If you’re familiar with the way in which documentation artifacts like this fall out of a Claude project, you will recognize that every place where Claude says ‘this changes everything’ or ‘this is the load bearing insight’ most likely resulted from a human looking at what Claude had done, and redirecting it towards a more fruitful line of inquiry. When Claude gets ‘excited’ about a thing like ‘we figured out which clock measurement approach helps us actually optimize performance’ - excited enough to explain it in this level of detail - it usually results from the user pulling Claude out of a rabbit hole where it was going about things the wrong way.

I think you severely lack in domain knowledge if you think “nothing else than a bit of prompting went in to this”.

"A bit of prompting" is subjective, and can indeed take a lot of work to craft accurate prompts which produce genuinely useful output.

This sounds like you have only had a superficial contact with LLMs. They do a lot of mechanical work, but "a bit of prompting" is not how they are used for something like this.

How about the desire to steer LLMs to a point of their choosing? LLMs wouldn't do this by themselves...