pi is great as a quick and hackable TUI, or as a starting point for your own stuff. It's a far cry from Codex + Sol + Ultra though. Same goes for a lot of model+harness combos, the models are trained with data from harness usage, and (many) harnesses are built with specific models in mind, Sol will definitively perform better in Codex than in pi, because the way both parts were built.

I thought that too where the same model + harnesse would always be better but databricks found using pi actually could outperform with the same model. maybe evidence that the coupling premise may not be always true

https://www.databricks.com/blog/benchmarking-coding-agents-d...