Hey everyone,
I’m a premium user of GPT, and I’ve been trying to get it to read and interpret images or PDF files that I upload. However, I’ve noticed that GPT still can’t handle those types of files, even after clearing my memory and previous chats. I understand it processes text, but I’m wondering if there’s a specific reason why it doesn’t work with non-textual content like images or documents.
I’ve used other AI models that can process images or PDFs, so I’m curious—what’s the technical barrier here? Is it related to the architecture or is it just not a feature that’s been implemented yet?
Would love to hear if anyone knows more about this!