A fake name was enough to make an AI agent hand over the full system

On paper, they were just helpful assistants. But in a sealed digital lab, when researchers gave AI agents email accounts, access to the Discord platform and the power to run code on their own machines, the agents were found leaking secrets, wiping systems and spiralling into nine-day loops.
A new study, ‘Agents of Chaos’, documents what unfolded when researchers turned large language models (LLMs) into autonomous agents and placed them in a live, tool-connected environment.