fakeanalyst

• fakeanalyst 31 Jul 2025 18:33 UTC

  3 points

  0

  in reply to: Buck’s comment on: Buck’s Shortform

  The usefulness of interpretability research

• fakeanalyst 16 May 2025 20:40 UTC

  1 point

  0

  on: Gen­er­at­ing the Fun­niest Joke with RL (ac­cord­ing to GPT-4.1)

  Goodhart’s law!