The youtube video covering it has an interesting run through of the desktop environment in the final section https://www.youtube.com/watch?v=eGS9su_inBY&t=2418s. But I agree a screenshot or two wouldn't hurt.
The live-feed is super cool. I wish I had a machine large enough to run this locally. It'd be nice if the ollama pro tier would allow running these historical models to play with at some point.
I/(claude?) created a gist that can be loaded into tampermonkey to expand the live-feed to make it easier to view on a bigger screen. [0] It's been fun to watch.
This feels like an AI agent doing it's own thing. The screenshot of this working is garble text (https://github.com/sophiaeagent-beep/n64llm-legend-of-Elya/b...), and I'm skeptical of reasonable generation with a small hard-coded training corpus. And the linked devlog on youtube is quite bizzare too.
This does exist to some degree, as far as I understand, along the lines of style-transfer and ControlNet in visual domains. Anthropic has some research called "persona vectors" which effectively push generative behaviors toward or away from particular traits.
