Re:GitHub Copilot is generally available
by hungryforcodes on Tuesday June 21, 2022 @03:18PM
(#31827946)
I won't rightly describe the confusion your post gives me. Nothing he says seems contradictory. It produces good looking code which upon further inspection has faulty logic.
You would expect that from a program that copies a database of all the examples in the world (or whatever) and then just does an autocomplete without any kind of comprehension of what the problem is that is trying to be solved.
No confusion or contradiction at all.
Re:GitHub Copilot is generally available
by omginternets on Tuesday June 21, 2022 @03:25PM
(#31828038)
So, the problem is that it produces incorrect code…
Specifically, the problem is it produces _almost_ correct code, which is worse than incorrect code because it might fool you into trusting it.
Re:GitHub Copilot is generally available
by omginternets on Tuesday June 21, 2022 @03:31PM
(#31828121)
Quite. So we agree that this code is incorrect, and thus, that we have a contradiction on our hands.
To be clear: we’re in agreement that incorrect code that passes for correct at a glance is even worse than obviously-incorrect code.
Re:GitHub Copilot is generally available
by lkfsfldkjfslk on Tuesday June 21, 2022 @03:17PM
(#31827936)
My read was that it produces code that is correct in some circumstances, but is incorrect for the author's use case.
Re:GitHub Copilot is generally available
by omginternets on Tuesday June 21, 2022 @03:42PM
(#31828237)
I realize I misinterpreted the OP, but you’ve set me up for a snarky remark so perfectly that I can’t resist. Please forgive me… here goes:
> it produces code that is correct in some circumstances, but is incorrect for the author's use case.
That’s a mighty convoluted way of saying “incorrect code” ;)
Phew! I feel better, now!
Re:GitHub Copilot is generally available
by chipotle_coyote on Tuesday June 21, 2022 @05:07PM
(#31829106)
"This code would be absolutely correct were it in a different program trying to achieve a different result."
> The biggest problem I've had is not that it doesn't write correctly, it's that it think it knows how and then produce good looking code at a glance but with wrong logic.
I cannot rightly apprehend the kind of confusion of ideas that would provoke such a statement.
EDIT: upon careful rereading, I think I misunderstood. The intended meaning is likely closer to: the problem is less so that codepilot produces incorrect code and more so that its incorrect code appears correct at first glance.
You have my sincerest apologies. I leave this thread intact as a testament to my hair-trigger snark.