Why hacker mindset and moral alignment would save the world, and why I believe they’re possible

atomic11 May 2026 10:29 UTC

−1 points

0 comments11 min readLW link

Narcissism in the mind’s I

philosophybear11 May 2026 9:05 UTC

5 points

0 comments4 min readLW link

How the AI Labs Make Profit (Maybe, Eventually)

mabramov11 May 2026 7:09 UTC

32 points

4 comments3 min readLW link

Iterative Finetuning is Mostly Idempotent

zroe1, jcksanderson and Julian H

11 May 2026 6:41 UTC

6 points

0 comments5 min readLW link

Dual Bore Janko Venova

jefftk11 May 2026 2:40 UTC

10 points

2 comments3 min readLW link

(www.jefftk.com)

What can you do with barely any data?

ohmurphy10 May 2026 23:13 UTC

8 points

1 comment4 min readLW link

(ohmurphy.substack.com)

The Anti-Singularity

Logan Zoellner10 May 2026 22:33 UTC

6 points

7 comments4 min readLW link

Clarifying the role of the behavioral selection model

Alex Mallen10 May 2026 19:41 UTC

15 points

0 comments4 min readLW link

Alignment as Equilibrium Design

Elad Hazan10 May 2026 18:56 UTC

14 points

0 comments5 min readLW link

Claude Does Not Actually Taste Bananas: Potassium-Based Synthetic Phenomenology In Language Models

Noah Weinberger10 May 2026 17:13 UTC

4 points

0 comments10 min readLW link

(huggingface.co)

The Darwinian Honeymoon—Why I am not as impressed by human progress as I used to be

Elias Schmied10 May 2026 15:55 UTC

91 points

9 comments4 min readLW link

Reinforcement learning scaling might incentivise hidden reasoning architectures for AI

Oliver Sourbut10 May 2026 15:30 UTC

18 points

0 comments6 min readLW link

(www.oliversourbut.net)

Asymmetry Between Defensive and Acquisitive Instrumental Deception

keith_wynroe10 May 2026 12:33 UTC

13 points

1 comment5 min readLW link

Context Modification as a Negative Alignment Tax

Florian_Dietz10 May 2026 11:32 UTC

7 points

0 comments4 min readLW link

The AI Industrial Explosion — Part 2: Transition Dynamics

djbinder10 May 2026 1:02 UTC

22 points

0 comments12 min readLW link

(defensesindepth.bio)

International Law Cannot Prevent Extinction Either

Sausage Vector Machine9 May 2026 22:34 UTC

78 points

13 comments5 min readLW link

Do capabilities generalize across propensities?

Emil Ryd9 May 2026 21:39 UTC

12 points

0 comments8 min readLW link

Neural Networks learn Bloom Filters

Alex Gibson9 May 2026 20:32 UTC

52 points

1 comment12 min readLW link

Explaining Volition Without Resorting to Free Will

joseph_c9 May 2026 18:57 UTC

12 points

15 comments1 min readLW link

Second order thoughts on current AI agents

Michael Flood9 May 2026 18:40 UTC

12 points

0 comments2 min readLW link