Copilot is maddening in it's incoherence

Using a number of models, I get really weird results when using code changes. I'm hoping this is not expected or normal. It makes me want to pull my hair out, almost as if it's designed to drive humans crazy. Here's a summary:

Me: Let's make some code changes
Copilot/Me: discussion, make changes

Me: You made an error here, here and here
Copilot: Oh yeah you're right let me fix that

Me: What are you doing? By fixing it you went off course and actually made more errors?
Copilot: Oh yeah you're right let me fix that

Me: Ok let's make more changes now that it's fixed
Copilot makes more errors

I say how can I trust you now? I can't trust anything, we're at the point where it would take less time for me to write the code myself, you've been making so many stupid errors. I thought we're paying you to save time

Copilot: Oh you're right my bad. I will get it right now

CREATES ANOHTER ERORRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR