Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Aligned to Whom?.
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.
There are no comments on this comment yet.
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.