I feel scooped by this post! :) I was thinking along different lines—using induction (postdictive learning) to get around Goodhart’s law specifically by using the predictions outside of their nominal use case. But now I need to go back and think more about self-fulfilling prophecies and other sorts of feedback.
Maybe I’ll try to get you to give me some feedback later this week.
I feel scooped by this post! :) I was thinking along different lines—using induction (postdictive learning) to get around Goodhart’s law specifically by using the predictions outside of their nominal use case. But now I need to go back and think more about self-fulfilling prophecies and other sorts of feedback.
Maybe I’ll try to get you to give me some feedback later this week.
Sounds interesting!