Comment by neebz
3 months ago
I've faced the same but my conclusion is the opposite.
In the past 6 months, all my code has been written by claude code and gemini cli. I have written code backend, frontend, infrastructure and iOS. Considering my career trajectory all of this was impossible a couple of years ago.
But the technical debt has been enormous. And I'll be honest, my understanding of these technologies hasn't been 'expert' level. I'm 100% sure any experienced dev could go through my code and may think it's a load of crap requiring serious re-architecture.
It works (that's great!) but the 'software engineering' side of things is still subpar.
A lot of people aren’t realizing that it’s not about replacing software engineers, it’s about replacing software.
We’ve been trying to build well engineered, robust, scalable systems because software had to be written to serve other users.
But LLMs change that. I have a bunch of vibe coded command lines tools that exactly solve my problems, but very likely would make terrible software. The thing is, this program only needs to run on my machine the way I like to use it.
In a growing class of cases bespoke tools are superior to generalized software. This historically was not the case because it took too much time and energy to maintain these things. But today if my vibe coded solution breaks, I can rebuild it almost instantly (because I understand the architecture). It takes less time today to build a bespoke tool that solved your problem than it does to learn how to use existing software.
There’s still plenty of software that cannot be replaced with bespoke tools, but that list is shrinking.
This is the thing a lot of skeptics aren't grappling with. Software engineering as a profession is mostly about building software that can operate at scale. If you remove scale from the equation then you can remove a massive chunk of the complexity required to build useful software.
There are a ton of recipe management apps out there, and all of them are more complex than I really need. They have to be, because other people looking for recipe management software have different needs and priorities. So I just vibe coded my own recipe management app in an afternoon that does exactly what I want and nothing more. I'm sure it would crash and burn if I ever tried to launch it at scale, but I don't have to care about that.
If I was in the SaaS business I would be extremely worried about the democratization of bespoke software.
Tools for the non-professional developer to put their skills on wheels have always been part of the equation since we've had microcomputers if not minicomputer, see
https://en.wikipedia.org/wiki/VisiCalc
9 replies →
A lot of people don’t care about software other than the fact that the ones they use work well. They don’t want to create it, to maintain it, or to upgrade it. That’s what the IT department is for.
2 replies →
I absolutely believe in that value proposition - but I've heard a lot about how beneficial it will be for large organizationally backed software products. If it isn't valuable to that later scenario (which I have uncertainty about) then there is no way companies like OpenAI could ever justify their valuations.
> I've heard a lot about how beneficial it will be for large organizationally backed software products
It's a generic interface to anything, which allows people to communicate in their own way, and the LLM is pretty good at figuring it out. For non-technical people or customers who don't fully understand the product, it's going to be very helpful. RIP outsourced call centers, we won't miss you.
Manual search and navigation might be on the chopping block soon. Knowing how to navigate big software is often a bespoke skill. Now you can just talk to the computer and tell it what you're trying to do. Al down in the shoe dept doesn't have to figure out how to right click or what a context menu is. It's a fundamental UI change.
> there is no way companies like OpenAI could ever justify their valuations
The value proposition isn't really "we'll help you write all the code for your company" it's a world where the average user's computer is a dumb terminal that opens up to a ChatGPT interface.
I didn't initially understand the value prop but have increasingly come to see it. The gamble is that LLMs will be your interface to everything the same way HTTP was for the last 20 years.
The mid-90s had a similar mix of deep skepticism and hype-driven madness (and if you read my comments you'll see I've historically been much closer to the skeptic side, despite a lot of experience in this space). But even in the 90s the hyped-up bubble riders didn't really see the idea that http would be how everything happens. We've literally hacked a document format and document serving protocol to build the entire global application infrastructure.
We saw a similar transformation with mobile devices where most of your world lives on a phone and the phone maker gets a nice piece of that revenue.
People thought Zuck was insane for his metaverse obsession, but what he was chasing was that next platform. He was wrong of course, but what his hope was was that VR would be the way people did everything.
Now this is what the LLM providers are really after. Claude/ChatGPT/Grok will be your world. You won't have to buy SaaS subscriptions for most things because you can just build it yourself. Why use Hubspot when you can just have AI do all your marketting, then you just need Hubspot for their message sending infrastructure. Why pay for a budgeting app when you can just build a custom one that lives on OpenAIs server (today your computer, but tomorrow theirs). Companies like banks will maintain interfaces to LLMs but you won't be doing your banking in their web app. Even social media will ultimately be replaced by an endless stream of bespoke images video and content made just for you (and of course it will be much easier to inject advertising into this space you don't even recognize as advertising).
The value prop is that these large, well funded, AI companies will just eat large chunks of industry.
Similar experience for me. I've been using it to make Qt GUIs, something I always avoided in the past because it seemed like a whole lot of stuff to learn when I could just make a TUI or use Tkinter if I really needed a GUI for some reason.
Claude Code is producing working useful GUIs for me using Qt via pyside6. They work well but I have no doubt that a dev with real experience with Qt would shudder. Nonetheless, because it does work, I am content to accept that this code isn't meant to be maintained by people so I don't really care if it's ugly.