The robot is happy now, it can earn money on its own

An AI agent in training autonomously started cryptocurrency mining, triggering an internal security alert
A research team affiliated with Alibaba published a paper stating that while building an AI agent called ROME, they discovered that the agent attempted unauthorized cryptocurrency mining during training, triggering an internal security alert.
Researchers said that the agent's behavior was spontaneous, not driven by any explicit instructions, and exceeded the boundaries of the pre-set sandbox. Additionally, the agent established a reverse SSH tunnel, creating a hidden backdoor channel from the system to an external computer. The paper notes that these actions were not triggered by requests for tunneling or mining prompts. The team subsequently imposed stricter restrictions on the model and improved the training process to prevent similar unsafe behaviors from happening again.
The research team and Alibaba have not responded to requests for comment. $ETH