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

241–250 of 483 posts

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

#241

Post by doix »

nextos wrote: post #181
mlinsey wrote: post #151

Earlier quoted context omitted.

Certainly if a human wrote code that solved this problem, and a second human copied and tweaked it slightly for their use case, we would have a word for them. Would we use the same word if two different humans wrote code that solved two different problems, but one part of each problem was somewhat analogous to a different aspect of a third human's problem, and the third human took inspiration from those parts of both…

In case of LLMs, due to RAG, very often it's not just learning but almost direct real-time plagiarism from concrete sources.

Isn't RAG used for your code rather than other people's code? If I ask it to implement some algorithm, I'd be very surprised if RAG was involved.

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

#242

Post by manlymuppet »

blks wrote: post #209
manlymuppet wrote: post #199

Couldn’t you just feed Claude all the raw, inspect element HTML from the website and have it “decrypt” that? The entire website is fairly small so this seems feasible. Usually there’s a big difference between a website’s final code and its source code because of post processing but that seems like a totally solvable Claude problem. Sure LLMs aren’t great with images, but it’s not like the person who originally wrote…

What do you mean? Raw html is the original website source code. Modern web development completely poisoned young generation

I'm using source code like it's used when referring to source code vs executables. React doesn't simply spit out HTML, nor the JSX used to write said React code, it outputs a mixture of things that's the optimized HTML/CSS/JS version of the React you wrote. This is akin to source code and the optimized binaries we actually use.

Perhaps the wrong usage of "source code". I probably should've been more precise. Forgive my lack of vocabulary to describe the difference I was referring to.

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

#243

Post by manlymuppet »

personjerry wrote: post #206
manlymuppet wrote: post #199

Couldn’t you just feed Claude all the raw, inspect element HTML from the website and have it “decrypt” that? The entire website is fairly small so this seems feasible. Usually there’s a big difference between a website’s final code and its source code because of post processing but that seems like a totally solvable Claude problem. Sure LLMs aren’t great with images, but it’s not like the person who originally wrote…

If you have the raw HTML why would you need to do this at all?

I should've been more precise with my words.

What I meant is doing inspect element on the Space Jam website, and doing select all + copy.

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

#244

Post by saalweachter »

CognitiveLens wrote: post #194
whatshisface wrote: post #176

Earlier quoted context omitted.

They key difference between plagarism and building on someone's work is whether you say, "this based on code by linsey at github.com/socialnorms" or "here, let me write that for you."

but as mlinsey suggests, what if it's influenced in small, indirect ways by 1000 different people, kind of like the way every 'original' idea from trained professionals is? There's a spectrum, and it's inaccurate to claim that Claude's responses are comparable to adapting one individual's work for another use case - that's not how LLMs operate on open-ended tasks, although they can be instructed to do that and produc…

It's not uncommon, in a well-written code base, to see documentation on different functions or algorithms with where they came from.

This isn't just giving credit; it's valuable documentation.

If you're later looking at this function and find a bug or want to modify it, the original source might not have the bug, might have already fixed it, or might have additional functionality that is useful when you copy it to a third location that wasn't necessary in the first copy.

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

#245

Post by manlymuppet »

manlymuppet wrote: post #199

Couldn’t you just feed Claude all the raw, inspect element HTML from the website and have it “decrypt” that? The entire website is fairly small so this seems feasible. Usually there’s a big difference between a website’s final code and its source code because of post processing but that seems like a totally solvable Claude problem. Sure LLMs aren’t great with images, but it’s not like the person who originally wrote…

https://pastebin.com/raw/F2jxZTeJ

The HTML I'm referring to, copied from the website.

Only about 7,000 characters or just 2,000 Claude tokens. This is feasible.

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

#246

Post by martin-t »

jacquesm wrote: post #121
thuttinger wrote: post #66

Claude/LLMs in general are still pretty bad at the intricate details of layouts and visual things. There are a lot of problems that are easy to get right for a junior web dev but impossible for an LLM. On the other hand, I was able to write a C program that added gamma color profile support to linux compositors that don't support it (in my case Hyprland) within a few minutes! A - for me - seemingly hard task, which w…

Claude didn't write that code. Someone else did and Claude took that code without credit to the original author(s), adapted it to your use case and then presented it as its own creation to you and you accepted this. If a human did this we probably would have a word for them.

Programmers are willingly blind to this, at least until it's their code being stolen or they lose their job.

_LLMs are lossily compressed archives of stolen code_.

Trying to achieve AI through compression is nothing new.[0] The key innovation[1] is that the model[2] does not output only the first order input data but also the higher order patterns from the input data.

That is certainly one component of intelligence but we need to recognize that the tech companies didn't build AI, they build a compression algorithm which, combined with the stolen input text, can reproduce the input data and its patterns in an intelligent-looking way.

[0]: http://prize.hutter1.net/

[1]: Oh, god, this phrase is already triggering my generated-by-LLM senses.

[2]: Model of what? Of the stolen text. If 99.9999% of the work to achieve AI wasn't done by people whose work was stolen, they wouldn't be called models.

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

#247

Post by pastel8739 »

manlymuppet wrote: post #242
blks wrote: post #209

Earlier quoted context omitted.

What do you mean? Raw html is the original website source code. Modern web development completely poisoned young generation

I'm using source code like it's used when referring to source code vs executables. React doesn't simply spit out HTML, nor the JSX used to write said React code, it outputs a mixture of things that's the optimized HTML/CSS/JS version of the React you wrote. This is akin to source code and the optimized binaries we actually use. Perhaps the wrong usage of "source code". I probably should've been more precise. Forgive…

For a website from 1996 though, there’s a very good chance that the page source is the source code

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

#248

Post by martin-t »

bsaul wrote: post #135
jacquesm wrote: post #121

Earlier quoted context omitted.

Claude didn't write that code. Someone else did and Claude took that code without credit to the original author(s), adapted it to your use case and then presented it as its own creation to you and you accepted this. If a human did this we probably would have a word for them.

That's an interesting hypothesis : that LLM are fundamentally unable to produce original code. Do you have papers to back this up ? That was also my reaction when i saw some really crazy accurate comments on some vibe coded piece of code, but i couldn't prove it, and thinking about it now i think my intuition was wrong (ie : LLMs do produce original complex code).

The whole "reproduces training data vebatim" is a red herring.

It reproduces _patterns from the training data_, sometimes including verbatim phrases.

The work (to discover those patterns, to figure out what works and what does not, to debug some obscure heisenbug and write a blog post about it, ...) was done by humans. Those humans should be compensated for their work, not owners of mega-corporations who found a loophole in copyright.

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

#249

Post by ineedasername »

jacquesm wrote: post #121
thuttinger wrote: post #66

Claude/LLMs in general are still pretty bad at the intricate details of layouts and visual things. There are a lot of problems that are easy to get right for a junior web dev but impossible for an LLM. On the other hand, I was able to write a C program that added gamma color profile support to linux compositors that don't support it (in my case Hyprland) within a few minutes! A - for me - seemingly hard task, which w…

Claude didn't write that code. Someone else did and Claude took that code without credit to the original author(s), adapted it to your use case and then presented it as its own creation to you and you accepted this. If a human did this we probably would have a word for them.

>we probably would have a word for them

Student? Good learner? Pretty much what everyone does can be boiled down to reading lots of other code that’s been written and adapting it to a use case. Sure, to some extent models are regurgitating memorized information, but for many tasks they’re regurgitating a learned method of doing something and backfilling the specifics as needed— the memorization has been generalized.

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

#250

Post by nitwit005 »

mlinsey wrote: post #151
jacquesm wrote: post #121

Earlier quoted context omitted.

Claude didn't write that code. Someone else did and Claude took that code without credit to the original author(s), adapted it to your use case and then presented it as its own creation to you and you accepted this. If a human did this we probably would have a word for them.

Certainly if a human wrote code that solved this problem, and a second human copied and tweaked it slightly for their use case, we would have a word for them. Would we use the same word if two different humans wrote code that solved two different problems, but one part of each problem was somewhat analogous to a different aspect of a third human's problem, and the third human took inspiration from those parts of both…

Ask for something like "a first person shooter using software rendering", and search github for the function names for the rendering functions. Using Copilot I found code simply lifted from implementations of Doom, except that "int" was replaced with "int32_t" and similar.

It's also fun to tell Copilot that the code will violate a license. It will seemingly always tell you it's fine. Safe legal advice.

Post reply on HN