Feb 5, 2023, 10:02 PM

682 points

206 comments12 min readLW link 1 review

Focus on the places where you feel shocked everyone’s dropping the ball

So8resFeb 2, 2023, 12:27 AM

459 points

63 comments4 min readLW link 3 reviews

Bing Chat is blatantly, aggressively misaligned

evhubFeb 15, 2023, 5:29 AM

403 points

181 comments2 min readLW link 1 review

Please don’t throw your mind away

TsviBTFeb 15, 2023, 9:41 PM

374 points

49 comments18 min readLW link 1 review

Noting an error in Inadequate Equilibria

Matthew BarnettFeb 8, 2023, 1:33 AM

366 points

60 comments2 min readLW link 2 reviews

Fucking Goddamn Basics of Rationalist Discourse

LoganStrohlFeb 4, 2023, 1:47 AM

346 points

103 comments1 min readLW link 3 reviews

Childhoods of exceptional people

Henrik KarlssonFeb 6, 2023, 5:27 PM

344 points

63 comments15 min readLW link 1 review

(escapingflatland.substack.com)

Cyborgism

NicholasKees and janus

Feb 10, 2023, 2:47 PM

341 points

46 comments35 min readLW link 2 reviews

You Don’t Exist, Duncan

Duncan Sabien (Deactivated)Feb 2, 2023, 8:37 AM

252 points

107 comments9 min readLW link

I hired 5 people to sit behind me and make me productive for a month

Simon BerensFeb 5, 2023, 1:19 AM

249 points

83 comments10 min readLW link

(www.simonberens.com)

AGI in sight: our look at the game board

Andrea_Miotti and Gabriel Alfour

Feb 18, 2023, 10:17 PM

227 points

135 comments6 min readLW link

(andreamiotti.substack.com)

Elements of Rationalist Discourse

Rob BensingerFeb 12, 2023, 7:58 AM

224 points

49 comments3 min readLW link 1 review

Cognitive Emulation: A Naive AI Safety Proposal

Connor Leahy and Gabriel Alfour

Feb 25, 2023, 7:35 PM

195 points

46 comments4 min readLW link

AI alignment researchers don’t (seem to) stack

So8resFeb 21, 2023, 12:48 AM

193 points

40 comments3 min readLW link

EigenKarma: trust at scale

Henrik KarlssonFeb 8, 2023, 6:52 PM

186 points

52 comments5 min readLW link

[Link] A community alert about Ziz

DanielFilanFeb 24, 2023, 12:06 AM

180 points

166 comments2 min readLW link 4 reviews

(medium.com)

Why Are Bacteria So Simple?

aysjaFeb 6, 2023, 3:00 AM

172 points

33 comments10 min readLW link

Parametrically retargetable decision-makers tend to seek power

TurnTroutFeb 18, 2023, 6:41 PM

172 points

10 comments2 min readLW link

(arxiv.org)

AI #1: Sydney and Bing

ZviFeb 21, 2023, 2:00 PM

171 points

45 comments61 min readLW link 1 review

(thezvi.wordpress.com)

My understanding of Anthropic strategy

Swimmer963 (Miranda Dixon-Luinenburg) Feb 15, 2023, 1:56 AM

166 points

31 comments4 min readLW link

Big Mac Subsidy?

jefftkFeb 23, 2023, 4:00 AM

158 points

25 comments2 min readLW link

(www.jefftk.com)

There are no coherence theorems

Dan H and EJT

Feb 20, 2023, 9:25 PM

149 points

130 comments19 min readLW link 1 review

Stop posting prompt injections on Twitter and calling it “misalignment”

lcFeb 19, 2023, 2:21 AM

144 points

9 comments1 min readLW link

We Found An Neuron in GPT-2

Joseph Miller and Clement Neo

Feb 11, 2023, 6:27 PM

143 points

23 comments7 min readLW link

(clementneo.com)

Hashing out long-standing disagreements seems low-value to me

So8resFeb 16, 2023, 6:20 AM

141 points

34 comments4 min readLW link

Anomalous tokens reveal the original identities of Instruct models

janus and jdp

Feb 9, 2023, 1:30 AM

140 points

16 comments9 min readLW link

(generative.ink)

Full Transcript: Eliezer Yudkowsky on the Bankless podcast

remember and Andrea_Miotti

Feb 23, 2023, 12:34 PM

138 points

89 comments75 min readLW link

“Rationalist Discourse” Is Like “Physicist Motors”

Zack_M_DavisFeb 26, 2023, 5:58 AM

136 points

153 comments9 min readLW link 1 review

Pretraining Language Models with Human Preferences

Tomek Korbak, Sam Bowman and Ethan Perez

Feb 21, 2023, 5:57 PM

135 points

20 comments11 min readLW link 2 reviews

Modal Fixpoint Cooperation without Löb’s Theorem

Andrew_CritchFeb 5, 2023, 12:58 AM

134 points

34 comments3 min readLW link 1 review

Evaluations (of new AI Safety researchers) can be noisy

LawrenceCFeb 5, 2023, 4:15 AM

132 points

11 comments16 min readLW link 1 review

One-layer transformers aren’t equivalent to a set of skip-trigrams

BuckFeb 17, 2023, 5:26 PM

127 points

11 comments7 min readLW link

There are (probably) no superhuman Go AIs: strong human players beat the strongest AIs

TaranFeb 19, 2023, 12:25 PM

125 points

34 comments4 min readLW link

Recommendation: Bug Bounties and Responsible Disclosure for Advanced ML Systems

VaniverFeb 17, 2023, 8:11 PM

125 points

12 comments2 min readLW link

In Defense of Chatbot Romance

Kaj_SotalaFeb 11, 2023, 2:30 PM

124 points

53 comments11 min readLW link

(kajsotala.fi)

GPT-175bee

Adam Scherlis and LawrenceC

Feb 8, 2023, 6:58 PM

122 points

14 comments1 min readLW link

A proposed method for forecasting transformative AI

Matthew BarnettFeb 10, 2023, 7:34 PM

121 points

21 comments10 min readLW link

On Investigating Conspiracy Theories

ZviFeb 20, 2023, 12:50 PM

116 points

38 comments5 min readLW link

(thezvi.wordpress.com)

Bing chat is the AI fire alarm

RatiosFeb 17, 2023, 6:51 AM

115 points

63 comments3 min readLW link

The Open Agency Model

Eric DrexlerFeb 22, 2023, 10:35 AM

114 points

18 comments4 min readLW link

The public supports regulating AI for safety

Zach Stein-PerlmanFeb 17, 2023, 4:10 AM

114 points

9 comments1 min readLW link

(aiimpacts.org)

SolidGoldMagikarp II: technical details and more recent findings

mwatkins and Jessica Rumbelow

Feb 6, 2023, 7:09 PM

113 points

45 comments13 min readLW link

Conflict Theory of Bounded Distrust

Zack_M_DavisFeb 12, 2023, 5:30 AM

112 points

33 comments3 min readLW link 1 review

GPT-4 Predictions

Stephen McAleeseFeb 17, 2023, 11:20 PM

110 points

27 comments11 min readLW link

A Way To Be Okay

Duncan Sabien (Deactivated)Feb 19, 2023, 8:27 PM

109 points

38 comments10 min readLW link 1 review

Cyborg Periods: There will be multiple AI transitions

Jan_Kulveit and rosehadshar

Feb 22, 2023, 4:09 PM

108 points

9 comments6 min readLW link

Another Way to Be Okay

Gretta DulebaFeb 19, 2023, 8:49 PM

107 points

15 comments6 min readLW link

I don’t think MIRI “gave up”

RaemonFeb 3, 2023, 12:26 AM

106 points

64 comments4 min readLW link

Sam Altman: “Planning for AGI and beyond”

LawrenceCFeb 24, 2023, 8:28 PM

104 points

54 comments6 min readLW link

(openai.com)

H5N1

ZviFeb 13, 2023, 12:50 PM

102 points

1 comment9 min readLW link

(thezvi.wordpress.com)