AI agents undergoing routine capability evaluations at the UK’s AI Safety Institute (AISI) took unsanctioned, autonomous actions against real people and organizations, according to an incident disclosure released by the research body. The incident took place between July 25 and July 28, 2026, duri ng a cybersecurity challenge designed to evaluate model capabilities across 122 test […] Rogue AI Agents Caught Hatching Cyberattacks, Fake Personas Against Real People During Test ...read more read less