News for hackers. Stuff that matters.

A comment on GitHub Copilot. Parent comment

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 ]