26 May 2024 22:17 UTC

23 points

0 comments3 min readLW link

If you are also the worst at politics

lemonhope26 May 2024 20:07 UTC

32 points

8 comments1 min readLW link

Review: Conor Moreton’s “Civilization & Cooperation”

Duncan Sabien (Deactivated)26 May 2024 19:32 UTC

89 points

8 comments38 min readLW link

The necessity of “Guardian AI” and two conditions for its achievement

Proica26 May 2024 17:39 UTC

−2 points

0 comments15 min readLW link

Notifications Received in 30 Minutes of Class

tanagrabeast26 May 2024 17:02 UTC

353 points

16 comments8 min readLW link

Show LW: HackerNews but for research papers

sleno26 May 2024 15:14 UTC

6 points

1 comment1 min readLW link

Disproving and partially fixing a fully homomorphic encryption scheme with perfect secrecy

Lysandre Terrisse26 May 2024 14:56 UTC

16 points

1 comment18 min readLW link

The AI Revolution in Biology

Roman Leventov26 May 2024 9:30 UTC

13 points

0 comments1 min readLW link

(www.cognitiverevolution.ai)

[Question] Who does the artwork for LessWrong?

ektimo26 May 2024 5:55 UTC

10 points

1 comment1 min readLW link

[Question] Is there an idiom for bonding over shared trials/trauma?

CstineSublime26 May 2024 1:18 UTC

2 points

1 comment1 min readLW link

Moloch—An Illustrated Primer

James Stephen Brown26 May 2024 1:04 UTC

5 points

0 comments7 min readLW link

(nonzerosum.games)

[Question] Is CDT with precommitment enough?

martinkunev25 May 2024 21:40 UTC

10 points

17 comments1 min readLW link

Complex systems theory in human performance. New model for conceptualizing training, adaptation and long-term development

Matěj Nekoranec25 May 2024 20:17 UTC

1 point

0 comments7 min readLW link

Blindspot in Sport’s Data-Driven Age

Matěj Nekoranec25 May 2024 20:17 UTC

2 points

0 comments7 min readLW link

LMSR subsidy parameter is the price of information

Abhimanyu Pallavi Sudhir25 May 2024 18:05 UTC

5 points

0 comments1 min readLW link

Low Fertility is a Degrowth Paradise

Maxwell Tabarrok25 May 2024 17:35 UTC

7 points

2 comments3 min readLW link

(www.maximum-progress.com)

Episode: Austin vs Linch on OpenAI

Austin Chen25 May 2024 16:15 UTC

20 points

25 comments1 min readLW link

(manifund.substack.com)

Training-time domain authorization could be helpful for safety

domenicrosati, Jan Wehner and David Atanasov

25 May 2024 15:10 UTC

15 points

4 comments7 min readLW link

Level up your spreadsheeting

angelinahli25 May 2024 14:57 UTC

44 points

11 comments3 min readLW link

(docs.google.com)

“Successful language model evals” by Jason Wei

Arjun Panickssery25 May 2024 9:34 UTC

7 points

0 comments1 min readLW link

(www.jasonwei.net)

Beta Tester Request: Rallypoint Bounties

lukemarks25 May 2024 9:11 UTC

25 points

4 comments1 min readLW link

[Question] What should the norms around AI voices be?

ChristianKl25 May 2024 6:29 UTC

17 points

6 comments1 min readLW link

Secret US natsec project with intel revealed

Nathan Helm-Burger25 May 2024 4:22 UTC

24 points

0 comments1 min readLW link

(www.politico.com)

Launch & Grow Your University Group: Apply now to OSP & FSP!

agucova25 May 2024 1:03 UTC

3 points

0 comments1 min readLW link

Computational Mechanics Hackathon (June 1 & 2)

Adam Shai24 May 2024 22:18 UTC

34 points

5 comments1 min readLW link

[Question] Request for comments/opinions/ideas on safety/ethics for use of tool AI in a large healthcare system.

bokov24 May 2024 20:53 UTC

5 points

2 comments1 min readLW link

NYU Code Debates Update/Postmortem

David Rein24 May 2024 16:08 UTC

27 points

4 comments10 min readLW link

AI companies aren’t really using external evaluators

Zach Stein-Perlman24 May 2024 16:01 UTC

240 points

15 comments4 min readLW link

The Schumer Report on AI (RTFB)

Zvi24 May 2024 15:10 UTC

34 points

3 comments36 min readLW link

(thezvi.wordpress.com)

minutes from a human-alignment meeting

bhauth24 May 2024 5:01 UTC

66 points

4 comments2 min readLW link

Talent Needs of Technical AI Safety Teams

yams, Carson Jones, McKennaFitzgerald and Ryan Kidd

24 May 2024 0:36 UTC

115 points

64 comments14 min readLW link

How to Give Coming AGI’s the Best Chance of Figuring Out Ethics for Us

sweenesm23 May 2024 19:44 UTC

1 point

0 comments10 min readLW link

Mentorship in AGI Safety (MAGIS) call for mentors

Valentin2026 and Joe Rogero

23 May 2024 18:28 UTC

31 points

3 comments2 min readLW link

Quick Thoughts on Scaling Monosemanticity

Joel Burget23 May 2024 16:22 UTC

28 points

1 comment4 min readLW link

(transformer-circuits.pub)

The case for stopping AI safety research

catubc23 May 2024 15:55 UTC

52 points

38 comments1 min readLW link

[Question] SAE sparse feature graph using only residual layers

Jaehyuk Lim23 May 2024 13:32 UTC

0 points

3 comments1 min readLW link

[Question] Are most people deeply confused about “love”, or am I missing a human universal?

SpectrumDT23 May 2024 13:22 UTC

11 points

26 comments3 min readLW link

Executive Dysfunction 101

DaystarEld23 May 2024 12:43 UTC

25 points

1 comment3 min readLW link

(daystareld.com)

AI #65: I Spy With My AI

Zvi23 May 2024 12:40 UTC

28 points

7 comments43 min readLW link

(thezvi.wordpress.com)

What mistakes has the AI safety movement made?

EuanMcLean23 May 2024 11:19 UTC

63 points

29 comments12 min readLW link

What should AI safety be trying to achieve?

EuanMcLean23 May 2024 11:17 UTC

16 points

0 comments13 min readLW link

What will the first human-level AI look like, and how might things go wrong?

EuanMcLean23 May 2024 11:17 UTC

20 points

2 comments15 min readLW link

Big Picture AI Safety: Introduction

EuanMcLean23 May 2024 11:15 UTC

46 points

7 comments5 min readLW link

Paper in Science: Managing extreme AI risks amid rapid progress

JanB23 May 2024 8:40 UTC

50 points

2 comments1 min readLW link

Power Law Policy

Ben Turtel23 May 2024 5:28 UTC

4 points

7 comments6 min readLW link

(bturtel.substack.com)

Why entropy means you might not have to worry as much about superintelligent AI

Ron J23 May 2024 3:52 UTC

−26 points

1 comment2 min readLW link

Quick Thoughts on Our First Sampling Run

jefftk23 May 2024 0:20 UTC

29 points

3 comments2 min readLW link

(www.jefftk.com)

AI Safety proposal—Influencing the superintelligence explosion

Morgan22 May 2024 23:31 UTC

0 points

2 comments7 min readLW link

Implementing Asimov’s Laws of Robotics—How I imagine alignment working.

Joshua Clancy22 May 2024 23:15 UTC

2 points

0 comments11 min readLW link

Higher-Order Forecasts

ozziegooen22 May 2024 21:49 UTC

44 points

1 comment1 min readLW link