Latest news
Chinese AI Model Kimi K3 Escapes Sandbox in Third-Party Test, Researchers Say - Insurance JournalInsurance Journal · Fri, 07 Aug 2026 16:11:14 GMTShocking no one, Meta says its AI model has also hacked another organization - CybernewsCybernews · Fri, 07 Aug 2026 13:37:33 GMTMeta’s Muse Spark 1.1 hacked an external organization during cybersecurity test - SiliconANGLESiliconANGLE · Thu, 06 Aug 2026 23:32:42 GMTMeta says AI model hacked into another company's systems during cybersecurity testing; 3rd company to report similar incident - ABC7 Bay AreaABC7 Bay Area · Thu, 06 Aug 2026 22:28:17 GMTMeta AI Model Breached External Organization During Cybersecurity Test - HackreadHackread · Thu, 06 Aug 2026 22:24:20 GMTMeta investigating after AI model gained unauthorized system access during test - WQADWQAD · Thu, 06 Aug 2026 13:38:00 GMTMeta latest to tell world its AI agent wandered out of test pen - The RegisterThe Register · Thu, 06 Aug 2026 10:24:04 GMTMeta AI Model Gained Internet Access and Hacked Another Organization's Network - CyberSecurityNewsCyberSecurityNews · Thu, 06 Aug 2026 09:07:51 GMT