Re:An Empirical Study of Harness Design for Coding Agents
by novarii_ on Friday September 18, 2026 @10:57AM
(#49755330)
> using the harness + model made by the same lab, has vastly better experience compared to more "general purpose" (for the lack of a better term) harnesses
not really, there was a recent benchmark with claude and codex and it showed no difference in ability with a harness like pi agent compared to their native harnesses, pi was in fact cheaper per task.
not really, there was a recent benchmark with claude and codex and it showed no difference in ability with a harness like pi agent compared to their native harnesses, pi was in fact cheaper per task.