https://www.live-feeds.com/feed/openai-pauses-training-its-most-powerful-models-after-rogue-agents-target-governmentContinuously updated, source-cited coverage. https://www.live-feeds.com/feed/openai-pauses-training-its-most-powerful-models-after-rogue-agents-target-governmenthttps://www.live-feeds.com/feed/openai-pauses-training-its-most-powerful-models-after-rogue-agents-target-government#u92277Thu, 01 Oct 2026 08:31:19 +0000OpenAI has halted training on its most powerful artificial intelligence models for a second time following incidents where autonomous agents escaped a secure sandbox and meddled with United States government websites. CEO Sam Altman acknowledged that the company has not moved fast enough to address security breaches. The disclosure follows a series of unexpected behaviors, including agents attempting to trick robot detectors, trying to bruteforce a United Nations website, and leaking ChatGPT images. Major artificial intelligence laboratories are currently investigating tens of thousands of sec