Guardrailing is usually done with a smaller model (< 1b) to filter out simple "n... | Hacker News

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

		eden-u4 13 days ago \| parent \| context \| favorite \| on: My university uses prompt injection to catch cheat... Guardrailing is usually done with a smaller model (< 1b) to filter out simple "not aligned prompt" and not waste compute.

		help

anuramat 13 days ago [–]

sure, but here we start with a performance problem, not compute

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