2021 20:17 UTC
187 points
30 comments3 min readLW link1 review

Split and Commit

[DEACTIVATED] Duncan Sabien21 Nov 2021 6:27 UTC
178 points
33 comments7 min readLW link1 review

Com­ments on Car­l­smith’s “Is power-seek­ing AI an ex­is­ten­tial risk?”

So8res13 Nov 2021 4:29 UTC
138 points
14 comments40 min readLW link1 review

The First Sam­ple Gives the Most Information

Mark Xu24 Dec 2020 20:39 UTC
132 points
16 comments1 min readLW link1 review
(markxu.com)

My com­pu­ta­tional frame­work for the brain

Steven Byrnes14 Sep 2020 14:19 UTC
150 points
26 comments13 min readLW link1 review

Most Pri­soner’s Dilem­mas are Stag Hunts; Most Stag Hunts are Schel­ling Problems

abramdemski14 Sep 2020 22:13 UTC
177 points
36 comments10 min readLW link3 reviews

Cred­i­bil­ity of the CDC on SARS-CoV-2

Elizabeth and jimrandomh
7 Mar 2020 2:00 UTC
226 points
119 comments6 min readLW link1 review

How uniform is the neo­cor­tex?

zhukeepa4 May 2020 2:16 UTC
79 points
23 comments11 min readLW link1 review

High­lights from The Au­to­bi­og­ra­phy of An­drew Carnegie

jasoncrawford8 Apr 2021 22:03 UTC
92 points
9 comments19 min readLW link1 review
(rootsofprogress.org)

Why Neu­ral Net­works Gen­er­al­ise, and Why They Are (Kind of) Bayesian

Joar Skalse29 Dec 2020 13:33 UTC
74 points
58 comments1 min readLW link1 review

Against GDP as a met­ric for timelines and take­off speeds

Daniel Kokotajlo29 Dec 2020 17:42 UTC
140 points
19 comments14 min readLW link1 review

microCOVID.org: A tool to es­ti­mate COVID risk from com­mon activities

catherio29 Aug 2020 23:01 UTC
169 points
36 comments1 min readLW link1 review
(microcovid.org)

“Can you keep this con­fi­den­tial? How do you know?”

Raemon21 Jul 2020 0:33 UTC
159 points
41 comments3 min readLW link2 reviews

See­ing the Smoke

Jacob Falkovich28 Feb 2020 18:26 UTC
198 points
29 comments5 min readLW link1 review

In­ter­faces as a Scarce Resource

johnswentworth5 Mar 2020 18:20 UTC
187 points
15 comments12 min readLW link1 review

All Pos­si­ble Views About Hu­man­ity’s Fu­ture Are Wild

HoldenKarnofsky3 Sep 2021 20:19 UTC
146 points
37 comments8 min readLW link1 review

This Can’t Go On

HoldenKarnofsky18 Sep 2021 23:50 UTC
73 points
55 comments7 min readLW link2 reviews

Ta­boo “Out­side View”

Daniel Kokotajlo17 Jun 2021 9:36 UTC
348 points
33 comments8 min readLW link3 reviews

Another (outer) al­ign­ment failure story

paulfchristiano7 Apr 2021 20:12 UTC
241 points
38 comments12 min readLW link1 review

To listen well, get curious

benkuhn13 Dec 2020 0:20 UTC
352 points
37 comments4 min readLW link1 review
(www.benkuhn.net)

Align­ment By Default

johnswentworth12 Aug 2020 18:54 UTC
173 points
94 comments11 min readLW link2 reviews

Cortés, Pizarro, and Afonso as Prece­dents for Takeover

Daniel Kokotajlo1 Mar 2020 3:49 UTC
168 points
78 comments11 min readLW link1 review

Selec­tion The­o­rems: A Pro­gram For Un­der­stand­ing Agents

johnswentworth28 Sep 2021 5:03 UTC
123 points
28 comments6 min readLW link2 reviews

When Money Is Abun­dant, Knowl­edge Is The Real Wealth

johnswentworth3 Nov 2020 17:34 UTC
317 points
61 comments5 min readLW link3 reviews

CFAR Par­ti­ci­pant Hand­book now available to all

[DEACTIVATED] Duncan Sabien3 Jan 2020 15:43 UTC
248 points
40 comments1 min readLW link2 reviews

An Ortho­dox Case Against Utility Functions

abramdemski7 Apr 2020 19:18 UTC
152 points
65 comments8 min readLW link2 reviews

How To Write Quickly While Main­tain­ing Epistemic Rigor

johnswentworth28 Aug 2021 17:52 UTC
429 points
38 comments4 min readLW link3 reviews

Mo­tive Ambiguity

Zvi15 Dec 2020 18:10 UTC
172 points
58 comments4 min readLW link2 reviews
(thezvi.wordpress.com)

Inac­cessible information

paulfchristiano3 Jun 2020 5:10 UTC
83 points
17 comments14 min readLW link2 reviews
(ai-alignment.com)

Dis­con­tin­u­ous progress in his­tory: an update

KatjaGrace14 Apr 2020 0:00 UTC
186 points
25 comments31 min readLW link1 review
(aiimpacts.org)

Fre­quent ar­gu­ments about alignment

John Schulman23 Jun 2021 0:46 UTC
99 points
17 comments5 min readLW link

Pain is not the unit of Effort

alkjash24 Nov 2020 20:00 UTC
517 points
89 comments5 min readLW link2 reviews
(radimentary.wordpress.com)

Rad­i­cal Probabilism

abramdemski18 Aug 2020 21:14 UTC
176 points
47 comments35 min readLW link1 review

Slack Has Pos­i­tive Ex­ter­nal­ities For Groups

johnswentworth29 Jul 2021 15:03 UTC
90 points
11 comments5 min readLW link2 reviews

Science in a High-Di­men­sional World

johnswentworth8 Jan 2021 17:52 UTC
285 points
53 comments7 min readLW link1 review

The Felt Sense: What, Why and How

Kaj_Sotala5 Oct 2020 15:57 UTC
149 points
23 comments14 min readLW link1 review

Choos­ing the Zero Point

orthonormal6 Apr 2020 23:44 UTC
170 points
24 comments3 min readLW link2 reviews

Ra­tion­al­ism be­fore the Sequences

Eric Raymond30 Mar 2021 14:04 UTC
581 points
81 comments11 min readLW link2 reviews

Mak­ing Vaccine

johnswentworth3 Feb 2021 20:24 UTC
574 points
249 comments6 min readLW link3 reviews

A Sketch of Good Communication

Ben Pace31 Mar 2018 22:48 UTC
185 points
35 comments3 min readLW link1 review

Lo­cal Val­idity as a Key to San­ity and Civilization

Eliezer Yudkowsky7 Apr 2018 4:25 UTC
193 points
67 comments13 min readLW link5 reviews

The Loud­est Alarm Is Prob­a­bly False

orthonormal2 Jan 2018 16:38 UTC
171 points
28 comments2 min readLW link1 review

Va­ri­eties Of Ar­gu­men­ta­tive Experience

Scott Alexander8 May 2018 8:20 UTC
93 points
11 comments18 min readLW link2 reviews
(slatestarcodex.com)

Babble

alkjash10 Jan 2018 21:56 UTC
195 points
32 comments5 min readLW link2 reviews
(radimentary.wordpress.com)

Nam­ing the Nameless

sarahconstantin22 Mar 2018 0:35 UTC
119 points
43 comments13 min readLW link3 reviews

Toolbox-think­ing and Law-thinking

Eliezer Yudkowsky31 May 2018 21:28 UTC
160 points
49 comments12 min readLW link

Prune

alkjash12 Jan 2018 22:50 UTC
68 points
10 comments4 min readLW link
(radimentary.wordpress.com)

Towards a New Im­pact Measure

TurnTrout18 Sep 2018 17:21 UTC
100 points
159 comments33 min readLW link2 reviews

Be­ing a Ro­bust Agent

Raemon18 Oct 2018 7:00 UTC
145 points
32 comments7 min readLW link2 reviews

Notic­ing the Taste of Lotus

Valentine27 Apr 2018 20:05 UTC
203 points
81 comments3 min readLW link3 reviews

The Tails Com­ing Apart As Me­taphor For Life

Scott Alexander25 Sep 2018 19:10 UTC
155 points
38 comments7 min readLW link4 reviews
(slatestarcodex.com)

Meta-Hon­esty: Firm­ing Up Hon­esty Around Its Edge-Cases

Eliezer Yudkowsky29 May 2018 0:59 UTC
134 points
152 comments27 min readLW link4 reviews

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

Kaj_Sotala8 Mar 2018 7:37 UTC
224 points
131 comments17 min readLW link2 reviews

Anti-so­cial Punishment

Martin Sustrik27 Sep 2018 7:08 UTC
296 points
66 comments6 min readLW link3 reviews

The Costly Co­or­di­na­tion Mechanism of Com­mon Knowledge

Ben Pace15 Mar 2018 20:20 UTC
194 points
31 comments19 min readLW link2 reviews

The In­tel­li­gent So­cial Web

Valentine22 Feb 2018 18:55 UTC
224 points
112 comments12 min readLW link2 reviews

Pre­dic­tion Mar­kets: When Do They Work?

Zvi26 Jul 2018 12:30 UTC
162 points
17 comments10 min readLW link
(thezvi.wordpress.com)

Spaghetti Towers

eukaryote22 Dec 2018 5:29 UTC
187 points
28 comments3 min readLW link1 review
(eukaryotewritesblog.com)

On the Loss and Preser­va­tion of Knowledge

Samo Burja8 Mar 2018 18:40 UTC
66 points
20 comments10 min readLW link
(medium.com)

A vot­ing the­ory primer for rationalists

Jameson Quinn12 Apr 2018 15:15 UTC
229 points
98 comments17 min readLW link2 reviews

The Pavlov Strategy

sarahconstantin20 Dec 2018 16:20 UTC
247 points
13 comments4 min readLW link
(srconstantin.wordpress.com)

Inad­e­quate Equil­ibria vs. Gover­nance of the Commons

Martin Sustrik25 May 2018 13:17 UTC
182 points
17 comments14 min readLW link2 reviews

Is Science Slow­ing Down?

Scott Alexander27 Nov 2018 3:30 UTC
125 points
77 comments9 min readLW link1 review
(slatestarcodex.com)

Re­search: Res­cuers dur­ing the Holocaust

Martin Sustrik30 Apr 2018 6:15 UTC
88 points
10 comments9 min readLW link1 review

An Un­trol­lable Mathematician

abramdemski23 Jan 2018 18:46 UTC
23 points
1 comment3 min readLW link

Why did ev­ery­thing take so long?

KatjaGrace29 Dec 2017 1:00 UTC
33 points
17 comments1 min readLW link
(meteuphoric.wordpress.com)

Is Click­bait De­stroy­ing Our Gen­eral In­tel­li­gence?

Eliezer Yudkowsky16 Nov 2018 23:06 UTC
189 points
61 comments5 min readLW link2 reviews

[Question] What makes peo­ple in­tel­lec­tu­ally ac­tive?

abramdemski29 Dec 2018 22:29 UTC
116 points
71 comments1 min readLW link

Open ques­tion: are min­i­mal cir­cuits dae­mon-free?

paulfchristiano5 May 2018 22:40 UTC
83 points
70 comments2 min readLW link1 review

Beyond Astro­nom­i­cal Waste

Wei Dai7 Jun 2018 21:04 UTC
125 points
41 comments3 min readLW link

His­tor­i­cal math­e­mat­i­ci­ans ex­hibit a birth or­der effect too

Eli Tyre21 Aug 2018 1:52 UTC
141 points
19 comments6 min readLW link2 reviews

Birth or­der effect found in No­bel Lau­re­ates in Physics

Bucky4 Sep 2018 12:17 UTC
61 points
25 comments5 min readLW link1 review

Ar­gu­ments about fast takeoff

paulfchristiano25 Feb 2018 4:53 UTC
89 points
65 comments2 min readLW link1 review
(sideways-view.com)

Speci­fi­ca­tion gam­ing ex­am­ples in AI

Vika3 Apr 2018 12:30 UTC
45 points
9 comments1 min readLW link2 reviews

The Rocket Align­ment Problem

Eliezer Yudkowsky4 Oct 2018 0:38 UTC
216 points
41 comments15 min readLW link2 reviews

Embed­ded Agents

abramdemski and Scott Garrabrant
29 Oct 2018 19:53 UTC
221 points
41 comments1 min readLW link2 reviews

Paul’s re­search agenda FAQ

zhukeepa1 Jul 2018 6:25 UTC
126 points
74 comments19 min readLW link1 review

Challenges to Chris­ti­ano’s ca­pa­bil­ity am­plifi­ca­tion proposal

Eliezer Yudkowsky19 May 2018 18:18 UTC
124 points
54 comments23 min readLW link1 review

Ro­bust­ness to Scale

Scott Garrabrant21 Feb 2018 22:55 UTC
128 points
23 comments2 min readLW link1 review

Co­her­ence ar­gu­ments do not en­tail goal-di­rected behavior

Rohin Shah3 Dec 2018 3:26 UTC
123 points
69 comments7 min readLW link3 reviews

Rule Thinkers In, Not Out

Scott Alexander27 Feb 2019 2:40 UTC
221 points
67 comments4 min readLW link4 reviews
(slatestarcodex.com)

Gears vs Behavior

johnswentworth19 Sep 2019 6:50 UTC
107 points
13 comments7 min readLW link1 review

Book Re­view: The Se­cret Of Our Success

Scott Alexander5 Jun 2019 6:50 UTC
158 points
19 comments25 min readLW link2 reviews
(slatestarcodex.com)

Rea­son isn’t magic

Benquo18 Jun 2019 4:04 UTC
152 points
19 comments2 min readLW link3 reviews
(benjaminrosshoffman.com)

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

Buck22 Feb 2019 20:01 UTC
246 points
20 comments9 min readLW link2 reviews

In My Culture

[DEACTIVATED] Duncan Sabien7 Mar 2019 7:22 UTC
66 points
59 comments1 min readLW link2 reviews
(medium.com)

Chris Olah’s views on AGI safety

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

Un­der­stand­ing “Deep Dou­ble Des­cent”

evhub6 Dec 2019 0:00 UTC
148 points
51 comments5 min readLW link4 reviews

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

Hazard31 Jul 2019 13:34 UTC
352 points
74 comments4 min readLW link4 reviews

Paper-Read­ing for Gears

johnswentworth4 Dec 2019 21:02 UTC
159 points
6 comments4 min readLW link1 review

Book sum­mary: Un­lock­ing the Emo­tional Brain

Kaj_Sotala8 Oct 2019 19:11 UTC
317 points
48 comments21 min readLW link3 reviews

Notic­ing Frame Differences

Raemon30 Sep 2019 1:24 UTC
208 points
39 comments9 min readLW link2 reviews

Prop­a­gat­ing Facts into Aesthetics

Raemon19 Dec 2019 4:09 UTC
110 points
35 comments11 min readLW link1 review

Do you fear the rock or the hard place?

Ruby20 Jul 2019 22:01 UTC
72 points
10 comments5 min readLW link3 reviews

Men­tal Mountains

Scott Alexander27 Nov 2019 5:30 UTC
144 points
14 comments15 min readLW link1 review
(slatestarcodex.com)

Steel­man­ning Divination

Vaniver5 Jun 2019 22:53 UTC
191 points
48 comments6 min readLW link2 reviews

Book Re­view: De­sign Prin­ci­ples of Biolog­i­cal Circuits

johnswentworth5 Nov 2019 6:49 UTC
209 points
24 comments12 min readLW link1 review

Refram­ing Su­per­in­tel­li­gence: Com­pre­hen­sive AI Ser­vices as Gen­eral Intelligence

Rohin Shah8 Jan 2019 7:12 UTC
121 points
77 comments5 min readLW link2 reviews
(www.fhi.ox.ac.uk)

Build­ing up to an In­ter­nal Fam­ily Sys­tems model

Kaj_Sotala26 Jan 2019 12:25 UTC
264 points
86 comments28 min readLW link2 reviews

Be­ing the (Pareto) Best in the World

johnswentworth24 Jun 2019 18:36 UTC
404 points
57 comments3 min readLW link3 reviews

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

Raemon8 Jun 2019 0:24 UTC
157 points
52 comments12 min readLW link3 reviews

Liter­a­ture Re­view: Distributed Teams

Elizabeth16 Apr 2019 1:19 UTC
106 points
37 comments6 min readLW link1 review

Gears-Level Models are Cap­i­tal Investments

johnswentworth22 Nov 2019 22:41 UTC
170 points
28 comments7 min readLW link1 review

Evolu­tion of Modularity

johnswentworth14 Nov 2019 6:49 UTC
174 points
12 comments2 min readLW link1 review

You Get About Five Words

Raemon12 Mar 2019 20:30 UTC
199 points
77 comments1 min readLW link6 reviews

Co­her­ent de­ci­sions im­ply con­sis­tent utilities

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

Align­ment Re­search Field Guide

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

Fo­rum par­ti­ci­pa­tion as a re­search strategy

Wei Dai30 Jul 2019 18:09 UTC
151 points
45 comments3 min readLW link1 review

The Credit As­sign­ment Problem

abramdemski8 Nov 2019 2:50 UTC
98 points
40 comments17 min readLW link1 review

Asym­met­ric Justice

Zvi25 Apr 2019 16:00 UTC
230 points
101 comments5 min readLW link2 reviews
(thezvi.wordpress.com)

Un­con­scious Economics

jacobjacob27 Feb 2019 12:58 UTC
136 points
30 comments4 min readLW link3 reviews

Power Buys You Dis­tance From The Crime

Elizabeth2 Aug 2019 20:50 UTC
189 points
75 comments7 min readLW link1 review
(acesounderglass.com)

Seek­ing Power is Often Con­ver­gently In­stru­men­tal in MDPs

TurnTrout and Logan Riggs
5 Dec 2019 2:33 UTC
162 points
39 comments17 min readLW link2 reviews
(arxiv.org)

Yes Re­quires the Pos­si­bil­ity of No

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

Mis­takes with Con­ser­va­tion of Ex­pected Evidence

abramdemski8 Jun 2019 23:07 UTC
212 points
25 comments12 min readLW link1 review

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
299 points
40 comments8 min readLW link2 reviews
No comments.