Can you personally (under your own power) and confidently prove that a particular tool will only recursively-trust safe-and-reliable tools, where this recursive tree reaches far enough to trust superhuman AI?
On the other hand, you can “follow” the tree for a distance. You can prove a calculator trustworthy and use it in your following proofs, for instance. This might make it more feasible.
Can you personally (under your own power) and confidently prove that a particular tool will only recursively-trust safe-and-reliable tools, where this recursive tree reaches far enough to trust superhuman AI?
On the other hand, you can “follow” the tree for a distance. You can prove a calculator trustworthy and use it in your following proofs, for instance. This might make it more feasible.
I don’t think proofs are the right tool here. Proof by induction was meant as an analogy.