Re:Stack Overflow Announces OverflowAI [video]
by mrtranscendence on Thursday July 27, 2023 @12:41PM
(#36896267)
I don’t know how to square this with the fact that I routinely ask GPT-4 for code and get back answers that are in fact correct. You’re making it sound like it’s purely random, like I’m just getting back a string of zhrueksnbd8373&;! or something.
[ Parent
| on HN ]
Re:Stack Overflow Announces OverflowAI [video]
by chx on Thursday July 27, 2023 @01:30PM
(#36897143)
But that is what you get, it's just dressed up to sound like the answer. But it's not the answer , it can not be. If it accidentally is the answer, that's an accident, nothing more. See my example above about dangling commits...
Re:Stack Overflow Announces OverflowAI [video]
by naasking on Thursday July 27, 2023 @02:02PM
(#36897713)
> If it accidentally is the answer, that's an accident, nothing more.
Accuracy rates much, much higher than chance are not accidental. While you're pointing to a valid failing of LLMs, you're not using the correct words to describe it.
yes, it is nonsense, all of it, we agree.