Hacker News Reader

Comment by prodigycorp | Hacker News Reader

These one shot vibecoded sites are always a complete visual headache. Endless clutter, pointless filler text all over the place, and zero regard for actual usability.

View on HN

AI output right now is like a final exam essay response from an anxious student. Instead of being edited for focus and clarity, it's anti-edited to cram in as many details as possible. Instead of worrying that the reader might get bored or confused, it assumes that the reader has no choice but to read the whole thing, even if they get a headache. It doesn't care about picking the most useful perspective on a problem; it cares about covering every possible angle that a grader might use to dock points from it.

It's basically the work you get from a smart, diligent person who is oblivious to any shared goal and approaches every assignment with a CYA attitude.

Pretty good analogy. I'd also compare it to a junior employee who tries to make people care about the how of their work rather than the results.

You just very nicely explained why I sometimes overcommunicate.... That's exactly how it feels

This is a great analogy

ironically, this would be useful for a prompt on how not to build build a site.

Here's my prompt when I don't know what the hell the AI is saying.

"Expand. Clarify for human. 5 minute read max. Senior engineer audience."

"Be terse."

Thanks! I will add this to the tricks. AI is a fuzzy search and a fuzzy function.

Also useful words: succinct, concise. Sometimes I use both. Maybe I'll ise all three: be succinct, terse, and concise.

"Write short paragraphs with simple words, use bullet lists when appropriate."

"wtf was all that garbage added for? No user needs to know that we're not doing X anymore, just stick to the fucking prompt"

Y'all are much nicer to the clankers than I am, I see.

That, and Every Sentence Is Punchy.

Every sentence sounds like it's trying to be in the trailer for a film.

That's how Henry David Thoreau wrote.

it's due to how rewards work during RL no? it needs to try to check off all the boxes to get a max score

It's not a bad attitude given that I don't trust it did the work right, so the more details it can include, the more opportunities I have to spot errors, which invalidate the whole result - and conversely, if all details seem right and self-consistent, it gives me greater confidence the work is correct.

> final exam essay from an anxious student

It's because so many of these models were trained on corporate content, which is the exact same vibe. "We're going to drone on for pages about how great we are for building the thing without explaining what it can do for you or how to use it, because spending real effort connecting with our customers isn't something we ever learned climbing the corporate ladder"

Berkshire got it right a long time ago.

https://www.berkshirehathaway.com/

This site proves to me that the better you are at the things that matter most in your niche, the more you can get away with not even trying in other areas.

It proves it? How?

This is more like an exception than the norm and Berkshire is not really something to generalize.

Most investment funds of that size do chose to maintain proper websites.

This is more like Berkshire branding, look at Warren living in the same house despite having billions (while conviniently ignoring dude owns personal jets), look how we have such a grandpa website, look at our humble branding, we are not like the other greedy bankers and are perfectly moral agents you can "trust" etc.

> If you have any comments about our WEB page, you can write us at the address shown above. However, due to the limited number of personnel in our corporate office, we are unable to provide a direct response.

A profoundly polite way to tell someone to stuff it.

I stuff what I have to say into AI's it.

Nah, if this was the OP website you’d be complaining that it tells you nothing and you have no idea what they do or what they are presenting still. Also that it looks like shit on mobile. You’re just glazing the company in this case.

You should go with the canonical HN quality website references: McMaster-Carr, Craigslist

McMaster-Carr is unbeaten.

McMaster’s paper catalogs were phenomenal, with an organization that quickly surfaced the part you wanted and often taught you taxonomy if you were looking for something unusual to you. A true masterpiece and they clearly carried their philosophy to their web design

Nothing will ever top gwern.net

>glazing

I’m not familiar with this term. Could you elaborate?

It’s when you mix milk sugar and vanilla and put it on a donut

this is a great example for me to use in meetings. I often see people looking for "good" examples of web design from fortune 500 companies or similar. Gonna use this to throw a wrench in that one soon.

The Geico ad gave me a laugh.

If you click on the message from warren buffet its another Geico endorsment!

There's a "unsloppify site" toggle on top but the unsloppified version looks exactly as vibe coded as the regular one.

Yeah, I'm not sure which way is supposed to be "sloppified". The default looks stylistically less slop-like, but obviously has the same filler content issue.

The blue one is the VibeTemplate_03. I see it everywhere.

The yellow one is at just a ripoff of an early 00s edgy news site. It could very well also be a VibeTemplate, but I've not seen a tool generate a site that looks like that by default.

I love how the 'unsloppify' button changes the theme but nothing else, and also messes with the layout enough that you can't actually toggle it without scrolling and repositioning your cursor.

I had to re-read a few times to figure out what the site was for and about. Still not sure I understand but that's the problem for them. If I'm a customer, I'm gone cause I can't figure out what it's for and I see this far too often nowadays for a lot of technical sites.

I already closed it after two pageful of not explaining what this thing is.

Glad to know its not just me. I also don't get it.

> These one shot vibecoded sites are always a complete visual headache.

Sure, but have you seen the Typesafe.ai site itself? I think this is meant as a homage.

I generated an guide for a project I'm working on. The structure and appearance were pretty much what I wanted, but I'm going to have to go through and rewrite all of the text and cut out all of the simple tautological statements that are there just because it felt like it had to say something but had nothing to say.

It's useful but any sense of style that is adequate for a wide group of people is never going to be great for a focused group. It is trying to tread the line between creating something that isn't bland without hallucinating something crazy, and products made for the mass market by large companies tend to steer towards bland. Regression to the mean as a service.

I'm not sure which version is the "unsloppified" one, perhaps it's derived from https://github.com/AlexSchmalex97/The-Nothing-Button

I.. kind of like it? Aware that it isn't great and that I'm in the minority.

It's nice to see some variation in websites. Makes each one feel so special.

What’s really hilarious is that there’s an “un-slop site” button that does absolutely nothing to un-sloppify the site

It improves the text readability quite a bit, at least for me, but the soullessness is still there.

Gonna need these people to at least prefix their prompts with "You are Edward Tufte and have an allergy to chartjunk".

There is an "Unsloppify site" button which makes it a bit better.

I'm soon going back to pure html, jesus christ

The unslopify toggle is pretty funny though lol

And yet, it makes the front page of HN. The bar is low.

The irony here being:

- the "vibecoded site" was not vibecoded.

- when you turn "vibecoded off" on this vibecoded site, you get standard Claude slop

Nasty little site, between that and pretending LLMs are the same as Jev.

I see you've edited your comment to remove the part about the vibecoded website being disrespectful towards humans. As a human I find these types of comments about the vibecoded websites, when the submission is not about the website, disrespectful.

Do you have anything to say about OpenJev, which is not about the website?

Yes. These jev-copy projects are all vibecoded, and only mimic the shape of output. Typesafe's documentation is excellent and provides developers with guidance on what exactly to expect from their model. It's also clear that typesafe developed a generalist model that they've tested to work across domains and use cases.

Using libraries like this provide none of those assurances. Sure, you can improve performance with fine tuning , but then we're going back to doing what a model like jev was created to eliminate.

> These jev-copy projects are all vibecoded

Since you've looked at all of them, why do you think https://huggingface.co/convaiinnovations/laya is vibecoded?

This is a link to a fine tuned modernbert model. Like I said, a bert model can produce jev shaped objects but they're too small to generalize.

I asked about it being vibecoded since you claimed that all jev-like projects are vibecoded. You responded to something I didn't ask.

https://github.com/NandhaKishorM/laya/commits/main/

Is this clear? The model has a waitlist and isn't publicly available. How can you claim it's proficient at general tasks?

Touche. I'm using it and find their claims credible but they deserve broader scrutiny.

It's generally available on OpenRouter now: https://openrouter.ai/~typesafe/jev-latest

Reply on news.ycombinator.com