I’m going to keep at it, because I was trained as an SRE, not a developer and have lots of ideas for side projects that have thus far taken a long time to get going, but I’ve been struggling, it sort of quickly gets into these infinite loop situations where it can’t seem it can’t seem to fix a feature and goes back and forth between multiple non working states. CSS layouts but even basic stuff like having the right web socket routes.
We’ll see, maybe my whole approach is wrong, I’m going to try with a simpler project, my first approach was relatively complex.
I can't explain why, but I do get pretty good results with closing a prompt session completely and then initiating a fresh session later on. I have actually seen quite different code from the very same prompt across two sessions.
However, the extra time between sessions does give me the chance to consider where the AI might have gone wrong in the first session and how I could have phrased the initial prompts more effectively.
As others have stated throughout the threads here, I definitely recommend giving it smaller nibbles of problems. When I take this route and get working modules, I will start a fresh prompt session to upload the working code module files and ask it to integrate them into a simple solution with static inputs in a 'main' function. (Because providing coherent inputs from the router function inputs of a web service are simple enough, once these basics are covered)
Basically - I do everything possible in order for the AI to not get distracted or go down a rabbit hole, chasing concerns that humans are very capable of taking care of (without paying tokens for). I will write most of the tests myself and then perhaps afterwards ask it to evaluate the test coverage and provide more of them. This way the new tests are in the format and platform of my choosing.
We’ll see, maybe my whole approach is wrong, I’m going to try with a simpler project, my first approach was relatively complex.