Its formalized in lean, which verifies each step. The steps themselves are relatively easy, and can be mechanically verified (think "A and A->B thus by modus ponens B").
Traditionally writing verified proofs is a hard undertaking, exactly because you need to write out a lot of steps "normal human" mathematics jump over, but with AI its easier.
At what point do we start worrying that it's found a bug in Lean instead?
> The steps themselves are relatively easy, and can be mechanically verified
They aren't