preprint · arXiv
Consistency of AI-Generated Exercise Prescriptions: A Repeated Generation Study Using a Large Language Model
In plain English
Asks the same model the same question repeatedly and measures the spread in answers. Non-determinism as a product risk rather than a curiosity.
large language models
consistency
safety
Related research
- Mind Companion: An Embodied Conversational Agent for Process-Based Psychotherapy
- The AI Recommendation Paradox: A Systematic Review Evaluating the Promise, Peril, and Path Forward for Large Language Models in Exercise Recommendation
- AI-Generated Exercise Prescriptions for At-Risk Populations: Safety and Feasibility of a Large Language Model Assessed by Expert Evaluation