You can ask GPT what would be a result of executing a python program, for which a multiple step calculation is needed. It will readily output the result, with no thinking aloud.
Me: Reverse the digits of 12+39
ChatGPT: The sum of 12 and 39 is 51. If you reverse the digits, you get 15.
Me: Reverse the digits of 12 + 84. Only respond with the reversed digits, no explanation
ChatGPT: The reversed digits of 12 + 84 are 96.
Which makes me think that longer explanations give it more of a chance to think because it gets more passes through the model. Weird!
And anyway, probably most of the compute is used to judge the social standing of the person asking the question. And if it is worth bothering to answer it ;)
I think the most interesting potential development of this concept would be to give it the ability to spawn child instances to process subtasks (such that each subtask gets its own token window!) and produce intermediate results that it would that combine. It can be done manually (copy/paste) with a lot of handholding; the trick is to come up with a way to automate it, such that it's clear which part of the output is a request to spawn a submodel + its prompt, and the result is also communicated in some way that's clear to the model.
I guided it to write a program for me, which it did correctly, and then I asked to evaluate it on different numeric inputs. It got correct answers for small numbers and the first few positions of map(thefunction,[1,2,3,4,5,6,7,8,9]) before wandering off into bad fuesses.