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

I think a future with LLM coding requires much more tests, both testing happy and bad flows.


I think the issue is with people taking mental shortcuts and thus no longer properly thinking about design decisions and the bigger picture in terms of concepts of the software.


It also needs proper guideline enforcement. If an engineer produces poorly tested and unreviewed code, then the buck stops with them. This is a human problem more than it is a tool problem.




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

Search: