DIY Jev

Excerpt

So this jev thingy is getting kind of big... tbh it seems overhyped by a large margin, but here we are. Not that its bad, just feels like we usually ignored larger things... Anyway to the point of this post: I’ve been experimenting with a simple Jev-like inference setup using ordinary open weight LLMs. Ive done jev-like thing before with llms and i never felt the need that we have to have a separate "system one models" for that and that llms do fine. So i played around a bit. The main difference