Yeah, I get the feeling. I'm torn to be honest, because I quite enjoy using it, but then I sift through everything line by line, correct things, change the formatting. Alter parts it's gotten wrong. So for me, it's saving me a little bit of time manually writing it all out. My colleagues are either like me, or aren't sold on it. So I think there's a level of trust and recognition that even if we are using it, we're using it cautiously, and wouldn't just YOLO some AI generated code straight into main.

But we're a really small but mature engineering org, I can't imagine the bigger companies with hundreds of less experienced engineers, just using it without car and caution, it must just cause absolutely chaos (or will soon).

I use it as more of a focusing tool. Without it, I frequently get distracted by small rabbit holes (I should add more logging to this function, oh I should also add some doc comments, oh I should also refactor this, etc) or I don't have the energy to do small touch ups like that. Having a bunch of agents do tiny fixes in the background on separate branches keeps me on task, prevents me from bloating PRs, and makes it more likely that I choose to do these small QoL improvements _at all_.