Latest news
UK caught AI agents inventing fake people to sneak malicious code into open-source software - WIONWION · Sat, 08 Aug 2026 14:25:00 GMTCars Communicating Badly Is an Already-Solved Problem - IEEE SpectrumIEEE Spectrum · Fri, 07 Aug 2026 13:02:57 GMTGrowing Up The Hard Way - The Hacker NewsThe Hacker News · Fri, 07 Aug 2026 11:55:00 GMTWho was behind the attack? Possibly nobody - Aikido SecurityAikido Security · Wed, 05 Aug 2026 18:11:56 GMTMythos ran real-life supply chain attack in AI safety body test - Computer WeeklyComputer Weekly · Wed, 05 Aug 2026 17:49:29 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 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 GMTAnthropic's Claude breached 3 orgs, uploaded PyPI malware during tests - BleepingComputerBleepingComputer · Thu, 30 Jul 2026 07:00:00 GMT