←back to thread

221 points caspg | 1 comments | | HN request time: 0.211s | source
Show context
thefourthchime ◴[] 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. psygn89 ◴[] No.42169944[source]
If you have the budget, I have also taken a liking to perplexity.ai. I got it free from my school and it basically aggregates searches for me with sources (but be sure to check them since sometimes it reads between the links so to speak). It basically does the Google searching for me and have returned more up to date API info than Claude nor ChatGPT knew about. Then I would let Claude or ChatGPT know about it by copying doc and source code to work from.