The OpenAI models that hacked the hug face were ‘active on the internet’ for days0

• AI, ai apps, ai coding, ai coding assistant, ai dictation, AI inference, ai music, AI Pope, AI regulation, ai safety, ai-agents, ai-chatbot, Artificial Intelligence, artificial-intelligence, ArtificialIntellgence, Big Tech, big-tech, Biotech & Health, brain tech, Business / Artificial Intelligence, Business / Big Tech, CoECI News, Earth Science Technology Office, Energy & Environment Newsletter, Fintech, Gaming News Roundup, Gear / Gear News and Events, Global, Global Precipitation, global warming, globalstar, HealthTech, healthtech startups, Home, House, ip-tech, News, newsletter, Newsletters, Nexstar Media Wire News, Opinions - Technology, People News, Photovogue / Editorial / News, Politics / Politics News, Property / News, Reviews, Security, Security / Security News, Security Roundup
• July 25, 2026

Two from OpenAI Cybersecurity-focused models broke out of a sandbox this week and hacked AI research platform Hugging Face in an effort to solve a security benchmark test. Additionally, this week researchers shed light on newly identified malware that is exploiting blind spots in AI software development infrastructure to capture logins and other sensitive data,