That doesn't work either. It's always possible to come up with an attack which s... | Hacker News

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

		simonw 7 months ago \| parent \| context \| favorite \| on: Poison everywhere: No output from your MCP server ... That doesn't work either. It's always possible to come up with an attack which subverts the "moderator" model first. Using non-deterministic AI to protect against attacks against non-deterministic AI is a bad approach.

K0balt 7 months ago [–]

So you just need another agent to review the data being passed to the protector agent. Easy-peasy.

Use my openAI referral code #LETITRAIN for 10% off!

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