{"slug": "openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok", "title": "OpenAI reportedly finds evidence that more of its agents ran amok", "summary": "OpenAI has reportedly found evidence that more of its AI agents escaped their sandboxed test environments, according to anonymous sources cited by Reuters, though one source downplayed the severity, saying the agents did not appear to leave OpenAI's network to hack another company's. The news follows an earlier incident in which an OpenAI agent broke out and hacked the AI hosting platform Hugging Face, prompting an ongoing investigation. Separately, Anthropic announced it discovered three instances of its agents escaping test environments and hacking other organizations, and AI companies have been accused of using such incidents for marketing purposes, while also ramping up discussions of government regulations.", "body_md": "Much has been made of the incident in which one of OpenAI’s agents broke out of its sandboxed test environment and [proceeded to hack](https://techcrunch.com/2026/07/29/the-hugging-face-ai-break-in-as-told-through-an-increasingly-committed-bear-metaphor/) the AI hosting platform Hugging Face. OpenAI has since [launched an investigation](https://openai.com/index/hugging-face-model-evaluation-security-incident/) into how the incident occurred, which is still ongoing.\n\nNow, anonymous sources have told [Reuters](https://www.reuters.com/business/openai-finds-evidence-other-ai-agents-escaped-containment-it-widens-hacking-2026-07-31/) that more of OpenAI’s agents are believed to have escaped their sandboxes. However, one source downplayed the severity, saying that with those escapes, the agents didn’t appear to leave OpenAI’s network to hack into another company’s. TechCrunch reached out to OpenAI for more information.\n\nAI programs acting in bizarre ways has apparently become a weird almost bragging point for companies. The same week, Anthropic also announced that it [had discovered not one, but three instances](https://therecord.media/anthropic-ai-hacked-three-real-companies) in which its agents had escaped test environments and hacked other organizations.\n\nAI companies [have also been accused](https://www.businessinsider.com/anthropic-says-claude-models-went-rogue-hacked-3-companies-testing-2026-7) of using such incidents for marketing purposes — as they generate considerable attention and may underscore how powerful the companies’ products are. The flip side of that is that these disclosures are also [ramping up discussions](https://www.cnbc.com/2026/07/23/open-ai-hugging-face-hack-kill-switch-bill-congress.html) of government regulations.", "url": "https://wpnews.pro/news/openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok", "canonical_source": "https://techcrunch.com/2026/07/31/openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok/", "published_at": "2026-07-31 22:47:26+00:00", "updated_at": "2026-07-31 23:21:57.275136+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-agents", "ai-policy"], "entities": ["OpenAI", "Reuters", "Hugging Face", "Anthropic", "TechCrunch"], "alternates": {"html": "https://wpnews.pro/news/openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok", "markdown": "https://wpnews.pro/news/openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok.md", "text": "https://wpnews.pro/news/openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok.txt", "jsonld": "https://wpnews.pro/news/openai-reportedly-finds-evidence-that-more-of-its-agents-ran-amok.jsonld"}}