A human doesn't need to understand the proof, they just have to understand why the proof is a proof.
Making a proof formal doesn't mean it is not understandable any more. First, certainly a machine can "understand" it now. I think with AI improving what exactly such an understanding is worth, and what you can do with it, will increase a lot.
Secondly, the inscrutable tactics-based proofs featured in Lean (I have written such proofs in Isabelle in 1996) are actually quite old-fashioned for such a "modern" prover. Isabelle has long featured human-friendly syntax, and these proofs are certainly as understandable as English text, if written with care.
What we will soon get are proof assistants which allow you to write your proofs (and definitions) in English, but which are still fully formal and checkable. That is an immense help if you are producing new knowledge, because usually nobody else looks at your work with sufficient scrutiny in the first place. If you understand it, and in addition the machine "understands" it, I think that will be the gold standard for proofs very soon.
It will also help mathematicians to clean up their act ;-)
Then you need to implement that logic in software, and again, you can and will mistakes here. You will use the first version of that software, or another logic software, to verify that your informal thoughts why your logic implementation is correct, can be formalised and checked. You will find mistakes, and fix them, and check that your correctness proof still goes through. It is very unlikely that it won't, but if it doesn't, you fix your correctness proof. If you can indeed fix it, you are done, no mistakes remain. If you cannot, something must be wrong with your implementation, so rinse and repeat.
At the end of this, you have a logic, and a logic implementation, which doesn't contain any mistakes. Guaranteed.