This NSI CTC Report:

1. Explores human vs. AI decisionmaking in a crisis simulation.
2. Details how humans consistently sought to raise the stakes and signal a willingness to confront China directly while AI played defensively and sought to limit the scope of nature of potential confrontation.
3. Finds that AI consistently demonstrated broad and structured thinking, though the AI’s response process presented challenges.
4. Concludes that reliability issues raise concerns and more wargames featuring humans and AI are needed to determine whether LLMs can reliably be integrated into national security and foreign policy decisionmaking in the future.

This Report was authored by NSI Founder and Executive Director Jamil N. Jaffer and NSI Deputy Executive Director Jessica Jones.

Download the PDF here.