Live data from Hacker News

The AI Aesthetic

blog.jim-nielsen.com

31–40 of 188 posts

Re: The AI Aesthetic

#31

> For example, there’s the hamburger menu (≡) which saw a proliferation during the rise of mobile due to the constraints around screen size. Speaking of this, GitHub replaced theirs with a pancake emoji. Maybe related to the stacked pull-requests announcement earlier today.

Did they write anywhere about it? I noticed it - and I think it uses the system emoji, because I noticed the pancake was different between my systems.

Re: The AI Aesthetic

#32
> There are other aesthetics my brain associates with AI, like beige/cream colors, orange accents, and serif typefaces

First, they took my em dash. Now, they’re taking my neutral background with orange accents.

Re: The AI Aesthetic

#33
post #25
post #10

> There are other aesthetics my brain associates with AI, like beige/cream colors, orange accents, and serif typefaces Something to consider regarding the narrow space AI-created designs align on: LLMs are trained to write consistent code. This makes sense for something like a billing or a backend function - you want that code to be consistent. The problem though is that LLMs write code to represent designs as well,…

I like your product and I’m gonna try it because I’m growing to hate the “Claude generated website aesthetic” but $0.13 is way too cheap.

Ha! Totally fair. 13 cents is 0% margin, which is what I'm targeting for individual plans.

I literally just got my SOC2 compliance complete an hour ago, and I'm gonna roll out team plans/enterprise plans next week (unified billing + shared brands). For teams I'm gonna charge a flat 25% margin on API costs, and for enterprise I'll have a 50% margin + minimum spend.

I think I'm going to keep the individual plans at 0% though. Realistically until my own diffusion models I'm training are the main model I'm using for generation, I'm just an API wrapper + harness. At the individual level I want to be competitive with going directly to the api and coding your own harness.

I am curious though - what would you pay per image?

Re: The AI Aesthetic

#35
post #10

> There are other aesthetics my brain associates with AI, like beige/cream colors, orange accents, and serif typefaces Something to consider regarding the narrow space AI-created designs align on: LLMs are trained to write consistent code. This makes sense for something like a billing or a backend function - you want that code to be consistent. The problem though is that LLMs write code to represent designs as well,…

How do you prompt your diffusion models? I see that you are a founder in this space :)

A few layers to it. When you prompt on my product I expand out that prompt into a semantic json blob that represents the style, theme, color palette, and subjects on the screen. I then feed that blob into the diffusion model itself.

The reason I feed in the json blob is it lets me better preserve subjects across multiple screens (ie you probably want to carry over the header exactly as it is in one image to another image).

The example sites above though were pretty simple. I think they were something like

"A tarot card website with an inky, painted artistic style, with rich illustrations on a card featured on the left, and a button to draw cards on the right"

and for the other it was something like,

"A cyberpunk inspired ramen cart website"

Re: The AI Aesthetic

#36
post #10

> There are other aesthetics my brain associates with AI, like beige/cream colors, orange accents, and serif typefaces Something to consider regarding the narrow space AI-created designs align on: LLMs are trained to write consistent code. This makes sense for something like a billing or a backend function - you want that code to be consistent. The problem though is that LLMs write code to represent designs as well,…

For Tarot, did you generate base-color, roughness and normal maps? How do you make sure something like the roughness map doesn't deviate slightly from the base-color?

Re: The AI Aesthetic

#37
post #23
post #10

> There are other aesthetics my brain associates with AI, like beige/cream colors, orange accents, and serif typefaces Something to consider regarding the narrow space AI-created designs align on: LLMs are trained to write consistent code. This makes sense for something like a billing or a backend function - you want that code to be consistent. The problem though is that LLMs write code to represent designs as well,…

Honestly these examples absolutely DO look like generic AI slop, no offense.

I think the neon ramen example looks pretty awesome.

Re: The AI Aesthetic

#38
An irony to this is that the front-ends generated by older models are gonna end up looking distinctive. If you rock a Claude Sonnet 3.7 (or was it Sonnet 4) mid-2025 purple gradient background forever you've set yourself well apart

Re: The AI Aesthetic

#39
post #31

> For example, there’s the hamburger menu (≡) which saw a proliferation during the rise of mobile due to the constraints around screen size. Speaking of this, GitHub replaced theirs with a pancake emoji. Maybe related to the stacked pull-requests announcement earlier today.

Did they write anywhere about it? I noticed it - and I think it uses the system emoji, because I noticed the pancake was different between my systems.

They published 17 pages [0] of docs about it. Here's their intro page: https://docs.github.com/en/pull-requests/get-started/about-s...

[0]: https://github.github.com/gh-stack/

Re: The AI Aesthetic

#40
post #32

> There are other aesthetics my brain associates with AI, like beige/cream colors, orange accents, and serif typefaces First, they took my em dash. Now, they’re taking my neutral background with orange accents.

Beige/cream colours and orange accents — wait, isn't that literally the HN design?

(Randomly, I love the Solarized colour schemes, so anything similar is great, vibe-coded or not.)

Post reply on HN