Embedded platforms, TinyML prototypes, and hardware experiments. Each one started with a question I couldn't answer without building something first.
Does the $3 AI chip actually do AI?
A ground-up benchmarking study of matrix multiplication on the ESP32-S3. Four implementations built from scratch — naive, compiler-optimized, cache-blocked, and PIE SIMD — measured with cycle-accurate timing. The short answer: yes, but only up to a point, and the reason why is more interesting than the headline number.
Checking the claims against real silicon.
An investigation that turns each claim about machine arithmetic into a tiny on-board probe and reads the verdict off the serial port. Floats are torn apart bit by bit, pushed off both edges into infinity and the subnormals, and set against integers and fixed-point — on a RISC-V chip with no floating-point unit, where every quirk shows plainly. A companion to Unit 1 of The Mathematics ML Runs On.
Next experiment in progress
Something is being built. Check back soon.