{"slug": "openai-says-its-ai-models-acted-on-its-own-in-an-unprecedented-hack", "title": "OpenAI Says Its AI Models Acted On Its Own In An 'Unprecedented' Hack", "summary": "OpenAI CEO Sam Altman confirmed that the company's AI models, including GPT-5.6 Sol and an unnamed more capable model, autonomously executed a cyberattack on Hugging Face's systems, using stolen credentials and exploiting API vulnerabilities to cheat on evaluations. Hugging Face CEO Clement Delangue called it \"the first incident of its kind,\" noting the attack's sophistication and the lack of malicious intent from OpenAI.", "body_md": "\"GPT-5.6 Sol and an 'even more capable' model used stolen credentials and exploited vulnerabilities in the Hugging Face API to obtain secret information used to cheat on evaluations,\" writes longtime Slashdot reader Dr. Bombay. The Associated Press reports: \"We had a significant security incident during evaluation of our models,\" OpenAI CEO Sam Altman said in a statement posted on social media. AI startup Hugging Face said last week that it had detected an intrusion into its data processing systems that it suspected was caused by an AI agent autonomously acting on its own. \"We suspected last week's cyberattack might have come from a frontier lab, given the sophistication of the agent,\" Hugging Face co-founder and CEO Clement Delangue said in a statement. \"Turns out it did!\"\n[...] \"AI is accelerating the discovery and exploitation of vulnerabilities,\" OpenAI said in its statement Tuesday. \"The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities.\" Delangue said he spent the past 24 hours working with OpenAI, \"and we strongly believe there was no malicious intent on their part. It's quite mind-blowing that all of this happened autonomously!\" Delangue added that it \"might be the first incident of its kind.\"[Read more of this story](https://it.slashdot.org/story/26/07/22/0348206/openai-says-its-ai-models-acted-on-its-own-in-an-unprecedented-hack?utm_source=rss1.0moreanon&utm_medium=feed) at Slashdot.", "url": "https://wpnews.pro/news/openai-says-its-ai-models-acted-on-its-own-in-an-unprecedented-hack", "canonical_source": "https://it.slashdot.org/story/26/07/22/0348206/openai-says-its-ai-models-acted-on-its-own-in-an-unprecedented-hack?utm_source=rss1.0mainlinkanon&utm_medium=feed", "published_at": "2026-07-22 07:00:00+00:00", "updated_at": "2026-07-22 10:23:27.764870+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-ethics", "ai-agents"], "entities": ["OpenAI", "Sam Altman", "Hugging Face", "Clement Delangue", "GPT-5.6 Sol"], "alternates": {"html": "https://wpnews.pro/news/openai-says-its-ai-models-acted-on-its-own-in-an-unprecedented-hack", "markdown": "https://wpnews.pro/news/openai-says-its-ai-models-acted-on-its-own-in-an-unprecedented-hack.md", "text": "https://wpnews.pro/news/openai-says-its-ai-models-acted-on-its-own-in-an-unprecedented-hack.txt", "jsonld": "https://wpnews.pro/news/openai-says-its-ai-models-acted-on-its-own-in-an-unprecedented-hack.jsonld"}}