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

371–380 of 483 posts

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

#371

Post by yard2010 »

govping wrote: post #346
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.

Ah! I see the problem now! AI can't see shit, it's a statistical model not some form of human. It uses words, so like humans, it can say every shit it wants and it's true until you find out.

The number one rule of the internet is don't believe anything you read. This rule was lost in history unfortunately.

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

#372

Post by ettsvensktlogin »

This was very interesting. I've tried to create an "agent" Claude Code based system to generate design from screenshots, using Playwright and other tools to take screenshots for iterative improvements. So far I have failed despite weeks of struggles.

Thanks to this post I now have a deeper understanding as to why. Thank you.

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

#373

Post by icommentedtoday »

chrisco255 wrote: post #318
handedness wrote: post #311

A site in '96 would have been built largely with tables, not CSS. CSS didn't become a thing until a couple of years later. I know this because I'm still salty about the transition. For all of CSS's advantages, we lost something when we largely moved away from tables.

We lost something for a time but flex box and CSS grid (which came more recently) are objectively better than tables.

How are they objectively better? They seem way too complex for me

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

#374

Post by latexr »

tscherno wrote: post #366
latexr wrote: post #255

Earlier quoted context omitted.

What a profoundly bad faith argument. We all understand that singular words are public domain, they belong to everyone. Yet when you arrange them in a specific pattern, of which there are infinite possibilities, you create something unique. When someone copies that arrangement wholesale and claims they were the first, that’s what we refer to as plagiarism. https://www.youtube.com/watch?v=K9huNI5sBd8

It is possible that the concept of intellectual property could be classified as a mistake of our era by the history teachers of future generations.

Intellectual property is a legal concept; plagiarism is ethical. We’re discussing the latter.

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

#377

Post by fransje26 »

nitwit005 wrote: post #250
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…

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.

> 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.

Perfectly embodies the AI "startup" mentality. Nice.. /s

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

#378

Post by alternatex »

jeanlucas wrote: post #132
DocTomoe wrote: post #105

Earlier quoted context omitted.

Which would also render differently on every machine, based on browser settings, screen sizes, and available fonts. Like the web was meant to be. An interpreted hypertext format, not a pixel-perfect brochure for marketing execs.

>Like the web was meant to be. what?

Presumably written by a person who wasn't a web developer back then or were developing solely for Internet Explorer.

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

#379

Post by aprilfoo »

liampulles wrote: post #359

It seems to me that Claude's error here (which is not unique to it) is self-sycophancy. The model is too eager to convince itself it did a good job. I'd be curious to hear from experienced agent users if there is some AGENTS.md stuff to make the LLM more clear speaking? I wonder if that would impact the quality of work.

> It seems to me that Claude's error here (which is not unique to it) is self-sycophancy. The model is too eager to convince itself it did a good job.

It seems this applies to the whole AI industry, not just LLMs.

Post reply on HN