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

211–220 of 483 posts

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

#211

Post by torginus »

Not sure how good Claude is nowadays, but I remember using Claude 3.5 to do some fiction writing and for a while I thought it was amazing at coming up with plots, setting ideas, writing witty dialogue - then after a short while I noticed it kept recycling the same ideas, phrases etc, quickly becoming derivative, and having 'tells', similar to the group of 3 quirk, with some otherwise decent writing patterns showing up with great frequency.

I've heard the same thing about it doing frontends - it produces gorgeous websites but it has similar 'tells', it does CSS and certain features the same way, and if you have a very concrete idea of what you want out of it, you'll end up fighting an uphill battle with it constantly trying to do things its own way.

Which is part of the 'LLM illusion' - I guess. To an unskilled individual, or when starting from scratch, it seems great, but the more complex the project gets, the harder it becomes to have it contribute meaningfully, leading to an ever-mounting frustration, and eventually me just giving up and doing it by hand.

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

#213

Post by naet »

ErrantX wrote: post #149

I just feel this is a great example of someone falling into the common trap of treating an LLM like a human. They are vastly less intelligent than a human and logical leaps that make sense to you make no sense to Claude. It has no concept of aesthetics or of course any vision. All that said; it got pretty close even with those impediments! (It got worse because the writer tried to force it to act more like a human wo…

The blog frequently refers to the LLM as "him" instead of "it" which somehow feels disturbing to me.

I love to anthropomorphize things like rocks or plants, but something about doing it to an AI that responds in human like language enters an uncanny valley or otherwise upsets me.

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

#214

Post by thecr0w »

fnordpiglet wrote: post #31
Wowfunhappy wrote: post #3

Claude is not very good at using screenshots. The model may technically be multi-modal, but its strength is clearly in reading text. I'm not surprised it failed here.

Especially since it decomposes the image into a semantic vector space rather than the actual grid of pixels. Once the image is transformed into patch embeddings all sense of pixels is entirely destroyed. The author demonstrates a profound lack of understanding for how multimodal LLMs function that a simple query of one would elucidate immediately. The right way to handle this is not to build it grids and whatnot, whi…

Great, thanks for that suggestion!

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

#215

Post by johnebgd »

wilsmex wrote: post #187

Well this was interesting. As someone who was actually building similar website in the late 90's I threw this into the Opus 4.5. Note the original author is wrong about the original site however: "The Space Jam website is simple: a single HTML page, absolute positioning for every element, and a tiling starfield GIF background.". This is not true, the site is built using tables, not positioning at all, CSS wasn't a th…

I cut my teeth developing for the web using GoLive and will never forget how they used tables to layout a page from that tool…

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

#216

Post by thecr0w »

mcbuilder wrote: post #83
fnordpiglet wrote: post #31

Earlier quoted context omitted.

Especially since it decomposes the image into a semantic vector space rather than the actual grid of pixels. Once the image is transformed into patch embeddings all sense of pixels is entirely destroyed. The author demonstrates a profound lack of understanding for how multimodal LLMs function that a simple query of one would elucidate immediately. The right way to handle this is not to build it grids and whatnot, whi…

Yeah, this is exactly what I was thinking. LLMs don't have precise geometrical reasoning from images. Having an intuition of how the models work is actually.a defining skill in "prompt engineering"

Yeah, still trying to build my intuition. Experiments/investigations like this help me. Any other blogs or experiments you'd suggest?

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

#217

Post by thecr0w »

manbash wrote: post #202
wilsmex wrote: post #187

Well this was interesting. As someone who was actually building similar website in the late 90's I threw this into the Opus 4.5. Note the original author is wrong about the original site however: "The Space Jam website is simple: a single HTML page, absolute positioning for every element, and a tiling starfield GIF background.". This is not true, the site is built using tables, not positioning at all, CSS wasn't a th…

Ah, those days, where you would slice your designs and export them to tables.

I learned recently that this is still how a lot of email html get generated.

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

#218

Post by gregoryl »

manbash wrote: post #202
wilsmex wrote: post #187

Well this was interesting. As someone who was actually building similar website in the late 90's I threw this into the Opus 4.5. Note the original author is wrong about the original site however: "The Space Jam website is simple: a single HTML page, absolute positioning for every element, and a tiling starfield GIF background.". This is not true, the site is built using tables, not positioning at all, CSS wasn't a th…

Ah, those days, where you would slice your designs and export them to tables.

Gosh, there was a website, where you submit a PSD + payment, and they spit out a sliced design. Initially tables, later, CSS. Life saver.

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

#219

Post by tyre »

torginus wrote: post #211

Not sure how good Claude is nowadays, but I remember using Claude 3.5 to do some fiction writing and for a while I thought it was amazing at coming up with plots, setting ideas, writing witty dialogue - then after a short while I noticed it kept recycling the same ideas, phrases etc, quickly becoming derivative, and having 'tells', similar to the group of 3 quirk, with some otherwise decent writing patterns showing u…

My boy loves a neon gradient.

To be fair, a lot of startup websites look very similar. And the number of Stripe blurples out there was a pre-LLM brand meme.

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

#220

Post by thecr0w »

cfbradford wrote: post #96
thecr0w wrote: post #44

Earlier quoted context omitted.

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.

Do you give Claude the screenshot as a file? If so I’d just ask it to write a tool to diff each asset to every possible location in the source image to find the most likely position of each asset. You don’t really need recognition if you can brute force the search. As a human this is roughly what I would do if you told me I needed to recreate something like that with pixel perfect precision.

Ok! will give it a shot. In a few iterations I gave him screenshots, i have given him the ability to take screenshots, and I gave him the Playwright MCP. I kind of gave up on the path you're suggesting (though I didn't get super far along) because I felt like I would run into this problem eventually of needing a model to figure out what a planet is, where the edge of the planet is, etc.

But if that could be done deterministically, I totally agree this is the way to go. I'll put some more time into it over the next couple weeks.

Post reply on HN