Comment by johnfn
2 days ago
I wrote a comment saying that this should be possible with a proper playwright harness and screenshot taking. My comment ended up in the negatives (though curiously no one stopped to explain why), as if I was saying something so absurdly inaccurate that it wasn’t even worth rebutting. Thank you for actually running the experiment and proving it - I was almost annoyed enough to do it myself.
I couldn’t understand why it had happened - it felt about as logical to my mind as writing a comment that Rust was faster than Node. I feel there is a strong anti-AI sentiment here, to the point that people will ignore evidence presented directly to them.
Personal vendetta aside, I enjoyed this post! You had some clever tricks I wouldn’t have considered. In fact, the idea of producing a pixel diff as output was particularly imaginative. And the bit about autoformalization definitely hits on something I’ve been feeling when working with AI recently.
EDIT: I notice my comment yesterday is in the positives. Please don’t vote it up. That was not my intention here.
There's a lot of LLM haters, simple as that.
For posterity: Claude is no longer “just” an LLM you’re interacting with.
I use AI everyday. But some AI adopters are getting a bit culty as well.
But there is nothing culty about saying “an LLM could one-shot this” when it has clearly been demonstrated that an LLM can, in fact, one shot this!
9 replies →
Note that I didn't even it tell it to use a pixel diff. Claude w/ Nori did that on its own by following the Nori TDD skill. I did very little, I'm actually very lazy :D
There is a quote about lazy developers, but I too lazy to search for it.
Laziness is one of the three virtues (of a good programmer), but I think Larry didn’t anticipate the current situation when he wrote it:
”The quality that makes you go to great effort to reduce overall energy expenditure. It makes you write labor-saving programs that other people will find useful and document what you wrote so you don't have to answer so many questions about it.”
I didn't get downvoted yesterday but I got pretty far strongly hinting Claude should use very basic image processing approaches and it went for opencv very successfully. It was very fast on the image layout but failed pretty hard on the footer. This morning I decided to walk it through basic image processing for text detection and word building and that went pretty well but I didn't tell it what we were doing and it was too much me telling it what to do. It did sort of realize what we were doing at one point. I was thinking about trying again with just a nudge to think about using basic OCR image processing techniques to detect words and lines and see what Claude comes up with. Was also wondering what it would do if I just told it to use tesseract or paddleocr.
Voting is meant to allow a community to police itself to some extent, although the downside to that is it incentivizes controlling the discussion over contributing to it. It’s a lot easier to vote in accordance with your own beliefs than articulate counter-arguments. The prisoner dilemma takes hold, people stop visiting as they get frustrated by the downvoting, and a bubble forms. It’ll be interesting to see how AI changes the online discussion landscape.
Also note that votes don't just mean agree/disagree. I frequently upvote comments I disagree with and downvote comments I agree with. The votes place the comments in the discussion ranking so plenty of people vote this way.
One example of this is I might like a conversation that's responding to a comment I don't like. But it's a common misunderstanding so I want the conversation to be boosted. Therefore I upvote the comment I disagree with because it's parent to the comments I want to be more visible.
I don't think I'm the only one that does this on HN. And I think doing this can help reduce the repeated comments. In the above example an early common misconception might get downvoted, not seen by others, and then repeated by some, where it can then rise because it's seen by a different subset.
Anyways, I don't think people should vote strictly on agree/disagree
Dude, the recreation is a joke (hopefully an intentional one). It uses the screenshot instead of the assets.
Go ahead, turn on the Web Inspector, and remove the body background:
https://tilework-tech.github.io/space-jam/screenshot.png
The article mentions this:
> So it kind of cheated, though it clearly felt angst about it. 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.
That does not make the title any less clickbaity. Moreover, it does not seem like a vindication of johnfn's original comment.
1 reply →
The outcome does not justify @johnfn's redemption celebration. That's why I decided to give him a heads up.
Aside from that, I think it's a joke. Like the value of pi example I gave in the other comment. If it's not, it is really just sad.
Please read the blog post!
It's a joke, right? A joke similar to this one:
---
> Make me a python script that calculates the value of PI
```python
print("3.1415")
```
"I think it's passable!" <--- The joke
---
If it's not a joke, then it's just sad.
4 replies →
I haven't seen your original comment but "It could work if they did it better" is in general a low value comment.
You should go read it and see if you can tell me a way I could improve it. I felt I gave actionable advice, but I’m always happy to know if I could have said things better.
Looking at the comment, I would argue that it's fairly vague. Maybe it's clear if you have done it but not clear to others type thing.
Then you undercut the advice by adding "I've always wondered if <confident suggestion> would work", making it unclear how much of the advice is a shot in the dark and how much you've actually seen results from that advice.
Claims like "you might even one shot it" also make it seem like simple hype and not the war story of someone who's actually taken the advice.
But you know, people are down voting me for engaging with your question as well so I don't know. Maybe it's all bots these days :p
1 reply →
You could improve it by simply doing the thing you describe and linking to it.
It is a task that could be _easily_ done manually in much shorter time without AI, probably by developers who even love to develop. The reaction on this shouldn't be misjudged as anti-AI. A lot of people, including me, just do not get it! For scientific purposes? Ok, fair enough. But what is the further meaning of this exercise?
The point is that if we agree that this task is truly a one shot, as long as you agree it’s faster to prompt than code, then while you “easily” do this task in around an hour (or however long you say it will take you), I’ll prompt Claude in around 5 minutes, and get a few more things done while I let it run in the background. What am I missing from your argument?
Reading the blog post, prompting Claude setting up Playwright etc. takes at least one hour maybe more? Not seeing where your 5 minutes coming from.
10 replies →
For me it's more that I'm not a web developer and it would definitely take me way longer to research all the parts of doing this. I have booksmarts (at best) about basic CSS and have given up trying to keep up with javascript anything.
It's seemingly an experiment to see how an LLM performs when the task is just outside of its milieu. The answer is not very well.