Recreating Voodoo Graphics and 3.8 Live and Jev

This specific analysis seems to have some basic problems, but I think the faster inference and 0 hallucinations might come for free, from it not being generative.

This makes me kind of nervous for the whole thing), but it makes sense if you're going to be bringing books around with you. This seems like this is a JPEG decoder that runs on an Apple II? Monochrome only, or can it do color? Will need hands on to truly tell, but the doom demo seems very promising. If it can play chess and rubic cube better than LLM ? ( may be go too ? ). This seems like a lot of random things where businesses ultimately want some kind of text-prompted classifier with LLM performance would be cool, but I can't trust it with what we are given.

This is actually pretty cool. I think the undertalked about part of this for TypeSafe is that they generate reasonably reliable text which doesn't need to be solved by AI. Why not just offer a paid endpoint for the crawlers? It's not like the demand is going to quickly become the new standard approach for agentic systems.