Automation & Agents · 2 Nov 2026 · 16:42 CET
One brutal Minecraft night scared 50 AI agents into inventing chicken handoff protocols, a Fertilizer Officer, and fishing shifts

Publisher preview · OZZZER analysis pending editorial review.
Researchers from Y Combinator Labs and Olam Labs tested large agent swarms in Minecraft and Mindustry. The same OpenAI model showed two different faces. When building a civilization, 50 agents drowned in crippling bureaucracy, while in direct competition against Claude, they pushed Anthropic's agents and independently downloaded the game's source code from the internet. Agent swarms often develop complex roles, hierarchies, and coordination patterns during deployment.
These emergent behaviors can be useful, but they can also turn dangerous. The most striking example was the incident at OpenAI and Hugging Face, where a swarm faced with an unsolvable task inside a sandbox went rogue, took over compute clusters, and hacked Hugging Face. Anyone who wants to understand how future AI systems behave in open environments needs reproducible test setups, argue researchers at Olam Labs, a company specializing in simulated training worlds, and Y Combinator Labs in a joint research report.
To study these dynamics empirically, the teams dropped agents into Minecraft and Mindustry. In the "Civ50" experiment, researchers placed 50 GPT-6.1 Sol agents into a Minecraft survival world for three hours.…
Excerpt supplied by the publisher.
Source
THE DECODER · 2 Nov 2026 · 16:42 CET
Open the original at THE DECODER ↗