News for hackers. Stuff that matters.
Re:Github Copilot Wants to Play Chess Instead of Code by cjbgkagh on Thursday January 13, 2022 @11:09AM (#29922283)
It would be nice if it could detect and avoid tautologies; more difficult would be to avoid circular reasoning but at least it should be possible to make the circles bigger.
Re:Github Copilot Wants to Play Chess Instead of Code by notahacker on Thursday January 13, 2022 @11:33AM (#29922724)
I was actually surprised by the sentence "bad means something is bad" given that substituting the second "bad" for a synonym is well within NLP models' capability, and you'd expect training processes to eliminate that level of tautology in model outputs.

Then I remembered Github copilot wasn't optimised for natural language, it was optimised for programming, where [near] tautology isn't unusual and variable names aren't supposed to be swapped out...

Re:Github Copilot Wants to Play Chess Instead of Code by cjbgkagh on Thursday January 13, 2022 @11:41AM (#29922876)
That’s a good point, I wasn’t thinking of the coding angle despite it being the whole point of the post.