Yeah that makes no sense. Those AI are not running macOS instances to make you a docx. If anything, I’d expect them to write the weirdo xml of that cursed file format directly.
Microsoft's own different versions of Office can't always reliably read/write docx between them.
Is a layer of LLM going to make this better or worse? Could you train a model to be very good at it?
Microsoft's own different versions of Office can't always reliably read/write docx between them.
Is a layer of LLM going to make this better or worse? Could you train a model to be very good at it?