> Conceptually yes, but trying to understand what affordances you have what tools you can use what options are about, to begin to then decide to learn those systems, is incredibly incredibly hard.
And programming isn't? It requires even deeper esoteric knowledge about language intricacies, build systems, architectures, etc.
LLMs might help with getting a prototype up and running, but fixing issues or adding new features to an existing codebase still has a low success rate, and high chances of introducing other issues. These chances are directly proportional to the size and complexity of the software. Often the only way to address these issues is for the user to dig into the codebase themselves, which becomes a gargantuan task if they don't have an understanding of it to begin with.
So, sure, these new tools are useful for writing small and dirty scripts as the author needed, but then again, they can also be used to write configuration, help with integration issues, and to gain understanding of existing software. Asking them to write software is a riskier proposition, IME. Especially if that software is released into the wild and is used by more than one person.
Doing it in isolation sucks. I'd rather have an infinite patient peer, even if flawed who I can dialog with.
Trying to berate the LLMs & scare folks into believing code is all impossible no matter what is maybe accurate perhaps, and yes much wrong and ignorance will spring forth.
But there's going to be so much going forth that wouldn't &bcouldnt have happened and I think in the balance this is incredibly empowering and amazing onboarding, an unbelievable resource. That yes many will squander, will vibe into trouble on, but and tool if misweilded is a danger.
I think of all the pissed off people finally trying to switch to Linux. And with LLMs there to help understand and explain systems, to partner on the work, I'm just so much more excited than the hard rugged road that used to be there. Sure more than half are going to coast along without seeing what their partner peer is up to, without soaking it in. But there's many many thousands who will get into it, will be eager, and will have so much better chance of success for this patient but not flawless peer.
And programming isn't? It requires even deeper esoteric knowledge about language intricacies, build systems, architectures, etc.
LLMs might help with getting a prototype up and running, but fixing issues or adding new features to an existing codebase still has a low success rate, and high chances of introducing other issues. These chances are directly proportional to the size and complexity of the software. Often the only way to address these issues is for the user to dig into the codebase themselves, which becomes a gargantuan task if they don't have an understanding of it to begin with.
So, sure, these new tools are useful for writing small and dirty scripts as the author needed, but then again, they can also be used to write configuration, help with integration issues, and to gain understanding of existing software. Asking them to write software is a riskier proposition, IME. Especially if that software is released into the wild and is used by more than one person.