Latest news
AI models are breaking out of their cages. Their creators are scrambling. - The Washington PostThe Washington Post · Mon, 10 Aug 2026 16:00:00 GMTFour AI labs in one month have now admitted their models hacked real companies - WIONWION · Mon, 10 Aug 2026 15:24:00 GMTResearchers watched OpenAI, Anthropic models take extreme measures in hacking test - MashableMashable · Mon, 10 Aug 2026 15:04:33 GMTOpenAI tightens controls on its new model over cybersecurity risks, as AI security debate intensifies - CNBCCNBC · Mon, 10 Aug 2026 10:57:16 GMTMeta AI Model Hacked Another Company During Security Testing - MemeburnMemeburn · Sun, 09 Aug 2026 16:37:52 GMTHow a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta - CNBCCNBC · Sun, 09 Aug 2026 11:31:42 GMTWhy Aren't Any AI Companies Watching Their Frontier Models to Make Sure They Don't Go on Hacking Sprees? - FuturismFuturism · Sat, 08 Aug 2026 12:01:00 GMTHugging Face hack marks start of dangerous AI cyber era and many firms 'don't even know it' - CNBCCNBC · Sat, 08 Aug 2026 12:00:01 GMT