News for hackers. Stuff that matters.

A comment on GitHub Copilot. Parent comment

Re:GitHub Copilot by fzaninotto on Tuesday June 29, 2021 @12:23PM (#27678111)
It's smarter than that. It suggests things that have never been written. It actually creates code based on the context, just like GPT-3 can create new text documents based on previous inputs.

Edit: Check this screencast for instance: https://twitter.com/francoisz/status/1409908666166349831

[ Parent | on HN ]
Re:GitHub Copilot by semi-extrinsic on Tuesday June 29, 2021 @12:57PM (#27678578)
Anyone tried this on any sort of numeric computation? Numpy, Julia, Pandas, R, whatever?

I definitely see the utility in the linked screencast. But I am left to wonder whether this effectiveness is really a symptom of the extreme propensity for boilerplate code that seems to come with anything web-related.

[ Parent | on HN ]
Re:GitHub Copilot by aqme28 on Tuesday June 29, 2021 @01:31PM (#27679102)
I'm not convinced that code snippet in the screencast had never been written. It's fairly generic React, no?
[ Parent | on HN ]
Re:GitHub Copilot by Jeff_Brown on Wednesday June 30, 2021 @09:25AM (#27688210)
Is the model similar to GPT-3? That seems extremely resource-intensive, particularly given how fast the suggestions appear.
[ Parent | on HN ]