Hacker News Reader

Comment by noloblo | Hacker News Reader

seems like Codex api is used in Github copilot https://openai.com/blog/openai-codex ; from their page, we are seriously worried about losing the tab completions features of codex api we have come to rely on in the excellent Github Copilot for neovim in our team

>> Codex is the model that powers GitHub Copilot, which we built and launched in partnership with GitHub a month ago. Proficient in more than a dozen programming languages, Codex can now interpret simple commands in natural language and execute them on the user’s behalf—making it possible to build a natural language interface to existing applications. We are now inviting businesses and developers to build on top of OpenAI Codex through our API.

View on HN

They are shutting down the free API, not copilot.

> we are seriously worried about losing the tab completions features of codex api

Not sure how to say this nicely, but if you rely on an AI so much for programming, maybe you are doing something horribly wrong.

Unless youre writing, say, Zig, LSP (e.g. native LSP with Mason, or coc-nvim) will give you as good of an autocomplete as you can get.

Imagine your laundry and dryer unit both break. Sure, you can wash everything by hand and hang dry, but I’m assuming most people are going to scramble to get it fixed instead of throwing up their hands and going back “to the old way”

Yes hoping what ($gpt-4) they replace the codex “obsolete” models to ease their compute needs is half as good as current codex

> Unless youre writing, say, Zig, LSP (e.g. native LSP with Mason, or coc-nvim) will give you as good of an autocomplete as you can get.

That's not true, Copilot can complete a whole function based on a comment by understanding the intent behind it, no LSP server can do that. On the other hand, Copilot can't do the kind of code analysis that an LSP server can, so you use them together, they don't really compete with each other

Yes, I get that, but "seriously worried" about not having that? Are they hiring monkeys?

If Copilot is making people 30% more productive then obviously they would be seriously worried that it might go away.

Reports vary massively on how useful Copilot is, some people say it makes them 3x as productive whereas others say it just gets in the way, I think 30% is a conservative estimate if you are working with the kind of code that Copilot is good for (front end JS/TS and backend python).

I would say for languages like bash haskell erlang 30% to 3x and doesn’t yet get in the way. It’s useful and acts as a muse when stuck with a cup-de-sac in terms of scarce human creativity

Reply on news.ycombinator.com