In threads where the LLM makes mistakes, it seems like it tends to make more mistakes.

· Bits and Bobs 8/31/26
  • In threads where the LLM makes mistakes, it seems like it tends to make more mistakes.
    • When you correct its mistakes, especially if you do it with strong language, the easiest explanation is "this is a thread where the LLM isn't very good at things, and the human is supposed to admonish them."
    • The easiest way to continue that narrative coherently is for the LLM to make additional small mistakes.