Full-circle Test-driven Firmware Development with OpenClaw Ladyada: "I've only had OpenClaw installed on this Raspberry Pi 5 for a couple of days, but boy, have we burned through a lot of tokens and learned a lot. Including what I think is a really fun improvement in my development process: “Agentic test-driven firmware development.” I've used LLMs for writing code as a sort of pair-programming setup, where I dictate exactly what I want done. But this is the first time that I'm giving full access to the hardware to the LLMs and letting Claude Opus 4.5 as a manager to control Codex subagents. Not only does it parse the datasheet for the register map and functionality, Claude also comes up with a full development and test plan, writes the library, tests it on existing hardware, and then also works up a test suite that covers all of the hardware registers to make sure that the library is exercising the entire chip capability. For example, here I give it an APDS-9999 color sensor and a Neopixel ring and tell it, “hey use the Neopixel ring to verify that we're really reading red, green, and blue data properly from the sensor,” and it will do the whole thing completely autonomously… no humans involved! I still review the final code and ensure the tests genuinely validate the functionality, not just take shortcuts. There is a phenomenon known as "reward hacking" (also called "specification gaming"). The model may optimize for passing tests as a metric, rather than ensuring the code truly works as intended. So far, the results have been excellent... no surprise, since these LLMs are trained on Adafruit open-source GitHub repositories!"