I failed to recreate the 1996 Space Jam website with Claude
1–10 of 483 posts
Re: I failed to recreate the 1996 Space Jam website with Claude
#2I'm curious. Did you ask it to use tables and no CSS?
In 1996, We had only css1. Ask it to use tables to do this, perhaps.
Re: I failed to recreate the 1996 Space Jam website with Claude
#3Claude 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.
Re: I failed to recreate the 1996 Space Jam website with Claude
#4I'm curious. Did you ask it to use tables and no CSS? In 1996, We had only css1. Ask it to use tables to do this, perhaps.
We actually had a myriad of competing specs. CSS proper wasn't released until december 1996.
Re: I failed to recreate the 1996 Space Jam website with Claude
#5Somehow 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 demonstration of Claude's poor spatial reasoning skills. Another good demonstration of this is the twitch.tv/ClaudePlaysPokemon where Claude has been failing to beat pokemon for months now.
Re: I failed to recreate the 1996 Space Jam website with Claude
#6I'm curious. Did you ask it to use tables and no CSS? In 1996, We had only css1. Ask it to use tables to do this, perhaps.
Yes yes great question!
I tried your suggestion and also tried giving it various more general versions of the limitations presented by earlier generations.
Claude's instinct initially was actually to limit itself to less modern web standards.
Unfortunately, nothing got those planets to be in the right place.
Re: I failed to recreate the 1996 Space Jam website with Claude
#7I'm curious. Did you ask it to use tables and no CSS? In 1996, We had only css1. Ask it to use tables to do this, perhaps.
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.
Re: I failed to recreate the 1996 Space Jam website with Claude
#8Somehow 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…
Not a homework assignment, and no deliberate attempt to conceal information, just very long and repetitive logs. A lot of the same "insights" so I just didn't provide them here.
> That's not how to successfully use LLM's for coding in my experience.
Yeah agree. I think I was just a little surprised it couldn't one-shot given the simplicity.
Re: I failed to recreate the 1996 Space Jam website with Claude
#9Space 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.
Re: I failed to recreate the 1996 Space Jam website with Claude
#10Space 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.