> You only have to read one or two of these answers to know exactly what’s up: the students just copy-pasted the output from a large language model.
I don't understand this either. I use it a lot, but I never just use what an LLM says verbatim. It's so incredibly obvious it's not written by a human.
Most of the time I write an initial draft, ask Claude to check it and improve it, and then I might touch up a few sentences here and there.
> Vibe coding; that is, writing programs almost exclusively by language-model generation; produces an artifact with no theory behind it. The result is simple: with no theory, the produced code is practically useless.
Maybe I still don't know what vibe coding is, but for the few times when I _can_ use an LLM to write code for me, I write a pretty elaborate instruction on what I want, how it should be written, ... Most of the time I use it for writing things I know it can do and seem tedious to me.
I don't understand this either. I use it a lot, but I never just use what an LLM says verbatim. It's so incredibly obvious it's not written by a human. Most of the time I write an initial draft, ask Claude to check it and improve it, and then I might touch up a few sentences here and there.
> Vibe coding; that is, writing programs almost exclusively by language-model generation; produces an artifact with no theory behind it. The result is simple: with no theory, the produced code is practically useless.
Maybe I still don't know what vibe coding is, but for the few times when I _can_ use an LLM to write code for me, I write a pretty elaborate instruction on what I want, how it should be written, ... Most of the time I use it for writing things I know it can do and seem tedious to me.