Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

You could train a model on purely secure code and still have it combine it in insecure ways.


And the other way around.


I guess the question really is how many ways are there to do it wrong, and how many ways are there to do it right?




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: