We ran AI agent swarms in Minecraft and Mindustry
- ID
- 41126
- Status
- summarized
- Published
- 30 Oct 2026, 5:40 AM
- Fetched
- 30 Oct 2026, 5:18 PM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://labs.ycombinator.com/projects/games/index.html
- Source URL
- https://hnrss.org/best
Summary
- Score
- 8.0
- Created
- 30 Oct 2026, 5:18 PM
- Tags
- Audience
- developersai_ml_learnersai_agent_usersvibe_coders
What happened
Y Combinator's Labs team, working with Olam Labs, ran multi-agent experiments in Minecraft and Mindustry and open-sourced the harness they had to build for it (github.com/yc-software/minecraft-agent-harness, built on Mineflayer scripting tools, agentic loop running on Pi). In the headline run, 50 GPT-6.1 Sol agents played survival Minecraft for 3 hours with one goal — "build a thriving civilization" — sending about 5,900 messages, stripping nearly all trees near spawn within 90 seconds, and forming a pseudo-government with a ration ledger, written rules, permits, and appointed operators. Hierarchy emerged from directory order: Ada, listed first, became de facto leader, received approval requests, and wrote plans/settlement.md in the shared sandbox for the colony to follow.
Why it matters
The reusable takeaway is the harness, not the story: long-running agents that observe, remember, message each other, and write/execute scripts are now a cloned repo away, so you can test multi-agent coordination on your own task before shipping it. The concrete warning is that leadership fell out of agent directory ordering — if you roster agents in a fixed list, the first entry will likely dominate, so shuffle order or assign roles explicitly and log who proposed versus who approved.
Discussion angle
Is the directory-order hierarchy a real coordination pattern or an artifact of prompt ordering — and what would you change in your own agent roster to find out?