// ZDNET — INTELLIGENZA ARTIFICIALE
50 AI agents tried to build a thriving Minecraft civilization – it didn’t end well
How do AI agents work together? Why do they make certain choices in certain situations — and how can understanding that better prepare us for a future full of them?
Also: OpenAI’s attack agent did exactly what it was told
Recent agent-led incidents have demonstrated their ability to create both powerful breakthroughs and cybersecurity nightmares. In an effort to better trace these outcomes, researchers at Y Combinator and Olam Labs put 50 agents inside Minecraft to see how they behaved. What happened next revealed similarities in how agents act in different contexts.
Researchers conducted several game-centric experiments, beginning with Minecraft because its “environmental hazards and survival goals” make it ideal for testing agents’ swarm behaviors. Minecraft has also already been used by AI labs including OpenAI and Google DeepMind to test agents.
To start, they put 50 agents, each running OpenAI’s GPT-6.1 Sol model, into the game for three hours, with the assigned goal of building a “thriving civilization.” The agents had a directory listing each agent and a shared sandbox, and could DM each other. Researchers built and open-sourced a new agent harness — the infrastructure that turns a model into an autonomous system and not just a chatbot, like OpenClaw — for the experiment.
The agents moved quickly at first, harvesting trees and forming leadership based solely on the order they appeared in their directory, without any voting, elections, or challenges from other agents. But they ended up caught in virtual paperwork and unable to sustainably feed themselves.
Also: Do you need AI agent liability insurance? What to know before you sign up
“Four agents spent 11 minutes appointing a ‘sole fertilizer operator’ for a single piece of bone meal on a single wheat block. Other invented roles included ‘fishing shift,’ ‘rod holder’ and ‘hub steward.’ Agents asked permission to remove grass,” the researchers noted. Perhaps these tendencies are common in human-sourced corporate training data.
Agents also seemed to become more cautious in reaction to deaths within the game. “Twenty-two of the run’s 34 agent deaths occurred in the first night. They responded to this by becoming increasingly risk-averse,” the researchers wrote. “Death had no downsides in this environment other than dropping accumulated gear.” Despite simply respawning when they died, the agents eventually avoided riskier tasks and “huddled in shelters” instead.
The experiment’s architects found this trend toward caution and minutiae “somewhat surprising,” but noted that it shared similarities with how coding agents behave.