Newer AI models still reproduce racial and gender stereotypes in medicine

Flinders University researchers person evaluated 2 next-generation reasoning ample connection models (LLMs)—o3-mini and DeepSeek-R1—and recovered that erstwhile asked to picture fictional patients with communal aesculapian conditions, the models often reproduced radical and sex stereotypes, indicating that advancements successful AI reasoning bash not inherently amended representational fairness.