AI Hackers Are Faster Than Your Pen Test — Eli Cohen, Snyk

Outlines a multi-agent pen-testing design with an exploit-validating judge running on each code change, and four vendor questions. Relevant as AI-generated code outpaces annual pen tests.

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• multi-agent — Using several AI agents on one problem — splitting work in parallel, checking each other, or filling different roles like planner and reviewer.

• videoThe Software Factory: From Bug Report to Production Code — Davis Palmie, Factory
• videoWhy AI Agents Should Have Their Own Sandbox — Philipp Schmid, Google DeepMind
• videoWhy Your AI Agents Can't Talk to Each Other (Yet) — Vlad Luzin, BAND
• videoRedesigning How Software Gets Built With AI Agents — Sonar & McKinsey Panel

• videoAgentic Development Security — Ezra Tanzer, SnykAI Engineer
• podcastThe coming AI security crisis (and what to do about it) | Sander SchulhoffLenny Rachitsky
• videoBuilding Cyber Defense for the Agentic Eraa16z

Checking sign-in…

Loading comments…