David Litman

Karma: 110

I like mechanistic interpretability, neuroscience, chess, pi recitation bees, dogs, and the bass.

Check out davidlitman.com for more

Insights into Curry’s Paradox?

David Litman1 Sep 2026 5:40 UTC

12 points

18 comments1 min readLW link

Ablating 1 of a chess transformer’s 128 attention heads makes the model stop finding Paul Morphy’s queen sacrifice

David Litman20 Aug 2026 21:17 UTC

7 points

1 comment1 min readLW link

(www.youtube.com)

Fork Around and Find Out Part 3: Interpreting the knight auditor

David Litman17 Aug 2026 18:11 UTC

18 points

0 comments5 min readLW link

One attention head carries knight forks in a chess transformer, and here’s a new toolkit that found it.

David Litman12 Aug 2026 16:48 UTC

8 points

0 comments1 min readLW link

(github.com)

Fork Around and Find Out Part 2: One Head does the Summing

David Litman15 Jul 2026 18:31 UTC

11 points

1 comment7 min readLW link

Watch a chess transformer think

David Litman15 Jul 2026 0:43 UTC

27 points

7 comments1 min readLW link

(github.com)

Fork Around and Find Out: Part 1—A Fork Snaps Into Existence at Block 5

David Litman7 Jul 2026 4:36 UTC

11 points

0 comments7 min readLW link

dl’s Shortform

David Litman7 Jul 2026 4:36 UTC

1 point

3 comments1 min readLW link