When the output is a servo, not a paragraph

Connecting models to hardware — relays, servos, sensors, robots — and the constraints that appear the moment software has to act on a physical thing.

Software that gets it wrong shows you a bad paragraph. Hardware that gets it wrong moves something in a room you are standing in. Everything changes once the output has mass: latency stops being an annoyance and becomes the feel of the thing, a retry is no longer free, and "it worked on my machine" has to survive a network that drops.

These posts are about that gap — the last few centimetres between a token and a moving part — and they assume cheap kit rather than a lab.

Writing on this

How to measure LLM latency: find which leg owns the two seconds — A voice command that takes two seconds to fire has four legs and only one of them is slow. Here is how to time each one separately before you optimise anything. (2026-08-03, 4 min)
From a token to a servo: the last ten centimetres — Everything between a model's output and something physically moving — the boundary, the failsafe, and why the interesting engineering is all on the hardware side of the API call. (2026-06-23, 4 min)

Courses that take it further

Atoms, not pixels — Get a model out of the browser and onto an arm that costs less than a phone. (29 lessons, 1615 min, 5 free)
Friday night: make one lamp answer to you — Voice in, relay click out, and the millisecond count that says where the wait actually lives. (3 lessons, 85 min, 3 free)
Build an autonomous greenhouse — A closed loop that runs for six weeks unattended, in a system where failure is measured in dead plants. (3 lessons, 100 min, 1 free)
What humanoid robots are actually for — Count the cuts in the demo video, then count the contacts in your own hands. Two numbers, one honest picture. (3 lessons, 70 min, 3 free)
Start a community robot lab — A room, some kit, and six sessions that other people finish. The hard part is not the robots. (3 lessons, 95 min, 1 free)