News for hackers. Stuff that matters.

A comment on GitHub Copilot. Parent comment

Re:GitHub Copilot by fabiospampinato on Tuesday June 29, 2021 @11:24AM (#27677185)
The problem I see with that is that's not possible for it to understand well which code is the best, GPT-3 is trying to mimic human writing in general, the thing is most human code is garbage, if this system was able to understand how to make code better you could keep training it until you had perfect code, which is not what the current system is giving you (a lot of the times anyway).
[ Parent | on HN ]
Re:GitHub Copilot by fzaninotto on Tuesday June 29, 2021 @11:36AM (#27677399)
I guess you miss the point. It's not trying to suggest the perfect code. Only you know it. It's saving you time by writing a good (sometimes perfect) first solution based on method/argument names, context, comments, and inline doc. And that is already a huge boost in productivity and coding pleasure (as you only have to focus on the smart part).
[ Parent | on HN ]
Re:GitHub Copilot by fabiospampinato on Tuesday June 29, 2021 @11:40AM (#27677455)
Maybe you are right, in my experience either the code you have easily available to you (either because another person or a computer wrote it) is perfect for your use case (to the best of your knowledge anyway) or rewriting it from scratch is usually better than morphing what you have into what you need.
[ Parent | on HN ]
Re:GitHub Copilot by drusepth on Tuesday June 29, 2021 @03:08PM (#27680338)
>if this system was able to understand how to make code better you could keep training it until you had perfect code

Based on the FAQ, it looks like some information about how you interact with the suggestions is fed back to the Copilot service (and theoretically OpenAI) to better improve the model.

So, while it may not understand "how to make code better" on its own, it can learn a bit from seeing how actual devs do make code better and theoretically improve from usage.

[ Parent | on HN ]
Re:GitHub Copilot by Trollmann on Tuesday June 29, 2021 @03:22PM (#27680529)
You're missing the problem he stated: Code written by humans is usually bad so the model is trained on garbage.
[ Parent | on HN ]
Re:GitHub Copilot by Jeff_Brown on Wednesday June 30, 2021 @10:56AM (#27689296)
The proof is in the pudding. I was skeptical too but the testimonials here are impressive.
[ Parent | on HN ]