alt Hacker NewsThe harness is pretty much irrelevant for general tasks.
You can write a 100 line harness that only has one tool - try either "bash" or the more fun "you're running within nodejs, here's eval", you'd be surprised in how close to CC/Codex performance you're going to get.
I did that, wrote my own harness “Jarvis”, simple loop. Still results were terrible using the same model in comparison to for example OpenCode. So X Doubt.