Hacker News new | ask | show | jobs
by lemagedurage 798 days ago
ChatGPT3.5 already spots bugs, e.g. when I swap the order of conditions in fizzbuzz. An error that a human could make. We've been at the point where AI can help spot bugs for a while already.

AI can be used poorly, AI can be used well.
2 comments
bayindirh 798 days ago
Another problem is how we arrive to a model that can be used poorly or well. There's huge copyright and ethical problems underneath every big model, and I refuse to use models which are trained with copyrighted materials, without consent.

Gentoo is right here, and until we pass these hurdles, I don't use any of these systems, even with a 100 feet pole.

link
hobs 798 days ago
Ok, now ask it how many Ms are in ammunition. Just because it can do somethings some of the time doesn't mean we'd happily accept contributions from it.
link
Philpax 798 days ago
1) It does not need to solve every issue to be useful; it just needs to surface some issue that a human reviewer can then validate. It's seen a lot of code; it can find common issues.

2) The specific issue you're talking about is because they don't see letters, they see tokens, which are groups of letters / subwords. It can't count those because it can't actually "see" what it's counting. This is being worked on as well.

link