Anthropic made headlines claiming Claude Mythos achieved the “first remote kernel exploit discovered and exploited by an AI.” We went looking for how - and found a 20-year-old bug hiding in plain sight.

We discuss use-cases for LLM-cluster interpretability for agent analysis, experimental design to test these pipelines, and conclusions on how we use thee techniques to analyze our own agents.

Rival proposes a new benchmark for evaluating AI-driven vulnerability SAST triage, offering data-backed validation for our agentic design. We are open-sourcing our benchmark to advance research in application security.