zlacker

I totally agree. The ”hard to control mech suit” is an excellent analogy.

When it works it’s brilliant.

There is a threshold point as part of the learning curve where you realize you are in a pile of spaghetti code and think it actually saves no time to use LLM assistant.

But then you learn to avoid the bad parts - thus they don’t take your time anymore - and the good parts start paying back in heaps of the time spent learning.

They are not zero effort tools.

There is a non-trivial learning cost involved.

>>fsloth+(OP)
The issue is we’re too early in the process to even have a solid education program for using LLMs. I use them all the time and continue to struggle finding an approach that works well. It’s easy to use them for documentation look up. Or filling in boilerplate. Sometimes they nail a transformation/translation task, other times they’re more trouble than they’re worth.

We need to understand what kind of guard rails to put these models on for optimal results.

>>teaear+M6
” we’re too early in the process to even have a solid education program for using LLMs”

We don’t even have a solid education program for software engineering - possibly for the same reason.

The industry loves to run on the bleeding edge, rather than just think for a minute :)

>>fsloth+F8
when you stop to think, your fifteen (...thousand) competitors will all attempt a different version of the thing you're thinking about and one of them will be the about the thing you'll come up with, except it'll be built.

it might be ok since what you were thinking about is probably not a good idea in the first place for various reasons, but once in a while stars align to produce the unicorn, which you want to be if you're thinking about building something.

caveat: maybe you just want to build in a niche, it's fine to think hard in such places. usually.

>>baq+Pr
Fwiw a legion of wishfull app developers is not ”the industry”. It’s fine for individuals to move fast.

Institution scale lack of deep thinking is the main issue.

>>fsloth+(OP)
also, the agents are actually pretty good at cleaning up spaghetti if you do it one module at a time, use unit tests. And some of the models are smart enough to suggest good organization schemes!

>>fsloth+F8
> We don’t even have a solid education program for software engineering - possibly for the same reason.

There's an entire field called computer science. ACM provides curricular recommendations that it updates every few years. People spend years learning it. The same can't be said about the field of, prompting.

>>sorami+mX2
But nobody seems to trust any formally specified education, hence practices like whiteboarding as part of job interviews.

How do we know a software engineer is competent? We can’t tell, and damned if we trust that msc he holds.

Computer science, while fundamental, is very little of help in the emergent large scale problems which ”software engineering” tries to tackle.

The key problem is converting capital investment to a working software with given requirements and this is quite unpredictable.

We don’t know how to effectively train software engineers so that software projects would be predictable.

We don’t know how to train software engineers so that employers would trust their degrees as a strong signal of competence.

If there is a university program that, for example FAANGM (or what ever letters forms the pinnacle of markets) companies respect as a clear signal of obvious competence as a software engineer I would like to know what that is.

>>fsloth+AS3
That says more about the industry than the quality of formal education. After all, it's the very same industry that's hailing mediocre robots as replacements of human software engineers. Even the article has this to say:

> As a mid-late career coder, I’ve come to appreciate mediocrity.

Then there's also the embracement of anti-intellectualism. "But I don't want to spend time learning X!" is a surprisingly common comment on, er, Hacker News.

So yeah, no surprise that formal education is looked down on. Doesn't make it right though.

>>sorami+QF4
I don't think two wrongs make a right, tho. Looking down at formal education is not the same as embracing anti-intellectualism. And while I admit the software industry is absolutely full of bullshit anti-intellectualism, I also don't believe formal education is or should be the standard for the education, formalism is not automatically better than alternative means of learning.

The problem of anti-intellectualism in SE is just the consequence of the field being more "democratized". Or, to put in other words, the mass is stupid and the mass-man is stupidier and primitive.