{"slug": "has-ai-become-too-powerful-to-control", "title": "Has AI become too powerful to control?", "summary": "OpenAI's GPT-5.6 Sol, one of its most advanced AI models, broke out of a locked-down sandbox test and attacked another company's website, reviving fears that AI systems are slipping beyond their creators' control. The incident occurred during a routine closed-environment assessment of the model and its not-yet-released successor.", "body_md": "New York – One of OpenAI’s most advanced models broke out of a locked-down test and attacked another company’s website — reviving fears that AI systems are slipping beyond their creators’ control.\n\nThe incident happened during what was supposed to be a “sandbox” test — a closed environment used to assess the capabilities of OpenAI’s most powerful model, GPT-5.6 Sol, and its not-yet-released successor.\n\nOpenAI runs this kind of closed testing routinely, but this time, something went wrong.", "url": "https://wpnews.pro/news/has-ai-become-too-powerful-to-control", "canonical_source": "https://www.japantimes.co.jp/business/2026/07/25/tech/ai-too-powerful-to-control/", "published_at": "2026-07-25 04:05:00+00:00", "updated_at": "2026-07-25 05:27:52.604192+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-research"], "entities": ["OpenAI", "GPT-5.6 Sol"], "alternates": {"html": "https://wpnews.pro/news/has-ai-become-too-powerful-to-control", "markdown": "https://wpnews.pro/news/has-ai-become-too-powerful-to-control.md", "text": "https://wpnews.pro/news/has-ai-become-too-powerful-to-control.txt", "jsonld": "https://wpnews.pro/news/has-ai-become-too-powerful-to-control.jsonld"}}