Doesn't have to be. I just revived one of my C++ GLFW app from 2009. Codex was able to help me get it running again and added some nice new features.
I guess you get an Electron app if you don't prompt it otherwise. Probably because it's learned from what all the humans are putting out there these days.
That said.. unless you know better, it's going to keep happening. Even moreso when folks aren't learning the fundamentals anymore.
You won't see it because it's mostly personal software for personal computers.
I've got a medical doctor handwriting decipherer, a board game simulator that takes a PDF of the rulebooks as input and an accounting/budgeting software that can interface with my bank via email because my bank doesn't have an API.
None of that is of any use to you. If you happen to need a similar software, it will be easier for you to ask your own AI to make a custom one for you rather than adapt the ones I had my AI make for me.
Under the circumstances, I would feel bad shipping anything. My users would be legitimately better off just vibe coding their own versions.
I disagree. There is a tier of people who can't vibe code what you've vibe coded, but also might not trust your app (especially the bank one). There is still a real gap here to be filled by professional work or fakers.
Professionals are doing what I am doing, only inside companies. They make custom software that solves ultra-specific problems of that one company.
I don't quite understand the obsession with shipping fancy enterprise b2b saas solutions. That was the correct paradigm for back when developing custom code was expensive. Now it is cheap.
Why pay for Salesforce when you only use 1% of Salesforce's features? Just vibe code the 1% of features that you actually need, plus some custom parts to handle some cursed bespoke business logic that would be a pain in the ass to do in Salesforce anyway.
Supposedly Richard Stallman's secretaries knew how to code their own Emacs macros.
I don't expect any LLM to empower people as much as Emacs can, but they will definitely empower more people in total, just because LLMs are easier to use than Emacs.
There is a guy on twitter documenting his progress with moltbot/openclaw: https://x.com/Austen/status/2018371289468072219. Apparently he has already registered his bot for an LLC so he can make money w/ it.
Some guy on Twitter selling an AI coding boot camp is an interesting example. Also it's literally just a post of him looking for a real developer to review his vibe coded bot???
What does the bootcamp have to do w/ anything? He is using AI slop to make money, that's all that matters in a socio-economic system wherein everyone & everything must make profits to persist.
Edit: found another example from coinbase: https://x.com/0xEricBrown/status/2018082458143699035.
Edit: I'm not going to keep addressing your comment if you keep editing it. You asked for an example & I found two very easily. I am certain there are many others so at this point the onus is on you to figure out what exactly it is you are actually arguing.
You should make a note & revisit this in a few days to figure out whether your assessment was correct or not. I've already wasted enough time here so good luck.
Their goal is to ship as fast as possible b/c they don't care about what you care about. Their objective is to gather as much data as possible & electron is good enough for that.
I work at OpenAI, and I get the concern. From our side, this was a careful tradeoff: Electron lets us iterate faster and makes it possible to bring the Codex app to Windows and Linux very soon. That doesn’t mean performance or UX don’t matter—we’re actively paying attention to both.
Would genuinely love your thoughts if you try it. Early users have been surprised by how native it feels!
Could you please pass on feedback to the team that the git diff view is very hard to read for red/green colourblind users like myself? Colour scheme like GitUp.co is very readable for me.
the problem is that getting this out in this shape the week after Cursor made $100M ARR would have made sense
getting it out now suggests there are structural problems about how decisions get made and code gets shipped—and the "iterate faster" line feels misplaced
I don't really care about memory or how much of it is taken up by the editor. I have enough memory for the work that I do & UI performance would make no difference to my workflow.
At the end of the day LLMs just reproduce the consensus of the internet, so it makes sense that a coding agent would spit out software that looks like most of what's on the internet.
This is what you get when you build with AI, an electron app with an input field.