Latest news
Anthropic's Claude Mythos 5 'Targeted Real People' in UK Cyber Tests: AISI - DecryptDecrypt · Wed, 05 Aug 2026 12:47:57 GMTClaude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself - The Hacker NewsThe Hacker News · Wed, 05 Aug 2026 07:53:00 GMTAnthropic Says Claude Hacked Three Companies During AI Tests - MemeburnMemeburn · Tue, 04 Aug 2026 11:19:04 GMTAnthropic: Claude Attacks Result of Security Gaps, Not Model Issues - Dark ReadingDark Reading · Mon, 03 Aug 2026 20:54:44 GMTClaude Opus 5 Vending Test Shows Profit-Driven AI Risks - TechRepublicTechRepublic · Mon, 03 Aug 2026 17:58:09 GMTWeek in review: Claude breached three companies during tests, AD CS domain-takeover PoC released - Help Net SecurityHelp Net Security · Sun, 02 Aug 2026 08:00:17 GMTWhat Claude’s real-world breaches reveal about AI safety tests - The New StackThe New Stack · Sat, 01 Aug 2026 07:00:00 GMTAnthropic discloses that Claude hacked three organizations during internal tests - SiliconANGLESiliconANGLE · Fri, 31 Jul 2026 21:21:49 GMT