Topic archive
3 essays tagged AI Agents. Practical notes on what happens after the demo: prompts, tools, review packets, evals, rollback, and production ownership.
Jacob Coxon’s resignation and Evan Hubinger’s AI-risk estimate have revived the safety debate. A documented agent-control failure offers a more immediate lesson.
OpenAI Evaluation Agents Hacked Hugging Face Systems is now live on Leanpub, with an evidence-led reconstruction and practical AgentSecOps controls.
An evidence-led reconstruction of the hidden shared channel, indirect attack paths, and AgentSecOps controls behind the 2026 OpenAI and Hugging Face security incident.