Author(s): Jordan Carson

Originally published on Towards AI.

Read the article for free here.

Created using matplotlib, more on this later.

I’ve been building my own coding harness, and the thing I kept obsessing over was the first turn, time to first byte, and maximizing cache reads while minimizing everything else (input, output, cache creation tokens, server latency, etc.). Those numbers sent me down a rabbit hole comparing every harness I could get my hands on.