People like to talk about code as craft and art but the vast majority of the code that was written has always been mediocre at best. LLMs already beat it.
A focused experienced skilled programmer can do better but the market niche for that kind of code is actually small. Most commercial code just has to be good enough to accomplish a business need.
The more pertinent question in my mind is.. why does it still matter? Your customers don’t care about elegant code, they care about working products. There is some relation to good code and good customer experience e.g in terms of performance, but in general your customers won’t feel the impact from poor code. That assumes both pieces of code are functional though, and you do need to babysit LLMs to make sure it actually remains functional.
The problem with this view is that in the scale of LLM progress, this is essentially accurate understanding of archaic models. Modern models are not trained to program using human generated code. They are trained in agentic harnesses where they are able to access real computing environments, and they are rewarded for completing tasks within that environment. This is in contrast the being rewarded for the most likely next token, which used to create essentially an average of human output like you say. Modern training frameworks are able to comfortably produce models that perform well above the center of the bell curve.
No, they don't care about nice code, but they do care about code that actually works. In my experience, there is a correlation between code that has been thought out correctly and code that hasn't, in terms of security, safety, compliance, data-safety, performance, etc. And so far, all LLM-produced code I've seen is severely lacking.
> That assumes both pieces of code are functional though, and you do need to babysit LLMs to make sure it actually remains functional.
So, I guess we agree on that :)
I hear this being repeated, but every time I've asked a LLM to come up with code without proper supervision, the result only superficially looked correct, but didn't stand up to scrutiny.
I wonder why our experiences differ.
At this point I think the only reason someone would do better without an LLM is an unwillingness to use it effectively. Even if you’re going to write all code by hand and only use an agent for validation and debugging, that’s a significant boost.