Claude AI built me a React app to compare maps side by side

For years I've kept a list of apps / ideas / products I may do someday. I never made the time, with Cursor AI I have already built one, and am working on another. It's enabling me to use frameworks I barely know, like React Native, Swift, etc..

The first prompt (with o1) will get you 60% there, but then you have a different workflow. The prompts can get to a local minimum, where claude/gpt4/etc.. just can't do any better. At which point you need to climb back out and try a different approach.

I recommend git branches to keep track of this. Keep a good working copy in main, and anytime you want to add a feature, make a branch. If you get it almost there, make another branch in case it goes sideways. The biggest issue with developing like this is that you are not a coder anymore; you are a puppet master of a very smart and sometimes totally confused brain.

> For years I've kept a list of apps / ideas / products I may do someday. I never made the time, with Cursor AI I have already built one, and am working on another.

This is one fact that people seem to severely under-appreciate about LLMs.

They're significantly worse at coding in many aspects than even a moderately skilled and motivated intern, but for my hobby projects, until now I haven't had any intern that would even as much as taking a stab at some of the repetitive or just not very interesting subtasks, let alone stick with them over and over again without getting tired of it.

I'm curious: what do you do when the LLM starts hallucinating, or gets stuck in a loop of generating non-working code that it can't get out of? What do you do when you need to troubleshoot and fix an issue it introduced, but has no idea how to fix?

In my experience of these tools, including the flagship models discussed here, this is a deal-breaking problem. If I have to waste time re-prompting to make progress, and reviewing and fixing the generated code, it would be much faster if I wrote the code from scratch myself. The tricky thing is that unless you read and understand the generated code, you really have no idea whether you're progressing or regressing. You can ask the model to generate tests for you as well, but how can you be sure they're written correctly, or covering the right scenarios?

More power to you if you feel like you're being productive, but the difficult things in software development always come in later stages of the project[1]. The devil is always in the details, and modern AI tools are just incapable of getting us across that last 10%. I'm not trying to downplay their usefulness, or imply that they will never get better. I think current models do a reasonably good job of summarizing documentation and producing small snippets of example code I can reuse, but I wouldn't trust them for anything beyond that.

[1]: https://en.wikipedia.org/wiki/Ninety%E2%80%93ninety_rule

These two projects were almost entirely written with LLMs:

https://github.com/williamcotton/search-input-query

https://github.com/williamcotton/guish

Both are non-trivial but certainly within the context window so they're not large projects. However, they are easily extensible due to the architecture I instructed as I was building them!

The first contains a recursive descent parser for a search query DSL (and much more).

The second is a bidirectional GUI for bash pipelines.

Both operate at the AST level, guish powered by an existing bash parser.

The READMEs have animated gifs so you can see them in action.

When the LLM gets stuck I either take over the coding myself or come up with a plan to break up the requests into smaller sized chunks with more detail about the steps to take.

It takes a certain amount of skill to use these tools, both with how the tool itself works and definitely with the expertise of the person wielding the tool!

If you have these tools code to good abstractions and good interfaces you can hide implementation details. Then you expose these interfaces to the LLM and make it easier and simpler to build on.

Like, once you've got an AST it's pretty much downhill from there to build tools that operate on said AST.