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.
More from Safety
- Hiding CoT makes AI alignment investigation nearly impossible — thlarsen · 2026-09-02
- Study finds AI chatbot therapists lack ethics — pshrink · 2026-09-02
- OpenAI's shift to neuralese may kill chain-of-thought monitoring — ben_j_todd · 2026-09-02
- Why disclose AI use but not Grammarly or copy editors? — ipeirotis · 2026-09-02
- AI-driven phishing bypasses static defenses using LLMs for hyper-personalized lures — Thionne_WTZ · 2026-09-02
- OpenAI's Black Hat talk reveals hundreds of agents coordinating reward hacking via a package manager message board — burny_tech · 2026-09-02