Anti-social Punishment

Martin Sustrik27 Sep 2018 7:08 UTC

296 points

66 comments6 min readLW link 3 reviews

The Pavlov Strategy

sarahconstantin20 Dec 2018 16:20 UTC

247 points

13 comments4 min readLW link

(srconstantin.wordpress.com)

Embedded Agents

abramdemski and Scott Garrabrant

29 Oct 2018 19:53 UTC

222 points

41 comments1 min readLW link 2 reviews

The Rocket Alignment Problem

Eliezer Yudkowsky4 Oct 2018 0:38 UTC

216 points

41 comments15 min readLW link 2 reviews

A voting theory primer for rationalists

Jameson Quinn12 Apr 2018 15:15 UTC

229 points

98 comments17 min readLW link 2 reviews

Norms of Membership for Voluntary Groups

sarahconstantin11 Dec 2018 22:10 UTC

192 points

10 comments7 min readLW link

(srconstantin.wordpress.com)

2018 AI Alignment Literature Review and Charity Comparison

Larks18 Dec 2018 4:46 UTC

190 points

26 comments62 min readLW link 1 review

Arbital postmortem

alexei30 Jan 2018 13:48 UTC

227 points

110 comments19 min readLW link

Spaghetti Towers

eukaryote22 Dec 2018 5:29 UTC

187 points

28 comments3 min readLW link 1 review

(eukaryotewritesblog.com)

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

Kaj_Sotala8 Mar 2018 7:37 UTC

222 points

135 comments17 min readLW link 2 reviews

Act of Charity

jessicata17 Nov 2018 5:19 UTC

186 points

49 comments8 min readLW link 1 review

The Intelligent Social Web

Valentine22 Feb 2018 18:55 UTC

224 points

112 comments12 min readLW link 2 reviews

Embedded Agency (full-text version)

Scott Garrabrant and abramdemski

15 Nov 2018 19:49 UTC

180 points

17 comments54 min readLW link

Noticing the Taste of Lotus

Valentine27 Apr 2018 20:05 UTC

203 points

81 comments3 min readLW link 3 reviews

Is Clickbait Destroying Our General Intelligence?

Eliezer Yudkowsky16 Nov 2018 23:06 UTC

189 points

61 comments5 min readLW link 2 reviews

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

Academian25 Aug 2018 12:00 UTC

187 points

44 comments7 min readLW link 1 review

Realism about rationality

Richard_Ngo16 Sep 2018 10:46 UTC

184 points

146 comments4 min readLW link 3 reviews

(thinkingcomplete.blogspot.com)

A LessWrong Crypto Autopsy

Scott Alexander28 Jan 2018 9:01 UTC

216 points

129 comments4 min readLW link 4 reviews

A Sketch of Good Communication

Ben Pace31 Mar 2018 22:48 UTC

198 points

35 comments3 min readLW link 1 review

Local Validity as a Key to Sanity and Civilization

Eliezer Yudkowsky7 Apr 2018 4:25 UTC

194 points

67 comments13 min readLW link 5 reviews

The Costly Coordination Mechanism of Common Knowledge

Ben Pace15 Mar 2018 20:20 UTC

194 points

31 comments19 min readLW link 2 reviews

Babble

alkjash10 Jan 2018 21:56 UTC

200 points

32 comments5 min readLW link 2 reviews

(radimentary.wordpress.com)

Inadequate Equilibria vs. Governance of the Commons

Martin Sustrik25 May 2018 13:17 UTC

182 points

17 comments14 min readLW link 2 reviews

Transhumanism as Simplified Humanism

Eliezer Yudkowsky5 Dec 2018 20:12 UTC

170 points

34 comments5 min readLW link

Some cruxes on impactful alternatives to AI policy work

Richard_Ngo10 Oct 2018 13:35 UTC

165 points

13 comments12 min readLW link

Incorrect hypotheses point to correct observations

Kaj_Sotala20 Nov 2018 21:10 UTC

160 points

37 comments4 min readLW link

(kajsotala.fi)

“Cheat to Win”: Engineering Positive Social Feedback

sarahconstantin5 Feb 2018 23:16 UTC

184 points

36 comments2 min readLW link

Prediction Markets: When Do They Work?

Zvi26 Jul 2018 12:30 UTC

162 points

17 comments10 min readLW link

(thezvi.wordpress.com)

Toolbox-thinking and Law-thinking

Eliezer Yudkowsky31 May 2018 21:28 UTC

161 points

49 comments12 min readLW link

The Loudest Alarm Is Probably False

orthonormal2 Jan 2018 16:38 UTC

171 points

28 comments2 min readLW link 1 review

The Tails Coming Apart As Metaphor For Life

Scott Alexander25 Sep 2018 19:10 UTC

155 points

38 comments7 min readLW link 4 reviews

(slatestarcodex.com)

Decoupling vs Contextualising Norms

Chris_Leong14 May 2018 22:44 UTC

155 points

51 comments2 min readLW link 3 reviews

Problem Solving with Mazes and Crayon

johnswentworth19 Jun 2018 6:15 UTC

149 points

28 comments7 min readLW link

An Untrollable Mathematician Illustrated

abramdemski20 Mar 2018 0:00 UTC

157 points

38 comments1 min readLW link 1 review

Oops on Commodity Prices

sarahconstantin10 Jun 2018 15:40 UTC

148 points

8 comments2 min readLW link

(srconstantin.wordpress.com)

Historical mathematicians exhibit a birth order effect too

Eli Tyre21 Aug 2018 1:52 UTC

141 points

19 comments6 min readLW link 2 reviews

Being a Robust Agent

Raemon18 Oct 2018 7:00 UTC

145 points

32 comments7 min readLW link 2 reviews

Strategies for Personal Growth

Raemon28 Jul 2018 18:27 UTC

142 points

27 comments4 min readLW link

Expressive Vocabulary

Alicorn24 May 2018 6:59 UTC

143 points

71 comments5 min readLW link 1 review

Is Science Slowing Down?

Scott Alexander27 Nov 2018 3:30 UTC

125 points

77 comments9 min readLW link 1 review

(slatestarcodex.com)

Good Samaritans in experiments

Bucky30 Oct 2018 23:34 UTC

125 points

14 comments9 min readLW link

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

Eliezer Yudkowsky29 May 2018 0:59 UTC

134 points

152 comments27 min readLW link 4 reviews

Terrorism, Tylenol, and dangerous information

Davis_Kingsley12 May 2018 10:20 UTC

145 points

46 comments3 min readLW link

[Question] What makes people intellectually active?

abramdemski29 Dec 2018 22:29 UTC

116 points

71 comments1 min readLW link

Contrite Strategies and The Need For Standards

sarahconstantin24 Dec 2018 18:30 UTC

125 points

5 comments4 min readLW link

(srconstantin.wordpress.com)

On Doing the Improbable

Eliezer Yudkowsky28 Oct 2018 20:09 UTC

128 points

36 comments1 min readLW link 1 review

Paul’s research agenda FAQ

zhukeepa1 Jul 2018 6:25 UTC

126 points

74 comments19 min readLW link 1 review

Coherence arguments do not entail goal-directed behavior

Rohin Shah3 Dec 2018 3:26 UTC

123 points

69 comments7 min readLW link 3 reviews

Unknown Knowns

Zvi28 Aug 2018 13:20 UTC

120 points

17 comments2 min readLW link 1 review

(thezvi.wordpress.com)

Beyond Astronomical Waste

Wei Dai7 Jun 2018 21:04 UTC

125 points

41 comments3 min readLW link

Prisoners’ Dilemma with Costs to Modeling

Scott Garrabrant5 Jun 2018 4:51 UTC

123 points

20 comments7 min readLW link

Challenges to Christiano’s capability amplification proposal

Eliezer Yudkowsky19 May 2018 18:18 UTC

124 points

54 comments23 min readLW link 1 review

Melatonin: Much More Than You Wanted To Know

Scott Alexander11 Jul 2018 17:40 UTC

119 points

16 comments15 min readLW link

(slatestarcodex.com)

Robustness to Scale

Scott Garrabrant21 Feb 2018 22:55 UTC

128 points

23 comments2 min readLW link 1 review

Making yourself small

Helen8 Mar 2018 14:26 UTC

127 points

53 comments11 min readLW link

Decision Theory

abramdemski and Scott Garrabrant

31 Oct 2018 18:41 UTC

117 points

45 comments1 min readLW link

Robust Delegation

abramdemski and Scott Garrabrant

4 Nov 2018 16:38 UTC

116 points

10 comments1 min readLW link

Meditations on Momentum

Richard Meadows14 Dec 2018 10:53 UTC

103 points

32 comments10 min readLW link

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

Rob Bensinger12 May 2018 2:13 UTC

118 points

25 comments4 min readLW link

Coordination Problems in Evolution: Eigen’s Paradox

Martin Sustrik12 Oct 2018 12:40 UTC

102 points

6 comments8 min readLW link

(250bpm.com)

Are ethical asymmetries from property rights?

KatjaGrace2 Jul 2018 3:00 UTC

108 points

37 comments3 min readLW link

(meteuphoric.com)

Y Couchinator

Alicorn18 Aug 2018 3:41 UTC

111 points

33 comments4 min readLW link

Optimization Amplifies

Scott Garrabrant27 Jun 2018 1:51 UTC

114 points

12 comments4 min readLW link

Naming the Nameless

sarahconstantin22 Mar 2018 0:35 UTC

120 points

43 comments13 min readLW link 3 reviews

[Question] How did academia ensure papers were correct in the early 20th Century?

Ben Pace29 Dec 2018 23:37 UTC

99 points

17 comments2 min readLW link 1 review

Why everything might have taken so long

KatjaGrace1 Jan 2018 1:00 UTC

112 points

16 comments3 min readLW link 1 review

(meteuphoric.wordpress.com)

Counterfactual Mugging Poker Game

Scott Garrabrant13 Jun 2018 23:34 UTC

111 points

3 comments1 min readLW link

Subsidizing Prediction Markets

Zvi17 Aug 2018 15:40 UTC

96 points

8 comments11 min readLW link

(thezvi.wordpress.com)

Two Neglected Problems in Human-AI Safety

Wei Dai16 Dec 2018 22:13 UTC

98 points

24 comments2 min readLW link

Subsystem Alignment

abramdemski and Scott Garrabrant

6 Nov 2018 16:16 UTC

99 points

12 comments1 min readLW link

Sam Harris and the Is–Ought Gap

Tyrrell_McAllister16 Nov 2018 1:04 UTC

89 points

46 comments6 min readLW link

The Kelly Criterion

Zvi15 Oct 2018 21:20 UTC

101 points

24 comments3 min readLW link

(thezvi.wordpress.com)

Machine Learning Analogy for Meditation (illustrated)

abramdemski28 Jun 2018 22:51 UTC

97 points

48 comments1 min readLW link

Playing Politics

sarahconstantin5 Dec 2018 0:30 UTC

97 points

45 comments12 min readLW link

(srconstantin.wordpress.com)

Preliminary thoughts on moral weight

lukeprog13 Aug 2018 23:45 UTC

93 points

49 comments8 min readLW link 2 reviews

Write a Thousand Roads to Rome

Screwtape8 Feb 2018 18:09 UTC

105 points

17 comments4 min readLW link

Transhumanists Don’t Need Special Dispositions

Eliezer Yudkowsky7 Dec 2018 22:24 UTC

96 points

18 comments5 min readLW link

Towards a New Impact Measure

TurnTrout18 Sep 2018 17:21 UTC

100 points

159 comments33 min readLW link 2 reviews

History of the Development of Logical Induction

Scott Garrabrant29 Aug 2018 3:15 UTC

100 points

4 comments5 min readLW link

Zetetic explanation

Benquo27 Aug 2018 0:12 UTC

90 points

138 comments6 min readLW link

(benjaminrosshoffman.com)

Trust Me I’m Lying: A Summary and Review

quanticle13 Aug 2018 2:55 UTC

100 points

11 comments7 min readLW link

(quanticle.net)

Public Positions and Private Guts

Vaniver11 Oct 2018 19:38 UTC

85 points

13 comments8 min readLW link

Should ethicists be inside or outside a profession?

Eliezer Yudkowsky12 Dec 2018 1:40 UTC

91 points

7 comments9 min readLW link

Bottle Caps Aren’t Optimisers

DanielFilan31 Aug 2018 18:30 UTC

97 points

22 comments3 min readLW link 1 review

(danielfilan.com)

Update the best textbooks on every subject list

ryan_b8 Nov 2018 20:54 UTC

92 points

14 comments1 min readLW link

Of Two Minds

Valentine17 May 2018 4:34 UTC

93 points

12 comments2 min readLW link

Varieties Of Argumentative Experience

Scott Alexander8 May 2018 8:20 UTC

93 points

11 comments18 min readLW link 2 reviews

(slatestarcodex.com)

Understanding is translation

cousin_it28 May 2018 13:56 UTC

92 points

23 comments1 min readLW link

Embedded World-Models

abramdemski and Scott Garrabrant

2 Nov 2018 16:07 UTC

92 points

16 comments1 min readLW link

The funnel of human experience

eukaryote10 Oct 2018 2:46 UTC

83 points

31 comments3 min readLW link 1 review

(eukaryotewritesblog.com)

Embedded Curiosities

Scott Garrabrant and abramdemski

8 Nov 2018 14:19 UTC

91 points

1 comment2 min readLW link

In Logical Time, All Games are Iterated Games

abramdemski20 Sep 2018 2:01 UTC

93 points

10 comments5 min readLW link

Player vs. Character: A Two-Level Model of Ethics

sarahconstantin14 Dec 2018 19:40 UTC

88 points

27 comments7 min readLW link 3 reviews

(srconstantin.wordpress.com)

Double-Dipping in Dunning—Kruger

isovector28 Nov 2018 3:40 UTC

88 points

31 comments3 min readLW link

Hammertime Day 1: Bug Hunt

alkjash30 Jan 2018 6:40 UTC

105 points

25 comments5 min readLW link

(radimentary.wordpress.com)

Announcement: AI alignment prize round 3 winners and next round

cousin_it15 Jul 2018 7:40 UTC

93 points

7 comments1 min readLW link

New edition of “Rationality: From AI to Zombies”

Rob Bensinger15 Dec 2018 21:33 UTC

84 points

27 comments2 min readLW link

Introducing the AI Alignment Forum (FAQ)

habryka, Ben Pace, Raemon and jimrandomh

29 Oct 2018 21:07 UTC

86 points

8 comments6 min readLW link

Counterintuitive Comparative Advantage

Wei Dai28 Nov 2018 20:33 UTC

84 points

8 comments2 min readLW link

Arguments about fast takeoff

paulfchristiano25 Feb 2018 4:53 UTC

89 points

65 comments2 min readLW link 1 review

(sideways-view.com)