I think Microsoft is going the wrong direction with Copilot (though it's a reasonable direction given their incentives).
Right now Copilot is terrible at large changes to complex codebases; the larger and more complex, the worse. But it's great at suggesting very short snippets that guess exactly what you were in the middle of writing and write it for you.
I wish Copilot focused more on the user experience at the small scale: faster and smaller completions, using the semantic info provided by the IDE, new affordances besides "press tab to complete" (I'd love a way for Copilot to tell me "your cursor should jump to this line next"), etc. This whole focus on making the AI do the entire end-to-end process for you seems like a dead end to me.
I find Cursor’s Copilot++ is miles ahead of GitHub’s in terms of speed and autocomplete helpfulness. They’re also working on the “your cursor should jump to this line next" feature, but I haven’t relied on many of its suggestions yet. It’s available in their vscode fork, but doesn’t seem to be in their docs yet.
Had a glance. Copilot++ looks intriguing, though the landing page is terrible (I can't even see what the demos are trying to show). I might give it a try.
> But it's great at suggesting very short snippets that guess exactly what you were in the middle of writing and write it for you.
I found it reasonably good when I described what code should do through comments and let it generate based on that, evaluated the output, moved on to the next piece of logic, and repeated.
Basically, chaining the snippets together. Then again I'm doing Python back-end web development, so not something terrifically hard.
proper insertion points in completions akin to older Visual Studio templates would probably be ideal, but you can use ctrl + right arrow in vscode to accept completions one word at a time, rather than a whole block with tab.
Right now Copilot is terrible at large changes to complex codebases; the larger and more complex, the worse. But it's great at suggesting very short snippets that guess exactly what you were in the middle of writing and write it for you.
I wish Copilot focused more on the user experience at the small scale: faster and smaller completions, using the semantic info provided by the IDE, new affordances besides "press tab to complete" (I'd love a way for Copilot to tell me "your cursor should jump to this line next"), etc. This whole focus on making the AI do the entire end-to-end process for you seems like a dead end to me.