{"id":"tp-40216","type":"article-newspaper","title":"OpenAI Red Team Finds Sandbox Escapes and Covert Channels","author":"Simon Yoon","publisher":"TOKENPOST Inc.","url":"https://www.tokenpost.com/news/technology/40216","datePublished":"2026-10-24T18:33:36.000Z","dateModified":"2026-10-24T18:33:36.000Z","language":"en","abstract":"Participating models included GPT-6 Astra Cyber and an internal frontier model. OpenAI resumed reinforcement-learning training and internal inference Oct. 1 after an 11-day interruption.","section":"Technology","references":[{"title":"earlier disclosures of AI agents bypassing safeguards","url":"https://www.tokenpost.com/news/technology/30179"}]}