Gray Swan cofounders Zico Kolter and Matt Fredrikson explain why AI systems need a different security mindset, focusing on indirect prompt injection, agent vulnerabilities and correlated failures. They walk through automated red teaming tools like Shade and the Gray Swan Arena, discuss guardrails, and argue that bigger models aren’t inherently safer and require bespoke security, identity management, and compliance measures.

Stanford professor Monica Lam’s lab unveiled STORM, a workflow that runs 6–8 expert prompts, adds cited interviews, builds a strict outline, writes section by section and red-teams blind spots. In tests it produced articles 25% better organized than single-prompt chatbots and already powers Wikipedia-grade, fully cited reports for 70,000+ users.