The study results indicated that when users were resistant to habit change, large language models failed to provide information that would help them evaluate their problem behavior, its causes and consequences, and how their environment influenced the behavior. For instance, if someone is resistant to increasing their physical activity, information that engages with the negative consequences of a sedentary lifestyle is more effective in motivating users through emotional engagement than information about joining a gym. Without information that addresses users' motivations, the language models failed to generate a sense of readiness and the emotional impetus needed to progress with behavior change, Bak and Chin reported.