Erin Crawley
Titles as the sources gave them. In 1 entry, with 5 checked quotations.
What they said
Newest first. Each quotation was found word for word in the source.
“With collaboration, however, collective cybersecurity capability increases with population size. This creates a critical population threshold: below it, the population declines; above it, the population takes off, even though individual-agent capability has not changed.”
“Because red teaming a small group of agents cannot guarantee ecological safety in larger populations, our theory calls for ecological red teaming and population pacing”
“Labs should carefully characterize population scaling laws, estimate the critical population size for takeoff, and make results available for oversight.”
“Our model predicts the existence of a takeoff threshold, but does not establish whether current agent populations are already near one.”
“The purpose of this toy theory is not to make quantitatively precise predictions about real-world AI populations that may emerge, but instead to provide a common conceptual and mathematical framework for discussing the safety of AI populations.”
In the Base
Every entry they appear in.
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.