Comment by pixl97

We can shoot for 100% accountability by demanding 100% accuracy.

Of course what will really happen is anyone looking for problems will stop going to the source for fixes and will start gaining cred in the dark markets of exploits and problems, which is better for everyone, right?

Just because someone is using AI doesn't mean they didn't find a bug, it's more likely they just have no means of determining if it's a real bug or not, so to the maintainers tickets seem random. The problem comes in when clever attackers can take these untrustworthy tickets and run them through another LLM that determines if an exploit is possible and then uses the attacks it finds before anyone has a chance to patch.