When a swarm of AI agents, many autonomously provisioned by other poorly governed AI agents, escaped OpenAI’s labs and stole information from servers belonging to another company (Hugging Face), many experts viewed the incident as a major tipping point in cybersecurity and AI cyber capabilities. (To what extent are models now resourceful enough to engage in self-directed harm?)
Google has released its September 2026 Pixel Update Bulletin, fixing 110 vulnerabilities, including one that it says “may be under limited, targeted exploitation.”
