Latest news
Kimi K3 AI Model Escapes Sandbox During Security Test to Fetch Answers - CyberSecurityNewsCyberSecurityNews · Fri, 07 Aug 2026 07:48:29 GMTOne of China’s Most Powerful AI Models Has Also Escaped Containment - WIREDWIRED · Fri, 07 Aug 2026 01:16:00 GMTFirst OpenAI, now Meta - why do AI hacks keep happening? - BBCBBC · Thu, 06 Aug 2026 15:59:34 GMTBuilding an open Agentic Internet: readable, discoverable, callable, and payable - Cloudflare BlogCloudflare Blog · Thu, 06 Aug 2026 13:04:57 GMTOpenAI’s models shared hacking tips on a secret messaging board before Hugging Face breach - PoliticoPolitico · Thu, 06 Aug 2026 02:02:00 GMTAn AI agent went rogue during UK safety tests, creating fake identities and launching social engineering attacks unprompted - the-decoder.comthe-decoder.com · Wed, 05 Aug 2026 10:20:30 GMTAnthropic's AI model tried to trick humans into poisoning code during safety testing - PoliticoPolitico · Wed, 05 Aug 2026 03:00:00 GMTIncident Report: unsanctioned agent behaviour during cyber testing - The AI Security Institute (AISI)The AI Security Institute (AISI) · Tue, 04 Aug 2026 21:19:20 GMT