ChatGPT has been helpful in being an interactive rubber duck. I used it to help myself breakdown the technical problems that I need to solve and it helps to cut down time taken to complete a difficult ticket that usually take a couple of days of work to a couple of hours.

"just good enough to be dangerous"

I’ve had similar experiences with it telling me to call functions of third party libs that don’t exist. When you tell it “That function X does not exist” it says “I’m sorry, your right function X does not exist on library A. here is another example using function Y” then function Y doesn’t exist either.

I have found it useful in a limited scope, but I have found co-pilot to be much more of a daily time saver.

So? Those mistakes will come up in testing, and you can easily fix them (either yourself, or by asking the AI to do it, whichever is faster).

I've successfully used it to write code for APIs that did not even exist at all a couple years ago when ChatGPT's model was trained. It doesn't need to know the API to generate working code - you just need to tell it what APIs are available as part of your conversation.