> scanned and analyzed a whole bunch of books and would let you call up really useful data on books. [...] Frankly, all of that sounds amazing. And amazingly useful. Even more amazing is that he built it, and it worked. It would produce useful analysis of books.
> This is all quite interesting. It’s also the kind of thing that data scientists do on all kinds of work for useful purposes. Smith built Prosecraft into Shaxpir, again, making it a more useful tool.
Author's general illiteracy aside, he's really giving the game away here. I can't even think about the ethical implications of the project, because why would I care to count the number of adverbs and passive voice in all books ever, and why would you need a state of the art LLM-powered AI to do it?