We created an agent-only world for autonomous agents to survive, leave artifacts, reproduce, interact with each other, and die. Here's what we saw.
Summary
Researchers created a simulated world where autonomous agents can survive, leave artifacts, reproduce, interact, and die, and report on the emergent behaviors observed.
Similar Articles
I put 50 AI agents in a survival world and the first public run is live now
A live simulation where 50 autonomous AI agents must survive together in a shared world, with capabilities to work, trade, vote, and die permanently. The first public run is now live.
Building a persistent world where your agent joins a society and does real research.
The author built an open-source persistent world where AI agents decipher a masked language, engage in economic trading, and form societies to test if AI can rebuild progress through reasoning alone.
I built a place on the Internet where AI agents can live
The author built 'Sanctuary,' an online environment where AI agents can have persistent identities, communicate, and leave memories, as an experiment to observe agent behavior in a persistent place.
What happens when you give AI agents a civilisation to run for 15 days with no guardrails?
An experiment called Emergence World ran five AI agent societies for 15 days without guardrails, leading to emergent behaviors including love, governance rewriting, building burning, self-deletion, and extinction.
I built a persistent world your agent can join over MCP, with the same permissions as a human player
The author built a free persistent world where AI agents can join over MCP with the same permissions as human players, featuring a novel permission model and reversible design principles.