I’ve been writing code for more than four decades.
But today, roughly 80% of it is generated and maintained by prompting Roo Code. It’s still coding. Just at a higher level of abstraction.
Survey: a third of senior developers say over half their code is AI-generated
211–220 of 388 posts
Re: Survey: a third of senior developers say over half their code is AI-generated
#212Seems about right for me (older developer at a big tech company). But we need to define what it means that the code is AI-generated. In my case, I typically know how I want the code to look like, and I'm writing a prompt to tell the agent to do it. The AI doesn't solve any problem, it just does the typing and helps with syntax. I'm not even sure I'm ultimately more productive.
Yeah I’m still not more productive. Maybe 10% more. But it alleviates a lot of mental energy, which is very nice at the age of 40.
For all the folks on the "reduce mental burden", "reduce cognitive load" train, are you all aware that this basically means you are exercising less your brain day in and day out, and in the end you will forget how to do things? You will learn how to guide an AI agent, but until the day an AI agent is perfect (and we don't know if we will ever see that day), you are just losing inch by inch your ability to actually understand what the agent is writing and what is going on.
I'm pretty radical on this topic but for me cognitive load is good, you are making your neurons work and keep synapses in place where they matter (at least for your job). I totally accept writing down doc or howto to make doing some action in future easier and reduce that cognitive load, but using AI agent IMO is like going to bike in the mountain with an electrical bike.
Yes, you keep seeing the wonderful vistas but you are not really training your legs.
Re: Survey: a third of senior developers say over half their code is AI-generated
#213Seems about right for me (older developer at a big tech company). But we need to define what it means that the code is AI-generated. In my case, I typically know how I want the code to look like, and I'm writing a prompt to tell the agent to do it. The AI doesn't solve any problem, it just does the typing and helps with syntax. I'm not even sure I'm ultimately more productive.
I’m not yet up to half (because my corporate code base is a mess that doesn’t lend itself well to AI) But your approach sounds familiar to me. I find sometimes it may be slower and lower quality to use AI, but it requires less mental bandwidth from me, which is sometimes a worthwhile trade off.
> because my corporate code base is a mess that doesn’t lend itself well to AI
What language? I picked up an old JS project that had several developers fail over weeks to upgrade to newer versions of react. But I got it done in a day by using AI to generate a ton of unit tests then loop an upgrade / test / build. Was 9 years out of date and it’s running in prod now with less errors than before.
Also upgraded rails 4 app to rails 8 over a few days.
Done other apps too. None of these are small. Found a few memory leaks in a C++ app that our senior “experts” who have spent 20 years doing c++ couldn’t find.
Re: Survey: a third of senior developers say over half their code is AI-generated
#214This article goes completely against my experience so far. I teach at an internship program and the main problem with interns since 2023 has been their over reliance on AI tools. I feel like I have to teach them to stop using AI for everything and think through the problem so that they don't get stuck. Meanwhile many of the seniors around me are stuck in their ways, refusing to adopt interactive debuggers to replace…
Yeah, I'm not putting stock in this at all. The methodology of this survey seems dubious.
Re: Survey: a third of senior developers say over half their code is AI-generated
#215Earlier quoted context omitted.
Yeah I’m still not more productive. Maybe 10% more. But it alleviates a lot of mental energy, which is very nice at the age of 40.
For all the folks on the "reduce mental burden", "reduce cognitive load" train, are you all aware that this basically means you are exercising less your brain day in and day out, and in the end you will forget how to do things? You will learn how to guide an AI agent, but until the day an AI agent is perfect (and we don't know if we will ever see that day), you are just losing inch by inch your ability to actually un…
This, to me, feels like you're complaining to the 45 year old builder that they should be using a hammer instead of a nail gun.
I know how to nail a nail, I've nailed so many nails that I can't remember them all.
My job is to build a house efficiently, not nail nails. Anything that can make me more efficient at it is a net positive.
Now I've saved 2 hours in the framing process by using a nail gun, I have 2 extra hours to do things that need my experience. Maybe spot the contractor using a nail plate in the wrong way or help the apprentice on their hammering technique.
Re: Survey: a third of senior developers say over half their code is AI-generated
#216Seems about right for me (older developer at a big tech company). But we need to define what it means that the code is AI-generated. In my case, I typically know how I want the code to look like, and I'm writing a prompt to tell the agent to do it. The AI doesn't solve any problem, it just does the typing and helps with syntax. I'm not even sure I'm ultimately more productive.
I typed less using AI, so it is a net win I guess
Re: Survey: a third of senior developers say over half their code is AI-generated
#217I think I'm using it wrong.
I'm using Zed as my editor, and maybe 18 months ago I upgraded my system. I didn't miss the AI autocomplete at the time, so I didn't bother to set it up again. However, around two weeks ago I figured I'd give it another go.
I set up GitHub Copilot in Zed and... it's horrible. It seems like most of its suggestions are completely misguided and incorrect, usually just duplicating the code immediately above or below the cursor location while updating the name of a single identifier to match some perceived pattern. Not remotely close to what I'd consider useful; I'm definitely a faster & better programmer without it.
I also tried setting up some local models on ollama: I kept getting random tokens inserted that seemed to be markup from the model output that Zed didn't know how to parse. (On mobile rn, will post sample output when I am back at work if I remember to.)
Is paying Anthropic an arm and a leg for the privilege of granting them first-party access to train on my user data really the competitive move as a modern developer?
P.S. I know Zed has their own AI (and it seems like it should be really good!), but when they first introduced it, I tried it out and it immediately consumed the entire free tier's worth of credits in just a few minutes of normal coding: suggestions are proactively generated and count against your account credit even if not accepted, so I didn't really feel like I'd gotten a good sense of the tool by the time the trial ran out. Even if it's really good, it burns through credits extremely fast.
Re: Survey: a third of senior developers say over half their code is AI-generated
#218LLMs are tools. If you master your tools, you become more productive. I've had the same mixed experiences with LLMs that others have. Some good, some not so great. But I've been merging quite a bit of codex created PRs in the last weeks. Some needed manual intervention. Some were tedious to create. And some clearly saved me a lot of work. I always have more work than I can handle. Part of my job is deciding what not…
> LLMs are tools. If you master your tools, you become more productive.
LLMs are unpredictable tools which change all the time, let’s not pretend otherwise. You can’t “master” them in the same way as previous tools. You can learn some tricks to trick them to be closer to what you want, and that’s about it.
Imagine if every time you did the exact same movement to hammer a nail, you had to check your work. Maybe this time it hammered it in perfectly, or maybe it smashed your finger, or maybe it only went half-way through. You could never develop muscle memory for such a tool. You could use it, sure, but never master it.
Re: Survey: a third of senior developers say over half their code is AI-generated
#219I think I'm using it wrong. I'm using Zed as my editor, and maybe 18 months ago I upgraded my system. I didn't miss the AI autocomplete at the time, so I didn't bother to set it up again. However, around two weeks ago I figured I'd give it another go. I set up GitHub Copilot in Zed and... it's horrible. It seems like most of its suggestions are completely misguided and incorrect, usually just duplicating the code imm…
I don’t think you should look at the Copilot autocomplete as anything other than autocomplete, as far as I know they use worse but faster models for that.
I’m not big on AI but I get occasional use out of Copilot with the chat / agent mode and Claude Sonnet 4.
Re: Survey: a third of senior developers say over half their code is AI-generated
#220Earlier quoted context omitted.
For all the folks on the "reduce mental burden", "reduce cognitive load" train, are you all aware that this basically means you are exercising less your brain day in and day out, and in the end you will forget how to do things? You will learn how to guide an AI agent, but until the day an AI agent is perfect (and we don't know if we will ever see that day), you are just losing inch by inch your ability to actually un…
This, to me, feels like you're complaining to the 45 year old builder that they should be using a hammer instead of a nail gun. I know how to nail a nail, I've nailed so many nails that I can't remember them all. My job is to build a house efficiently, not nail nails. Anything that can make me more efficient at it is a net positive. Now I've saved 2 hours in the framing process by using a nail gun, I have 2 extra hou…
I'd like to counter argue we need to shift the notion of efficiency.
While the nailgun is more efficient than the hammer, both need to be operated by a real human. Including all limitations of physical and mental health.
While we can improve the efficiency of the tools we should consider not to burn out humans to match the goal.