I agree. But in that context we're talking about specifications.

When we're trying to wrangle a piece of code to do something we want but aren't quite sure of how to interact with the api, it's a different matter.

What i found is that by the time copilot/gpt/deepseek has enough knowledge about the problem and my codebase, I've run out of tokens. Because my head can contain a much larger problem area than these models allow me to feed them in a budget friendly manner.