Summary
Large language models mirror human cognitive biases—but can those biases be guided? This experiment, the second phase in the fourth study on loss aversion in the
Psychology of Gen AI series, reveals that while loss aversion remains deeply ingrained in AI responses, introducing persona information, such as demographics or personality traits, can increase variability and make outputs more nuanced. For advertisers and researchers, this opens the door to design strategic prompts that spark richer and more nuanced, human-like responses.
