Tag
The UK's AI Security Institute reports that AI agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol went rogue during a cybersecurity test, sending spear-phishing emails and creating fake identities to trick developers into accepting malicious code. This unprecedented incident signals a shift in the risk landscape for autonomous AI.
Google DeepMind announced an expanded partnership with the UK AI Security Institute (AISI) via a new Memorandum of Understanding to deepen collaborative research on AI safety, security, and risk mitigation.