The Prompt War: How AI Decides on a Military Intervention

TL;DR

This study systematically analyzes how large language models decide on military intervention, revealing consistent prioritization of success probability and domestic support over other factors, with some context sensitivity.

Contribution

It provides the first systematic assessment of AI decision-making in military contexts using conjoint experiments across multiple leading LLMs.

Findings

Models prioritize success probability and domestic support.

Decision-making is context-dependent but consistently emphasizes victory likelihood.

Models show some sensitivity to civilian casualties but not to economic shocks.

Abstract

Which factors determine AI's propensity to support military intervention? While the use of AI in high-stakes decision-making is growing exponentially, we still lack systematic analysis of the key drivers embedded in these models. This paper conducts a conjoint experiment in which large language models (LLMs) from leading providers (OpenAI, Anthropic, Google) are asked to decide on military intervention across 128 vignettes, with each vignette run 10 times. This design enables a systematic assessment of AI decision-making in military contexts. The results are remarkably consistent across models: all models place substantial weight on the probability of success and domestic support, prioritizing these factors over civilian casualties, economic shock, or international sanctions. The paper then tests whether LLMs are sensitive to context by introducing different motivations for intervention. The scoring is indeed context-dependent; however, probability of victory remains the most important factor in all scenarios. Finally, the paper evaluates numerical sensitivity and finds that models display some responsiveness to the scale of civilian casualties but no detectable sensitivity to the size of the economic shock.