Can the Safety Tax Be Highly Concentrated?

ozziegooen15 Jun 2026 18:48 UTC

7 points

0 comments2 min readLW link

A frontier AI company should shut down

MichaelDickens15 Jun 2026 16:56 UTC

51 points

4 comments2 min readLW link

Links #3: 2026/06 Part 1

papetoast15 Jun 2026 12:53 UTC

9 points

0 comments27 min readLW link

How reality turns to slop

julius vidal15 Jun 2026 10:42 UTC

8 points

3 comments4 min readLW link

On Responsibility and Death: Can We See Reality for What It Is or Will It Break Us

Dawn Drescher15 Jun 2026 10:14 UTC

6 points

0 comments3 min readLW link

(impartial-priorities.org)

VFUSE: Virulent Feature Understanding With Sparse AutoEncoders

michaelwaves15 Jun 2026 5:06 UTC

11 points

0 comments2 min readLW link

The Power to Punish

Ben Pace15 Jun 2026 2:22 UTC

19 points

6 comments5 min readLW link

You need to know about the Baruch Plan

aggliu15 Jun 2026 1:21 UTC

26 points

1 comment3 min readLW link

(signoregalilei.com)

Exploring Known Unknowns in the AI Regulatory Landscape

NelsonDP14 Jun 2026 22:36 UTC

6 points

0 comments22 min readLW link

(open.substack.com)

Attack of the Killer Differential Equations

Fernand014 Jun 2026 22:20 UTC

6 points

0 comments2 min readLW link

I built a public arena where people attack a “pro-human” steering direction

sohampadia10@gmail.com14 Jun 2026 21:26 UTC

1 point

0 comments9 min readLW link

(sohampadianeu-steering-arena.hf.space)

Why Do Naive SFT Filters For Safety Properties Fail?

Josh Engels and Neel Nanda

14 Jun 2026 19:45 UTC

41 points

0 comments10 min readLW link

Why I think a global AI pause (almost) certainly won’t happen

Expertium14 Jun 2026 19:20 UTC

19 points

0 comments2 min readLW link

Gradual disempowerment at the scale of one user

ppal14 Jun 2026 18:01 UTC

10 points

0 comments4 min readLW link

How does congressmember use AI?

Ilyass Mofaddel14 Jun 2026 18:00 UTC

10 points

1 comment4 min readLW link

The Posture of Thought

dongerous14 Jun 2026 18:00 UTC

12 points

0 comments5 min readLW link

The Dual-Use Gap

Yogesh Prabhu14 Jun 2026 17:43 UTC

5 points

0 comments4 min readLW link

(yogesh.bearblog.dev)

Can a stronger model fake being a weaker one? Mostly not

Rob Kopel14 Jun 2026 17:30 UTC

8 points

0 comments7 min readLW link

(www.robkopel.me)

The 1890 Census as a fun cluster

Fernand014 Jun 2026 15:41 UTC

0 points

3 comments1 min readLW link

The Hidden Structures of Problems

spencerg14 Jun 2026 13:51 UTC

79 points

8 comments3 min readLW link

(www.spencergreenberg.com)