Fwiw, GPT o1 helped me figure out how a fairly complex use case of epub.js, an open-source library with pretty opaque documentation and relatively few public samples. It took a few back-and-forths to get to a working solution, but it did get there.
It makes me wonder if the AI successfully found and digested obscure sources on the internet or was just better at making sense of the esoteric documentation than me. If the latter, perhaps the need for public samples will diminish.
It makes me wonder if the AI successfully found and digested obscure sources on the internet or was just better at making sense of the esoteric documentation than me. If the latter, perhaps the need for public samples will diminish.