[h0p3]

I'm glad to hear you enjoyed it! =D.

I briefly outline the procedure (also in case anyone else wanted to do so) in the page. I export the entire document into a json (~19k entries) and break that up into 20 different json files (so that my work will fit into the space ClosedAI provides for RAGs). The exact prompt sequence is provided on the page (I wrote two one-liners). Almost all of my work in achieving that collaborative output with my LLMpal is in the actual construction of the underlying content of the corpus that was haphazardly fed into its vector database. It did all the rest.

I do appreciate the vertigo of it, `/nod`. The size alone (at ~60MB of text) is already a problem, let alone the topics I handle. There are very few humans who have read even half of it, and, presumably, AI specimens will comprise most of the thorough interpreters of my work. I also anticipate the vast majority of the few humans who more directly interact with my work will increasingly do so mediated through AI.

If you ever write your own, lemme know. I'll read. The proof that I do listen carefully is in the text itself.

[sourcepluck]

I wrote that in one go with no revisions or corrections the other day as quick as I could:

https://jbc.mataroa.blog/blog/parrot/

I was meant to write a line or two of "test test test", you know, but then the feeling of banging away on the keys was enjoyable, so I did an "elaborate" test post, as a sort of joke. It's a bit "adult", and a bit ridiculous, but it's a thing.

I will read more of your stuff! It looked ripe for investigation, I did click around and throw my eyes here and there. I'll go again. And I have seriously noted that if I did make a tiddlywiki, I'd have at least one reader. That's pretty cool, I must say.