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

341–350 of 483 posts

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

#341

Post by retsibsi »

isoprophlex wrote: post #88

I have a very weird tangential nit to pick: gendering LLMs. I swear I'm not pushing any sort of gender agenda/discussion that can be had anytime anywhere else in the current age, but to me there is something quintessentially a-gendered about the output of a computer program. Calling Claude (or GPT-5 or Gemini or my bash terminal for that matter) a "he" seems absurd to the point of hilarity. In my mind, they've always…

Does it happen much with non-Claude models? If someone genders ChatGPT, it makes me worry that they're taking the character it's playing too literally. But if someone genders Claude, that seems pretty normal, given that it has a man's name.

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

#342

Post by FanaHOVA »

pests wrote: post #327
FanaHOVA wrote: post #133

Earlier quoted context omitted.

Are you saying that every piece of code you have ever written contains a full source list of every piece of code you previously read to learn specific languages, patterns, etc? Or are you saying that every piece of code you ever wrote was 100% original and not adapted from any previous codebase you ever worked in or any book / reference you ever read?

While I generally agree with you, this "LLM is a human" comparisons really are tiresome I feel. It hasn't been proven and I don't know how many other legal issued could have solved if adding "like a human" made it okay. Google v Oracle? "oh, you've never learned an API??!?" or take the original Google Books controversy - "its reading books and memorizing them, like humans can". I do agree its different but I don't li…

I agree, that's why I was trying to point out that saying "if a person did that we'd have a word for them" is useless. They are not people, and people don't behave like that anyway. It adds nothing to the discussion.

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

#343

Post by jasonkester »

jonplackett wrote: post #169
smoghat wrote: post #106

Earlier quoted context omitted.

That's fair. But I always think of it as an intern I am paying $20 a month for or $200 a month. I would be kind of shocked if they could do everything as well as I'd hoped for that price point. It's fascinating for me and worth the money. I am lucky that I don't depend on this for work at a corporation. I'd be pulling my hair out if some boss said "You are going to be doing 8 times as much work using our corporate AI…

Don get me wrong, doing 80% of my work for me is still great. And I’m actually quite glad I’m still needed for the other 20%

The problem is that your intern in this case is doing 1600% of the work, and now it’s your job to find and remove that extra 1520% so that you’re left with something usable.

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

#344

Post by measurablefunc »

cornel_io wrote: post #334
measurablefunc wrote: post #229

Earlier quoted context omitted.

This is known as the data processing inequality. Non-invertible functions can not create more information than what is available in their inputs: https://blog.blackhc.net/2023/08/sdpi_fsvi/ . Whatever arithmetic operations are involved in laundering the inputs by stripping original sources & references can not lead to novelty that wasn't already available in some combination of the inputs. Neural networks can at best…

Theoretical "proofs" of limitations like this are always unhelpful because they're too broad, and apply just as well to humans as they do to LLMs. The result is true but it doesn't actually apply any limitation that matters.

You're confused about what applies to people & what applies to formal systems. You will continue to be confused as long as you keep thinking formal results can be applied in informal contexts.

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

#345

Post by tovej »

handoflixue wrote: post #294
fpoling wrote: post #155

Earlier quoted context omitted.

Pick up a book about programming from seventies or eighties that was unlikely to be scanned and feed into LLM. Take a task from it and ask LLM to write a program from it that even a student can solve within 10 minutes. If the problem was not really published before, LLM fails spectacularly.

It's telling that you can't actually provide a single concrete example - because, of course, anyone skilled with LLMs would be able to trivially solve any such example within 10 minutes. Perhaps the occasional program that relies heavily on precise visual alignment will fail - but I dare say if we give the LLM the same grace we'd give a visually impaired designer, it can do exactly as well.

I recently asked an LLM to give me one of the most basic and well-documented algorithms in the world: a blocked matrix multiply. It's essentially a few nested loops and some constants for the block size.

It failed massively, spitting out garbage code, where the comments claimed to use blocking access patterns, but the code did not actually use them at all.

LLMs are, frankly, nearly useless for programming. They may solve a problem every once in a while, but once you look at the code, you notice it's either directly plagiarized or bad quality (or both, I suppose, in the latter case).

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

#346

Post by govping »

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…

The failure mode here (Claude trying to satisfy rather than saying 'this is impossible with the constraints') shows up everywhere. We use it for security research - it'll keep trying to find exploits even when none exist rather than admit defeat. The key is building external validation (does the POC actually work?) rather than trusting the LLM's confidence.

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

#347

Post by jacquesm »

marcus_holmes wrote: post #281
moron4hire wrote: post #270

Earlier quoted context omitted.

No, the thing needing proof is the novel idea: that LLMs can produce original code.

LLMs can definitely produce original other stuff: ask it to create an original poem and on an extremely specific niche subject and it will do so. You can specify the niche subject to the point where it is incredibly unlikely that there is a poem on that subject in its training data, and it will still produce an original poem on that subject [0]. The well-known "otter using wifi on a plane" series of images [1] is ano…

No, it transformed your prompt. Another person giving it the same prompt will get the same result when starting from the same state. f('your prompt here') is a transformation of your prompt based on hidden state.

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

#348

Post by tovej »

Aeolun wrote: post #164
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.

Software engineer? You think I cite all the code I’ve ever seen before when I reproduce it? That I even remember where it comes from?

You don't?

If you reproduce something, usually you have to check the earlier implementation for it and copy it over. This would inevitably require you to look at the license and author of said code.

Assuming of course, you're talking about nontrivial functionality, because obviously we're not talking about trivial one-liners etc.

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

#349

Post by tovej »

DangitBobby wrote: post #156
jacquesm wrote: post #146

Earlier quoted context omitted.

What's with the bad takes in this thread. That's two strawmen in one comment, it's getting a bit crowded.

Or the original point doesn't actually hold up to basic scrutiny and is indistinguishable from straw itself.

The original point, that LLMs are plagiarising inputs, is a very common and common sense opinion.

There are court cases where this is being addressed currently, and if you think about how LLMs operate, a reasonable person typically sees that it looks an awful lot like plagiarism.

If you want to claim it is not plagiarism, that requires a good argument, because it is unclear that LLMs can produce novelty, since they're literally trying to recreate the input data as faithfully as possible.

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

#350

Post by littlecranky67 »

ubercow13 wrote: post #266
littlecranky67 wrote: post #93

Earlier quoted context omitted.

> Claude/LLMs in general are still pretty bad at the intricate details of layouts and visual things Because the rendered output (pixels, not HTML/CSS) is not fed as data in the training. You will find tons of UI snippets and questions, but they rarely included screenshots. And if they do, the are not scraped.

Why wouldn't they be?

Why would they be?
Post reply on HN