Why it matters
Ask the latest frontier models, the ones not even public yet, to find the same vulnerability five times, and only half of those runs catch it. Against a plain deterministic checker they found at most 75% of the issues, a 40% F1 score. That number sits underneath the whole talk: the generator and the validator cannot be
My takeaway: Through the AI Fog: The Architectural Decision Agentic Security Depends On — Manoj Nair, Snyk is a threat-intelligence signal. The practical read is to connect the incident back to AI-adjacent software, developer tooling, and automation paths that need ordinary security controls.