After some technical difficulties, the episode actually starts at 4:00ish.
Originally recorded July 2022 to show folks what by now should be obvious after three episodes of listening to this show, that GPT-NeoX-20B combined with NovelAI's TTS, created at the very least the illusion of a device that can output whatever-at-all into something that seems like a constant epic poem. You heard it with contemporary English, now we're gonna have it use more highbrow English styles, like the English translated from the Italian contained in the Decameron, courtesy of Project Gutenberg.
Thanks to:
EleutherAI for making the GPT-NeoX-20B model that generates the text.
NovelAI for making the text generation service I use for most of these episode, and the text-to-speech version 2 model that makes these episodes potentially entertaining.
@BoneAmputee of EleutherAI for making VQGAN+CLIP and Diffusion image models available for use, which is what makes the background images.
Katherine Crowson (@RiversHaveWings on Twitter) for the KLMC2 animation notebook that will be used on future episodes.
Nerd Odyssey whose Twitch friendly no copyright playlists were the background for many episodes.
Any voices from the text-to-speech model that might resemble persons living or dead are coincidental, which is my speculation, there's a multi-dimensional latent vocal space, there were many awesome finds, and if I use them it's because of my deep-seated respect for their work, and I think they'd get a hoot that their voice was being used to show how large language models, given the right environment, would speak 24/7 epic poems about anything if we let them.
