362 points

127 comments34 min readLW link 2 reviews

Shallow review of live agendas in alignment & safety

technicalities and Stag

Nov 27, 2023, 11:10 AM

348 points

73 comments29 min readLW link 1 review

AI Timelines

habryka, Daniel Kokotajlo, Ajeya Cotra and Ege Erdil

Nov 10, 2023, 5:28 AM

300 points

135 comments51 min readLW link 2 reviews

OpenAI: The Battle of the Board

ZviNov 22, 2023, 5:30 PM

281 points

83 comments11 min readLW link

(thezvi.wordpress.com)

The 6D effect: When companies take risks, one email can be very powerful.

scasperNov 4, 2023, 8:08 PM

279 points

42 comments3 min readLW link

The 101 Space You Will Always Have With You

ScrewtapeNov 29, 2023, 4:56 AM

273 points

22 comments6 min readLW link 1 review

OpenAI: Facts from a Weekend

ZviNov 20, 2023, 3:30 PM

271 points

166 comments9 min readLW link

(thezvi.wordpress.com)

What are the results of more parental supervision and less outdoor play?

juliawiseNov 25, 2023, 12:52 PM

228 points

31 comments5 min readLW link

Thinking By The Clock

ScrewtapeNov 8, 2023, 7:40 AM

197 points

29 comments8 min readLW link 1 review

Ability to solve long-horizon tasks correlates with wanting things in the behaviorist sense

So8resNov 24, 2023, 5:37 PM

197 points

84 comments5 min readLW link 1 review

Propaganda or Science: A Look at Open Source AI and Bioterrorism Risk

1a3ornNov 2, 2023, 6:20 PM

193 points

79 comments23 min readLW link

Sam Altman fired from OpenAI

LawrenceCNov 17, 2023, 8:42 PM

192 points

75 comments1 min readLW link

(openai.com)

The other side of the tidal wave

KatjaGraceNov 3, 2023, 5:40 AM

189 points

86 comments1 min readLW link

(worldspiritsockpuppet.com)

How to (hopefully ethically) make money off of AGI

habryka, Zvi, Cosmos and NoahK

Nov 6, 2023, 11:35 PM

171 points

95 comments32 min readLW link 1 review

You can just spontaneously call people you haven’t met in years

lcNov 13, 2023, 5:21 AM

167 points

21 comments1 min readLW link

Loudly Give Up, Don’t Quietly Fade

ScrewtapeNov 13, 2023, 11:30 PM

165 points

12 comments6 min readLW link 1 review

Vote on Interesting Disagreements

Ben PaceNov 7, 2023, 9:35 PM

159 points

131 comments1 min readLW link

My thoughts on the social response to AI risk

Matthew BarnettNov 1, 2023, 9:17 PM

157 points

37 comments10 min readLW link

Moral Reality Check (a short story)

jessicataNov 26, 2023, 5:03 AM

149 points

45 comments21 min readLW link 1 review

(unstableontology.com)

Does davidad’s uploading moonshot work?

Bird Concept, lisathiergart, Anders_Sandberg, davidad and Arenamontanus

Nov 3, 2023, 2:21 AM

146 points

35 comments25 min readLW link

EA orgs’ legal structure inhibits risk taking and information sharing on the margin

ElizabethNov 5, 2023, 7:13 PM

136 points

17 comments4 min readLW link

Integrity in AI Governance and Advocacy

habryka and OliviaJ

Nov 3, 2023, 7:52 PM

134 points

57 comments23 min readLW link

Apocalypse insurance, and the hardline libertarian take on AI risk

So8resNov 28, 2023, 2:09 AM

134 points

40 comments7 min readLW link 1 review

One Day Sooner

ScrewtapeNov 2, 2023, 7:00 PM

121 points

8 comments8 min readLW link 1 review

8 examples informing my pessimism on uploading without reverse engineering

Steven ByrnesNov 3, 2023, 8:03 PM

118 points

12 comments12 min readLW link

The Soul Key

Richard_NgoNov 4, 2023, 5:51 PM

112 points

10 comments8 min readLW link 1 review

(www.narrativeark.xyz)

How much to update on recent AI governance moves?

habryka and So8res

Nov 16, 2023, 11:46 PM

112 points

5 comments29 min readLW link

Deception Chess: Game #1

Zane, aphyer, Alex A and AdamYedidia

Nov 3, 2023, 9:13 PM

111 points

22 comments8 min readLW link 1 review

Experiences and learnings from both sides of the AI safety job market

Marius HobbhahnNov 15, 2023, 3:40 PM

110 points

4 comments18 min readLW link

Stuxnet, not Skynet: Humanity’s disempowerment by AI

RokoNov 4, 2023, 10:23 PM

107 points

24 comments6 min readLW link

My techno-optimism [By Vitalik Buterin]

habrykaNov 27, 2023, 11:53 PM

107 points

17 comments2 min readLW link

(www.lesswrong.com)

New LessWrong feature: Dialogue Matching

Bird ConceptNov 16, 2023, 9:27 PM

106 points

22 comments3 min readLW link

Picking Mentors For Research Programmes

Raymond DNov 10, 2023, 1:01 PM

105 points

8 comments4 min readLW link

Learning-theoretic agenda reading list

Vanessa KosoyNov 9, 2023, 5:25 PM

103 points

1 comment2 min readLW link 1 review

Never Drop A Ball

ScrewtapeNov 23, 2023, 4:15 AM

101 points

8 comments6 min readLW link 1 review

On the Executive Order

ZviNov 1, 2023, 2:20 PM

100 points

4 comments30 min readLW link

(thezvi.wordpress.com)

Kids or No kids

Kids or no kidsNov 14, 2023, 6:37 PM

98 points

10 comments13 min readLW link

Coup probes: Catching catastrophes with probes trained off-policy

Fabien RogerNov 17, 2023, 5:58 PM

93 points

9 comments11 min readLW link 1 review

Public Call for Interest in Mathematical Alignment

DavidmanheimNov 22, 2023, 1:22 PM

90 points

9 comments1 min readLW link

Growth and Form in a Toy Model of Superposition

Liam Carroll and Edmund Lau

Nov 8, 2023, 11:08 AM

89 points

7 comments14 min readLW link

Large Language Models can Strategically Deceive their Users when Put Under Pressure.

ReaderMNov 15, 2023, 4:36 PM

89 points

9 comments2 min readLW link 1 review

(arxiv.org)

Untrusted smart models and trusted dumb models

BuckNov 4, 2023, 3:06 AM

87 points

17 comments6 min readLW link 1 review

Some Rules for an Algebra of Bayes Nets

johnswentworth and David Lorell

Nov 16, 2023, 11:53 PM

85 points

45 comments14 min readLW link 1 review

Dario Amodei’s prepared remarks from the UK AI Safety Summit, on Anthropic’s Responsible Scaling Policy

Zac Hatfield-DoddsNov 1, 2023, 6:10 PM

85 points

1 comment4 min readLW link

(www.anthropic.com)

Saying the quiet part out loud: trading off x-risk for personal immortality

disturbanceNov 2, 2023, 5:43 PM

84 points

89 comments5 min readLW link

My Criticism of Singular Learning Theory

Joar SkalseNov 19, 2023, 3:19 PM

83 points

56 comments12 min readLW link

Agent Boundaries Aren’t Markov Blankets. [Unless they’re non-causal; see comments.]

abramdemskiNov 20, 2023, 6:23 PM

82 points

11 comments2 min readLW link

New report: “Scheming AIs: Will AIs fake alignment during training in order to get power?”

Joe CarlsmithNov 15, 2023, 5:16 PM

81 points

28 comments30 min readLW link 1 review

Bostrom Goes Unheard

ZviNov 13, 2023, 2:11 PM

81 points

9 comments18 min readLW link

Self-Referential Probabilistic Logic Admits the Payor’s Lemma

Yudhister KumarNov 28, 2023, 10:27 AM

80 points

14 comments6 min readLW link