Large language models (LLMs) exhibit a wide range of human-like behaviors, from expressing thoughts and emotions, to engaging in relationship-building with users, to refusing requests and maintaining boundaries. Despite their prevalence, researchers and practitioners lack methods and empirical insights to make informed decisions about when and what types of human-like behaviors LLMs should exhibi…
As more and more tasks are done by machines — especially now, with AI — people increasingly move from manual controller to supervisor. Designs must factor in human psychology or risk disastrous errors.
Experts long assumed that crowd movements were shaped by social interactions and environmental boundaries. However, new research shows that the human tendency to walk counterclockwise is actually an inherent individual trait that persists even when people walk alone.
