sim04ful

So it's what lies between saying "I want x website" -[.....] -> Code+Assets

The issue has to do with specification fidelity, in short a grill-me style aesthetic interrogation using illustrative tooling - ascii diagrams for specifying layout, copy and user-flow, image-gen mockups for higher fidelity mockups. References are also very important for nailing down the aesthetical qualities. I've noticed it's far better vs purely text description to simply gather up a mood-board telling the llm to find commonalities and come up with a design system and brand guide.

So I don't believe it's an unsolvable problem, it's simply a lack of effort on the implementors part. Also there's probably some survivor's bias here (you won't notice an intentionally designed vibe-coded site)

For example here's one reference exploration site i recently made with grok: https://explorer.withfudge.com/

Let's assume in the next decade GPT-7 PRO Ultra is cheaply ubiquitous, inspectable, reproducible, transferable, reasonably un-constrained by any institutional interests.

What say the 1% ?

Lifted up my comment for addition visibility

Is the fear post-apocalyptic in nature ? We need some human priesthood to carry on tradition ? why ?

Let's assume in the next decade GPT-7 PRO Ultra is cheaply ubiquitous, inspectable, reproducible, transferable, reasonably un-constrained by any institutional interests.

What say the 1% ?

Just a thought.

Suppose we eventually have GPT-7-class models running practically on $100 devices, with their activity transparent, inspectable, and reproducible. At that point, what exactly is left for us to fear from this threat?

1. User request understanding: natural language -> a more rigorous representation, in my case Datalog.

2. Result interpretation: facts and derived facts -> natural language.

Between those terminals, the work should be mechanical reasoning over some ontology or formal knowledge structure.

That connects to another principle I've been thinking about, which I call Weathering: useful reasoning should change the shape of the system. If an LLM has already had to infer a relation, mapping, rule, or abstraction, repeated use should wear that inference into the system so that the next similar request doesn't require discovering it again from scratch.

With continued use, a weathering-capable system should therefore require less and less probabilistic intelligence for recurring work. Put another way, there should be a declining marginal cost of cognition since the products of intelligence harden into structure that can subsequently be reused and evaluated mechanically.

It's well on the way to make $600+/month now, almost doubling since last month. I've realised given the ease at which software can be ideated and maintained, i would rather focus on having a more dataset-intensive moat.

It's a database of website section screenshots I've been hand collecting with others for almost 2 years now (it's crowdsourced via a seperate chrome extension), each section has styling metadata linked - typography usage (leading, weights, tracking, sizes,etc), font details (foundry, designer), colors and alot more.

What really helped was my positioning, instead of trying to compete with established players (mobbin, landbook, refero), decided to focus on the MCP integration; the giving LLMs design taste angle.

https://en.wikipedia.org/wiki/Natural_arch

It's doing all that it can.