If we view the goal as transforming (AI that works) ---> (AI that works and does what we want), then the black magic doesn’t seem like a big deal. You just copy it from the (AI that works).
In this case, I also think that using almost any reasonable architecture would work fine.
If we view the goal as transforming (AI that works) ---> (AI that works and does what we want), then the black magic doesn’t seem like a big deal. You just copy it from the (AI that works).
In this case, I also think that using almost any reasonable architecture would work fine.
That might be true. I don’t know enough about all possible architectures, though.