Post

My 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."

So essentially for a “real” project patience is key

maybe you already answered this, but why do you think this is? is it that context is necessary but weighs you down at the same time, hence why initial prototype or small edits can hit the other corners?

I think it's a variety of factors. Agentic coding already incentivizes greater investment in testing rigor because it helps the agent write correct code and it gives you assurance against its mistakes. Pair that with greater scope or more ambitious projects, and now you have another reason for rigor

Another thing is, in some ways, the scope & ambition around testing itself has grown. Simtests & synthetic environments, mocks, and code coverage has become equally more attainable, so now we do it way more than before