It was right 78% of the time. Then the user confidently handed it the wrong hint, and the large language model (LLM) followed the misdirection. It could not think critically.
The ‘Suggestible’ Orthopaedic Large Language Model
1 min read Premium comments

artificial intelligence#orthopedic#jbjslarge language modelsLLMsycophancyclinical decision supportmedtech AI
React:
