Interesting. In that case, would you say an AI that provably implements CEV’s replacement is, for that reason, provably Friendly?
I think that’s MIRI’s usage of the term friendly.
If it’s open to the public, then I’d like to understand how EY proposes to install a general framework similar to CEV at the “initial dynamic” stage
He’s not proposing a mechanism as far as I know. That’s another open problem.
I think that’s MIRI’s usage of the term friendly.
He’s not proposing a mechanism as far as I know. That’s another open problem.