“The reason that tech generally — and coders in particular — see LLMs differently than everyone else is that in the creative disciplines, LLMs take away the most soulful human parts of the work and leave the drudgery to you,” [the author] says. “And in coding, LLMs take away the drudgery and leave the human, soulful parts to you.”
wtf is he talking about? You get to do spec writing, code reviews, QA and debugging - this is far from the joyful part of coding.
That’s a terrible take and its desperately trying to draw an equivalence where there isn’t one.
I’d argue that the slop code creates more drudgery with having to constantly babysit the LLM. Never mind a new blog post every week about how your “agentic workflow” from last week is all wrong and you need even more infrastructure to wrangle the LLM. It’s worse than the way the JavaScript ecosystem used to be!
Reading someone else’s code is challenging, but at least with a person you can ask them questions or debate.
I guess I’m just someone who finds reviewing someone else’s work tedious, though a necessary part of the job.
To each their own I suppose. By which I mean maybe the author enjoys different parts of coding than you do. Trying to wrangle AI into writing something decent is generally an exercise in frustration for me. But I enjoy architecting and figuring out how to define units of work that are small and self-contained enough to get AI to understand.
I’ve been mulling over what kinds of architectural changes might make it easier for AI to be able to contribute. That’s a puzzle I find interesting in the same way I enjoy other programming problems.
By which I mean maybe the author enjoys different parts of coding than you do.
It seems to me like the part of coding the author enjoys least is coding.
Trying to wrangle AI into writing something decent is generally an exercise in frustration for me.
This is my issue with it. The output of these tools, uhchecked, evolves into something abysmal over time. I find it quicker to just rewrite the output than to try to prompt it over and over again to produce something good.
The same thing we do after interns, fix it.
