Looks good, thank you

You need to use an LLM with a very long context length, potentially 1 million+ tokens. I don’t know if any local LLMs can even go that far, and if they can, you’ll need an outrageous amount of ram and vram.

But honest question… Why? If you’re planning on generating fake books or stories, it’s not going to happen, you’ll create the most generic barely coherent text.

And fair warning, if you’re trying to sell AI generated stories you’ll quickly be permabanned from any store, so don’t even try it.

I never understood the hate for it either. Sure, the animation is a bit dated and has some uncanny valley, but it’s a fun family movie.

Also has the greatest scene in cinema history: the train that drifts on ice https://www.youtube.com/watch?v=COdoHpU_a8U

Upvoting you out of sheer respect, but wow I can’t believe there is someone out there that enjoyed that hot garbage.

Hell yeah. Huge respect to him and the other youtuber that exposed this, it’s crazy that Honey just pocketing most of the referral money has been undiscovered for so many years.

Apps listening to your mic to give you targeted ads is an urban legend. There’s tools to see which apps listen to you and there isn’t any evidence that any of the popular stuff ever open the microphone (unless you’re in a call or something). If you’re too worried about it, you can always turn off the mic permission for the app.

The ads are actually coming from other ways of tracking you like browser fingerprinting to follow what things you browse and build a profile on what you like/are interested in.

See also EFF’s article on it: https://www.digitalrightsbytes.org/topics/is-my-phone-listening-to-me

Mosquitos. I’m so fed up with those things.

AFAIK web scraping (the act of grabbing and downloading any data you see available on the internet) isn’t illegal, and I would assume downloading PDFs provided to you online would fall under that. Since it is copyrighted it would probably be illegal to share it, though.