←back to thread

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

(github.com)
221 points caspg | 3 comments | 17 Nov 24 13:39 UTC | HN request time: 0.418s | source
Show context
thefourthchime ◴[17 Nov 24 17:28 UTC] No.42165457[source]▶
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.

replies(5): >>42165545 #>>42165831 #>>42166210 #>>42169944 #>>42170110 #
1. elorant ◴[17 Nov 24 18:22 UTC] No.42165831[source]▶
Good luck debugging it on production.
replies(2): >>42168119 #>>42168267 #
2. cloverich ◴[17 Nov 24 22:56 UTC] No.42168119[source]▶
I mean i debug code other engineers wrote every single day... being good at that is part of the job. The biggest difference is i never have to deal with the LLM writing parts i don't want it to write.
3. poszlem ◴[17 Nov 24 23:25 UTC] No.42168267[source]▶
This is such a lazy, pointless comment that doesn't add anything to the conversation. It's also way off base about what LLMs can actually do, and the fact that they're pretty handy for debugging production code too.