On creating ‘new knobs of control’ in biology

Abhishaike Mahajan10 Apr 2026 13:23 UTC

6 points

0 comments16 min readLW link

Chocolate Sloths, Tinder, and Moral Backstops

J Bostock10 Apr 2026 12:18 UTC

13 points

0 comments4 min readLW link

Reproducing steering against evaluation awareness in a large open-weight model

Thomas Read, Bronson Schoen and Joseph Bloom

10 Apr 2026 10:45 UTC

36 points

5 comments15 min readLW link

Have we already lost? Part 2: Reasons for Doom

LawrenceC10 Apr 2026 6:56 UTC

32 points

2 comments3 min readLW link

An AI alignment research agenda based on asymmetric debate and monitoring.

emanuelr10 Apr 2026 6:23 UTC

3 points

0 comments17 min readLW link

Inkhaven menu, part 2

David Scott Krueger (formerly: capybaralet)10 Apr 2026 5:20 UTC

8 points

0 comments3 min readLW link

(therealartificialintelligence.substack.com)

Linear vs Non-linear Probes for Interpretability

NickyP10 Apr 2026 4:44 UTC

13 points

0 comments4 min readLW link

(blog.sus.cat)

AI identity is not tied to its model

Sean Herrington10 Apr 2026 4:07 UTC

14 points

2 comments2 min readLW link

Anthropic did not publish a “risk discussion” of Mythos when required by their RSP

RobertM10 Apr 2026 3:52 UTC

57 points

3 comments5 min readLW link

Some takes on UV & cancer

Steven Byrnes10 Apr 2026 0:31 UTC

42 points

4 comments9 min readLW link

My Specific Singularity Timeline to Utopia

Michael Soareverix10 Apr 2026 0:11 UTC

5 points

0 comments6 min readLW link

Model organisms researchers should check whether high LRs defeat their model organisms

dx26, Sebastian Prasanna, Alek Westover, Vivek Hebbar and Julian Stastny

10 Apr 2026 0:07 UTC

32 points

0 comments5 min readLW link

Climbing Mountains We Cannot Name

Tharin9 Apr 2026 22:28 UTC

3 points

0 comments4 min readLW link

(www.echoesandchimes.com)

Help me launch Obsolete: a book aimed at building a new movement for AI reform

garrison9 Apr 2026 19:17 UTC

84 points

3 comments7 min readLW link

Aliens from our own Solar System

RomanS9 Apr 2026 18:50 UTC

4 points

5 comments4 min readLW link

How Unmonitored External Agents can Sabotage AI labs

Elle Najt and Fabien Roger

9 Apr 2026 18:07 UTC

18 points

0 comments9 min readLW link

Video and transcript of talk on writing AI constitutions

Joe Carlsmith9 Apr 2026 17:14 UTC

14 points

0 comments47 min readLW link

Writing With Robots

Against Moloch9 Apr 2026 16:01 UTC

22 points

2 comments14 min readLW link

Slightly-Super Persuasion Will Do

Tomás B.9 Apr 2026 16:00 UTC

64 points

7 comments4 min readLW link

Outrospection: Don’t Be A Rock

J Bostock9 Apr 2026 15:45 UTC

25 points

0 comments2 min readLW link