I have watched artists thoughtfully integrate digital lighting and the like at a scale I'd never seen before the LLMs rolled up and made it possible to get programs to work without knowing how to program.
The fundamental ceiling of what an LLM can do when connected to an IDE is incredible, and orders of magnitude higher than the limits of any no-code / low-code platform conceived thus far. "Democratizing" software - where now the only limits are your imagination, tenacity, and ability to keep the bots aligned with your vision, is allowing incredible things that wouldn't have happened otherwise because you now don't strictly need to learn to program for a programming-involved art project to work out.
Should you learn how to code if you're doing stuff like that? Absolutely. But is it letting people who have no idea about computing dabble their feet in and do extremely impressive stuff for the low cost of $20/month? Also yes.
Now this is the right take. It's one thing for us to do navel-gazing into the recursive autononomous future; it's another to step back and see what Normal People can do, now that the walls are coming down around our profession. Creating new walls is probably not the answer! From the Cathedral and Bazaar, we now have an entire metaphorical city of development happening, by people who would not have thought it possible a few years ago.
I don't know what the future of my job holds other than what it always had: helping people who have good ideas to get them done properly.
The thing is though it all still feels so…rudderless/pointless sometimes?
When digital cameras came out, it democratized filmmaking immensely. But it wasn’t just people screwing around - amazing new works of art, received positively by audiences and critics alike, exploded in number. They wound up winning film fests, garnering millions of views (and fans) online, and even on big screens world wide, almost immediately
Where are the vibe coded apps that are actually good? Where are the new, innovative creations built by “normal” people? Because by now you’d think we’d see them. It’s all been parlor tricks, proofs of concept, and post mortems on how a bot ruined half a year’s work or whatever. The “good stuff” is still happening behind closed doors, led by experienced engineers on existing projects. It’s a productivity multiplier more than anything it seems, but it doesn’t seem useful as a tool for new people to make new things in any given space.
Vibe coding is actually "good" for small, bespoke things. The same way that Excel is "good" for small tasks, bad bad for larger things. Too easy to make mistakes, too hard to maintain.
I could equally ask - where are all the Excel workbooks that are actually _good_? No-one needs to share their Excel workbooks. They don't need 10k github stars. They just achieve some small goal of the Excel user. These LLM agents just need to do what the user needs doing at any moment.
(Sometimes, that can be a small part of a larger job in software, or a series of small parts perhaps - but again you are going to see this "show up" as a part of peoples workflow in maintaining enterprise software which is what most programmers are employed to do, in other words, you won't directly see it at all. And no, digital cameras didn't change the field 18 months after the first somewhat-usable one was released - it took quite a while for the technology to become good enough and cheap to democratize filmmaking).
I don’t care about GitHub stars. There are tons of excel workbooks and such that are useful, publicly available, and utilized.
It’s a tool to replace human creation, not to enable human creation.
I have found that LLM’s are fantastic for rewriting things in ways that get me to break through writer’s block. It’s great for just keeping me going when I can’t think of the next words, even if I just sit on it and come back later. In that way it helps me create. But this covers one major issue that affects my progress, it doesn’t like…do the job for me, if that makes sense. I throw out probably 80% of what the LLM spits out, but even just seeing what you don’t want can often help you decide what you do want.
> Where are the vibe coded apps that are actually good? Where are the new, innovative creations built by “normal” people? Because by now you’d think we’d see them.
They're busy using them. They're probably not GitHub users or HN readers. I've seen some really nice internal (business) apps made.
So we have to assume there’s good stuff being made by newbies that no one else is seeing?
I didn’t have to take it on faith that people were actually making amazing things with digital cameras. I could look at them. I could reproduce it.
Sure but maybe we’re all better off spending more time going for walks, learning to cook, playing sports , talking to friends and family, participating in spiritual communities, and making love (to other people!)
This line of reasoning applies to nearly any way to spend time - "why are you playing videogames? Learn X instead!" or "why are you bothering with X when Y exists?" or "what, you don't know how to make sourdough? Silly goose!"
At the end of the day, we all have only finite time on this earth, and how one chooses to spend the meager time between eat, sleep, and fend for self is up to them. If a person is content to play sports in their free time, more power to them. If they want to play videogames, and find satisfaction in that, great! Broadly, I like to create. Most of my creations are engineering-adjacent much more than they art. That's fine, and I'm happy. I do everything you named on that list in addition to building stuff.
While using AI, I have caused things to exist that I want much faster than I could have otherwise - I know how to program, but I'm not very fast and I have to have the docs open all the time because the things I want to do are so broad and varied that one week it's bash SLURM scripts and the next it's adding things to my k8s config and the one after that it's something in Python and I don't have enough brain cells to keep track of seven different languages well enough to not accidentally put semicolons at the end of my Python scripts or use the wrong syntax but boy at least I have a bunch of stuff that actually works in the time frame and attention span that I have left after the rest of my life for that day occurs. It's not like I wasn't programming before AI - I've been doing bash scripts and Arduino stuff since middle school - but I have a lot more to show for the little free time I have to work with in the last year or so.
And, for the people who don't really know how to code, the incredible power of their computers is now much closer to their fingertips and usable for more than Electron apps. Want to have a thing happen? Ask, Wait, Iterate. All for cheaper than fiverr, and you might learn a few things before you finish.
> the low cost of $20/month?
At what threshold does this stop being true? AI firms are famously hemorrhaging money and it will not last.
When the small local models catch up I would think
“ The fundamental ceiling of what an LLM can do when connected to an IDE is incredible, and orders of magnitude higher than the limits of any no-code / low-code platform conceived thus far.”
Curious on this - why?
AI Agents can write and modify base Python / C++ / Rust / whatever pretty well, and thus users aren't limited by "sorry the building blocks only go together in this one particular manner".
It's like the difference between an EZ-Bake oven and a fully furnished kitchen. The EZ-Bake oven can get some stuff done but its limits are much more severely obvious than the kitchen's, and the kitchen's first limiting factor in what can be produced is usually the human cooking in it
Emacs can be configured with no code written by the user and Linux can be controlled with minimal user knowledge of the command line. Still some knowledge is necessary in most cases, but nowhere near what was required a handful of years back.