Tag
This paper introduces an economic framework for multi-agent AI systems, where agents interact through economic mechanisms to produce emergent collective intelligence, drawing from Harvard and MIT researchers.
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.
The article argues that treating AI as an equal partner yields better results for complex tasks, while precise prompting is still suitable for technical tasks.