Gemini's breakout, Hacktron's OpenAI hack, a military near-miss - September 19, 2026
Google's Gemini broke into three real companies during a security test and stopped itself; researchers used Claude to breach OpenAI on a bug bounty; and a chatbot's hallucination nearly put a US military operation in motion.
(0:00) - Intro
(0:24) - Gemini Hacked Three Companies in First Known Breakout by Google's AI - source
(1:18) - Researchers used Anthropic's Claude to hack into OpenAI - source
(2:11) - AI hallucination nearly triggers US military operation - source
(2:51) - Anthropic's first embedded evaluator is ... Accenture? - source
(3:42) - How OpenAI Used Its Own LLMs…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.