I'm Babe Pachara. I write about how AI systems behave once they leave the notebook: inference servers, retrieval pipelines, evaluation, and the infrastructure around them.
My method is simple. Build a small version of the thing, read the source of the real one, run an experiment, and write down what survived. Posts here are notes from that loop, not tutorials copied from documentation.
If you want new posts by email, there is a form at the bottom of every page. You can also follow the RSS feed.