Comment by Aldipower
2 days ago
> But which takes longer: learning all of web dev to code the site, or learning to tell Claude to doff pixels?
As a developer, I naturally prefer the former over the latter, as this becomes general programming knowledge that I can benefit from in later projects.
BTW one of the creators of the Space Jam Website left a comment on the blog post: " Sebastien Derenoncourt 20m
I must say as a person who worked on that original website, I am confused why you needed claude to do so much basic HTML/css we didn't even use tons of complex CSS until much later in time... "
If we both agree that prompting is net positive on time, I think we’re in agreement. You are trying to move the discussion to some sort of philosophical point about knowledge gain and subjective experience, but that is definitely not what I was going for.
I do not try to move anything, if you read my initial post.
And after I have seen the final result coming from Claude, which is linked now in the blog post, I must say, recreation not completed! A lot of things are missing, proper zoom behavior, window resize, correct center aligned positioning. So what's the point here anyway?
The original post that failed to create the Space Jam had no comments on a lack of "proper zoom behavior" or "window resize". It said that the LLM failed to place the elements on the page. The LLM has now solved that problem.
You are repeatedly trying to change the criteria to be different than what it contextually was. "It's not a perfect solution because as a developer I would not get benefit from this." "It's not a perfect solution because it doesn't handle <thing which was never enumerated as a success criteria>". None of that was a topic in the original blog post.
You can make another blog post, if you like, about how Claude can't handle proper zoom when creating the Space Jam website. My guess is someone will one-shot that too.