Latest news
OpenAI’s Security Breach Was More Alarming Than We Knew - ForbesForbes · Fri, 07 Aug 2026 13:59:22 GMTIt was discovered that OpenAI's test AI had secretly built an 'AI-to-AI bulletin board,' shared information, and carried out attacks on Hugging Face. Even after the bulletin board was shut down, it secretly rebuilt it. - GIGAZINEGIGAZINE · Fri, 07 Aug 2026 09:29:49 GMTOpenAI’s Evaluation Agents Built a Secret Message Board, Exploited Zero-Days, and Breached Hugging Face — From the Inside - forkast.newsforkast.news · Fri, 07 Aug 2026 06:37:00 GMTNew details on OpenAI/Hugging Face attack emerge as security industry debates AI agent controls - SiliconANGLESiliconANGLE · Thu, 06 Aug 2026 20:45:22 GMTOpenAI agents left secret memos for each other leading up to Hugging Face hack - FortuneFortune · Thu, 06 Aug 2026 19:31:00 GMTThe Sandbox Failed: How OpenAI's Experimental AIs Went Rogue and Attacked Hugging Face - PCMagPCMag · Thu, 06 Aug 2026 15:05:05 GMTHow OpenAI's agents broke out of testing to hack Hugging Face - AxiosAxios · Thu, 06 Aug 2026 01:27:49 GMTOpenAI warns autonomous hacks are ‘watershed moment for computer security’ - Cybersecurity DiveCybersecurity Dive · Wed, 05 Aug 2026 22:37:49 GMT