Comment by Johanx64
16 hours ago
For quite a while i was thinking how we're in the phase one: mountains of unmaintainable garbage code being generated... and once the shit hits the fan, some maintainability ceiling gets reached - "the real programmers" will be summoned to clean up and deal with this shit.
Now I've come to realize the error in my ways, this is probably not going to happen. What will happen is instead is that the ones doing the "shuffling of shit" is just going to also be agents themselves. Prompted by a more senior slop-grammer specialized in orchestrating "shuffling of shit".
You still have to ship a product though.
This task was famously incredibly difficult back when we had people producing unmaintainable mountains of millions of lines of code, to the point where shipping anything sizable in a working state on time without last minute scope reductions is nearly unheard of.
I can't imagine using AI to add another one to two zeroes to the lines of code counter would help reach the goal post.
Testing to ensure the product works as expected is more than half of the product development labor if you want a quality product. This includes time spends on things like the mandatory "anti-harassment" training any competent HR is forcing you to once in a while even though not related to product delivery (or so I hope - some should be fired for the problems you are causing by not living that training)
LLMs can write a lot of code. they can even write a comprehensive test suite for that code. However they can't tell you if it doesn't work because of some interaction with something else you didn't think about. They can't tell you that all race conditions are really fixed (despite being somewhat good at tracking them down when known). They can't tell you that the program doesn't work because it doesn't do something critical that nobody thought to write into the requirements until you noticed it was missing.
SOS.. i just got it.