You’re thinking of retrieval augmented generation (RAG) with a vector database. Its something that’s being actively developed. I haven’t had time to dig much into it, especially currently. But the terms themselves should give you a starting point.

Edit: a quick google gives what could be a promising starting point https://huggingface.co/learn/cookbook/rag_llamaindex_librarian

Saints row: the third remastered please

A fond memory is beating the light world in lttp and seeing the dark world for the first time

Nothing wrong with using the output as a starting point then editing it from there

And even if there are legal ramifications. The fines are low enough that its a cost of doing business for the most part. Especially in comparison to the amount of money they make spying. Possibly on top of whatever else they sell depending on the business in question.

Most insidious part about the whole thing is the fact that most legal stuff is “licensed” rather than owned. A convenient legal fiction to allow them to revoke access at any time and (likely) keep your money.

Legal stuff isn’t much better these days. Advertisements unless you pau more, user tracking regardless, etc.