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

11–20 of 483 posts

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

#11

Post by CharlesW »

throwaway314155 wrote: post #5

Somehow I suspect Claude Code (in an interactive session with trial, error, probing, critiquing, perusing, and all the other benefits you get) would do better. This example seems to assume Claude can do things in "one shot" (even the later attempts all seem to conceal information like it's a homework assignment). That's not how to successfully use LLM's for coding in my experience. It is however perhaps a good demons…

Using https://github.com/anthropics/claude-code/tree/main/plugins/... with style-supporting instructions and context would've improved the outcome as well.

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

#12

Post by thecr0w »

CharlesW wrote: post #11
throwaway314155 wrote: post #5

Somehow I suspect Claude Code (in an interactive session with trial, error, probing, critiquing, perusing, and all the other benefits you get) would do better. This example seems to assume Claude can do things in "one shot" (even the later attempts all seem to conceal information like it's a homework assignment). That's not how to successfully use LLM's for coding in my experience. It is however perhaps a good demons…

Using https://github.com/anthropics/claude-code/tree/main/plugins/... with style-supporting instructions and context would've improved the outcome as well.

thank you! I'll try this

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

#13

Post by lagniappe »

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.

Models are trained with content scraped from the net, for the most part. The availability of content pertaining to those specs is almost nil, and of no SEO value. Ergo, models for the most part will only have a cursory knowledge of a spec that your browser will never be able to parse because that isn't the spec that won.

Nonetheless, here is a link to a list of the specs you asked for: https://www.w3.org/Style/History/Overview.en.html

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

#16

Post by WhyOhWhyQ »

supern0va wrote: post #14

Honestly, if you had showed this article to me even eighteen months ago, I would have been blown away at how good of a job Claude did. It's remarkable how high our expectations have been steadily creeping.

This comment is missing the point. The real goal of all this is not to amaze. It's to create better software. Let's graduate past the amazement phase into the realism phase as soon as possible. What parts of my project is the LLM for? That is the real question worth asking.

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

#17

Post by supern0va »

WhyOhWhyQ wrote: post #16
supern0va wrote: post #14

Honestly, if you had showed this article to me even eighteen months ago, I would have been blown away at how good of a job Claude did. It's remarkable how high our expectations have been steadily creeping.

This comment is missing the point. The real goal of all this is not to amaze. It's to create better software. Let's graduate past the amazement phase into the realism phase as soon as possible. What parts of my project is the LLM for? That is the real question worth asking.

Oh, to be clear, this isn't a criticism. I think it's super cool that we're moving onto the nitpick/refinement phase of this tech. :)

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

#18

Post by smallnix »

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.

That's not the point of the article. It's about Claude/LLM being overconfident in recreating pixel perfect.

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

#19

Post by sigseg1v »

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 radius. If a planet is not, output the difference you must shift it by to make the test pass. Use this feedback until all planets are perfectly aligned."

Post reply on HN