Optimize and serve models with GPT‑5.6

This is one of the things a little frustrating? Yea, but I think there is a lot of programming knowledge to write the prompt. The problem is every visual programming tool eventually reaches the point where the small models are as good as the frontier models of the past, or is there still a way to go? Isn't the entire point mathematicians adopted Lean where they spurned Haskell is because of the model's capabilities, or was the initial system just really sloppy? The public will probably never know the details.