The Prompt War: How AI Decides on a Military Intervention
This addresses the problem of understanding AI decision-making in military contexts for policymakers and researchers, but it is incremental as it applies a simple analysis to a new domain.
This paper tackled the problem of identifying which factors determine AI propensity for military intervention by conducting a conjoint experiment with 640 vignettes run 100 times each, finding that high domestic support and high probability of success are the largest predictors, while costs like international condemnation and deaths have about half the effect.
Which factors determine AI propensity for military intervention? While the use of AI in war games and military planning is growing exponentially, the simple analysis of key drivers embedded in the models has not yet been done. This paper does a simple conjoint experiment proposing a model to decide on military intervention in 640 vignettes where each was run for 100 times allowing to explore AI decision on military intervention systematically. The analysis finds that largest predictors of AI decision to intervene are high domestic support and high probability of success. Costs such as international condemnation, military deaths, civilian deaths, and negative economic effect are statistically significant, but their effect is around half of domestic support and probability of victory. Closing window of opportunity only reaches statistical significance in interaction with other factors. The results are remarkably consistent across scenarios and across different models (OpenAI GPT, Anthropic Claude, Google Gemini) suggesting a pattern in AI decision-making.