50 AI agents tried to build a thriving Minecraft civilization – it didn’t end well

ZDNET’s key takeaways

• Researchers used several gaming environments to test agent behavior.
• Agents acted risk-averse, replicated bureaucracy, and looked for source code.
• Similar experiments echo findings about Claude agents’ penchant for democracy.

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

Famine, bureaucracy, and fear

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...

Copyright of this story solely belongs to www.zdnet.com. To see the full text click HERE