Arguably you could improve the instructions it follows by finding it when AI does something wrong. I think I use AI more for design specs and acceptance criteria than I do for writing actual code. Though, to be fair, my current role as tech lead offers very little opportunity for writing code other than one-off scripts.
That may fix the current task, but the next one is going to need all those corrections repeated back to it. That’s what I mean by never learning. Each task is its own little world that’s completely disconnected from everything else. Copilot has “memories” that seem like they are trying to fix it, but I’ve never had any luck with it actually working.
We’re all AI babysitters now. For a baby that never learns anything.
Arguably you could improve the instructions it follows by finding it when AI does something wrong. I think I use AI more for design specs and acceptance criteria than I do for writing actual code. Though, to be fair, my current role as tech lead offers very little opportunity for writing code other than one-off scripts.
That may fix the current task, but the next one is going to need all those corrections repeated back to it. That’s what I mean by never learning. Each task is its own little world that’s completely disconnected from everything else. Copilot has “memories” that seem like they are trying to fix it, but I’ve never had any luck with it actually working.