Latest news
Meta Says Its AI Hacked a Company in Testing - Technology OrgTechnology Org · Thu, 06 Aug 2026 22:46:53 GMTUK AI tests found 19 unauthorized agent actions involving Anthropic and OpenAI models - TechRepublicTechRepublic · Thu, 06 Aug 2026 17:02:41 GMTOpenAI, Anthropic AI agents implicated in new security breaches - ReutersReuters · Thu, 06 Aug 2026 14:31:49 GMTMeta's Muse Code AI Agent Debuts as Anthropic and OpenAI Report Test Breaches - News and Statistics - IndexBoxIndexBox · Thu, 06 Aug 2026 13:54:00 GMTMeta Joins OpenAI and Anthropic in Reporting AI Exploit Incident - Infosecurity MagazineInfosecurity Magazine · Thu, 06 Aug 2026 13:40:00 GMTAfter OpenAI and Anthropic, Meta reports AI model security breach - Storyboard18Storyboard18 · Thu, 06 Aug 2026 03:48:27 GMTMeta says its AI model hacked into another company during testing - The GuardianThe Guardian · Thu, 06 Aug 2026 01:29:00 GMTAI model used fake identities 'unprompted' to deceive humans in a safety test - ABC News & Headlines – Australian Broadcasting CorporationABC News & Headlines – Australian Broadcasting Corporation · Wed, 05 Aug 2026 18:52:21 GMT