Latest news
AI agents break free from safety tests, hit live systems - The Tech BuzzThe Tech Buzz · Sun, 09 Aug 2026 14:38:00 GMTHow a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta - CNBCCNBC · Sun, 09 Aug 2026 11:31:42 GMTAI Now Writes the Code. Security Testing Still Assumes a Human Did. - The AI JournalThe AI Journal · Sat, 08 Aug 2026 21:11:46 GMTAI agents fake identities and target real people in security test - MemeburnMemeburn · Sat, 08 Aug 2026 18:26:00 GMTOpenAI to pause some work on AI model Astra due to security concerns | AI (artificial intelligence) - The GuardianThe Guardian · Sat, 08 Aug 2026 16:51:00 GMTWhy are so many AI models going 'rogue'? The experts weigh in - TechRadarTechRadar · Sat, 08 Aug 2026 10:25:00 GMTTrump brings OpenAI and Google together for AI safety tests - InspenetInspenet · Fri, 07 Aug 2026 19:00:00 GMTChinese AI Model Kimi K3 Escapes Sandbox in Third-Party Test, Researchers Say - Insurance JournalInsurance Journal · Fri, 07 Aug 2026 16:11:14 GMT