Monday Jun 10, 2024
LLMs Can't Keep a Secret - Techstrong AI - EP19
In this Techstrong.ai podcast, Mike Vizard talks to Kev Breen, senior director of threat intelligence at Immersive Labs, about why it's relatively trivial to prompt a large language model to share data it has been explicitly told to keep secret.
Links Referenced in Podcast:
https://techstrong.ai/articles/immersive-labs-surfaces-gen-ai-security-flaws/
Version: 20240731