timing-discipline — measure first, restructure early

The expensive mistake in computational work is rarely the wrong algorithm. It is the run that consumes a night, a weekend, or a machine-week and returns something a ten-minute pilot would have predicted. Runtime intuition is systematically optimistic — in people, and worse in language models, which produce fluent, confident durations for jobs they have never timed, because plausible-sounding ETAs are easy to generate and nothing in the generation process consults a clock. Hence the founding rule:

An estimate not derived from a measurement of this calculation, in this configuration, on this machine, is a guess. Every projection is either (a) fit from the job's own time-stamped log, (b) taken from a measured prior run of identical configuration on the same hardware, or (c) reported as "unknown — measuring now." There is no fourth category.