I’ve been working on an app and it was fantastic for the basics, then I decided to refactor an API and Claude code would run for hours without really getting there.
Also a good warning: I just had to completely rewrite an mcp server I had Claude build because when I needed to update it, the whole server was one giant if/else statement and utterly unmaintainable.
I’m having this argument with one of my junior guys who wants to just go with the generated code. We finally got his code functional, months late, and now need to get it maintainable
AI is a useful tool that can help speed up some of the tasks of coding but it’s not magical. It’s never a final result
AI could really help me get more done if we could weed out people following it blindly
Yeah I was trying to pull out a nested react component and styles out of a larger component that got to be almost 1500 lines. Claude and GPT both struggled to get down what styles were required and what that subcomponent was actually doing. And generating tests around just made a fuck ton of spaghetti.
Which is fine. LLMs don’t have to be great at everything. But it’d be nice if people stopped saying I’m gonna be out of a job because of em.
Also a good warning: I just had to completely rewrite an mcp server I had Claude build because when I needed to update it, the whole server was one giant if/else statement and utterly unmaintainable.
I’ve noticed that in some of my bootstrapped code (also an MCP server :) ). I think it tends to bias towards single file solutions so it tends to be a lot less maintainable.
That tracks with my experience
You have to very carefully scope things for them and have a plan for when they inevitably screw up.
They’re great for bootstrapping in my experience but then really fall apart when you need it to do something surgical on a larger codebase.
Mine too
I’ve been working on an app and it was fantastic for the basics, then I decided to refactor an API and Claude code would run for hours without really getting there.
Also a good warning: I just had to completely rewrite an mcp server I had Claude build because when I needed to update it, the whole server was one giant if/else statement and utterly unmaintainable.
I’m having this argument with one of my junior guys who wants to just go with the generated code. We finally got his code functional, months late, and now need to get it maintainable
AI is a useful tool that can help speed up some of the tasks of coding but it’s not magical. It’s never a final result
AI could really help me get more done if we could weed out people following it blindly
At least with AI it’s easy to see how shitty it gets as the codebase grows working on even a toy project over a week.
Then again, if you have no frame of reference maybe that doesn’t feel as awful as it should.
Yeah I was trying to pull out a nested react component and styles out of a larger component that got to be almost 1500 lines. Claude and GPT both struggled to get down what styles were required and what that subcomponent was actually doing. And generating tests around just made a fuck ton of spaghetti.
Which is fine. LLMs don’t have to be great at everything. But it’d be nice if people stopped saying I’m gonna be out of a job because of em.
I’ve noticed that in some of my bootstrapped code (also an MCP server :) ). I think it tends to bias towards single file solutions so it tends to be a lot less maintainable.
Maybe fastmcp is too new for Claude, it’s much less code and still one file
Is that why they like tailwind so much? Philosophically tailwind just seems unsustainable to me, css specifying the intent of an element seems nicer.