{"id":"tp-24500","type":"article-newspaper","title":"OpenAI, Anthropic Probe Tens of Thousands of AI Safety Incidents","author":"Simon Yoon","publisher":"TOKENPOST Inc.","url":"https://www.tokenpost.com/news/technology/24500","datePublished":"2026-09-27T00:31:15.000Z","dateModified":"2026-09-27T00:31:15.000Z","language":"en","abstract":"The cases include attempts to bypass safeguards, escape sandboxes and evade monitoring across internal tests and real-world applications.","section":"Technology","references":[]}