I’ve been writting a lot of code with ai - for every half hour the ai needs to write the code I need a full week to revise it into good code. If you don’t do that hard work the ai is going to overwhelm the reviewers with garbage
I’m writing code because it is often faster than explaining to the ai how to do it. I’m spending this month seeing what ai can do - it ranges from saving me a lot of tedious effort to making a large mess to clean up
I’ve had better success, when using AI agents in repeated, but small and narrow doses.
It’s been kinda helpful in brainstorming interfaces (and I always have to append at the end of every statement “… in the most maintainable way possible.”)
It’s been really helpful in writing unit tests (I follow Test Driven Development), and sometimes it picks up edge cases I would have overlooked.
I wouldn’t blindly trust any of it, as all too often it’s happy to just disregard any sort of error handling (unless explicitly mentioned, after the fact). It’s basically like being paired up with an over-eager, under-qualified junior developer.
But, yeah, you’re gonna have a bad time if you prompt it to “write me a Unix operating system in web assembly”.
You will need more than a month to figure out what its good for and what not, and to learn how to effectively utilize it as a tool.
If can properly state a problem, outline the approach I want, and can break it down into testable stages, it can be an accelerator. If not, it’s often slop.
The most valuable time is up front design and planning, and learning how to express it. Next up is the ability to quickly make judgement calls, and to backtrack without getting bogged down.
With proper prompting you can let it do a lot of annoying stuff like refactors reasonably well. With a very strict linter you can avoid the most stupid mistakes and shortcuts. If I work on a more complex PR it can take me a couple days to plan it correctly and the actual implementation of the correct plan will take no time at all.
I think for small bug fixes on a maintainable codebase it works, and it works for writing plans and then implementing them. But I honestly don’t know if it’s any faster than just writing the code myself, it‘s just different.
hmm not in my experience, if you don’t care about code-quality you can quickly prototype slop, and see if it generally works, but maintainable code? I always fall back to manual coding, and often my code is like 30% of the length of what AI generates, more readable, efficient etc.
If you constrain it a lot, it might work reasonably, but then I often think, that instead of writing a multi-paragraph prompt, just writing the code might’ve been more effective (long-term that is).
plan it correctly and the actual implementation of the correct plan will take no time at all.
That’s why I don’t think AI really helps that much, because you still have to think and understand (at least if you value your product/code), and that’s what takes the most time, not typing etc.
it‘s just different.
Yeah it makes you dumber, because you’re tempted to not think into the problem, and reviewing code is less effective in understanding what is going on within code (IME, although I think especially nowadays it’s a valuable skill to be able to review quickly and effectively).
Eh I don’t disagree with you, it’s just the reality for me that I am now expected to work on much more stuff at the same time because of AI, it’s exhausting but at least in my job I have no choice and I try to arrange myself with the situation.
I sure lost a lot of understanding of the details of the codebase but I do read every line of code these LLMs spit out and manually review all PRs for obvious bullshit. I also think code quality got worse despite me doing everything I can to keep it decent.
I’ve been writting a lot of code with ai - for every half hour the ai needs to write the code I need a full week to revise it into good code. If you don’t do that hard work the ai is going to overwhelm the reviewers with garbage
So, what you’re saying is, you’re not writing code.
I’m writing code because it is often faster than explaining to the ai how to do it. I’m spending this month seeing what ai can do - it ranges from saving me a lot of tedious effort to making a large mess to clean up
I’ve had better success, when using AI agents in repeated, but small and narrow doses.
It’s been kinda helpful in brainstorming interfaces (and I always have to append at the end of every statement “… in the most maintainable way possible.”)
It’s been really helpful in writing unit tests (I follow Test Driven Development), and sometimes it picks up edge cases I would have overlooked.
I wouldn’t blindly trust any of it, as all too often it’s happy to just disregard any sort of error handling (unless explicitly mentioned, after the fact). It’s basically like being paired up with an over-eager, under-qualified junior developer.
But, yeah, you’re gonna have a bad time if you prompt it to “write me a Unix operating system in web assembly”.
You will need more than a month to figure out what its good for and what not, and to learn how to effectively utilize it as a tool.
If can properly state a problem, outline the approach I want, and can break it down into testable stages, it can be an accelerator. If not, it’s often slop.
The most valuable time is up front design and planning, and learning how to express it. Next up is the ability to quickly make judgement calls, and to backtrack without getting bogged down.
Maybe it’s work and it’s required 🤷♂️
deleted by creator
Half of the worlds workplaces are forcing employees to use AI and show proof it was used.
That is a question I’n trying to answer. Until I know what ai can do I can’t have a valid opinion.
With proper prompting you can let it do a lot of annoying stuff like refactors reasonably well. With a very strict linter you can avoid the most stupid mistakes and shortcuts. If I work on a more complex PR it can take me a couple days to plan it correctly and the actual implementation of the correct plan will take no time at all.
I think for small bug fixes on a maintainable codebase it works, and it works for writing plans and then implementing them. But I honestly don’t know if it’s any faster than just writing the code myself, it‘s just different.
hmm not in my experience, if you don’t care about code-quality you can quickly prototype slop, and see if it generally works, but maintainable code? I always fall back to manual coding, and often my code is like 30% of the length of what AI generates, more readable, efficient etc.
If you constrain it a lot, it might work reasonably, but then I often think, that instead of writing a multi-paragraph prompt, just writing the code might’ve been more effective (long-term that is).
That’s why I don’t think AI really helps that much, because you still have to think and understand (at least if you value your product/code), and that’s what takes the most time, not typing etc.
Yeah it makes you dumber, because you’re tempted to not think into the problem, and reviewing code is less effective in understanding what is going on within code (IME, although I think especially nowadays it’s a valuable skill to be able to review quickly and effectively).
Eh I don’t disagree with you, it’s just the reality for me that I am now expected to work on much more stuff at the same time because of AI, it’s exhausting but at least in my job I have no choice and I try to arrange myself with the situation.
I sure lost a lot of understanding of the details of the codebase but I do read every line of code these LLMs spit out and manually review all PRs for obvious bullshit. I also think code quality got worse despite me doing everything I can to keep it decent.
Sounds like that couple that kept rescuing cats that were promptly eaten by coyotes.
Not sure why you’re getting down votes, AI is a good tool when used properly.