Testing ChatGPT-4 for ‘UX Audits’ Shows an 80% Error Rate & 14–26% Discoverability Rate

OpenAI recently opened up access for image upload in ChatGPT-4. This allows anyone to upload a screenshot of a webpage and ask, “What UX improvements can be made to this page?” We decided to test how accurate the AI model is when it comes to discovering UX issues on a webpage. We then manually compared the responses of the AI with 6 human UX professionals’ results for the very same webpages.