Utility is potentially a good thing to critique, but the case for seems sticky and maybe we’re just holding it wrong or something. An issue is that I don’t “have” a utility function; the vnm axioms hold in the limit of unexploitability but it seems like the process of getting my mistakes gently corrected by interaction with the universe is itself something I prefer to have some of. In active inference terms, I don’t only want to write to the universe.
But this post seems kinda vague too. I upvote hesitantly.
Utility is potentially a good thing to critique, but the case for seems sticky and maybe we’re just holding it wrong or something. An issue is that I don’t “have” a utility function; the vnm axioms hold in the limit of unexploitability but it seems like the process of getting my mistakes gently corrected by interaction with the universe is itself something I prefer to have some of. In active inference terms, I don’t only want to write to the universe.
But this post seems kinda vague too. I upvote hesitantly.