Superintelligence vs. The Second Strike

Felix Choussat23 Jun 2026 20:55 UTC

7 points

0 comments7 min readLW link

What the Shadow Feels: A projected model of life

Winry Rockbell23 Jun 2026 20:02 UTC

1 point

0 comments4 min readLW link

The worthlessness of vitamin D is mildly exaggerated

dynomight23 Jun 2026 19:39 UTC

22 points

1 comment20 min readLW link

(dynomight.net)

And what happens next?

Sean Herrington23 Jun 2026 13:01 UTC

27 points

4 comments2 min readLW link

Catastrophic Forgetting and Safety Erosion Are Driven by the Same Mechanism and Should Be Monitored by the Same Tools

frpatry23 Jun 2026 11:54 UTC

3 points

0 comments18 min readLW link

A system overview for near-term, low-trust AI compute verification

Naci Cankaya23 Jun 2026 10:59 UTC

38 points

2 comments41 min readLW link

Alignment problem by extended science

PeterL23 Jun 2026 6:01 UTC

1 point

0 comments1 min readLW link

On TEEs for Privacy-Preserving Monitoring in AI Governance

pithospothos23 Jun 2026 2:48 UTC

10 points

4 comments28 min readLW link

Model Size Scaling in 2023-2031

Vladimir_Nesov22 Jun 2026 23:07 UTC

52 points

8 comments12 min readLW link

LLM-Driven Feature Discovery

Josh Engels, bilalchughtai and Neel Nanda

22 Jun 2026 22:26 UTC

10 points

0 comments5 min readLW link

Pathological Narcissism: The Pendulum Swing between Echoism and Sovereignism

Dawn Drescher22 Jun 2026 21:56 UTC

5 points

0 comments8 min readLW link

(impartial-priorities.org)

Speedup from AI Ghostwriting

Dawn Drescher22 Jun 2026 21:47 UTC

8 points

0 comments5 min readLW link

(impartial-priorities.org)

Functional Emotions and The Pope’s Encyclical on AI — Digital Minds Newsletter #3

22 Jun 2026 19:44 UTC

14 points

0 comments39 min readLW link

(www.digitalminds.news)

Planning for Preservation in the Age of AI

Raelifin22 Jun 2026 17:51 UTC

27 points

1 comment13 min readLW link

Learning to Understand Evil

Yulia22 Jun 2026 14:43 UTC

2 points

5 comments7 min readLW link

Defeatism as Disempowerment

Ramya22 Jun 2026 14:24 UTC

4 points

0 comments3 min readLW link

A Mechanistic Explanation of Prompt Injection (and why you should study roles)

Charles Ye and lesscertain

22 Jun 2026 14:09 UTC

129 points

16 comments16 min readLW link

The AI Industrial Explosion — Part 4: Cheap power

djbinder22 Jun 2026 13:30 UTC

61 points

0 comments16 min readLW link

(defensesindepth.bio)

Not all features are created equal

enricobottazzi22 Jun 2026 13:20 UTC

22 points

0 comments9 min readLW link

Brittle model organisms obstructs deception elicitation work

Advik, Daniel Tan and Chloe Li

22 Jun 2026 10:48 UTC

19 points

6 comments7 min readLW link