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

A schema with response metadata (so responses that deviate from it fail automatically), plus a challenge question that's calibrated to be hard enough that the disruption of instruction following from prompt injection can cause the model to answer incorrectly.


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

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

Search: