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

Can we really name this "Prompt engineering"? The prompt is so simple this is hardly any work even less than this comment


Fair point but it's not social either. It's a new class of exploit that's based on tricking the AI.


It's not based on plugging an LLM into an area where it doesn't belong in the first place?




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: