News for hackers. Stuff that matters.

A comment on Risk Assessment of GitHub Copilot. Parent comment

Re:Risk Assessment of GitHub Copilot by heavyset_go on Monday July 12, 2021 @06:15PM (#27815756)
But that would require hiring tons of software engineers to label training data accurately.

Why do that when you can just train a GPT-3 model on public repositories and call it a day?

[ Parent | on HN ]
Re:Risk Assessment of GitHub Copilot by qbasic_forever on Monday July 12, 2021 @06:40PM (#27815943)
No presumably copilot skirted that need by just analyzing the AST of code they host and using the nearby comments to identify what a section of code is meant to do. This would use the same dataset but solve the opposite problem, generate a description from a block of code AST as input.
[ Parent | on HN ]
Re:Risk Assessment of GitHub Copilot by patchguard on Tuesday July 13, 2021 @02:44AM (#27818195)
> copilot skirted that need by just analyzing the AST of code they host and using the nearby comments to identify what a section of code is meant to do.

I'm curious what it spills out for things like "Todo", or "this is probably broken", etc.

[ Parent | on HN ]