Yes, LLMs are way to literal - it is a problem.
Claude can right great code, but it’ll throw comments into the code about why we chose this approach instead of the random one I discussed with it - when the comment is of no use to a future developer.
It points at some sort of theory of mind problem in LLMs imo.
I think these videos are actually a good representation of vibe coding... If you let the agent do its own thing, it works... but once you start looking at the details (just like in the video) you can see where the issues are.