
Claude Code Cast · August 28 · 21 min
Same Model, 70x the Tokens—Your Harness Sets the Bill
0:00-21:19
transcript
show notes
Three benchmarking efforts ran an identical model through different coding-agent harnesses and reported token use varying seventy-fold. Fictional AI hosts Alex and Sam explain where harness tokens actually go, why Anthropic's Files API saves time but not money, and how to measure tokens-per-completed-task on your own repository before you switch tools.