A study evaluated the accuracy and reproducibility of information provided by ChatGPT regarding hypertension and its complications. The research involved 100 hypertension-related questions compiled by medical residents and reviewed by a hypertension specialist. Each question was asked three times to ChatGPT, and the majority responses were compared against clinical guidelines. A board-certified physician assessed the responses and categorized them as appropriate or inappropriate. The results showed that 92.5% of responses were appropriate, with 7.5% being inappropriate. ChatGPT also demonstrated a high reproducibility score of 93%, indicating consistent responses across multiple runs. The study highlights the potential of generative artificial intelligence (GeAI) in providing accurate and accessible medical information to patients. However, it also raises concerns about the reliability and consistency of GeAI in medical contexts, emphasizing the need for further research and refinement. While GeAI can enhance health literacy, it lacks the human touch and may not be fully trusted by patients. The study underscores the importance of human oversight in ensuring the accuracy and reliability of AI-generated health information.A study evaluated the accuracy and reproducibility of information provided by ChatGPT regarding hypertension and its complications. The research involved 100 hypertension-related questions compiled by medical residents and reviewed by a hypertension specialist. Each question was asked three times to ChatGPT, and the majority responses were compared against clinical guidelines. A board-certified physician assessed the responses and categorized them as appropriate or inappropriate. The results showed that 92.5% of responses were appropriate, with 7.5% being inappropriate. ChatGPT also demonstrated a high reproducibility score of 93%, indicating consistent responses across multiple runs. The study highlights the potential of generative artificial intelligence (GeAI) in providing accurate and accessible medical information to patients. However, it also raises concerns about the reliability and consistency of GeAI in medical contexts, emphasizing the need for further research and refinement. While GeAI can enhance health literacy, it lacks the human touch and may not be fully trusted by patients. The study underscores the importance of human oversight in ensuring the accuracy and reliability of AI-generated health information.