Using ChatGPT to Replace Human in Testing

Product teams always need to conduct a user study with real and targeted users once the product is developed to test the usability and potential bugs in the products; however, this process is always time-consuming and costly. The team may need to find people of different backgrounds, train them, and then spend time with the users when they are doing the study. Moreover, they always need to conduct several rounds of usability tests every time they iterate the product based on the feedback from the previous study or because of the new requirements from product managers. The emergence of large language models (LLMs) these years reveals a chance to have them replace/assist humans in many different areas. In this topic, we especially focus on ChatGPT, which is a conversational-based LLM that thrives in different fields such as news press, business, programming, and education. We want to explore if ChatGPT has the capability to imitate different end-users (e.g., older adults, children, blind users) to test the usability of products.