InsanityBench: Cryptic Puzzles as a Probe for Lateral Thinking

RobinHa22 Feb 2026 14:20 UTC

15 points

0 comments4 min readLW link

(www.robinhaselhorst.com)

The world won’t end, but we should be ashamed for trying

George3d622 Feb 2026 13:01 UTC

−2 points

0 comments12 min readLW link

(cerebralab.com)

Multiple Independent Semantic Axes in Gemma 3 270M

CharlesL22 Feb 2026 1:55 UTC

12 points

0 comments3 min readLW link

A Taxonomy of Traces

aleph_four22 Feb 2026 1:28 UTC

0 points

0 comments10 min readLW link

Hierarchical Goal Induction With Ethics

aleph_four22 Feb 2026 0:53 UTC

5 points

0 comments4 min readLW link

Did Claude 3 Opus align itself via gradient hacking?

Fiora Starlight21 Feb 2026 22:24 UTC

171 points

9 comments19 min readLW link

If you don’t feel deeply confused about AGI risk, something’s wrong

Dave Banerjee21 Feb 2026 15:34 UTC

62 points

8 comments5 min readLW link

(open.substack.com)

Ponzi schemes as a demonstration of out-of-distribution generalization

TFD21 Feb 2026 13:19 UTC

9 points

2 comments6 min readLW link

(www.thefloatingdroid.com)

LLMs and Literature: Where Value Actually Comes From

derelict543221 Feb 2026 13:16 UTC

7 points

7 comments4 min readLW link

The Spectre haunting the “AI Safety” Community

Gabriel Alfour21 Feb 2026 11:14 UTC

142 points

9 comments6 min readLW link

(cognition.cafe)

Alignment to Evil

Matrice Jacobine21 Feb 2026 3:29 UTC

54 points

2 comments1 min readLW link

(tetraspace.substack.com)

Robert Sapolsky Is Simply Not Talking About Compatibilism

Julius21 Feb 2026 1:27 UTC

11 points

4 comments8 min readLW link

(thegreymatter.substack.com)

How will we do SFT on models with opaque reasoning?

Alek Westover and Vivek Hebbar

21 Feb 2026 0:00 UTC

31 points

11 comments7 min readLW link

Agent-first context menus

Surya Kasturi20 Feb 2026 23:45 UTC

3 points

1 comment2 min readLW link

Hodoscope: Visualization for Efficient Human Supervision

Ziqian Zhong and Shashwat Saxena

20 Feb 2026 23:41 UTC

7 points

0 comments2 min readLW link

(hodoscope.dev)

Can Current AI Match (or Outmatch) Professionals in Economically Valuable Tasks?

saahir.vazirani20 Feb 2026 21:38 UTC

6 points

0 comments5 min readLW link

METR’s 14h 50% Horizon Impacts The Economy More Than ASI Timelines

Michaël Trazzi20 Feb 2026 21:08 UTC

40 points

11 comments2 min readLW link

New video from Palisade Research: No One Understands Why AI Works

peterbarnett20 Feb 2026 20:29 UTC

55 points

2 comments1 min readLW link

(www.youtube.com)

Militaries are going autonomous. But will AI lead to new wars? A tour of recent research

Mordechai Rorvig20 Feb 2026 18:26 UTC

1 point

0 comments2 min readLW link

(www.foommagazine.org)

Unprecedented Catastrophes Have Non-Canonical Probabilities

E.G. Blee-Goldman20 Feb 2026 18:23 UTC

7 points

2 comments14 min readLW link