The requirements didn’t really change, opus just couldn’t see all the real world potential issues with its various suggestions.
But it was helpful for me to talk it out. So I guess it fell in the (very) slow category of productive use.
You do have to be very careful of when the AI might be confidently wrong, or leading you down some kind of weird narrow path.
When searching the web to gather info on a topic, all have a tendency to find 2-4 search results and fixate on those as if they represented the entire scope of the topic. No surprise about the fixation because that's kind of how LLMs work (X, Y, and Z are in context -> more tokens about X, Y, and Z). But you have to be aware of it, and I often have to prompt it to do another search and keep turning up more options.
Unfortunately this recent experience wasn’t that as much as it producing rapid-fire misses when it did have the constraints. It regularly just violated X to kinda-solve Y. Or made up a solution to both that solves neither. And this wasn’t some wildly complicated scenario.
Sure made me solidify some opinions (we ended up pretty close to where I had started without it), but woo-boy… it was a painful journey.