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

I am telling you that I've seen AI support fail at level 1 and it's frustrating. It should be simple, but even cancelling your service or returning an item can have many edge cases that only a human can sort out.


I have also experienced this; I'm not saying LLMs are great or infallible. Just saying that they are generally a reasonable replacement for L1 support. They are worthless for L2 or above.




Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

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

Search: