I recently started using ChatGPT for comparisons. Sometimes the information is just wrong. When I pointed this out, it adjusted and provided different results. It is just like any other resource at this point. It is just retrieving information from the internet and re-packaging it, albeit a bit more efficiently than if I was pulling all the information together myself. I use it as a starting point. Ultimately, we need to determine what sounds best in our particular systems, unless you want to jump into the ASR pool and rely only on data points rather than what brings joy to you. I still trust my ears and judgement.