LLMs are doing what you train them to do. See for example " The Instruction Hier... | Hacker News

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

		red75prime 9 months ago \| parent \| context \| favorite \| on: New Vulnerability in GitHub Copilot, Cursor: Hacke... LLMs are doing what you train them to do. See for example " The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions " by Eric Wallace et al.

MattPalmer1086 9 months ago [–]

Interesting. Doesn't solve the problem entirely but seems to be a viable strategy to mitigate it somewhat.

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