Economists urged to join multi-agent, long-running AI evals

Afinetheorem · x · 2026-09-02

Responding to a call for more AI alignment researchers, the post emphasizes the need for developing more game theory-related evaluations, such as ultimatum game variants and cooperative/adversarial games. The author highlights that multi-agent, long-running evals represent a significant opportunity for economists and game theorists to contribute, noting that writing evals is both fun and surprisingly difficult.

Original post →

More from Safety

Safety channel →