Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I failed to recreate the 1996 Space Jam website with Claude

j0nah.com

Post reply on HN
Print view View original

41–50 of 483 posts

Re: I failed to recreate the 1996 Space Jam website with Claude

#41

Post by swatcoder »

thecr0w wrote: post #10
999900000999 wrote: post #9

Space Jam website design as an LLM benchmark. This article is a bit negative. Claude gets close , it just can't get the order right which is something OP can manually fix. I prefer GitHub Copilot because it's cheaper and integrates with GitHub directly. I'll have times where it'll get it right, and times when I have to try 3 or 4 times.

ya, this is true. Another commenter also pointed out that my intention was to one-shot. I didn't really go too deeply into trying to try multiple iterations. This is also fairly contrived, you know? It's not a realistic limitation to rebuild HTML from a screenshot because of course if I have the website loaded I can just download the HTML.

> rebuild HTML from a screenshot

???

This is precisely the workflow when a traditional graphic designer mocks up a web/app design, which still happens all the time.

They sketch a design in something like Photoshop or Illustrator, because they're fluent in these tools and many have been using them for decades, and somebody else is tasked with figuring out how to slice and encode that design in the target interactive tech (HTML+CSS, SwiftUI, QT, etc).

Large companies, design agencies, and consultancies with tech-first design teams have a different workflow, because they intentionally staff graphic designers with a tighter specialization/preparedness, but that's a much smaller share of the web and software development space than you may think.

There's nothing contrived at all about this test and it's a really great demonstration of how tools like Claude don't take naturally to this important task yet.

Re: I failed to recreate the 1996 Space Jam website with Claude

#42

Post by smoghat »

Ok, so here is an interesting case where Claude was almost good enough, but not quite. But I’ve been amusing myself by taking abandoned Mac OS programs from 20 years ago that I find on GitHub and bringing them up to date to work on Apple silicon. For example, jpegview, which was a very fast and simple slideshow viewer. It took about three iterations with Claude code before I had it working. Then it was time to fix some problems, add some features like playing videos, a new layout, and so on. I may be the only person in the world left who wants this app, but well, that was fine for a day long project that cooked in a window with some prompts from me while I did other stuff. I’ll probably tackle scantailor advanced next to clean up some terrible book scans. Again, I have real things to do with my time, but each of these mini projects just requires me to have a browser window open to a Claude code instance while I work on more attention demanding tasks.

Re: I failed to recreate the 1996 Space Jam website with Claude

#44

Post by thecr0w »

sigseg1v wrote: post #19

Curious if you've tested something such as: - "First, calculate the orbital radius. To do this accurately, measure the average diameter of each planet, p, and the average distance from the center of the image to the outer edge of the planets, x, and calculate the orbital radius r = x - p" - "Next, write a unit test script that we will run that reads the rendered page and confirms that each planet is on the orbital ra…

Hm, I didn't try exactly this, but I probably should!

Wrt unit test script, let's take Claude out of the equation, how would you design the unit test? I kept running into either Claude or some library not being capable of consistently identifying planet vs non planet which was hindering Claude's ability to make decisions based on fine detail or "pixel coordinates" if that makes sense.

Re: I failed to recreate the 1996 Space Jam website with Claude

#45

Post by thecr0w »

swatcoder wrote: post #41
thecr0w wrote: post #10

Earlier quoted context omitted.

ya, this is true. Another commenter also pointed out that my intention was to one-shot. I didn't really go too deeply into trying to try multiple iterations. This is also fairly contrived, you know? It's not a realistic limitation to rebuild HTML from a screenshot because of course if I have the website loaded I can just download the HTML.

> rebuild HTML from a screenshot ??? This is precisely the workflow when a traditional graphic designer mocks up a web/app design, which still happens all the time . They sketch a design in something like Photoshop or Illustrator, because they're fluent in these tools and many have been using them for decades, and somebody else is tasked with figuring out how to slice and encode that design in the target interactive…

You know, you're totally right and I didn't even think about that.

Re: I failed to recreate the 1996 Space Jam website with Claude

#46

Post by wanderingstan »

thecr0w wrote: post #7
lagniappe wrote: post #4

Earlier quoted context omitted.

We actually had a myriad of competing specs. CSS proper wasn't released until december 1996.

Any names for the competing specs? Maybe i could try re-prompting with that direction.

There were specs competing for adoption, but only tables (the old way) and CSS were actually adopted by browsers. So no point trying to use some other positioning technique.

Re: I failed to recreate the 1996 Space Jam website with Claude

#49

Post by daemonologist »

Lerc wrote: post #32
daemonologist wrote: post #24

Interesting - these models are all trained to do pixel-level(ish) measurement now, for bounding boxes and such. I wonder if you could railroad it into being accurate with the right prompt.

What models are good at this? I have tried passing images to models and asking them for coordinates for specific features, then overlaid dots on those points and passed that image back to the model so it has a perception of how far out it was. It had a tendency to be consistently off by a fixed amount without getting closer. I don't doubt that it is possible eventually, but I haven't had much luck. Something that see…

I've found Qwen3-VL to be fairly accurate at detection (though it doesn't always catch every instance). Note that it gives answers as per-mille-ages, as if the image was 1000x1000 regardless of actual resolution or aspect ratio.

I have also not had luck with any kind of iterative/guess-and-check approach. I assume the models are all trained to one-shot this kind of thing and struggle to generalize to what are effectively relative measurements.

Post reply on HN