The Day After Move 37

Eneasz10 Mar 2026 23:05 UTC

10 points

0 comments6 min readLW link

(deathisbad.substack.com)

Interview with Steven Byrnes on His Mainline Takeoff Scenario

Liron10 Mar 2026 20:17 UTC

30 points

0 comments57 min readLW link

(doomdebates.com)

AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors

abhayesian10 Mar 2026 19:31 UTC

21 points

1 comment8 min readLW link

(alignment.anthropic.com)

Economic efficiency often undermines sociopolitical autonomy

Richard_Ngo10 Mar 2026 19:30 UTC

65 points

6 comments12 min readLW link

(www.mindthefuture.info)

Letting Claude do Autonomous Research to Improve SAEs

chanind10 Mar 2026 18:52 UTC

48 points

2 comments7 min readLW link

Don’t Let LLMs Write For You

JustisMills10 Mar 2026 18:49 UTC

58 points

1 comment3 min readLW link

(justismills.substack.com)

Questions to ask when everyone is shooting themselves in the foot

jasoncrawford10 Mar 2026 18:36 UTC

20 points

1 comment1 min readLW link

The case for satiating cheaply-satisfied AI preferences

Alex Mallen10 Mar 2026 18:09 UTC

60 points

3 comments23 min readLW link

Gemma Needs Help

Anna Soligo10 Mar 2026 17:39 UTC

108 points

8 comments6 min readLW link

Not Loving Liking What You See

Tomás B.10 Mar 2026 16:05 UTC

35 points

5 comments5 min readLW link

Statisticism: How Cluster-Thinking About Data Creates Blind Spots

Benquo10 Mar 2026 13:59 UTC

22 points

0 comments12 min readLW link

(benjaminrosshoffman.com)

Spontaneous Symmetry Breaking (Stat Mech Part 4)

J Bostock10 Mar 2026 13:21 UTC

13 points

2 comments4 min readLW link

Why I don’t usually recommend dead drops

samuelshadrach10 Mar 2026 13:13 UTC

7 points

2 comments4 min readLW link

(samuelshadrach.com)

Four Scenarios of Job-Reducing AI

Celer10 Mar 2026 13:10 UTC

11 points

2 comments4 min readLW link

(keller.substack.com)

Understanding Reasoning with Thought Anchors and Probes

JeaniceK, Johannes Taraz and Matthew Robbins

10 Mar 2026 11:50 UTC

7 points

0 comments13 min readLW link

Contra Myself on Free Will

Julius10 Mar 2026 6:29 UTC

9 points

5 comments10 min readLW link

(thegreymatter.substack.com)

The case for AI safety capacity-building work

abergal10 Mar 2026 2:43 UTC

44 points

14 comments22 min readLW link

Chore Standards

jefftk10 Mar 2026 2:30 UTC

27 points

1 comment2 min readLW link

(www.jefftk.com)

Ancient Theories On The Origins Of Life

Algon10 Mar 2026 1:55 UTC

21 points

0 comments3 min readLW link

(algon33.substack.com)

Immortality: A Beginner’s Guide (Part 2)

MarkelKori10 Mar 2026 0:11 UTC

9 points

4 comments5 min readLW link