That's why I tried it twice. I've been hearing people say they liked it. But I haven't found it very helpful, and often distracting, so I ended up turning it off. I'll probably try again next year when the models are improved to see if I feel any differently then.
Yeah, I understand. I just see a lot of people on here who seem to be deliberately looking for reasons not to like Copilot.
You don't fit that stereotype, of course. So feel free to ignore the following.
Developer tools have learning curves. One doesn't simply open vim/emacs for the first time with a full understanding of how to use it (or why it's a good tool to use, even). Historically, we have had _no_ problem with the steepness of this curve. But, when it comes to Copilot, there's a lot of "tried it and it output an obvious bug! how did this make it past quality assurance?? such a liability!" Just very reactionary and all-that.
The difference between other Dev tools and GitHub is the probability of getting things wrong. Like when intellij types out boilerplate or a compiler generates code it's 100 percent correct and if it fails, it fails predictably. Copilot is impressive sometimes but there's no guarantee of correctness or failure mode. I cannot trust such tools for anything serious. If you're in the habit of copy / pasting code from the internet then I can see why it might help speed that up. But imo that too is dangerous and I avoid it unless absolutely necessary
I don’t see how that’s relevant to anything in my comment, but since you brought it up I assume you take both of those notions as a given - but they aren’t necessarily concerns of all programmers.
