> 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…
> 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…