I disagree. I have both but I use Copilot a lot more. Editing the results of ChatGPT takes as long as it would take for me to write the code myself. Whereas Copilot is autocomplete, you can choose whether to accept it or not line by line.

Are you using ChatGPT 4 or 3.5? GPT 4 is phenomenal.

How are you prompting ChatGPT such that you get useful results in a real world code base? It doesn’t have any context. The context is what makes Copilot work.

By default, ChatGPT can only give a generic answer. Do you just paste the entire file in there?

For example let’s say I want to write a function foo() that calls functions bar() and baz() defined in the same file and uses a library Y that I already imported. If I just write the name of the function, Copilot will often autocomplete a reasonable body for me. If I wanted to use ChatGPT then I would have to first tell it about foo() and bar() and the dependency on Y, and by the time I’ve finished telling it about all of that I could have written the function by hand twice over.

Copilot is chat gpt4, and has been since roughly April. It's built on top of it.

The underlying model might be as good, but how you interface with it seems to deliver wildly different results. I can easily get chat-gpt to give me entire blocks of code. Copilot just trickles out small bits. Copilot is also very distracting because I find myself constantly waiting to see if what it's going to do next is helpful or not, whereas just typing into chat gpt I know I'm going to get something in the direction of what I want.

VS Code now has a Copilot Chat panel where you can have large conversations.

For me it is very different use cases. Copilot often prevents me from needing to write mundane blocks of code, as it will often fill in what I'm looking for after I write the function name.

If I'm still unsure how I might approach a certain problem, or if it isn't immediately clear to me how I'd write the function I want, I might type in a prompt to ChatGPT and see what it comes up with. But it would really slow down my workflow if I had to prompt ChatGPT for every mundane function I plan to write.

Is that actually true? I remember Copilot-X being containing the GPT4 version and I'm pretty sure that wasn't out back in April. I don't even think it was out this summer

X also isn't GPT-4 but the previous cheaper model

I suspect the cost problem arose specifically upgrading to ChatGPT 4 over ChatGPT 3 - right there their costs increased more than 5x. So before it was likely under $5/month on average, but once you changed to ChatGPT 4, it jumped to like $20/month on average.

Wow, I didn't know there, I must have missed the news. I swear I have seen everywhere that it was using this "Codex" model

I think codex is what early versions of copilot used.

To be fair, before they switched to GPT-4 it was pretty bad..

Interesting that you say that. I had the opposite thought that it doesn’t seem to have improved much over time, but I think my perception might be influenced by my habit of ignoring large suggestions and only looking at the results when it fills the rest of the line I was typing.

I’m also using it with intellij instead of vscode, so for all I know I could be using an old version still.

It’s built on it, and pretrained on most of the open source code on GitHub.

I don't see how this can be true. It generates code so much faster than GPT-4 does when you call it through chatgpt.

It's not. Copilot is based on GPT-3

For code completion, it uses an improved version of Codex[1], and for chat beta (part of Copilot X), it uses 3.5-turbo[2].

[1]: https://github.blog/2023-07-28-smarter-more-efficient-coding...

[2]: https://github.com/orgs/community/discussions/56975#discussi...

It's not GPT-4, it's gpt-3.5-turbo (or a variant there-of). Source: I'm sitting in the audience of a talk about it at AI Engineering summit right now, the speaker confirmed it as gpt-3.5-turbo, switched from Codex.

Constant transmission is what makes it so useful, though