- Read an .icc file from disk
- parsed the file and extracted the VCGT (video card gamma table)
- wrote the VCGT to the video card for a specified display via amdgpu driver APIs
The only thing I had to fix was the ICC parsing, where it would parse header strings in the wrong byte-order (they are big-endian).
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.
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).
What do you mean? The programmers work is literally combining the existing patterns into solutions for problems.
I don’t think it’s fair to call someone who used Stack Overflow to find a similar answer with samples of code to copy to their project an asshole.
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.
> took that code without credit to the original author(s), adapted it to your use case
Aka software engineering.
Humans do this all the time.
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?
_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.
Who?
Not to mention the moral vagaries of "if you use a library, is the complete articulation of your thing actually 100% your code?"
Is there a difference between loading and using a function from ImageMagick, and a standalone copycat function that mimics a function from ImageMagick?
What if you need it transliterated from one language to another?
Is it really that different than those 1200 page books from the 90's that walk you through implementing a 3D engine from scratch (or whatever the topic might be)? If you make a game on top of that book's engine, is your game truly yours?
If you learn an algorithm in some university class and then just write it again later, is that code yours? What if your code is 1-for-1 a copy of the code you were taught?
It gets very murky very quick!
Obviously I would encourage proper citation, but I also recognize the reality of this stuff -- what if you're fully rewriting something you learned decades ago and don't know who to cite? What if you have some code snippet from a website long forgotten that you saved and used? What if you use a library that also uses a library that you're not aware of because you didn't bother to check, and you either cite the wrapper lib or cite nothing at all?
I don't have some grand theory or wise thoughts about this shit, and I enjoy the anthropological studies trying to ascertain provenance / assign moral authority to remarkable edge cases, but end of the day I also find it exhausting to litigate the use of a tool that exploited the fact that your code got hoovered up by a giant robot because it was public, and might get regurgitated elsewhere.
To me, this is the unfortunate and unfair story of Gregory Coleman [0] -- drummer for The Winstons, who recorded "Amen, Brother" in 1969 (which gave us the most-sampled drum break in the world, spawned multiple genres of music, and changed human history) -- the man never made a dime from it, never even knew, and died completely destitute, despite his monumental contribution to culture. It's hard to reconcile the unjustness of it all, yet not that hard to appreciate the countless positive things that came out of it.
I don't know. I guess at the end of the day, does the end justify the means? Feels pretty subjective!
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.
"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 thing back then...
Here was its one-shot attempt at building the same type of layout (table based) with a screenshot and assets as input: https://i.imgur.com/fhdOLwP.png
I'm keeping it in for now because people have made some good jokes about the mistake in the comments and I want to keep that context.
The number one rule of the internet is don't believe anything you read. This rule was lost in history unfortunately.
Still works, only Claude can not understand what those tables means.
But then DreamWeaver came out, where you basically drew the entire page in 2D and it spat out some HTML tables that stitched it all back together again, and the freedom it gave our artists in drawing in 2D and not worrying about the output meant they went completely overboard with it and you'd get lots of tiny little slices everywhere.
Definitely glad those days are well behind us now!
But was Space Jam using multiple images or just one large image with and image map for links?
I think it's easier if you adapt and get a VPN or a new government.
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.
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.
the same thing that always happens if a dev gets something wrong without even knowing it's wrong - either code review/QA catches it, or the user does, and a ticket is created
>if it fails here, it will fail with other things, in not such obvious ways.
is infallibility a realistic expectation of a software tool or its operator?
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).
I've tried these tools a number of times and spent a good bit of effort on learning to maximize the return. By the time you know what prompt to write you've solved the problem yourself.
If the tool needs you to check up on it and fix its work, it's a bad tool.
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.
All tools have failure modes and truthfully you always have to check the tool's work (which is your work). But being a master craftsman is knowing all the nuances behind your tools, where they work, and more importantly where they don't work.
That said, I think that also highlights the issue with LLMs and most AI. Their failure modes are inconsistent and difficult to verify. Even with agents and unit tests you still have to verify and it isn't easy. Most software bugs are created from subtle things, often which compound. Which both those things are the greatest weaknesses of LLMs: nuance and compounding effects.
So I still think they aren't great tools, but I do think they can be useful. But that also doesn't mean it isn't common for people to use them well outside the bounds of where they are generally useful. It'll be fine a lot of times, but the problem is that it is like an alcohol fire[0]; you don't know what's on fire because it is invisible. Which, after all, isn't that the hardest part of programming? Figuring out where the fire is?
This is also fairly contrived, you know? It's not a realistic limitation to rebuild HTML from a screenshot because of course if I have the website loaded I can just download the HTML.
???
This is precisely the workflow when a traditional graphic designer mocks up a web/app design, which still happens all the time.
They sketch a design in something like Photoshop or Illustrator, because they're fluent in these tools and many have been using them for decades, and somebody else is tasked with figuring out how to slice and encode that design in the target interactive tech (HTML+CSS, SwiftUI, QT, etc).
Large companies, design agencies, and consultancies with tech-first design teams have a different workflow, because they intentionally staff graphic designers with a tighter specialization/preparedness, but that's a much smaller share of the web and software development space than you may think.
There's nothing contrived at all about this test and it's a really great demonstration of how tools like Claude don't take naturally to this important task yet.
- "First, calculate the orbital radius. To do this accurately, measure the average diameter of each planet, p, and the average distance from the center of the image to the outer edge of the planets, x, and calculate the orbital radius r = x - p"
- "Next, write a unit test script that we will run that reads the rendered page and confirms that each planet is on the orbital radius. If a planet is not, output the difference you must shift it by to make the test pass. Use this feedback until all planets are perfectly aligned."
One of the keys to being productive with LLMs is learning how to recognize when it's going to take much more effort to babysit the LLM into getting the right result as opposed to simply doing the work yourself.
Wrt unit test script, let's take Claude out of the equation, how would you design the unit test? I kept running into either Claude or some library not being capable of consistently identifying planet vs non planet which was hindering Claude's ability to make decisions based on fine detail or "pixel coordinates" if that makes sense.
That said, I love this project. haha
The loop here, imo, refers to the feedback loop. And it's true that ideally there should be no human involvement there. A tight feedback loop is as important for llms as it is for humans. The more automated you make it, the better.
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 the Space Jam website was meticulously messing around with positioning from a reference image to create a circular orbit — they just used the tools they had to create an acceptable result. Claude can do the same.
Perhaps the best method is to re-create, rather than replicate the design.
Modern web development completely poisoned young generation
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.
What I meant is doing inspect element on the Space Jam website, and doing select all + copy.
The HTML I'm referring to, copied from the website.
Only about 7,000 characters or just 2,000 Claude tokens. This is feasible.
<https://pubs.opengroup.org/onlinepubs/9799919799/utilities/c...>
CSS didn't exist.
You say that as if that’s uncommon.
Absolute positioning wasn't available until CSS2 in 1998. This is just a table with crafty use of align, valign, colspan, and rowspan.
I'm keeping it in for now because have made some good jokes about the mistake in the comments and I want to keep that context.
Like the web was meant to be. An interpreted hypertext format, not a pixel-perfect brochure for marketing execs.
(Fun fact, the most amazing layout foot-guns, then: Effective font sizes and line-heights are subject to platform and configuration (e.g., Win vs Mac); Netscape does paragraph spacing at 1.2em, IE at 1em (if this matters, prefer `<br>` over paragraphs); frames dimensions in Netscape are always calculated as integer percentages of window dimensions, even if you provide absolute dimensions in pixels, while IE does what it says on the tin (a rare example), so they will be the same only by chance and effective rounding errors. And, of course, screen gamma is different on Win and Mac, so your colors will always be messed up – aim for a happy medium.)
The right way to handle this is not to build it grids and whatnot, which all get blown away by the embedding encoding but to instruct it to build image processing tools of its own and to mandate their use in constructing the coordinates required and computing the eccentricity of the pattern etc in code and language space. Doing it this way you can even get it to write assertive tests comparing the original layout to the final among various image processing metrics. This would assuredly work better, take far less time, be more stable on iteration, and fits neatly into how a multimodal agentic programming tool actually functions.
They are vastly less intelligent than a human and logical leaps that make sense to you make no sense to Claude. It has no concept of aesthetics or of course any vision.
All that said; it got pretty close even with those impediments! (It got worse because the writer tried to force it to act more like a human would)
I think a better approach would be to write a tool to compare screenshots, identity misplaced items and output that as a text finding/failure state. claude will work much better because your dodging the bits that are too interpretive (that humans rock at and LLMs don't)
I would more phrase it like that they are a completely alien “intelligence” that cant really be compared to human intelligence
They model what looks like intelligence but with very hard limits. The two advantages they have over human brains are perfect recall and data storage. They are also faster.
But the brain is vastly more intelligent:
- It can learn concepts (e.g. language) with an order of magnitude less information
- It responds in parallel to multiple formats of stimuli (e.g. sight/sound)
- LLMs lack the ability to generalise
- The brain interprets and understands what it experienced
That's just the tip of the iceberg. Don't get me wrong: I use AI, it is by far some of the most impressive tech we have built so far, and it has potential to advance society significantly.
But it is definitely, vastly, less intelligent than us.
I love to anthropomorphize things like rocks or plants, but something about doing it to an AI that responds in human like language enters an uncanny valley or otherwise upsets me.
I don't doubt that it is possible eventually, but I haven't had much luck.
Something that seemed to assist was drawing a multi coloured transparent chequerboard, if the AI knows the position of the grid colours it can pick out some relative information from the grid.
I have also not had luck with any kind of iterative/guess-and-check approach. I assume the models are all trained to one-shot this kind of thing and struggle to generalize to what are effectively relative measurements.
And
> I'm an engineering manager
I can't tell if this is an intentional or unintentional satire of the current state of AI mandates from management.
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 firmly been "it"s.
In other languages, chairs have a gender, along with other everyday items like scissors and it doesn't especially make logical sense, although you can squint and tell a story as why something is the gender that's been assigned. Thus making the gender of AI simply a matter"that's just how things are".
> What he produces
I feel like personifying LLMs more than they currently are is a mistake people make (though humans always do this), they're not entities, they don't know anything. If you treat them too human you might eventually fool yourself a little too much.
Aside from that point: if you are reading this and making people do a project as part of the hiring process, you should absolutely be paying them for their time (even a token amount).
I can confirm that this is what it does.
And if you ask it to not use tables, it cleverly uses div with the same layout as the table instead.
Anachronistic would be something like creating an apparent flash website for a fictional 90s internet related movie.
Warner Bros anachronistically keeps this website online would be a simple fix; here used to reference and to point out that maintaining an untouched 1996 promotional site at it's original location is not typical for the lifecycle of a website, usually the publisher would rather redirect clicks to some current offer.
Othwerwise there is no anachronism here with the website itself, just it's location under the original URL and not in some archive only.
The website itself fulfilled its purpose for promoting the movie when it was released and simply continues to exist.
You wouldn’t call posters, magazines, or other artifacts from the ’90s anachronistic just for still existing. Being retrievable doesn’t make something outdated by itself.
“Anachronistic” would apply only if a new promotional site were created today to look like this—though that would more likely be called “retro.”
Or if the movie industry insisted on using CSS-free table layouts for all its promotional websites, similar to other norms or laws that feel anachronistic because they no longer match current needs.
Sadly the whole piece reads like it was written 80%+ by an LLM too, seriously why all the emojis? But apparently this is where content is heading in general.
I'm not well at the moment, perhaps your ML model has flu?!!
In 1996, We had only css1. Ask it to use tables to do this, perhaps.
I tried your suggestion and also tried giving it various more general versions of the limitations presented by earlier generations.
Claude's instinct initially was actually to limit itself to less modern web standards.
Unfortunately, nothing got those planets to be in the right place.
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.
Bullshit. Right click -> view source
Or just press ctrl+s and the browser will also gather all the assets into a folder for you.
The arrogance of thinking that the only way you know how is the only way....
You literally forgot the save feature all browsers have just because you set out to "solve" this using "ai"
That's not how to successfully use LLM's for coding in my experience. It is however perhaps a good demonstration of Claude's poor spatial reasoning skills. Another good demonstration of this is the twitch.tv/ClaudePlaysPokemon where Claude has been failing to beat pokemon for months now.
> That's not how to successfully use LLM's for coding in my experience.
Yeah agree. I think I was just a little surprised it couldn't one-shot given the simplicity.
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...
That being said, sloppy copy can make doing actual work a lot faster if you treat it with the right about of skepticism and hand-holding.
It's first attempt at the Space Jam site was close enough that it probably could have been manually fixed by an experienced developer in less time than in takes to write the next prompt.
There are other ways such as downloading an archive and the preserving the file in one or more cloud storages.
> 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. Believe me, I'm an engineering manager with a computer science degree. Please please please help (sad emoji)
https://news.ycombinator.com/item?id=46193412
As of right now, it seems to have been flagged into oblivion by the anti-AI crowd. I found both posts to be interesting, and it's unfortunate that one of them is missing from the conversation.
Give Claude a way to iteratively poke at what it created (such as a playwright harness), and screenshot of what you want, and maybe a way to take a screenshot in Playwright and I think you will get much closer. You might even be able to one shot it.
I’ve always wondered what would happen if I gave it a screenshot and told it to iterate until the Playwright screenshot matched the mock screenshot, pixel perfect. I imagine it would go nuts, but after a few hours I think it would likely get it. (Either that or minor font discrepancies and rounding errors would cause it to give up…)
I'd be curious to see how Antigravity compares for the same task with its automatic browser agentic validation logic.
I've heard the same thing about it doing frontends - it produces gorgeous websites but it has similar 'tells', it does CSS and certain features the same way, and if you have a very concrete idea of what you want out of it, you'll end up fighting an uphill battle with it constantly trying to do things its own way.
Which is part of the 'LLM illusion' - I guess. To an unskilled individual, or when starting from scratch, it seems great, but the more complex the project gets, the harder it becomes to have it contribute meaningfully, leading to an ever-mounting frustration, and eventually me just giving up and doing it by hand.
To be fair, a lot of startup websites look very similar. And the number of Stripe blurples out there was a pre-LLM brand meme.
You're just holding it wrong if you're asking it to simply count the characters in a sentence.
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 this applies to the whole AI industry, not just LLMs.
Also I have noticed that AI generates things close to what you want, and it sticks really hard to that "close" qualifier, not wanting to cross any borders to get too close, so I'd be happy with the effect you have shown, as it is what AI does
Can confirm: Claude is weirdly good at generating functional game logic from vague prompts, but spatial precision is a constant battle. Anything involving exact pixel positions needs validation/correction layers on top.
The suggestion upthread about having it write its own measurement tools seems promising - haven't tried that approach yet.
Interesting that it handles this fine (functional orbital mechanics, animation) but would probably struggle to recreate the exact pixel positions of the Space Jam layout. Confirms the pattern: good at "make something like X" but bad at "recreate X exactly."
Edit: yup very easy for claude. Most of the wall time was spent installing cv2 in a venv (uv dropped python 3.14 on claude, which seemed to get stuck compiling numpy or something so I interrupted and told claude to just use python 3.13 instead).
ME: In this directory there are two images: @p-pressbox.gif and @screenshot.png. @p-pressbox.gif is an image that exists somewhere inside @screenshot.png Write a script that finds the precise location
CLAUDE: Looking at the images, I can see that p-pressbox.gif (the spaceship with "PRESS BOX SHUTTLE" text) appears in the upper-left area of screenshot.png. I'll write a Python script using OpenCV to find the precise location.
[ some venv stuff/telling claude to use uv and python 3.13 ]
CLAUDE: The script found the precise location of p-pressbox.gif within screenshot.png:
| Measurement | Value |
|---------------------|-----------------|
| Top-left corner | (87, 110) |
| Bottom-right corner | (218, 166) |
| Center | (152, 138) |
| Template size | 131 × 56 pixels |
| Match confidence | 97.2% |
The script is at /tmp/search/find_image.py and uses OpenCV's template matching with normalized cross-correlation.
CLAUDE: Done! The visualization shows a green rectangle highlighting the exact location where p-pressbox.gif was found within the screenshot. The match is at coordinates (87, 110) to (218, 166).
I confirmed the result was correct.
All I did was give Lovable a single prompt: "with pixel perfect accuracy recreate this website: https://www.spacejam.com/1996/"
Edit: Commenter below may be right.
Any LLM with browser tool can do it (Kombai one shots it too for example), because it's just cheating.
Suuuuuuuuure they are.
I haven't found a single multimodal model, vision LLM, or any model at all that can segment and extract music charts/infographics.
Can Gemini 3 Pro, in one shot, turn charts like these into lists of "artist - album" without choking on the visuals?
https://reddit.com/r/citypop/comments/10fu1t5/city_pop_album...
https://reddit.com/r/indieheads/comments/173o33z/the_new_ind...
https://knowyourmeme.com/memes/my-father-in-law-is-a-builder...
Would this actually work, or am I missing something?
This article is my typical experience with LLM coding. Endless correction and handholding, and manual cleanup of subtle mistakes. With no long-term learning from them.
Kinda makes me livid, the amount of false hype coming out of the mouths of the stewards of these investor-subsidized LLM companies.
But they're amazing Google replacements, and learning tools. And once in a blue moon they ace a coding assignment and delight me.
Edit: 90% of coding work by June to September 2025: https://www.businessinsider.com/anthropic-ceo-ai-90-percent-...
It's remarkable how high our expectations have been steadily creeping.
Help, I can't recreate a website with AI! There's no other way, no way I could fix up some HTML code! Believe me, I'm an engineering manager with a computer science degree!
Absolutely disgusting.
What's with the panicked pleas and need to preserve the site, assuming locally...?
> After these zoom attempts, I didn't have any new moves left. I was being evicted. The bank repo'd my car. So I wrapped it there.
“Reference the original uploaded image. Between each image in the clock face, create lines to each other image. Measure each line. Now follow that same process on the app we’ve created, and adjust the locations of each image until all measurements align exactly.”
https://aistudio.google.com/app/prompts?state=%7B%22ids%22:%...
(2) The kind of dialog he's having with Claude is a kind of communication pattern I've found never works with LLMs. Sure there is the kind of conversation that goes
Do X
... that's pretty good except for Y
Great!
Do X
Your goal is to create an HTML5 website that is pixel-accurate as the screenshot @Space-Jam.png . You can use the image files in the `img` folder. To achieve pixel-level reproduction, first write auxiliary programs to measure the pixel locations of the objects on this page. Then use your measurements to create the page. Consider using feature detection/matching with per-object (x, y) offsets and a global scale factor shared by all objects as the free parameters. Consider using RANSAC for robust estimation. After obtaining an initial estimation, crop the image of each object and use local sparse optical flow for refinement. Use JPG format for visual inspection of intermediate results. Your webpage should be able to scale with the window size.
More details here: https://gist.github.com/jia-kai/802de63816711d67f0a090fa267a...
We can’t. We don’t know how to do it.
Now that's a novel sentence if I've ever read one.
I recently experimented alot with agentic coding (mostly with gemini+ intellij plugin, copilot intellij plugin and intellij's own junie) and also condsidered to give it a try and feed images to the AI, but than all tasks i tried so far were pure backend-ish so it never came to the point.
Im really curious how especially junie will act and i will give it a try with the very same task you gave it. We gonne see how it ends :D
Sure, you can argue this is some sort of modern ACID-Test - but the ACID tests checked for real-world use-cases. This feels more like 'I have this one very specific request, the machine doesn't perfectly fullfill it, so the machine is at fault.'. Complaining from a high pedestal.
I'm more surprised at how close Claude got in its reimagined SpaceJam-site.
The AI: https://chatgpt.com/share/6923df03-7304-8010-bd08-cd335f0ee9...
They all fail massively 100% of the time. Even if I break it down into chunks once they get to the chunks that matter the most (i.e. physics, collision detection and resolution, event handling and game logic) they all break down horribly and no amount of prompting back and forth will fix it.
I hadn't even considered handing it a visual mockup to work from. Event though that workflow is par for the course for any web design team.
I would assume there must be at least some prior work into locating individual assets in a larger canvas. It just needs to be integrated into the pipeline.
Thanks to this post I now have a deeper understanding as to why. Thank you.
Why not downscale the image and feed it as a second input so that entire planets fit into a patch and instruct it to use the doensampled image for coarse coordinate estimation
Give the LLM access to the site's DOM and let it recreate the site with modern CSS. LLMs are much better with source code, aka text, right? :)
Common at the time before flash took over.
TLDR:
"The plan is designed to ‘autoformalize’ the problem by using Test Driven Development (TDD). TDD is incredibly important for getting good outputs from a coding agent, because it helps solve the context rot problem. Specifically, if you can write a good test when the model is most ‘lucid’, it will have an easier time later on because it is just solving the test instead of ‘building a feature’ or whatever high dimensional ask you originally gave it.
From here, Nori chugged away for the better part of half an hour in yolo mode while I went to do other things. And eventually I got a little pop up notification saying that it was done. It had written a playwright test that would open an html file, screenshot it, diff it with the original screenshot, and output the final result...
After trying a few ways to get the stars to line up perfectly, it just gave up and copied the screenshot in as the background image, then overlaid the rest of the HTML elements on top.
I’m tempted to give this a pass for a few reasons.
This obviously covers the original use case that tripped up Jonah.
It also is basically exactly what I asked the model to do — that is, give me a pixel perfect representation — so it’s kind of my fault that I was not clearer.
I’m not sure the model actually can get to pixel perfect any other way. The screengrab has artifacts. After all, I basically just used the default linux screenshot selection tool to get the original output, without even paying much attention to the width of the image.
If you ask the model to loosen the requirements for the exact screengrab, it does the right thing, but the pixel alignment is slightly off. The model included this as index_tiled.html in the repo, and you can see the pixel diff in one of the output images..."
It seems Nano Banana Pro can understand the layout/spatial well.
Just out of curiosity, how big was what you considered Claude's best attempt to be?