Leading AI chatbots show dementia-like cognitive decline in tests, raising questions about their future in medicine

Leading AI chatbots, tested using the Montreal Cognitive Assessment (MoCA) test, show signs of mild cognitive impairment, particularly in visuospatial skills and executive functions. While excelling in language and memory tasks, their performance in interpreting complex visual scenes and demonstrating empathy is lacking. These findings challenge the notion that AI will soon replace human doctors in medical settings.

*****
Written on