Hacker News new | ask | show | jobs
by olmo23 15 days ago
What really grinds my gears is how easy it is to get better designs out of LLMs. But if you don't ask, you get the default.
4 comments

as someone who doesn't know how to get better design out of LLMs, can you elaborate?
Have an opinion on the design, imagine something, then tell it to do just that, then iterate. It's when you're unspecific you get the generic, bland and typical LLM design, you just have to be subjective and influence it in some (human) direction.
Also check out https://impeccable.style/, it's really good
what would you ask to get a better design?
Here is a provocative thought - maybe these are the so-called "better designs" from LLMs? It's not like writing English sentences is some huge secret you are sitting on that no one else knows.
> It's not like writing English sentences is some huge secret you are sitting on that no one else knows.

I'd actually say what really makes an excellent engineer stick out among many great engineers, is their ability to communicate clearly and knowing what needs to be communicated vs not, basically being way better at language and communication in general, and they also understand the important of it.

I agree. But I was talking about the "super secret" ability to write prompts, which pretty much anyone can do.
My point being that not everyone writes as good prompts as everyone else, the way you communicate, how clearly and how exact you are matters a lot, much more than you seemingly is under the impression of.

Same goes with the "LLM does web design" example from before, a web designer with great communication skills in web design, will (naturally) have a better prompt for something that'll potentially could look good, compared to a web designer that isn't at good at communicating what they actually want.

Outside design systems I rarely get good CSS from LLMs.

3D type stuff too, it's useless outside boilerplate.

Very little spatial reasoning training, no end-user subjective reasoning inference (Google is starting to though even in unrelated chats), so it's no surprise the LLM doesn't know what you want.

Since I don't even know what I want half the time until I saw it, the subjective reasoning piece is key - that is, being able to predict what I'll want to pretty good accuracy. Then you have your agents etc.