> It checks these using an LLM which is instructed to score the user's prompt. Y... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

SahAssar 88 days ago | parent | context | favorite | on: Data Exfiltration from Slack AI via indirect promp...

> It checks these using an LLM which is instructed to score the user's prompt.

You need to seriously reconsider your approach. Another (especially a generic) LLM is not the answer.

gregatragenet3 87 days ago [–]

What solution would you recommend then?

namaria 87 days ago | | [–]

Don't graft generative AI on your system? Seems pretty straightforward to me.

SahAssar 87 days ago | | [–]

If you want to defend against prompt injection why would you defend with a tool vulnerable to prompt injection?

I don't know what I would use, but this seems like a bad idea.

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