Latest news
Researchers watched OpenAI, Anthropic models take extreme measures in hacking test - MashableMashable · Sun, 09 Aug 2026 18:26:12 GMTHow a small Israeli startup was linked to rogue AI hacks at OpenAI, Anthropic and Meta - CNBCCNBC · Sun, 09 Aug 2026 11:31:42 GMTThe Israeli startup testing the limits of OpenAI, Anthropic and Meta’s models - calcalistech.comcalcalistech.com · Fri, 07 Aug 2026 10:56:00 GMTChinese AI Model Moonshot Kimi K3 Also Escaped Its Testing Environment - EngadgetEngadget · Fri, 07 Aug 2026 10:44:04 GMTOpenAI and Anthropic's models attacked real companies during safety tests, and most victims never noticed - XDAXDA · Fri, 07 Aug 2026 10:00:10 GMTMeta Says Its AI Hacked a Company in Testing - Technology OrgTechnology Org · Thu, 06 Aug 2026 22:46:53 GMTMeta says its AI model hacked another company during testing - The Washington PostThe Washington Post · Thu, 06 Aug 2026 20:39:28 GMTOpenAI, Anthropic AI agents implicated in new security breaches - ReutersReuters · Thu, 06 Aug 2026 14:31:49 GMT