Comment by mikert89

4 days ago

I just restyled a full saas app thats doing 50k in arr per month, bootstrapped. I already shipped it to production. A major UX/element/component overhaul.

It looks 10x more professional. I did it this afternoon, sitting on my couch. I took a raw css/html assets from a very professional saas app, and gave it to claude code. I wrote no code, and did not even review the code. This field is truly on its way to full automation.

I can't imagine ever voluntarily divulging this kind of thing to others. Anyways, drop a link so we can see what an afternoon of vibe coding is capable of.

  • divulging what? its not far from taking a screenshot and generating a backend. which will probably be possible some time in 2027, and is mostly possible now. the moat on software is gone for people that know how to use the tooling

What do you mean by "I took a raw css/html assets from a very professional saas app"?

  • I’ll fill in the part between OPs story and “then they all clapped” that he left out.

    He’s likely talking about “Save As”ing or scraping the DOM for rendered HTML/CSS and feeding that to an LLM to convert to actual in app wired up components.

    • eventually you will be able to generate a database schema/api by just feeding saas app html to an llm. you wont get everything, but you will get close

      1 reply →

I mean, I can take the assets from very professional software and use that to make a clone even faster than one afternoon. Copying on disk is quick.

do not share the link.

they aren't engaging in good faith.

haters are going to hate regardless.

> This field is truly on its way to full automation.

What do you even mean by that? Full automation of irrelevant, simple as hell, saas apps? Maybe yes. Everything else that actually needs some thought? Nah, not happening anytime soon - given that no genius with a brand new architecture comes around tomorrow. LLMs just ain't getting any better really. It's just micro steps by now

  • "LLMs just ain't getting any better really. It's just micro steps by now"

    The models itself, maybe yes. But the agents mixing model input and output with classical programming to achieve whatever you programm them to? That just has started to show it's potential.

  • What industry are you in and what do you do there? I’m always baffled by these “actually needs some thought” that end up being just another CRUD. Maybe you’re Peter Norvig’s alt, or Linus casually browsing on a burner account?

    • Anything that is safety related or needs signal control. So embedded systems and anything related. Aerospace, defense, anything. There is so so much stuff.

      Not even talking about AI writing HDL's. They just can't do it and put latches everywhere (they are bad. you should put registers instead)

      2 replies →

sorry but isn't this just theft²?

  • the time is coming when you can take screenshots of an app and generate a full backend. we are no where near the limits of what we are about to see happen to software. idk whats legal, but its soon an irrelevant question

    • legality will soon be an irrelevant question? i genuinely fear the world which you would to usher into existence

  • Well you see he ran it through in through an LLM, but LLMs are lossy, so who can say if the output was a direct result of the copyrighted code or if the model focused on his unique prompting words and conjured the output from its own latent space without referencing copyrighted input at all? /s

    Alternatively, we could take the model makers’ view and say that if they didn’t want their code reused, they wouldn’t have made it publicly accessible on the internet.

    • the model makers opinion is no different than "if she didn't want to be ogled/cat called, she shouldn't have been wearing [insert literally any type of clothing here] when travelling from A to B in a public place"