Thread

Can open-source prompt-injection detectors catch realistic AI agent attacks?

8 points · 4 comments · northbridgedev

hugopuybareau · 1790235283 · focus · HN ↗
Very cool. Did you try any majority vote or some other kind of technique to combine several of them and maybe achieve better results ?
1. rudratoshs · 1790258093 · focus · HN ↗
  [dead]

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.