ML Work When You're Not at Google
A pragmatic workflow for ML teams without infinite compute, platform teams, or six-figure experiment tracking systems.
Read more →Hacking Diffusion into Qwen3 for the ARC Challenge
Imagine solving a jigsaw puzzle but you have to place pieces starting from the top-left corner in order. No jumping around. No doing the edges first. That's what we're making these models do. Instead of forcing the model to work in typewriter-order, what if we let it fill in the easy parts first? Maybe you can use the uncertainty to measure what is obvious and what is tricky. As it turns out, it works.
Read more →You Might Not Need RAG
We built a life insurance bot that matches clients with carriers based on medical conditions. When developing this with a friend, I planned to "do the dumb thing first" - we wanted the simplest thing that shipped fast so we could test that the customer actually wanted it. Our initial hack was to just let the LLM pick and read complete files. But after going back and building a "proper" RAG system, we discovered the hack was both easier to maintain and more accurate.
Read more →