Chain of thought reasoning is being explored with some success. It’s better for it to be explicit output instead of internal, remember that the next token is being predicted based on the previous ones.
Your two points may not be as sound as you think. The second one can be defeated now since ChatGPT is quite good at generating descriptions of what code is doing. The first point is more subtle, you can iterate on code with ChatGPT but right now you need to know how to run the code to get the results before providing feedback. Once tools are developed for ChatGPT to do that itself then it could just show the results and a non technical person could ask for follow up changes.
Your two points may not be as sound as you think. The second one can be defeated now since ChatGPT is quite good at generating descriptions of what code is doing. The first point is more subtle, you can iterate on code with ChatGPT but right now you need to know how to run the code to get the results before providing feedback. Once tools are developed for ChatGPT to do that itself then it could just show the results and a non technical person could ask for follow up changes.