It is a task that could be _easily_ done manually in much shorter time without AI, probably by developers who even love to develop. The reaction on this shouldn't be misjudged as anti-AI. A lot of people, including me, just do not get it! For scientific purposes? Ok, fair enough. But what is the further meaning of this exercise?
The point is that if we agree that this task is truly a one shot, as long as you agree it’s faster to prompt than code, then while you “easily” do this task in around an hour (or however long you say it will take you), I’ll prompt Claude in around 5 minutes, and get a few more things done while I let it run in the background. What am I missing from your argument?
author here -- it took like 5 minutes of actual attention from me? I'm not sure why you are counting reading the blog post or setting up playwright. I guess I did read the blog post, but im not sure that should count. And claude set up playwright, not me.
“Setting up playwright” is about two sentences of a prompt to Claude. I know this because I’ve done it many times. The authors prompt in the post is only a few hundred words. (Most of the post is just LLM output.) I’m certain I could type that out in 5 minutes.
Do we really need another post where I time how long it takes to prompt Claude to create the Space Jam website?
> 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.
When I did it, vanilla Claude (Max5, default Opus 4.5, no special skills loaded, etc) had playwright up and running for screenshots in minutes (after intervening to tell it to use python 3.13 after noticing python 3.14 seems to be missing a lot of wheels and uv was rebuilding numpy for some reason) without me telling how to screenshot at all.
(One fun wrinkle I enjoyed watching was I created the target screenshot in Firefox, and Claude was using playwright with Chrome. Ultimately, I have no idea whether either Firefox or Chrome has the correct actual fonts and I'm not a webdev and don't remember how to figure that all out)
For me it's more that I'm not a web developer and it would definitely take me way longer to research all the parts of doing this. I have booksmarts (at best) about basic CSS and have given up trying to keep up with javascript anything.
