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

51–60 of 483 posts

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

#51

Post by egeozcan »

smoghat wrote: post #42

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 so…

Side note: As a person who started using a mac since march, I found phoenix slides really good.

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

#52

Post by docheinestages »

> Note: please help, because I'd like to preserve this website forever and there's no other way to do it besides getting Claude to recreate it from a screenshot.

Why not use wget to mirror the website? Unless you're being sarcastic.

$ wget --mirror --convert-links --adjust-extension --page-requisites --no-parent http://example.org

Source: https://superuser.com/questions/970323/using-wget-to-copy-we...

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

#53

Post by thecr0w »

docheinestages wrote: post #52

> Note: please help, because I'd like to preserve this website forever and there's no other way to do it besides getting Claude to recreate it from a screenshot. Why not use wget to mirror the website? Unless you're being sarcastic. $ wget --mirror --convert-links --adjust-extension --page-requisites --no-parent http://example.org Source: https://superuser.com/questions/970323/using-wget-to-copy-we...

The stuff about not being able to download it is a bit of a joke and I don't think the tone landed with everybody haha. This was just an experiment to see if Claude could recreate a simple website from a screenshot, of course to your point you could download it if you wanted.

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

#54

Post by malfist »

docheinestages wrote: post #52

> Note: please help, because I'd like to preserve this website forever and there's no other way to do it besides getting Claude to recreate it from a screenshot. Why not use wget to mirror the website? Unless you're being sarcastic. $ wget --mirror --convert-links --adjust-extension --page-requisites --no-parent http://example.org Source: https://superuser.com/questions/970323/using-wget-to-copy-we...

Because that wasn't the goal of this exercise

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

#55

Post by dcanelhas »

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.

Even with text, parsing content in 2D seems to be a challenge for every LLM I have interacted with. Try getting a chatbot to make an ascii-art circle with a specific radius and you'll see what I mean.

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

#56

Post by bigstrat2003 »

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.

> it just can't get the order right which is something OP can manually fix.

If the tool needs you to check up on it and fix its work, it's a bad tool.

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

#57

Post by sdenton4 »

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.

Feels like the "right" approach would be to have it write some code to measure how far off the elements are in the original vs recreated image, and then iterate using the numerical output of the program...

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

#59

Post by markbao »

bigstrat2003 wrote: post #56
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.

> it just can't get the order right which is something OP can manually fix. If the tool needs you to check up on it and fix its work, it's a bad tool.

“Bad” seems extreme. The only way to pass the litmus test you’ve described is for a tool to be 100% perfect, so then the graph looks like 99.99% “bad tool” until it reaches 100% perfection.

It’s not that binary imo. It can still be extremely useful and save a ton of time if it does 90% of the work and you fix the last 10%. Hardly a bad tool.

It’s only a bad tool if you spent more time fixing the results than building it yourself, which sometimes used to be the case for LLMs but is happening less and less as they get more capable.

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

#60

Post by th0ma5 »

I personally don't understand why asking these things to do things we know they can't do is supposed to be productive. Maybe for getting around restrictions or fuzzing... I don't see it as an effective benchmark unless it can link directly to the ways the models are being improved, but, to look at random results that sometimes are valid and think more iterations of randomness will eventually give way to control is a maddening perspective to me, but perhaps I need better language to describe this.
Post reply on HN