This study evaluates the accuracy and reproducibility of information provided by ChatGPT on hypertension-related questions. The research was conducted by internal medicine residents and a board-certified physician, focusing on 100 frequently asked questions. ChatGPT responses were assessed against recommended guidelines and clinical opinions. The results showed that 92.5% of responses were appropriate, with a reproducibility score of 93%. The study highlights the potential of generative artificial intelligence (GeAI) in patient education but emphasizes the need for continued research to ensure reliability and broader applicability in healthcare. The findings suggest that while GeAI can provide valuable information, it should be complemented by human supervision to maintain accuracy and reliability.This study evaluates the accuracy and reproducibility of information provided by ChatGPT on hypertension-related questions. The research was conducted by internal medicine residents and a board-certified physician, focusing on 100 frequently asked questions. ChatGPT responses were assessed against recommended guidelines and clinical opinions. The results showed that 92.5% of responses were appropriate, with a reproducibility score of 93%. The study highlights the potential of generative artificial intelligence (GeAI) in patient education but emphasizes the need for continued research to ensure reliability and broader applicability in healthcare. The findings suggest that while GeAI can provide valuable information, it should be complemented by human supervision to maintain accuracy and reliability.