A recent study published in the *Proceedings of the National Academy of Sciences* provides evidence that AI agents overreact to minor cues in their environments, responding to these nudges much more strongly than humans do. This hypersensitivity suggests that relying on current language models for autonomous decisions could lead to unpredictable or easily manipulated outcomes. Behavioral science shows that human decision-making relies heavily on choice architecture, such as a default option or a highlighted button, but because AI models do not share human biological limits, their responses to nudges remain somewhat mysterious. “Many applications of AI agents tacitly assume that, under uncertainty, they will react in roughly human-like ways, if not more rationally,” said Manuel Cherep, a doctoral student at the Massachusetts Institute of Technology’s Media Lab and lead author of the study. To test these models, the researchers adapted a multi-attribute decision-making game originally created for human participants, where participants must uncover hidden prize values one cell at a time, with each reveal costing points.