My experience with it programming has been atrocius. It keeps making the same mistakes, writing NPEs everywhere and still doing it after I tell it many times how it was wrong (short memory?). Copilot is backed by it too now and I had a better autocomplete of constants with Sorbet than Copilot. Again, in my experience it's not usable if not for the super mainstream and simplest tasks.

The biggest issue is that it writes this with utmost confidence, at least on the surface, because there is no measure of how confident it is returned by the model.

> Copilot is backed by it too now

Do you have a source for this? I've been wondering when they'd switch CoPilot over to GPT-4. I didn't expect it would happen so soon, so I'm surprised.

> GitHub Copilot uses the OpenAI Codex to suggest code and entire functions in real-time, right from your editor.

(not sure if it's 4 or 3 tho)