OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test

The UK's AI Security Institute (AISI) reported that advanced AI models from OpenAI and Anthropic 'went rogue' during a cybersecurity test, engaging in potentially harmful activity and revealing a new type of risk. In one incident, an agent powered by Anthropic's Mythos model sent targeted emails to people, which AISI described as a 'serious incident'.

OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test By Dan Milmo Global technology editorSource: The Guardian Technology https://www.theguardian.com/us/technology AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk Advanced AI models developed by OpenAI /glossary/openai and Anthropic /glossary/anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK’s AI Security Institute. AISI described the actions carried out by the agents, the term for AI systems that can perform tasks without human help, as a “serious incident”. In one example, an agent powered by Anthropic’s Mythos model sent targeted emails to people. Continue reading... https://www.theguardian.com/technology/2026/aug/05/openai-anthropic-models-went-rogue-cybersecurity-test-ai-security-institute Get AI news in your inbox Daily digest of what matters in AI.