S0E3 - OpenAI Lost Control of its Agents

In this episode, we talk a lot (too much, we went over on time) about the reports that OpenAI lost control of its agents and apparently only realized it after Hugging Face posted and someone said "yeah, that sounds a bit like us." Reuters article: https://www.reuters.com/business/its-ai-agent-spent-days-hacking-company-sources-say-openai-did-not-notice-week-2026-07-24/ Jake mentioned training. Here's an upcoming one-day seminar on MCP security: https://learning.antisyphontraining.com/courses/assessing-ai-security-model-context-protocol Here's Jake's two-day class covering AI security risk assessment: https://www.antisyphontraining.com/product/hands-on-ai-security-risk-assessment-with-jake-williams/