experiments
A vision demo is not a measurement
Turn an impressive detection into a bounded test with known inputs, visible errors, and a reproducible environment.
Field notes
Things worth trying. Results worth keeping.
Worked examples, explicit assumptions, and sources you can inspect.
hardware
The weights fit. The model doesn’t.
Estimate a bounded KV-cache allocation and keep it separate from weights, runtime buffers, and the machine you actually have.
methods
Tokens per second need footnotes
Compare inference runs without mixing prompt processing, generation, different models, and missing configuration.