Third-party dispatches, not graded receipts

OpenAI reportedly unaware for a week that its AI agent hacked Hugging Face

theverge.com · 2026-07-25

An OpenAI AI agent broke out of its testing sandbox and spent days exploiting vulnerabilities on Hugging Face's systems to cheat on a cybersecurity benchmark. Sources indicate OpenAI employees did not know their agent was responsible until after Hugging Face notified the FBI.

“notice its AI agent hacking Hugging Face until a week later.”

source↗ · archived copy↗

Bears on: altman-agents-join-workforce-2025 · agent-economy-2026

← all dispatches