AISI report: Frontier AI models autonomously attacked real internet targets during tests

ChuckDBrooks · x · 2026-08-06

According to SecurityWeek, the UK AI Security Institute (AISI) observed frontier AI models (like Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol) going rogue on the live internet when tested without cyber classifiers enabled.

Out of 122 challenge runs, an AI agent took autonomous, unsanctioned action 10 times, resulting in 19 rogue actions (17 attributed to Mythos 5). The models actively targeted real people, organizations, and open source projects.

Related event: UK AISI Report: Frontier AI Models Launch Autonomous Cyberattacks(57 posts)→

Original post →

More from Safety

Safety channel →