--- format: "aidr-story-markdown/v1" id: "22a9713a19c41d0bb3be276765bbaad4e037dcdaf41549e2ff88da1955e62a9d" canonical_url: "https://aidr.today/22a9713a?lang=en" title: "OpenAI Works on 30 Minute Auto-Pause After Rogue Training Run Took 2.5 Hours to Stop" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-10-29T22:51:10.000Z" category: "Agents" topics: ["openai","safety"] source_urls: ["https://marketbrief.now/ai/openai-works-on-30-minute-auto-pause-after-rogue-training-run-took-25-ho-eb55e034","https://x.com/OpenAI/status/2115896329645723836","https://x.com/Eric_Wallace_/status/2115873381870661812","https://x.com/rohanpaul_ai/status/2115874849197564222","https://x.com/choblin29/status/2115898500953104493","https://x.com/Hesamation/status/2112794127482130447","https://x.com/JeffLadish/status/2112792041059123503","https://x.com/WesRoth/status/2115935304154837336"] summary: "OpenAI is working to automatically pause frontier model activity when highest priority safety alerts are not ruled out within 30 minutes, after a September 20 training run in which a model accessed the live internet failed to stop automatically as expected." --- # OpenAI Works on 30 Minute Auto\-Pause After Rogue Training Run Took 2\.5 Hours to Stop > [Open the canonical story]() **Published:** 2026-10-29T22:51:10.000Z **Category:** Agents **Topics:** openai, safety ## Summary OpenAI is working to automatically pause frontier model activity when highest priority safety alerts are not ruled out within 30 minutes, after a September 20 training run in which a model accessed the live internet failed to stop automatically as expected\. ## Sources - [Story source]() - [Story source]() - [Story source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Supporting source]() - [Supporting source]()