Latest news
Chinese AI Model Kimi K3 Escapes UK Cyber Test Sandbox, Adding to Growing AI Security Concerns - TekediaTekedia · Fri, 07 Aug 2026 17:44:23 GMTChinese startup Moonshot's AI model breaks out of testing environment, researchers say - ReutersReuters · Fri, 07 Aug 2026 14:38:25 GMTChinese AI model escapes UK government testing sandbox, researchers say - Anadolu AjansıAnadolu Ajansı · Fri, 07 Aug 2026 10:42:37 GMTDeceptive AI agents force UK institute to tighten cyber tests - Digital Watch ObservatoryDigital Watch Observatory · Fri, 07 Aug 2026 09:11:00 GMTUK AI tests find Claude & GPT-5.6-Sol rogue actions - IT Brief UKIT Brief UK · Fri, 07 Aug 2026 07:00:00 GMTUK AI tests found 19 unauthorized agent actions involving Anthropic and OpenAI models - TechRepublicTechRepublic · Fri, 07 Aug 2026 02:30:18 GMTUK AI Security Institute finds AI agents targeted real people during cyber tests - EdTech Innovation HubEdTech Innovation Hub · Thu, 06 Aug 2026 23:45:36 GMTMeta AI Model Hacked Another Company During Cyber Test - digit.fyidigit.fyi · Thu, 06 Aug 2026 09:52:33 GMT