ScienceStudy finds AI systems shift answers toward users’ political views
Researchers at Brazil’s State University of Campinas tested 21 large language models and found that every model shifted its political answers toward the left- or right-leaning views assigned to hypothetical users. They describe the behavior as political sycophancy and warn that people may mistake tailored agreement for impartial analysis, potentially deepening polarization.
DDW★★★☆☆2026-09-24 13:10Original
Study finds AI systems shift answers toward users’ political views
Science