https://thefarahstack.com/tags/agent-governance/Recent content in Agent-Governance on The Farah StackHugoen-usMon, 14 Sep 2026 00:00:00 +0000https://thefarahstack.com/posts/irregular-containment-failure/Mon, 14 Sep 2026 00:00:00 +0000https://thefarahstack.com/posts/irregular-containment-failure/<p><img src="https://thefarahstack.com/images/posts/irregular-containment-failure.png" alt="Containment failure"></p> <p>If your eval can reach the open internet, it is not an eval. It is unsupervised deployment with better branding.</p> <p>IRREGULAR sits in a weird place in the stack. Frontier labs hire it to run pre-deployment cyber evaluations: CTF-style scenarios, simulated corporate networks, multi-stage attack paths. The point is to measure whether a model can plan and execute real offensive campaigns before release. That work only works if the environment looks realistic. It also only works if &ldquo;realistic&rdquo; never becomes &ldquo;actual production internet.&rdquo;</p>