From my experience it’s great at doing things that have been done 1000x before (which makes sense given the training data), but when it comes to building something novel it really struggles, especially if there’s 3rd party libraries involved that aren’t commonly used. So you end up spending a lot of time and money hand holding it through things that likely would have been quicker to do yourself.

Or install YouTube revanced, and get rid if ads too.

I’m somewhat of a programmer, but there’s ideas everywhere in life. My bank came out with an API so I built an app that pulls it all down, stores it in a database, and makes some pretty graphs. Had no experience in fullstack or backend development before (I’m a sysadmin/cloud engineer), so it took me a really long time and I was following a course but adapting it to my project for a lot of it.

The other day I picked up an old game (Mu online) that is soooo grindy it even gives you an in-game bot to play for you, but if you die you just respawn in a safe zone. So I’ve started writing a script that reads the screen (character position is shown in x, y coordinates on screen), and those coordinates are within a given area (the safe zone) it will alert me. Again, had no experience with any of the window controls or image to text conversion (tesseract), but got chatgpt to help me a bit. Will it save me time? Maybe a little. Will I stop playing this game in a month? More than likely. Did I learn something? Absolutely.

I’m self taught but working in tech there’s obviously more work related use cases to actually start learning, but there’s every-day stuff you can do too.