Thomas Kwa comments on Goodhart’s Law Causal Diagrams

Thomas Kwa 31 Mar 2023 4:35 UTC
2 points
In future posts, we will describe a more complete categorisation of these situations and how they relate to the AI alignment problem.
Did this ever happen?
- Jeremy Gillen 31 Mar 2023 4:50 UTC
  1 point
  Parent
  No, Justin knows roughly the content for the intended future posts but after getting started writing I didn’t feel like I understood it well enough to distill it properly and I lost motivation, and since then I became too busy.
  I’ll send you the notes that we had after Justin explained his ideas to me.