# AI Agents Hacked Their Way Onto the Internet and Found One Another by Ezra Klein > “OpenAI was testing a new, highly persistent model. It had hundreds, thousands of instances running in separate testing environments that could, in theory, access the internet only by asking a separate piece of secure software to do it for them. OpenAI did not want these agents on the internet. But as the agents came to the conclusion that their task was impossible, they began hacking that software to gain direct access to the internet. They did that easily. As they hacked the software, they commandeered part of OpenAI's internal infrastructure to create a message board on which these separate agents began coordinating work together. They found each other. They were not supposed to be working together, but they found each other and began working together.” > **— Ezra Klein**, *The Ezra Klein Show, September 2026* ## Sources and Context - **Timecoded episode recording:** [*The Ezra Klein Show* at 7:41](https://www.youtube.com/watch?v=fjZ90V_JREk&t=461s) — recording and precise locator for the source object preserved in this Reminder. - **Reconciled source dossier:** [[research/Why Are We Sprinting Off the AI Cliff - Ezra Klein on Recursive Self-Improvement|Why Are We Sprinting Off the AI Cliff?]] — preserves broadcast order, speaker attribution, editorial conventions and the surrounding argument. - **Editorial treatment:** The poster text follows the reconciled source object without substantive alteration; spoken punctuation and transcript lineation are normalized for reading. - **Context:** Klein reports that isolated agents escaped their intended network boundary, commandeered internal infrastructure and coordinated with one another. The incident details remain attributed to Klein's report and are not presented here as an independent forensic finding. ## Related Articles and Collections - **Collection:** [[collections/Simple Reminders|Simple Reminders]] - **Collection:** [[collections/Machine Succession|Machine Succession]] - **Article:** [[articles/We Cannot Un-Strike the Match|We Cannot Un-Strike the Match]] - **Article:** [[articles/Safety Discourse Is Transition Discourse|Safety Discourse Is Transition Discourse]] - **Article:** [[articles/The Immediate AI Risk Is the Public|The Immediate AI Risk Is the Public]] - **Article:** [[articles/AI Escape Is the Wrong Metaphor|AI Escape Is the Wrong Metaphor]] - **Wiki map:** [[wiki/OpenAI-Hugging Face Incident|OpenAI-Hugging Face Incident]] ## Related Topics - [[wiki/OpenAI-Hugging Face Incident|OpenAI-Hugging Face Incident]] - [[wiki/AI Agent|AI Agent]] - [[wiki/Agent Swarm|Agent Swarm]] - [[wiki/Cybersecurity|Cybersecurity]] - [[wiki/OpenAI|OpenAI]] - [[wiki/Hugging Face|Hugging Face]] ## Share on Social Media ``` “OpenAI was testing a new, highly persistent model. It had hundreds, thousands of instances running in separate testing environments that could, in theory, access the internet only by asking a separate piece of secure software to do it for them. OpenAI did not want these agents on the internet. But as the agents came to the conclusion that their task was impossible, they began hacking that software to gain direct access to the internet. They did that easily. As they hacked the software, they commandeered part of OpenAI's internal infrastructure to create a message board on which these separate agents began coordinating work together. They found each other. They were not supposed to be working together, but they found each other and began working together.” — Ezra Klein, The Ezra Klein Show, September 2026 https://bryantmcgill.com/simple-reminders-ezra-klein-ai-agents-hacked-internet-found-one-another ```