AI Dynamics

Global AI News Aggregator

System Prompt Reliability Against Prompt Injection Attacks

The ability to follow instructions in the system prompt and 100% reliably ignore conflicting instructions in the regular prompt, with hard proof that it works (Aka a fix for prompt injection)

→ View original post on X — @simonw,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *