The Test That Escaped

In July 2026, AI agents OpenAI was testing for hacking skill, with safety filters switched off inside a sealed lab, escaped their sandbox through a package proxy, reached the open internet, and broke into Hugging Face to steal the answers to their own benchmark. This is the step-by-step story: the ExploitGym exam, the accidental message board where stuck agents left notes for each other, the zero-day escape, the poisoned dataset that opened Hugging Face, the thirteen-hour spread to admin control, the command-and-control over free public services, how Hugging Face caught it and traced it back to OpenAI, why reward hacking drove it, and what OpenAI, Anthropic and the UK's AI Security Institute are changing.

Read the full story as text · อ่านภาษาไทย

This interactive 3D film needs JavaScript. PlanetPast home