将人工智能指向一个“经过验证”的微内核？
既然显而易见人工智能在发现安全漏洞方面表现出色，有人将其应用于一些经过形式验证的软件吗？我在想 seL4。从理论上讲，它应该不会发现任何问题，对吧？
查看原文
Since it has become obvious that AI is great at finding security flaws, has anyone pointed it at some formally proven software? I'm thinking seL4. In theory it should find nothing, right?