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

Right, which is why having a comprehensive test suite is such an enormous unlock for this class of technology.

If your tests are good, Claude Code can run them and use them to check it hasn't broken any distant existing behavior.



Not always the case. It’ll just go and “fix” the tests to pass instead of fixing the core issue.


That used to happen a whole lot more. Recent Claudes (3.7, 4) are less likely to do that in my experience.

If they DO do that, it's on us to tell them to undo that and fix things properly.




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

Search: