Exactly same thinking. I can usually type it out faster than AI (when taking into account latency, context building, prompt writing, prompt fixing, AI hallucination review) if I know what exactly needs to be done.

When you’re out of your depth, it shines in providing beautifully confident and a botanical garden of a code piece that wil most likely be broken and break in new and exciting ways. Great for incompetent sycophantically-challenged managers that forgot how to code, or never actually had any experience.

Large-scale code transformations, taking into account the bigger picture of the repository are most likely hallucination free (not generative, just transformative, as per the actual LLM model) and a very exciting use-case.

Also it’s currently a very nice pragmatic tool for checking for any mistakes, because it can connect the larger context of the repository quickly to the diff. Terrible if done by a manager without understanding of copilot and workflow, but a great tool if done through claude and cli as a pre-commit step with just quick checklists. Makes plenty of mistakes, but allows to catch your own big mistakes nicely quickly.