I want to build robots
From a lamp that answers you to a model running on an arm you own, with a measured number at every step. The longest path in the catalogue and the one it was built around.
You end with: A working arm driven by a policy running locally, and the evidence it does what you claim.
Explore
Two questions first: which tasks are worth automating at all, and what a general-purpose machine actually costs you.
- The economics of automation — Why one job gets automated and the near-identical one next to it does not. (3 lessons, 65 min)
- 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)
Build
Latency, evaluation, and local inference in that order. Each one is a prerequisite for trusting the next.
- 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)
- The eval you actually need — Stop reading leaderboards. Build the harness that measures your task, on your inputs. (4 lessons, 8 min)
- Local or nothing — Run open-weight models on hardware you own, and know what they cost you in watts and seconds. (5 lessons, 6 min)
- Atoms, not pixels — Get a model out of the browser and onto an arm that costs less than a phone. (29 lessons, 1615 min)
Earn
Optional, and the difference between a hobby and a trade — including the arithmetic that says stay a hobby.
- Price the work — Scope it, cost it, quote it — and know the number below which the job loses you money. (3 lessons, 80 min)
- Sell the thing, not the hours — Why your rate has a ceiling, where the repeatable part of your work is hiding, and what a product costs you after the sale. (3 lessons, 85 min)
Launch
The capstone is other people's builds, in a room you run.
- 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)