alt Hacker NewsI don't think AI is particularly worse at multi-threading code than humans are: humans are notoriously bad at it. I've had reasonably good success with telling Claude and Gemini to go into a codebase, insert clang -Wthread-safety annotations, fix any issues it finds, and refactor code that isn't amenable to the annotations to make it possible.
But there are any number of humans who will tell you that humans are bad at multithreading the codes and all but the smallest codebases are headed for heisenbug deadlock city if you do things like they told you to in that Introduction to OOP with JavaTM book.
But is Claude going to tell you "No, dear user, this project is going to follow an excessively simple and sub-optimal locking regime because experience shows that it is easier to write code than it is to reason about its exponentially-growing complexity" ?