Re:"Erdos problem #728 was solved more or less autonomously ...
by rhdunn on Saturday January 10, 2026 @06:01AM
(#46564653)
This is also an issue with non-AI and non-Lean proofs. Andrew Wiles' initial Fermat's Last Theorem proof initially had an error in it. That was spotted by peer review, fixed, and an updated proof was submitted.
The lean proof checker then checks to make sure the proof actually proves the statement.
In this case an AI is generating the proof, but if it "compiles" it's correct. The only thing humans need to check is the statement to be proven.
(I don't know anything about this project but I've played around with lean and used other proof checkers more sesrisously).