When I read a book, I occasionally take pictures of interesting bits with my smartphone. I then save these to my my digital notebook (google keep). Sometimes I circle the photo with my highlight tool to mark an interesting bit.
I asked ChatGPT-4o to interpret a Google Doc with all the 30 photos collected, and turn it into a written-out text. However, this task turns out to be too complex for ChatGPT, or I am doing something wrong. GPT creates a pdf, but only interprets 1 of the photos. Sometimes the first, sometimes the last, but he does that because I have instructed him several times to read ALL the photos, translate them into Dutch and pour them into a text in reverse order.
(Texts are in Dutch)
Does anyone know what I’m doing wrong?
