AI Chatbots Faltered on High-Risk Questions About Late-Life Depression
In a July 2026 benchmark, 3 chatbots gave acceptable answers to 80-93% of routine late-life depression questions, vs. 37-63% of high-risk questions.
Read articlePublished research on patient safety.
In a July 2026 benchmark, 3 chatbots gave acceptable answers to 80-93% of routine late-life depression questions, vs. 37-63% of high-risk questions.
Read article