I haven't found a way to use it that makes me develop faster.
The articles talks about "tedious code." If you need to generate a large static value table or something, then OK an LLM might give you a really fast result and cut through the tedium. Most of us were already writing short scripts to do that. I'm open to the possibility that an LLM can do it faster. But it's such a rare requirement that the productivity gains are truly negligible here even if they can. And in those cases, it's obvious what the repetitive task needs to be. I often find myself writing the code by hand to be quicker than coming up with a prompt to get it to write the code that I then need to review for correctness.
The article then mentions scaffolding. Things like "bookkeeping" when it comes to creating and setting up a new repo (whatever he means by that). This is why I have, historically, been a big fan of frameworks and generators. Point being, this is already a solved problem and I haven't found a way to further improve the state of this world with LLMs. LLMs might be an alternate tool that work just as well. But they haven't made my existing daily workflow any faster. Setting up new repos is also something that is done so rarely that even if an LLM netted a 100% increase in efficiency, it wouldn't really impact much.
I am an AI "skeptic" but I'm not a naysayer. I do use LLMs regularly. I just don't use them for developing code because I have yet to find a problem that they solve for me. Don't get me wrong, there are problems that they can solve... I just haven't come across any solutions to previously-unsolved problems. Meaning I can swap an existing solution for an LLM-based one... and it is a valid solution... but I don't observe any increase in productivity from doing so. The existing solution was already working fine.
I am genuinely looking forward to the day when this changes. When I identify a single existing problem without an existing solution that LLMs solve for me when developing software. I just have yet to come across one.
I have pycharm pro with the ai. I can right click a function and there's 12 things AI can just do for you.
"find problems" where the linter has no concerns and it finds problems that dont show up from linter are shockingly good. This is like "Hey, you need to make sure this function is only running once at a time or it can easily overwhelm the cpu."
"write documentation" and it just fills in the documentation. I havent a clue what it writes and I wont be doing it.
"generate unit tests" is interesting? I have literally never written a unit test before and the code it produces is lengthy. Unit tests are a waste of time; but others disagree and so AI can produce it.
"explain code" look I wrote the code years ago half drunk, half high. No comments. It explains it all in depth and perfectly. Comments sometimes go stale after bug fixes and then make things confusing. Comments arent important when you have this beautifulness.
Lets go back to that cpu DOS attack example. I then can prompt what is claude 3.5 sonnet to give me to solution to fix it. It gives me this beautiful cache option. I could just hit apply and it'd be done. But then i said it's too complicated give me something simpler. It then gives me a solution that is simpler.
>nd in those cases, it's obvious what the repetitive task needs to be. I often find myself writing the code by hand to be quicker than coming up with a prompt to get it to write the code that I then need to review for correctness.
Its all about the boring busy work crap that doesnt need to be done that now gets done.