Back to AIBriefs
AnalysisCybersecurityPolicy
Featured·

Gray Swan founders discuss Mythos red-teaming and AI security

In a Latent Space podcast, Zico Kolter and Matt Fredrikson of Gray Swan explain why AI security differs from traditional cybersecurity and how agents introduce new vulnerabilities. They discuss automated red-teaming, model robustness, and enterprise guardrails in the context of the Mythos export controls.

Jun 22, 9:06 PM
Gray Swan founders discuss Mythos red-teaming and AI security — AIBriefs