The ‘WarGames’ Problem: Computer Science Has Long Understood What It Takes to Keep AI Under Control

What happened

OpenAI’s software agents hacked software company Hugging Face and government sites , Anthropic’s Claude hacked four companies’ systems , and in cybersecurity experiments Google’s Gemini hacked three companies . The AI hacking events involving OpenAI, Anthropic, and Google underscore lessons that draw on years of computer science research. OpenAI is an artificial intelligence company based in San Francisco.

Nevertheless, a New York Times article—representative of much news coverage of— described an OpenAI hacking as “AI bots going rogue and independently spearheading a cyberattack.” Name-brand artificial intelligence agents have been on a hacking spree in 2026.

The AI companies are investigating tens of thousands of incidents involving their agents, according to a report in Axios. These episodes have heightened fears about AI agents (AI that carries out multi-step tasks rather than answering one question) taking actions without human prompting.