"different errors is good."
there's some kind of weird 80/10/10 thing that i've experienced developing with ai so far: it's incredibly easy, and getting easier by the day, to get all the code written and test on a local host in minutes (sometimes seconds).
the next 10% is spend figuring out why this little command in the terminal returned an error, what that error means, and how to communicate it back to the ai i'm coding with with enough context to move the ball forward. this part's very difficult. i've likely sent tried to "debug" the same error by sending marginally different messages back to the ai, all for it to send marginally different messages back.
this is a massive own goal. often, it's a failure to zoom out on my part; a failure to learn as i go. for the first 80%, you feel like a god when you watch the code stream down the screen. when i run into these bugs, it takes courage to stop and reflect. for some reason, this is painful (or at least uncomfortable) to do.
if, instead, i tried to understand what api calls are and did some googling on 404 errors quicker, i might find that i'd been trying to deploy to vercel without the vercel CLI installed. or, that i'd had code referencing my old netlify frontend as well as my new vercel backend.
if you have any ambition at all, slowing down to think about what things are and how they fit together is a risk. there's a serious line between doing and thinking about doing. and for me, as someone who is not a programmer, doing is the thing is thing i think i have to keep doing in order to stay in the game. to not quit.
if i spend long enough not quitting, at some point i will win.