"Great design prompts require design vocabulary. Most people don't have it."
Vocabulary is just the surface. Beneath it is an understanding of how to achieve your goals with design. How to make things that are easy to use, accessible, that create a certain impression.
Does this website (presumably made with the help of these AI tools) show this kind of understanding of design? Not really. It's chaotic, the text is often hard to read and there is a ton of fluff, both in terms of visuals and copy.
There is a "Frequently Asked Questions" section and a "Popular" $100 tier in the "Support the Project" section, even though this project seems to be brand new. Why lie to the reader?
I was about to make a similar comment. The before/after showcases look in many cases harder to grasp and navigate on the after side.
Roundabout what I would expect as a result from the prompt "make a website that demonstrates how LLMs can better designs"
> Does this website (presumably made with the help of these AI tools) show this kind of understanding of design? Not really. It's chaotic, the text is often hard to read and there is a ton of fluff, both in terms of visuals and copy.
I agree. I tried figuring it out for 1-2 minutes, and then closed the tab.
> Vocabulary is just the surface.
Yes, but with LLMs, sometimes simply mentioning the right words is enough to prime the model in the direction you want to take it. If you start a prompt talking about leading and type pairings, it will take greater care with typography. You don't need to be an expert typographer to take advantage of this phenomenon.
How will an LLM "take greater care with typography" if it can't see the page it is creating? How will it "improve" leading if you need a human to see that there's too much distance between lines or too little?
With playwright, it can see what it is creating. Unsurprisingly, it works much better if you hook it up to a browser.
There's also the Claude extension for Chrome which integrates with Claude Code.
I'm assuming this is in the context of an agent that can see what it's doing. And I wouldn't assume humans have a monopoly on judging leading.
Because humans have already annotated diagrams and examples of what ‘too much’ and ‘too little’ look like, and these have been incorporated into the model. It tries to reproduce the content that is associated with humans indicating that they are taking greater care, and that content has the ‘not too much / not too little’ judgement already baked into it.
Or, said another way, vocabulary provides us with the words (semantics). You also need a grammar (syntax), which itself needs to be ordered toward an end (pragmatics).
This isn't really what I said, and is considerably less clear. What I meant is that you can't boil design down to certain stylistic flourishes and words denoting them (e.g. "vertical rhythm", to take an example from the linked page). Whatever you're doing, it involves understanding how the viewer will react to what you will show them and why.