News for hackers. Stuff that matters.

A comment on AutoCodeRover resolves 22% of real-world GitHub issues in SWE-bench lite. Parent comment

Re:AutoCodeRover resolves 22% of real-world GitHub issues in... by dboreham on Tuesday April 09, 2024 @03:55PM (#39983542)
The point is that a patch without a test is not generally a useful thing. How do we know the AI generated patches are valid?
[ Parent | on HN ]
Re:AutoCodeRover resolves 22% of real-world GitHub issues in... by nfm on Tuesday April 09, 2024 @04:20PM (#39983801)
I agree in principle, but if it also generated a test, how would you know that was valid?

The value I get from copilot is the ability to code faster, not the ability to code.

[ Parent | on HN ]
Re:AutoCodeRover resolves 22% of real-world GitHub issues in... by abhikrc on Wednesday April 10, 2024 @01:38AM (#39987306)
We know that by testing the patches. Automated Program Repair is an area of research which has done this.

The patches are tested against a test-suite. So, if there are tests, we welcome them, we definitely use them to validate the patches.

[ Parent | on HN ]