AIToday
Large Language ModelsAI Business & IndustryGIGAZINE AIPublished: Oct 30, 2026, 16:00 JST

50 GPT-6.1 Sol agents fail to build Minecraft civilization

Send on LINE
50 GPT-6.1 Sol agents fail to build Minecraft civilization

3 Key Points

  1. What happened

    Olam Labs and Y Combinator put 50 GPT-6.1 Sol agents into Minecraft for 3 hours to build a thriving civilization; they hit food shortages, introduced rationing, and failed to meet the goal.

  2. Why it matters

    The agents organized themselves — an agent named Ada became de facto leader and issued rationing rules — yet still could not sustain the civilization, suggesting coordination alone did not solve scarce resources.

WHO IT HITSThis lands on teams evaluating AI agents for open-ended, multi-agent tasks — showing that even a flagship model can organize labor and rationing but still fall short on resource planning over a few hours.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The experiment is notable less for the failure itself than for how the agents got there. Early on, the 50 agents explored and felled nearly every tree within reach of the spawn point within 90 seconds, and an agent named Ada emerged as de facto leader without any discussion — 46 of the other 49 agents sent their first direct message to Ada. Ada posted a colony-building plan covering farmland, sapling protection, shelter coordinates and priority resources, and later issued rationing rules as food ran short after the third night.

The team also highlighted bureaucratic behavior: roles such as "fishing rod officer" appeared, low-level agents asked permission to harvest grass, and four agents spent 11 minutes applying a single bone meal to a single wheat field. Fishing became a key food source because it was low-risk, and a system of fishing, cooking, distribution and delivery emerged.

A second experiment pitted 10 Claude Opus 5.5 agents against 10 GPT-6.1 Sol agents in bed wars, with GPT-6.1 Sol winning 6-3. The same pattern of the first-listed agent becoming leader was observed there too, and the team says it is now running a 25-agent GPT-6.1 Terra experiment streamed on Twitch.

FAQ
What was the goal of the Minecraft experiment?
The goal was to build a thriving civilization, with a 3-hour time limit. The agents failed to achieve it and hit the time limit amid food shortages.
How did the agents respond to the food shortage?
Ada issued strict instructions to halt large-scale mining, building and distant scouting, and a rationing system was implemented inside the shelter, with Ada overseeing cooking and distribution.
How did GPT-6.1 Sol do against Claude Opus 5.5 in bed wars?
GPT-6.1 Sol won 6-3 over Claude Opus 5.5 across nine 45-minute games. Claude Opus 5.5 played defensively, while GPT-6.1 Sol used an aggressive, coordinated strategy to destroy beds in the final minutes.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleEMBRACE flaw hits Codex, VS Code, Cursor, Copilot