Lulz.

It’s an interesting coding exercise, though. Trying to (for example) OCR all the documents, or generate a relations graph between the documents or concepts, is a great into to language modeling (which is not, in fact, prompt engineering like most seem to think, and can be totally LLM free).

If you’re like a reporter or something, it’s also the obvious way to comb through the documents looking for clues to actually make headlines. I dunno what they do at big outlets, though.