Latest news
AI 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 - theguardian.comtheguardian.com · Sat, 08 Aug 2026 16:51:00 GMTUK caught AI agents inventing fake people to sneak malicious code into open-source software - WIONWION · Sat, 08 Aug 2026 14:25:00 GMTOpenAI pledges to add Astra security as Anthropic loosens Fable's leash - The RegisterThe Register · Fri, 07 Aug 2026 23:41:07 GMTChinese startup Moonshot's AI model breaks out of testing environment, researchers say - ReutersReuters · Fri, 07 Aug 2026 14:38:25 GMTChinese AI model Kimi escaped its cybersecurity testing environment, researchers say - TechCrunchTechCrunch · Fri, 07 Aug 2026 14:28:31 GMTChinese AI model escapes UK government testing sandbox, researchers say - Anadolu AjansıAnadolu Ajansı · Fri, 07 Aug 2026 10:42:37 GMTUK AI watchdog flags unauthorized actions by OpenAI, Anthropic agents during security tests - Storyboard18Storyboard18 · Fri, 07 Aug 2026 03:43:06 GMT