We tore down our no-code site and went back to code
twitter.comMy instinct tells me this website will become a large unmaintainable mess within a few months. LLMs like to write a lot of code.
Jokes on you, they didn't learn the first time, they won't learn now.
It is like Western gaming studios burning billions into slope game while watching other Western gaming studios losing billions by doing the same thing and yet, do it anyway I guess because "this time is gonna be different".
These companies forget the most important thing: You cannot protect what you don't know.
Cool, agentic AI can write code for you, and they are pleased with what it delivered, yet, nobody talks about running scanning tools to check for vulnerabilities, broken code, unmaintained code.
It is indeed faster to ask an AI service for an example than reading endless posts, but boy oh boy, it loves to add unnecessary code.
It will be beautiful watching all the companies falling one after another, big companies are already burning their annual AI budget within half 2026, they thought they were saving money by firing people only to spend 10x more with AI tokens hahaha
This is a bit of a tangent but can you explain the Western gaming studios analogy a bit further? It's not something I'm familiar with but am curious (I get the idea and broad parallel, but actually would love to better understand the details).
I wondered about this as well, but could also imagine AI tools (perhaps at the application layer and not root-LLM layer) helping to mitigate this - that's a world I've been exploring.
Don't think we're there yet, but it feels like there's a future dream of everyone being able to build and maintain custom software with AI, and not having to make the tradeoff of creativity vs. components that's historically been true with low/no code.
That said, where we are today, completely agree with what you're saying. LLMs like to generate code, and in my experience are pretty bad at iterating on or maintaining the prolific code they've created.