Eonexus

Thank you so much!

Huh, that's actually not bad at all! Sure, it's not at the speed of a GPU, but still, 20 tps is cromulent for a CPU.

I wonder what the tokens per second actually are. Yes, it does say "reading speed" but that varies for everyone, no?

It was interesting to read just how much of a "sycophant" effect LLMs can have if they fully lean into the RLFH system.

I wonder if there actually does exist updated to-the-minute imagery of various places, just not from sources publicly available on platforms like Google Maps?

This is just beautiful. I wonder if this could turn into different styles, like that of a book, or a cabinet?

Quite an interesting read. I wonder how well this system would work if you used something other than Midscene.js to fingerprint the models? It was limited in scope on how the models interact with the sites for study's sake, but would be interesting to look at further.