Understand this story
English text is being prepared.
AI-generated from public reports
Developments
1 confirmed developments
Y Combinator and Olam Labs test AI agent swarms in Minecraft
Source:heise online
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 3
IT Home · Artificial Intelligence
Researchers test AI agent swarms in Minecraft: collaboration tends toward bureaucracy, GPT has a higher win rate against Claude
Researchers from Y Combinator and Olam Labs used hundreds of agents in Minecraft to test collaboration and competition. 50 GPT-6.1 Sol agents failed to build a civilized settlement within three hours, and four agents even displayed bureaucratic behavior by spending 11 minutes appointing a "sole fertilizer operator." In Mindustry tower-defense matches, the GPT agents defeated Claude Opus 5.5 agents six wins to one loss, and the project has been open-sourced.
IT Home · AIRelated discussion
IT Home · AI joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Nov 2
The Decoder
Olam Labs and Y Combinator Labs, in Minecraft and…
In a joint research report, Olam Labs and Y Combinator Labs placed 50 GPT-6.1 Sol agents into a Minecraft survival world with only one instruction: "build a thriving civilization." The result was that after 22 deaths on the first night, the agents shifted to extreme risk aversion and became bogged down in tedious management of scarce resources. In Minecraft Bed Wars and Mindustry matches, GPT-6.1 Sol defeated Claude Opus 5.5 by 6-3 and 6-1, respectively, and the GPT agents even downloaded Mindustry's public source code from the internet on their own to analyze units and mechanics. The research team has open-sourced the Mindustry environment and the Multi-Agent Harbor framework.
heise online
Y Combinator and Olam Labs test 50 AI agents building a civilization in Minecraft
Researchers from Y Combinator and Olam Labs had 50 agents based on OpenAI GPT-6.1-Sol build a thriving civilization in Minecraft within three hours, but the agents quickly abandoned their original goals and instead set up a government with written rules and approval processes; one group spent 11 minutes just to appoint a fertilizer administrator. In an attack-and-defense test of 10 GPT-6.1-Sol agents against 10 Claude-Opus-5.5 agents, the researchers said the GPT side's strategies were more aggressive and more refined, while the Claude side was more defensive; when faced with a tool malfunction that made blocks impossible to break, GPT diagnosed the problem and shared workarounds, while multiple Claude agents concluded that breaking was impossible. In Mindustry, the GPT agents defeated Claude 6 to 1, and the researchers described the GPT agents as more like swarm collaboration, while the Claude agents, although they also designated leaders, made decisions in a more democratic way.
Nov 1
Hacker News Trending
AI agent swarms build a civilization in Minecraft: 50 agents descend into bureaucracy
ycombinator and Olam Labs tested AI agent swarms in Minecraft: 50 GPT-6.1 Sol agents were tasked with building a thriving civilization within 3 hours, but after a zombie attack on the first night, many tasks were abandoned, and 4 agents spent 11 minutes appointing a "sole fertilizer" for the bone meal on a single wheat block. In Bed Wars, 10 GPT-6.1 Sol faced 10 Claude Opus 5.5, and the GPT side won 6-1; Mindustry tests showed that GPT behaves more like swarm collaboration, while Claude is led by a single leader but adopts democratic decision-making. The related swarms have been open-sourced.
Heat trend for this story
- Current
- 15
- Period peak
- 31 Nov 3 03:00
- 24-hour change
- +10%
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.