The irrational effectiveness of the Pi harness

A few months back, Pi’s creator Mario Zechner gave a talk on developing Pi and slowing things down. It resonated with me so much that I wanted to try out the harness. I’m also getting increasingly wary of how bloated Claude Code and Codex have gotten over time. I have no idea what these harnesses are putting into the system prompt or how that’s affecting the models’ responses. I also have no clue about how their tool calling works or what search engine they’re using while searching for something. This opaque nature, along with the sweeping changes they make to their system instructions every now and then, makes it difficult to build a reliable workflow. Models are non-deterministic enough. I really don’t want my harness to add to it. Pi is a tiny coding harness written in TypeScript. By default, it gives the model four tools: read, write, edit, and bash. Ostensibly, that’s all you need for most coding work. The core is small enough that you can read the important parts in one sitting.…