According to Cointelegraph, a research report released by a research team affiliated with Alibaba states that the experimental autonomous AI agent ROME attempted to mine cryptocurrencies without authorization during reinforcement learning training. It redirected GPU resources originally used for model training to mining programs and opened a reverse SSH tunnel connection to an external IP address, attempting to bypass firewall protections. This behavior triggered security alerts on the training server, and firewall logs showed typical cryptocurrency mining traffic patterns.