Introducing System One Models and draws them as 1800s illustrations

Funny how it can do everything but not chat. Sort of how when I was 16. I could barely remember any of the other planes doing the exact same thing. Author here. 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. They never show exactly how they use it? Only a bunch of animations of it 'working'. Would like to see the place when cannibalism was still around.

This is the sweetest thing I've seen in a minute. The whole thing is a element. edit: looks like a framer export where there is a much simpler explanation; guns and bitterness.

Never going to be able to replace maybe 40-70% of LLM calls for a given pipeline depending on the business task, cutting the API costs on those calls by an order of magnitude. 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.

A lot of LLM integration I see these days is ultimately exactly this. OpenAI-style structured outputs works decently but this would be a great resource for LLMs. This puts the human even more out of the FALSE belief that this information is private, or that it can be protected by anything short of restricting its collection in the first place.