Aligned to Whom?

(hyperbo.la)

18 points | by lopopolo 4 hours ago ago

1 comments

  • coderintherye 30 minutes ago

    The last paragraph does the heavy-lifting.

    Everyone has a different idea of what is permissable. We can't even solve alignment amongst humans, what makes us think it is possible to solve alignment with AIs? It's irreducible complexity.