I spent the evening working on an app called Poster. The app cross posts between Bluesky and Mastodon/GoToSocial. It’s not special, but it was fun to write. It took awhile, since my Python is still very noobish, and very much a “how do I do this” -> “Google how to do this” workflow.

But I did not write the README.md you see in that git repo. I had Claude do that for me (along with fixing a whole host of bugs because I’m shit at fixing my own code). I don’t feel bad about having Claude do that for me. Maybe I should, but it has to be better than no README at all. And Claude is pretty damn good at looking at some code and telling people how to use the outcome. Better than I would have been, at least.

I don’t vibe code. I’m pretty proud of that fact. I like to create my own code, even though I’m painfully aware of how bad at it I am. I’m not a developer and I never will be. I can put out the simplest of things and be happy about that. It’s more than some people can do, so there’s no real need to feel bad about it.

Because I’m not a great coder, I have to constantly look things up online. I’m a long time user of the Google-it-always method of coding. The issue is, I’m doing that less and less and going to AI instead. And it is a serious problem. I can feel myself getting dumber every time I use “AI” for some menial task or question. Things I would usually go figure out myself by reading through other’s solutions on random forum 133, I now copy and paste from ChatGPT. Sure the AI bot will tell me what the code does and how it should work, but I don’t read that shit. I just take the code and if it works, GREAT! If it doesn’t work, I go back to AI, tell it that it didn’t work and ask it to try again.