No shit. Senior devs have been saying this the whole time. AI, in its current form, for developers, is like handing a spatula to a gourmet chef. Yes it is useful to an extremely small degree, but that’s it…for now.
Technology
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
A convoluted spatula that sometimes accidentally cuts what your cooking im half instead of flipping it and consumes as much power as the entirety of Japan.
Good devs gain little.
I gain a lot.
Just beware, sometimes the AI suggestions are scary good, some times they’re batshit crazy.
Just because AI suggests it, doesn’t mean it’s something you should use or learn from.
I partly disagree, complex algorithms are indeed a no, but for learning a new language it is awesome.
Currently learning Rust and although it cannot solve everything, it does guide you with suggestions and usable code fragments.
Highly recommended.
Is there anything it provided you so far that was better than the guidance from the Rust compiler errors themselves? Every error ends with "run this command for a tutorial on why this error happened and how to fix it" type of info. A lot of times the error will directly tell you how to fix it too.
I agree, although some messages are still cryptic for a newbie like me, but thats maybe more the person on the chair than the compiler 😇.
I'd estimate copilot to be correct in only 10% of the time, solving a situation like that. Most of the time the solution suggested is also wrong, but just differently.
Having said that: sometimes (small chance, 1% maybe) the solution is spot on.
AI mainly helps with the initial syntax and on language constructs and for that it is awesome.
It introduced me to the basics of C# in a way that traditional googling at my previous level of knowledge would've made difficult.
I knew what I wanted to do and I didn't know what was possible or how to ask without my question being closed as a duplicate with a link to an unhelpful post.
In that regard, it's very helpful. If I had already known the language well enough, I can see it being less helpful.
I learned bash thanks to AI!
For years, all I did was copy and paste bash commands. And I didn't understand arguments, how to chain things, or how it connects.
Great for Coding 101 in a language I'm rusty with or otherwise unfamiliar.
Absolutely useless when it comes time to optimize a complex series of functions or upgrade to a new version of the .NET library. All the "AI" you need is typically baked into Intellisense or some equivalent anyway. We've had code-assist/advice features for over a decade and its always been mid. All that's changed is the branding.
This is what I've used it for and it's helped me learn, especially because it makes mistakes and I have to get them to work. In my case it was with Terraform and Ansible.
Generative AI is great for loads of programming tasks like helping create regular expressions or syntax conversions between languages. The main issue I've seen in codebases that rely heavily on generative AI is that the "solutions" often fix today's bug while making future debugging more difficult. Generative AI makes it easy to go fast in the wrong direction. Used right it's a useful tool.
I'm a penetration tester and it increases my productivity a lot
I mainly use AI for learning new things. It’s amazing at trivial tasks.
so it's a vector of attack?
Every now and then, GitHub Copilot saves me a few seconds suggesting some very basic solution that I am usually in the midst of creating. Is it worth the investment? No, at least not yet. It hasn't once "beaten" me or offered an improved solution. It (more frequently than not) requires the developer to understand and modify what it proposes for its suggestions to be useful. Is is a useful tool? Sure, just not worth the price yet, and obviously not perfect. But, where I'm working is testing it out, so I'll keep utilizing it.
It's great as essentially a StackOverflow that I can talk to in real time. But as with SO, I've still got to figure out what pieces are legit and where they go.
The writer has a clear bias and a lack of a technical background (writing for Techies.com doesn't count) .
You don't have to look hard to find devs saving time and learning something with AI coding assistants. There are plenty of them in this thread. This is just an opinion piece by someone who read a single study.
if you are already competent and you are aware that it doesn't necessarily give you correct information, the it is really helpful. I know enough to sense when it is making shit up. Also it is, for some scenarios, faster and easier then looking at a documentation. I like it personally. But it will not replace competent developers anytime soon.
While I am not fond of AI, we do have access to it at work and I must admit that it saves some time in some cases. I'm not a developer with decades of experience in a single language, so something I am using AI to is asking "Is it possible to do a one-liner in language X where it does Y?" It works very well and the code is rarely unusable, but it is still up to my judgement whether the AI came up with a clever use of functions that I didn't know about or whether it crammed stuff into a single unreadable line.
I truly don't understand the tendency of people to hate these kinds of tools. Honestly seems like an ego thing to me.
Typical lack of nuance on the Internet, sadly. Everything has to be Bad or Good. Black or White. AI is either The best thing ever™ or The worst thing ever™. No room for anything in between. Considering negative news generates more clicks, you can see why the media tend to take the latter approach.
I also think much of the hate is just people jumping on the AI = bad band-wagon. Does it have issues? Absolutely. Is it perfect? Far from it. But the constant negativity has gotten tired. There's a lot of fascinating discussion to be had around AI, especially in the art world, but God forbid you suggest it's anything but responsible for the total collapse of civilisation as we know it...
I think you nailed it with everything you just said.
If it didn't significantly contribute to the cooking of all lifeforms on planet Earth, most of us would not mind. We would still deride it because of its untrustworthiness. However, it's not just useless: it's also harmful. That's the core of the beef I (and a lot of other folks) have against the tech.
Oh for sure. How we regulate AI (including how we power it) is really important, definitely.
Everyone keeps talking about autocomplete but I've used it successfully for comments and documentation.
You can use vs code extensions to generate and update readme and changelog files.
Then if you follow documentation as code you can update your Confluence/whatever by copy pasting.
Claude is my coding mentor. Wouldn't want to work without it.
I run code snippets by three or four LLMs and the consensus is never there. Claude has been the worst for me.
It has some uses.
But I'm waiting for a good self hosted model and to have a more powerful gpu to properly run it.
For me, it is a glorified auto-complete function. Could definitely live without it.
Same for me, but that glorified auto complete helps a lot.
Hell yea. Our unit test coverage went way up because you can blow through test creation in second. I had a large complicated migration from one data set to another with specific mutations based on weird rules and GPT got me 80% of the way there and with a little nudging basically got it perfect. Code that would've taken a few hours took about 6 prompts. If I'm curious about a new library I can get a working example right away to see how everything fits together. When these articles say there's no benefit I feel people aren't using these tools or don't know how to use them effectively.
Yeah, it's useful, you just gotta keep it on a short leash, which is difficult when you don't know what you're doing
Basically, it's a useful tool for experienced developers that know what to look out for
From the combined comments it looks like if you are a beginner or a pro then it's great; if you only have just enough knowledge to be dangerous (in german that's proverbial "gefährliches Halbwissen") you should probably stay away from it :-)
lol Uplevel's """full report""" saying devs using Copilot create 41% more bugs has 2 pages and reads like a promotional material.
you can download it with a 10 minute email if you really want to see for yourself.
just some meaningless numbers.
I honestly stopped using it after a week