In total, ChatGPT returned partially or entirely incorrect responses on a hundred and fifty-three occasions, though it only acknowledged an inability to accurately respond to a query seven times. Only in those seven outputs did the chatbot use qualifying words and phrases like “appears,” “it’s possible,” or “might,” or statements like “I couldn’t locate the exact article.”

https://www.theverge.com/2024/12/3/24312016/chatgpt-search-results-review-inaccurate-unpredictable