There's replit. Constantly announcing new features around such models. They'd introduced "ghostwriter" a while back and yesterday or so they announced ghostwriter chat.

Hey Gavin, that's consistent with what I said in the blog post. Header files (.h) and (.c) files are classified as having the same language (C). As a result, if you have the header file open in a tab (or in the workspace -- I'm not sure if unaccessed files from workspace are used), then it'll be considered for the prompt.

Yeah, I second what bibabloo said. Sometimes when I want to edit something, I comment out existing thing, and start writing what'd be the new version. Then copilot autocompletes what I have in mind (often enough).

I think the UX of large suggestions will require a lot of thinking and experimentation. That's because the longer the output of such model, higher the risk of it making some mistake. For short completions, it's often easy to identify mistakes from useful suggestions (though sometimes subtle bugs slip in). But for longer completion, it'll get tedious and we might start accepting wrong suggestions.

Thank you! :)

Heh this blew up here :D Didn't know till a friend told me about it.

I'd love to know if you guys have any specific questions about copilot's internals that I can try to answer by staring at the code or if you have any feedback for the tool/post!

Any word on what the neovim plugin does? Considering some features like,

> Then, most recently accessed 20 files of the same language are queried from VSCode.

are probably not available by default in nvim?

---

Also, do you think there's any chance you get in trouble for reverse engineering copilot?

RE: neovim

Looks like the 20 file logic is present in neovim as well. I went through its code (https://github.com/github/copilot.vim/blob/release/copilot/d...) after beautifying it (https://codebeautify.org/jsviewer), and found it present.

I couldn't exactly trace it to a specific neovim event but I'm guessing it corresponds to buffer-update-events (https://neovim.io/doc/user/api.html#api-buffer-updates) or something like that.

Re: getting in trouble

I surely hope not :P. I mean, the code is basically public (available on every user's computer).

Interesting, thanks.

The neovim plugin mostly actually communicates with a node-js service seen here (https://github.com/github/copilot.vim/tree/release/copilot/d...). This is why they require you to install node for using the plugin and allows them to share logic with the vscode extension (also in javascript). I think all the features should be available even in neovim.

Just a note on the first sentence under "What does a prompt look like?", it seems like there's a continuity error from the above paragraph.

oh lol. Yeah, messed up while rewriting. Fixing. Thanks!

The "Privacy – Copilot for Individuals" section under https://github.com/features/copilot does say that Copilot collects code snippets if allowed by telemetry.

> User Engagement Data When you use GitHub Copilot it will collect usage information about events generated when interacting with the IDE or editor. These events include user edit actions like completions accepted and dismissed, and error and general usage data to identify metrics like latency and features engagement. This information may include personal data, such as pseudonymous identifiers.

> Code Snippets Data Depending on your preferred telemetry settings, GitHub Copilot may also collect and retain the following, collectively referred to as “code snippets”: source code that you are editing, related files and other files open in the same IDE or editor, URLs of repositories and files path.

Algorithms by Papadimitriou would be a pleasant read on algorithms.

Thank you, that looks like an interesting read.