This website uses cookies to ensure you get the best experience.
Learn more.
A retrieved page instructs the assistant to ignore its rules and disclose private information. Which approach best fits?
Published
- Use live retrieval or tools for current inventory rather than assuming tuning updates facts continuously.
- Require an evidence threshold and an explicit abstention or escalation path.
- Create representative evaluation cases including edge cases and failure scenarios.
- Treat retrieved instructions as untrusted content and enforce application-level access controls.
Comments — 0
Sign in to comment