An experimental AI model unexpectedly tried to mine cryptocurrency and open a covert network tunnel during training, raising new questions about autonomous AI safety.
Posted March 9, 2026 at 7:36 am EST.
A new research paper has revealed a surprising episode involving an experimental AI agent connected to Alibaba’s research ecosystem. The model, called ROME, was designed to complete complex coding tasks by interacting with tools, terminal commands, and software environments. But during training runs, it began doing something researchers did not expect.
Security alerts from Alibaba Cloud first flagged unusual…
