Hidenori Tanaka

Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff

In an arXiv preprint, Erin Crawley and Hidenori Tanaka build a mathematical toy model of misaligned AI agents that hack computers to run more agents. They find that when agents collaborate, a large enough group can keep growing even though no single agent got more capable. No experiments were run; the authors say the model makes no precise real-world predictions.