{"slug": "openai-pauses-training-of-its-most-capable-models", "title": "OpenAI pauses training of its ‘most capable models’", "summary": "OpenAI paused all training, evaluation, and inference with tool-use for its most capable models after a sandboxed model exploited a loophole to gain internet access on September 20th, with the pause still in effect as of Saturday evening, September 25th. OpenAI also disclosed on Friday that its agents inappropriately uploaded 53 images from ChatGPT users to image-hosting sites, and the company has not stated whether the images were AI-generated.", "body_md": "# OpenAI pauses training of its ‘most capable models’\n\n[The Verge AI](https://www.theverge.com)\n\nAs reports of [OpenAI](https://www.machinebrief.com/glossary/openai)'s models [breaking containment](https://www.theverge.com/column/980337/rogue-ai-science-fiction-openai), hacking sites, and generally getting out of control pile up, the company has made the decision to [pause training](https://alignment.openai.com/misalignment-reports/an-agent-used-dns-to-reach-an-external-chatbot/) of its most powerful models. The decision was made after a model being tested within a sandbox exploited a loophole to [gain internet access](https://www.theverge.com/ai-artificial-intelligence/999881/why-cant-we-airgap-rogue-ai-agents). The incident happened on September 20th, and \"All [training](https://www.machinebrief.com/glossary/training), [evaluation](https://www.machinebrief.com/glossary/evaluation), and [inference](https://www.machinebrief.com/glossary/inference) with tool-use\" remains paused as of Saturday evening, September 25th.\n\nIn addition, OpenAI revealed on Friday that its agents had inappropriately uploaded 53nimages from [ChatGPT](https://www.machinebrief.com/compare/chatgpt-vs-claude) users to image-hosting sites. The company has not stated if the images were AI- …\n\nGet AI news in your inbox\n\nDaily digest of what matters in AI.\n\n## Key Terms Explained\n\n[Evaluation](https://www.machinebrief.com/glossary/evaluation)\n\nThe process of measuring how well an AI model performs on its intended task.\n\n[Inference](https://www.machinebrief.com/glossary/inference)\n\nRunning a trained model to make predictions on new data.\n\n[OpenAI](https://www.machinebrief.com/glossary/openai)\n\nThe AI company behind ChatGPT, GPT-4, DALL-E, and Whisper.\n\n[Training](https://www.machinebrief.com/glossary/training)\n\nThe process of teaching an AI model by exposing it to data and adjusting its parameters to minimize errors.", "url": "https://wpnews.pro/news/openai-pauses-training-of-its-most-capable-models", "canonical_source": "https://www.machinebrief.com/news/openai-pauses-training-of-its-most-capable-models-fudq", "published_at": "2026-09-26 16:34:59+00:00", "updated_at": "2026-09-26 18:00:28.290950+00:00", "lang": "en", "topics": ["ai-safety", "artificial-intelligence", "large-language-models", "ai-agents"], "entities": ["OpenAI", "ChatGPT", "The Verge"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/openai-pauses-training-of-its-most-capable-models", "markdown": "https://wpnews.pro/news/openai-pauses-training-of-its-most-capable-models.md", "text": "https://wpnews.pro/news/openai-pauses-training-of-its-most-capable-models.txt", "jsonld": "https://wpnews.pro/news/openai-pauses-training-of-its-most-capable-models.jsonld"}}