Earlier quoted context omitted.
> But of course writing code directly will always maintain the benefit of specificity. If you want to write instructions to a computer that are completely unambiguous, code will always be more useful than English. Unless the defect rate for humans is greater than LLMs at some point. A lot of claims are being made about hallucinations that seem to ignore that all software is extremely buggy. I can't use my phone witho…
Yeah, I don't really accept the argument that AI makes mistakes and therefore cannot be trusted to write production code (in general, at least - obviously depends on the types of mistakes, which code, etc.). The reality is we have built complex organizational structures around the fact that humans also make mistakes, and there's no real reason you can't use the same structures for AI. You have someone write the code,…
Re: Reports of code's death are greatly exaggerated
#111Humans also make mistakes, but unlike LLMs, they are capable of learning from their mistake and will not repeat it once they have learned. That, not the capacity to make mistakes, is why you should not allow LLMs to do things.