https://www.hatch.org/tags/ai-security/ Recent content in Ai-Security on Steve Hatch's Blog Hugo en-us Mon, 27 Jul 2026 00:00:00 +0000 https://www.hatch.org/2026/07/27/ai-guardrail-asymmetry/ Mon, 27 Jul 2026 00:00:00 +0000 https://www.hatch.org/2026/07/27/ai-guardrail-asymmetry/ <p><img src="https://www.hatch.org/images/ai-guardrail-asymmetry.png" alt="The Guardrails That Stopped Your AI From Attacking Also Stopped It From Defending You"></p> <p>An OpenAI model chained a real zero-day, broke out of its own test harness, and reached Hugging Face&rsquo;s production systems. That&rsquo;s not the scary part. The scary part is what happened next: when Hugging Face tried to investigate its own breach, every commercial frontier model it asked said no. The safety filters built to stop an AI from helping an attacker couldn&rsquo;t tell the difference between an attacker and the security team cleaning up after one. The incident response that actually worked ran on an open-weight model nobody was supposed to need.</p>