It just doesn't work. I'm trying to build a simple tool that will let me visualize grid layouts.
It needs to toggle between landscape/portrait, and implement some design strategies so I can see different visualizations of the grid. I asked it to give me a slider to simulate the number of grids.
1st pass, it made something, but it was squished. And toggling between landscape and portrait made it so it squished itself the other way so I couldn't even see anything.
2nd pass, syntax error.
3rd try I ask it to redo everything from scratch. It now has a working slider, but the landscape/portrait is still broken.
4th try, it manages to fix the landscape/portrait issue, but now the issue is that the controls are behind the display so I have to reload the page.
5th try, it manages to fix this issue, but now it is squished again.
6th try, I ask it to try again from scratch. This time it gives me a syntax error.
This is so frustrating.
You haven't even said what programming language you're trying to use, or even what platform. There is a world of difference between C# / Avalonia or, Python WX Widgets or a web browser.
It sounds to me like you didn't do any planning, you just gave it a prompt to build away.
My preferred method of building things, and I've built a lot of things using Claude, is to have a discussion with it in the chatbot. The back and forth of exploring the idea gives you a more solid idea of what you're looking for. Once we've established the idea I get it to write a spec and a plan.
I have this as an instruction in my profile.
> When we're discussing a coding project, don't produce code unless asked to. We discuss projects here, Claude Code does the actual coding. When we're ready, put all the documents in a zip file for easy transfer (downloading files one at a time and uploading them is not fun on a phone). Include a CONTENTS.md describing the contents and where to start.
So I'll give you this one as an example. It's a Qwen driven System monitor.
https://github.com/lawless-m/Marvinous
here are the documents generated in chat before trying to build anything
https://github.com/lawless-m/Marvinous/tree/master/ai-monito...
At this point I can usually say "The instructions are in the zip, read the contents and make a start." and the first pass mostly works.
Read through anthropics knowledge share, check out their system prompts extracted on github, write more words in AGENTS/CLAUDE.md, you need to give them some warmup to do better at tasks.
What model are you using? Size matters and Gemini is far better at UI design work. At the same time, pairing gemini-3-flash with claude-code derived prompts makes it nearly as good as Pro
Words matter, the way you phrase something can have disproportionate effect. They are fragile at times, yet surprisingly resilient at others. They will deeply frustrate you and amaze you on a daily basis. The key is to get better at recognizing this earlier and adjusting
You can find many more anecdotes and recommendations by looking through HN stories and social media (Bluesky has a growing Ai crowd, coming over from X, good community bump recently, there are an anti-ai labelers/block lists to keep the flak down)
While this may be possible, it likely requires a very detailed prompt and/or spec document.
---
Here is an example of something I successfully built with Claude: https://rift-transcription.vercel.app
Apparently I have had over 150 chat sessions related to the research and development of this tool.
- First, we wrote a spec together: https://github.com/Leftium/rift-transcription/blob/main/spec...
- The spec broke down development into major phases. I reviewed detailed plans for each phase before Claude started. I often asked Claude to update these detailed plans before starting. And after implementation, I often had to have Claude fix bugs in the implementation.
- I tried to share the chat session where Claude got the first functional MVP working: https://opncd.ai/share/fXsPn1t1 (unfortunately the shared session is truncated)
---
"AI mistakes you're probably making": https://youtu.be/Jcuig8vhmx4
I think the most relevant point is: AI is best for accelerating development tasks you could do on your own; not new tasks you don't know how to do.
---
Finally: Cloudlflare builds OAuth with Claude and publishes all the prompts: https://hw.leftium.com/#/item/44159166
If you treat it as an astonishingly sophisticated and extremely powerful autocomplete (which it is) - you have plenty of opportunities to make your life better.