I find the models conceptually design the structure, then fill it up with text.

This leads to 'fixing' the amount of text areas it needs to fill, so it works to a constraint of having to fill a collection of text areas instead of outputting the message that would otherwise best suit.

My way to combat this is to start by refining the words/messages to be put on the canvas before letting the agent try designing something.

Language models, amiright?! Text is the blood flowing through their veins. It’s all they care about.

As they say, to a hammer, everything is a nail.

I tell the agent to outline the greebling, which is the when you add extra details that aren't really necessary.

Initially it feels like the result will be too empty, but once the greebling is removed it most often looks better

Honestly I prefer that over the overabundance of empty space that's been the norm in “modern” web design for more than a decade now.