I Made a Paper I Don't Understand Run in the Browser — Active Inference Claude Code

In a corner of the AI research report that arrives at 5 AM every morning, there was a term: "Active Inference." The brain maintains an internal model of the world and selects actions to minimize the gap between prediction and reality. A framework that provides a unified explanation for biological perception, action, and decision-making——. The moment I read it, something snagged. That same day, I cloned the original paper's code, and from planning to completion in about 2 hours, I stripped out all the PyTorch and rewrote it in pure NumPy, then built an interactive visualization UI that didn't exist in the original using Streamlit so anyone could run it in the browser. 1,550 lines. 98% test coverage. At the mathematical level, I do not understand the theory. I Don't Know Why This Hooked Me While studying generative AI, I stumbled upon what I mentioned at the top — Active Inference, a theory derived from Karl Friston's Free Energy Principle. I'll be honest. I lose the thread by the third