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

151–160 of 483 posts

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

#151

Post by mlinsey »

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.

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 solutions to create code that solved a third problem?

What if it were ten different humans writing ten different-but-related pieces of code, and an eleventh human piecing them together? What if it were 1,000 different humans?

I think "plagiarism", "inspiration", and just "learning from" fall on some continuous spectrum. There are clear differences when you zoom out, but they are in degree, and it's hard to set a hard boundary. The key is just to make sure we have laws and norms that provide sufficient incentive for new ideas to continue to be created.

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

#152

Post by godelski »

GeoAtreides wrote: post #33
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.

>which is something OP can manually fix what if the LLM gets something wrong that the operator (a junior dev perhaps) doesn't even know it's wrong? that's the main issue: if it fails here, it will fail with other things, in not such obvious ways.

I think that's the main problem with them. It is hard to figure out when they're wrong.

As the post shows, you can't trust them when they think they solved something but you also can't trust them when they think they haven't[0]. The things are optimized for human preference, which ultimately results in this being optimized to hide mistakes. After all, we can't penalize mistakes in training when we don't know the mistakes are mistakes. The de facto bias is that we prefer mistakes that we don't know are mistakes than mistakes that we do[1].

Personally I think a well designed tool makes errors obvious. As a tool user that's what I want and makes tool use effective. But LLMs flip this on the head, making errors difficult to detect. Which is incredibly problematic.

[0] I frequently see this in a thing it thinks is a problem but actually isn't, which makes steering more difficult.

[1] Yes, conceptually unknown unknowns are worse. But you can't measure unknown unknowns, they are indistinguishable from knowns. So you always optimize deception (along with other things) when you don't have clear objective truths (most situations).

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

#154

Post by epgui »

manmal wrote: post #153

I would put Claude into a loop and let it make screenshots itself, diffing them against the original screenshot, until it has found the right arrangement at the planets‘ starting position (pixel perfect match).

At that point you may as well just do the work yourself.

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

#155

Post by fpoling »

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).

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.

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

#156

Post by DangitBobby »

jacquesm wrote: post #146
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?

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.

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

#157

Post by hooo »

epgui wrote: post #154
manmal wrote: post #153

I would put Claude into a loop and let it make screenshots itself, diffing them against the original screenshot, until it has found the right arrangement at the planets‘ starting position (pixel perfect match).

At that point you may as well just do the work yourself.

Why? Just give it access to the playwright mcp server.

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

#158

Post by crawshaw »

fpoling wrote: post #155
bsaul wrote: post #135

Earlier quoted context omitted.

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).

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.

This does not appear to be true. Six months ago I created a small programming language. I had LLMs write hundreds of small programs in the language, using the parser, interpreter, and my spec as a guide for the language. The vast majority of these programs were either very close or exactly what I wanted. No prior source existed for the programming language because I created it whole cloth days earlier.

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

#159

Post by fluidcruft »

manmal wrote: post #153

I would put Claude into a loop and let it make screenshots itself, diffing them against the original screenshot, until it has found the right arrangement at the planets‘ starting position (pixel perfect match).

I would try giving it a tool to work with projections and process axis by axis to see if it works better in 1D than 2D. I dunno how clever claude is about signal processing though. There's no noise here so... I mean really it's just template matching without rotation and without noise so... But I doubt claude can do or reason about basic image processing.

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

#160

Post by ekropotin »

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.

> If a human did this we probably would have a word for them.

What do you mean? The programmers work is literally combining the existing patterns into solutions for problems.

Post reply on HN