Comment by agentultra

LLMs are far more flexible in what you can create, opening up many niche use cases for non programmers (or those with very limited programming experience).

For example, I use LLMs for one specific thing, making plugins for an app I use (which need to be written in javascript/typescript). No code tools wouldn't be of any use to me here.

No code tools put you in a box that limits what you can create, whereas LLMs allow you to code pretty much anything (though of course how far you can get does depend on having at least some technical ability/knowledge).

The OP and the farmer are people who coded in the past. There can be a big difference between someone who understands how computers and code work generally, and someone who doesn't.

I was a software engineer up till about 8 years ago. I still dabbled in scripts here and there for things I needed since then. LLMs have proved hugely useful for me to do a wide variety of things that wouldn't have been worth bothering with before. The biggest barrier that LLMs overcome for me is being able to quickly find and adapt to different tools, libraries, languages, etc. But it does help immensely to understand how software works to some degree for being able to approach the problem in the first place. I think the two factors multiply together.

I imagine if I want to I could get back into real software engineering much easier and faster than I could have a few years ago, because I still understand how things work fundamentally, I'm just out of date on what's changed in libraries and systems and languages in the last 8 years.

It's also useful for working with spreadsheets and databases.

Anyway I don't mean to shill for LLMs, I hate where this all is taking civilization in general but I'll still use it where it helps me accomplish things I do value.

> Sorry for yucking into everyone's yum here but... did we miss an opportunity here as programmers to provide simpler tools for people to build simple applications for themselves?

It's not that programmers should've made tools with training wheels, but that the regular programmer tools exploded in complexity. Microservices, Kubernetes, etc. Not saying those don't have their places, but they've made programming less approachable.

As someone who was part of the "everyone should learn to code" movement, no, we didn't. We tried all kinds of stuff for a decade and none of it was actually any good, only the people who would have learned to make stuff anyway learned to make stuff. LLMs are radically different: despite their results being terrible, and only just starting to show that maybe that can be a little better than terrible with opus 4.5, they actually meet people who want to make something where they are: skilled folks can make highly complex things (with code quality that's just as good as before because they know how to take what the LLM gives them and make it better), and unskilled folks can make "that one thing they want to" (and the code quality if irrelevant because it's a one-off that's not going to be maintained).

> If LLMs are covering a gap here maybe there's an opportunity for better, local, lower-tech tooling that doesn't require such a huge tech stack (and subscriptions/rent) to solve simple, tractable problems?

I see this with every new technology stack. Way back, we had folks putting out browser "applets" to do the same things that could be done in excel. And then, we had these apps built in the cloud, in mobile, on ios/android, in react, on raspberry pi, on a gpu etc..etc.. ie, Simple apps reinvented with some new tooling. It is almost the equivalent of 'printf("hello world")' when you are learning a new language. This is not to undermine the OPs efforts, but I see it in the spirit of "learning" rather than that of solving a hard problem.

Visual Basic scratched this itch for anyone who was willing to spend roughly the time learning it as, say, becoming basically proficient at Excel. But the ship appears to have sailed for that kind of RAD development.

That's a great take. The duality between hobby code and employable skills is striking. For a very long time you could transition into it, but I don't think so anymore. The job market demands X+Y+Z, so you need to know and follow X+Y+Z or you're not doing anything productive (hobby coding). Insane.

This is what Ruby, Rails and DHH personally tried to do for a long time. The concept of "One Person Framework" where one engineer could work on frontend/backend/devops/mobile stuff is kinda cool, and works to some degree. With questionable tools like Stimulus, but it's there. However, when you're one sentence away from 500-line react component, it's not relevant anymore.

There was never any money in making tools that allow people to make their own applications. There is only money in walling people into your garden, forcing them to use all of the decaying or enshittified tools in your ecosystem.

There actually still isn't any money in LLM, but we're in the "cheap ubers" era where everything is subsidized by capital that has congealed thanks to economic deregulation in the 80s. Yay, capitalism.

> did we miss an opportunity here as programmers to provide simpler tools for people to build simple applications for themselves?

Not really? To someone who doesn't care about software, software is a means to an end of actually doing something, and everything between idea <> execution of value is basically overhead. This has always been true and the overhead is getting carved further and further down over time.

> Since when did "average" people have time to set up a CI pipeline, agents, MCPs, and all the rest needed to get vibe coded apps to work become the "simple" way for non-programmers to use computers to mush some data together for their small businesses and neighbors and stuff?

You don't need all of this. You can basically just download Cursor, the Claude app, Claude code, opencode, whatever today and run something locally. I do think "deployment and productionization" is a bit of a gap but stuff like Replit or even Vercel + Supabase is pretty far along towards agents just being able to do most of infra for you for anything small scale, or at least tell you the buttons to press to hook things up.

> Did spreadsheets, embedded databases, and visual form builders stop working or are lacking in some way?

Pretty much all the LLM/agent products are obviously way ahead of form builders at this point. Take Retool for example, you could spend minutes to hours plugging together "programming-lite" concepts. A single prompt and a few minutes, and maybe 1-2 back and forths can basically get you to the same place with probably less overall jank in a lot of situations. Form-builder stuff is totally dead outside of maybe being an escape-hatch for some LLM situations, or letting users do higher-level scaffolding, but even then I think stuff like Cursor's "select the part of the app you want to change and prompt" is going to be a better UX.

> maybe there's an opportunity for better, local, lower-tech tooling that doesn't require such a huge tech stack

I think you are viewing this from the "tech" angle rather than the deliver value to the end user angle. The tech stack can be arbitrarily complex as long as it works to reduce end user friction and provide value with as much ease as possible. This might as well be the core idea of all consumer tech.

I think your core theses are basically "people care about the underlying tech" and "people want to learn programming or programming-adjacent" and those are both wrong for the vast vast majority of people.