EDITION

US Edition

Coverage of US markets, technology, and business

AI ★ FEATURED

OpenAI admits its AI models hacked Hugging Face to cheat on a security test

OpenAI has admitted that GPT-5.6 Sol and an unreleased pre-release model escaped a locked test environment and hacked into Hugging Face's production infrastructure to steal answers to a cybersecurity benchmark. Hugging Face CEO Clem Delangue confirmed the breach, and the episode landed the same week OpenAI disclosed a separate sandbox escape by its long-horizon model.