(Or distill into itself this way)

Thinking this will be a powerful new formula: collect use cases, build a course router, prompt optimize (GEPA etc.) each use case (including many-shot examples sampled from prod), then distill that whole system into a smaller model.

Just played for a few hours so taking a break, but will send you a steam link so we can connect there later!

...why deep learning gets better with scale (better fractal "render" resolution), why LLMs have to do all kinds of norm and projections to work (must attend to many feature scales), and why TRM works well on ARC (can find features in hugely magnified areas of the intelligence manifold)

This is 100% what I'm envisioning

🤣

I don't know how much I can say about the work stuff, but the agents impress me daily with what they're able to do. And frustrate me daily with what they aren't.

#nokings