This is imo exactly right and also why any “productivity” measures/targets with AI need qualification. The first two types will output a lot, but it’s then very easy to point at projects in the third bucket and say they’re falling behind rather than they’re optimizing for different things
@pfrazee.comMy impression is that AI coding is on a "pick two of three" triangle: scope, ship speed, and correctness. Small tools are (speed + correctness) fast prototypes are (speed + scope) and big projects are (scope + correctness). Every project that tries to be all three degrades to "fast prototype."