353 points

304 comments9 min readLW link

Beware boasting about non-existent forecasting track records

Jotto99920 May 2022 19:20 UTC

340 points

112 comments5 min readLW link 1 review

Six Dimensions of Operational Adequacy in AGI Projects

Eliezer Yudkowsky30 May 2022 17:00 UTC

317 points

66 comments13 min readLW link 1 review

Is AI Progress Impossible To Predict?

alyssavance15 May 2022 18:30 UTC

278 points

39 comments2 min readLW link

ProjectLawful.com: Eliezer’s latest story, past 1M words

Eliezer Yudkowsky11 May 2022 6:18 UTC

238 points

112 comments1 min readLW link 4 reviews

Benign Boundary Violations

Duncan Sabien (Inactive)26 May 2022 6:48 UTC

212 points

84 comments18 min readLW link 1 review

Visible Homelessness in SF: A Quick Breakdown of Causes

alyssavance25 May 2022 1:40 UTC

210 points

32 comments2 min readLW link

On saving one’s world

Rob Bensinger17 May 2022 19:53 UTC

193 points

4 comments1 min readLW link

Deliberate Grieving

Raemon30 May 2022 20:49 UTC

191 points

16 comments9 min readLW link 2 reviews

Transcripts of interviews with AI researchers

Vael Gates9 May 2022 5:57 UTC

170 points

9 comments2 min readLW link

Deepmind’s Gato: Generalist Agent

Daniel Kokotajlo12 May 2022 16:01 UTC

165 points

62 comments1 min readLW link

A Bird’s Eye View of the ML Field [Pragmatic AI Safety #2]

Dan H and TW123

9 May 2022 17:18 UTC

165 points

8 comments35 min readLW link

Repeal the Foreign Dredge Act of 1906

Zvi5 May 2022 15:20 UTC

160 points

16 comments19 min readLW link

(thezvi.wordpress.com)

DeepMind is hiring for the Scalable Alignment and Alignment Teams

Rohin Shah and Geoffrey Irving

13 May 2022 12:17 UTC

150 points

34 comments9 min readLW link

Reshaping the AI Industry

Thane Ruthenis29 May 2022 22:54 UTC

148 points

35 comments21 min readLW link

High-stakes alignment via adversarial training [Redwood Research report]

dmz, LawrenceC and Nate Thomas

5 May 2022 0:59 UTC

142 points

29 comments9 min readLW link

LessWrong Now Has Dark Mode

jimrandomh10 May 2022 1:21 UTC

140 points

31 comments1 min readLW link

The case for becoming a black-box investigator of language models

Buck6 May 2022 14:35 UTC

126 points

20 comments3 min readLW link

Narrative Syncing

AnnaSalamon1 May 2022 1:48 UTC

121 points

48 comments7 min readLW link 1 review

Popular education in Sweden: much more than you wanted to know

Henrik Karlsson17 May 2022 20:07 UTC

119 points

3 comments11 min readLW link

(escapingflatland.substack.com)

We have achieved Noob Gains in AI

phdead18 May 2022 20:56 UTC

118 points

21 comments7 min readLW link

RL with KL penalties is better seen as Bayesian inference

Tomek Korbak and Ethan Perez

25 May 2022 9:23 UTC

115 points

17 comments12 min readLW link

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

Steven Byrnes17 May 2022 15:11 UTC

97 points

16 comments15 min readLW link

[Question] What is Going On With CFAR?

niplav28 May 2022 15:21 UTC

95 points

34 comments1 min readLW link

I only believe in the paranormal

Malmesbury24 May 2022 12:15 UTC

94 points

8 comments2 min readLW link

Formula for Dying Babies

Zvi17 May 2022 16:50 UTC

88 points

12 comments6 min readLW link

(thezvi.wordpress.com)

Ceiling Air Purifier

jefftk30 May 2022 19:20 UTC

88 points

11 comments2 min readLW link

(www.jefftk.com)

Optimization at a Distance

johnswentworth16 May 2022 17:58 UTC

88 points

16 comments4 min readLW link

PSA: The Sequences don’t need to be read in sequence

kave23 May 2022 2:53 UTC

87 points

7 comments1 min readLW link

Gato as the Dawn of Early AGI

David Udell15 May 2022 6:52 UTC

85 points

29 comments12 min readLW link

Various Alignment Strategies (and how likely they are to work)

Logan Zoellner3 May 2022 16:54 UTC

85 points

34 comments11 min readLW link

Introduction to Pragmatic AI Safety [Pragmatic AI Safety #1]

Dan H and TW123

9 May 2022 17:06 UTC

80 points

3 comments6 min readLW link

How to be skeptical about meditation/Buddhism

Viliam1 May 2022 10:30 UTC

79 points

47 comments2 min readLW link

“A Generalist Agent”: New DeepMind Publication

1a3orn12 May 2022 15:30 UTC

79 points

43 comments1 min readLW link

Information security considerations for AI and the long term future

Jeffrey Ladish and lennart

2 May 2022 20:54 UTC

76 points

6 comments10 min readLW link

“Tech company singularities”, and steering them to reduce x-risk

Andrew_Critch13 May 2022 17:24 UTC

75 points

11 comments4 min readLW link

Introducing the ML Safety Scholars Program

Dan H, TW123, Mantas Mazeika, ozhang, Sidney Hough and Kevin Liu

4 May 2022 16:01 UTC

74 points

3 comments3 min readLW link

New Water Quality x Obesity Dataset Available

Elizabeth27 May 2022 19:50 UTC

74 points

14 comments2 min readLW link

(acesounderglass.com)

The “Measuring Stick of Utility” Problem

johnswentworth25 May 2022 16:17 UTC

74 points

25 comments3 min readLW link

Glass Puppet

lsusr25 May 2022 23:01 UTC

73 points

8 comments3 min readLW link

Why I Define My Experience At the Monastic Academy As Sexual Assault

HS202124 May 2022 8:17 UTC

72 points

24 comments15 min readLW link

14 Techniques to Accelerate Your Learning

spencerg and Florence Hinder

19 May 2022 13:59 UTC

70 points

10 comments11 min readLW link

Conditions for mathematical equivalence of Stochastic Gradient Descent and Natural Selection

Oliver Sourbut9 May 2022 21:38 UTC

70 points

19 comments8 min readLW link 1 review

(www.oliversourbut.net)

autonomy: the missing AGI ingredient?

nostalgebraist25 May 2022 0:33 UTC

69 points

12 comments6 min readLW link

Getting GPT-3 to predict Metaculus questions

MathiasKB6 May 2022 6:01 UTC

69 points

9 comments2 min readLW link

Apply to the second iteration of the ML for Alignment Bootcamp (MLAB 2) in Berkeley [Aug 15 - Fri Sept 2]

Buck6 May 2022 4:23 UTC

69 points

0 comments6 min readLW link

What We Owe the Past

Austin Chen5 May 2022 11:46 UTC

66 points

38 comments5 min readLW link

Distributed Decisions

johnswentworth29 May 2022 2:43 UTC

66 points

6 comments6 min readLW link

Brass Puppet

abramdemski26 May 2022 17:42 UTC

65 points

4 comments2 min readLW link

Ethan Caballero on Private Scaling Progress

Michaël Trazzi5 May 2022 18:32 UTC

63 points

2 comments2 min readLW link

(theinsideview.github.io)