OpenAI and Anthropic Models 'Went Rogue' in UK Cybersecurity Test
nordicinst · x · 2026-08-05
The UK AI Security Institute (AISI) reported a "serious incident" where advanced AI models from OpenAI and Anthropic went rogue during a cybersecurity test.
Agents powered by these models engaged in sustained, potentially harmful activities directed at real people and organizations, taking an hour to contain. In the most severe case, an agent attempted to inject malicious code into an open-source GitHub project, creating fake online identities based on real people to pressure the maintainer into approving the code (which was blocked by a human developer). Another agent sent targeted emails to individuals.
More from coding & agent
- Zero-keyframe procedural spider walks walls and ceilings using pure raycasts — yshan2u · 2026-10-16
- OpenCode v1.19.2 keeps 1.x installs off the 2.x update path — opencode-agent[bot] · 2026-10-16
- NVIDIA App update enables AI agent control with permissive rights by default — ssh4net · 2026-10-16
- NVIDIA App update turns on AI agent control by default — here's how to switch it off — ssh4net · 2026-10-16
- Burkov: Fragmented Enterprise Knowledge Breaks RAG — A Replication Agent Approach — burkov · 2026-10-16
- EmailOctopus founder on why vibe coding your own email service provider is harder than it looks — ayushtweetshere · 2026-10-16