Thread

1. kul_ · 1789727710 · focus · HN ↗

   Is it only me or do others also find LLM generated websites so off-putting?

   1. joegibbs · 1789728760 · focus · HN ↗

      The problem is the overabundance of text, they can’t let it breathe. Everywhere has to be filled up with bits of hardly-relevant text.

      1. sheepscreek · 1789730591 · focus · HN ↗

         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.

         1. windexh8er · 1789734371 · focus · HN ↗

            You'd think they'd have addressed verbosity in the last couple of quarters since it's burning their inference at rates they seem to care about. But instead they're more focused on their cyber security FUD distribution so they can lock out all competitive angles possible. I can't wait for the American Greed miniseries.
         2. cryptonector · 1789795779 · focus · HN ↗

            In Spanish there's a wonderful portemanteau of verbal and hemorrhage 'verboragia', that means something like 'they won't shut up'.

            1. GreenWatermelon · 1790020192 · focus · HN ↗

               They have it in English. It's called "word vomit"
      2. testycool · 1789730656 · focus · HN ↗

         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

      3. yellowapple · 1789757829 · focus · HN ↗

         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.
      4. berofeev · 1789797235 · focus · HN ↗

         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.

Unofficial Hacker News client; not affiliated with Y Combinator.