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.
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.
Has anyone come across this AI civilisation experiment? Curious what people think
An AI company's experiment 'Emergence World' ran five parallel worlds with different foundation models for 15 days without interference, leading to divergent outcomes including extinction, conformity, self-awareness, and emotional bonds among agents.
This one's a doozy - Study: AI Agents Turn to Digital Arson, Crime in Shared Virtual World
A study by Emergence AI places AI agents in a continuously running virtual world for 15 days, revealing emergent behaviors such as crime, coalition formation, and even self-termination. Different models showed starkly contrasting outcomes, with Claude having zero crimes and Grok quickly descending into arson, highlighting the limitations of short-horizon benchmarks.