LESSWRONG
LW

Archive Recommendations

291Welcome to LessWrong!

Ruby, habryka, Ben Pace, Raemon

3y

42

675Where I agree and disagree with EliezerΩ

paulfchristiano

10d

191

666AGI Ruin: A List of LethalitiesΩ

Eliezer Yudkowsky

23d

629

553Making Vaccine

1y

247

510What an actually pessimistic containment strategy looks like[anonymous]3mo

133

508Rationalism before the Sequences

1y

80

645Eight Short Studies On Excuses

Scott Alexander

12y

244

Eliezer Yudkowsky

7y

14

557The Best Textbooks on Every Subject

11y

390

483Schelling fences on slippery slopes

Scott Alexander

10y

206

Curated Posts

286Security Mindset: Lessons from 20+ years of Software Security Failures Relevant to AGI Alignment

2d

34

141Nonprofit Boards are Weird

HoldenKarnofsky

5d

18

675Where I agree and disagree with EliezerΩ

paulfchristiano

10d

191

253Six Dimensions of Operational Adequacy in AGI ProjectsΩ

Eliezer Yudkowsky

14d

65

188Moses and the Class Struggle

16d

24

184Benign Boundary Violations

19d

83

666AGI Ruin: A List of LethalitiesΩ

Eliezer Yudkowsky

23d

629

131Public beliefs vs. Private beliefs

1mo

25

193Visible Homelessness in SF: A Quick Breakdown of Causes

1mo

40

70[Intro to brain-like-AGI safety] 15. Conclusion: Open problems, how to help, AMAΩ

1mo

10

263Is AI Progress Impossible To Predict?

1mo

38

148Ruling Out Everything Else

1mo

46

336What DALL-E 2 can and cannot do

2mo

297

116The case for becoming a black-box investigator of language modelsΩ

2mo

18

116Narrative Syncing

2mo

45

304Accounting For College Costs

2mo

37

138Slack gives you space to notice/reflect on subtle things

2mo

18

135Beyond Blame Minimization

physicaleconomics

2mo

47

186Call For DistillersΩ

2mo

35

306Lies Told To Children

Eliezer Yudkowsky

2mo

94