A coworker was trying to tell me that models perform better in their own agent harnesses. I use both `pi` and `omp` and I'm somewhat skeptical. I understand that the tool calls might be slightly different. But really how much impact on the model itself does the harness have?
nixpulvis · · focus · HN ↗
capocasa · · focus · HN ↗
Each family gets their own system prompt, based on the original harness one, but compacted and includes instructions for more brevity.