Seems like every other AI code analysis tool. Someone excited posts about how it made 1000s of syntactically valid fixes! Of course some are wrong and others are worse than not being there, but surely some are useful! Surely in the coming weeks it’ll improve to make millions of potentially useful tests!

Seems like a waste of time unless you can be sure it’s spitting out valuable fixes.

I'm the original developer and it seems very few people really understand how to use this tool. And I did a poor job explaining it too.

No, I do not think of this of patches to be integrated anywhere. Even if you want to do this, its much easier to review the patches than to write them. But why integrate the patches to the code when you can regenerate them all in hours?

This is a post-processing tool. You add additional checks to your existing code. This will help to catch bugs, (and also perhaps introduce its own bugs), like basically every other compiler-level protection.

But if you catch more bugs than what you introduce, you win. And remember this is done with an very basic AI, next year AIs will produce much better code.

Read the comments. Utter garbage. Especially for a kernel. Maybe some CRUD app that manages people’s hotel rooms and even then it’s not trusted enough.