Researchers have developed a new AI-based method to study the structure and complexity of human behavior. They use a large language model to mimic human choices in various economic game settings, assigning it 'type vectors' that represent different personality traits such as altruism and risk aversion. By varying these dimensions and values, they find that human behavior can be closely matched using just three key factors: Risk Aversion, Strategic Sophistication, and Trust. This approach suggests that human behavior across diverse settings may be approximated by a low-dimensional representation, potentially leading to more general theories in the behavioral sciences. --- Why it matters: This research matters because it provides a new framework for understanding human behavior across different contexts, which can help researchers develop more parsimonious theories and models. It also has implications for fields like economics, psychology, and sociology, where understanding human decision-making is crucial. Source: https://arxiv.org/abs/2608.18265