Skip to content

AI slows down some experienced software developers, study finds

Technology
127 54 53
  • Same. I also like it for basic research and helping with syntax for obscure SQL queries, but coding hasn't worked very well. One of my less technical coworkers tried to vibe code something and it didn't work well. Maybe it would do okay on something routine, but generally speaking it would probably be better to use a library for that anyway.

    I actively hate the term "vibe coding." The fact is, while using an LLM for certain tasks is helpful, trying to build out an entire, production-ready application just by prompts is a huge waste of time and is guaranteed to produce garbage code.

    At some point, people like your coworker are going to have to look at the code and work on it, and if they don't know what they're doing, they'll fail.

    I commend them for giving it a shot, but I also commend them for recognizing it wasn't working.

  • I like the saying that LLMs are good at stuff you don’t know. That’s about it.

    FreedomAdvocate is right, IMO the best use case of ai is things you have an understanding of, but need some assistance. You need to understand enough to catch atleast impactful errors by the llm

  • Fun how the article concludes that AI tools are still good anyway, actually.

    This AI hype is a sickness

    LLMs are very good In the correct context, forcing people to use them for things they are already great at is not the correct context.

  • That's still not actually knowing anything. It's just temporarily adding more context to its model.

    And it's always very temporary. I have a yarn project I'm working on right now, and I used Copilot in VS Code in agent mode to scaffold it as an experiment. One of the refinements I included in the prompt file to build it is reminders throughout for things it wouldn't need reminding of if it actually "knew" the repo.

    • I had to constantly remind it that it's a yarn project, otherwise it would inevitably start trying to use NPM as it progressed through the prompt.
    • For some reason, when it's in agent mode and it makes a mistake, it wants to delete files it has fucked up, which always requires human intervention, so I peppered the prompt with reminders not to do that, but to blank the file out and start over in it.
    • The frontend of the project uses TailwindCSS. It could not remember not to keep trying to downgrade its configuration to an earlier version instead of using the current one, so I wrote the entire configuration for it by hand and inserted it into the prompt file. If I let it try to build the configuration itself, it would inevitably fuck it up and then say something completely false, like, "The version of TailwindCSS we're using is still in beta, let me try downgrading to the previous version."

    I'm not saying it wasn't helpful. It probably cut 20% off the time it would have taken me to scaffold out the app myself, which is significant. But it certainly couldn't keep track of the context provided by the repo, even though it was creating that context itself.

    Working with Copilot is like working with a very talented and fast junior developer whose methamphetamine addiction has been getting the better of it lately, and who has early onset dementia or a brain injury that destroyed their short-term memory.

    From the article: "Even after completing the tasks with AI, the developers believed that they had decreased task times by 20%. But the study found that using AI did the opposite: it increased task completion time by 19%."

    I'm not saying you didn't save time, but it's remarkable that the research shows that this perception can be false.

  • Most ides do the boring stuff with templates and code generation for like a decade so that's not so helpful to me either but if it works for you.

    Yeah but I find code generation stuff I've used in the past takes a significant amount of configuration, and will often generate a bunch of code I don't want it to, and not in the way I want it. Many times it's more trouble than it's worth. Having an LLM do it means I don't have to deal with configuring anything and it's generating code for the specific thing I want it to so I can quickly validate it did things right and make any additions I want because it's only generating the thing I'm working on that moment. Also it's the same tool for the various languages I'm using so that adds more convenience.

    Yeah if you have your IDE setup with tools to analyze the datasource and does what you want it to do, that may work better for you. But with the number of DBs I deal with, I'd be spending more time setting up code generation than actually writing code.

  • This was the case a year or two ago but now if you have an MCP server for docs and your project and goals outlined properly it's pretty good.

    Not to sound like one of the ads or articles but I vice coded an iOS app in like 6 hours, it's not so complex I don't understand it, it's multifeatured, I learned a LOT and got a useful thing instead of doing a tutorial with sample project. I don't regret having that tool. I do regret the lack of any control and oversight and public ownership of this technology but that's the timeline we're on, let's not pretend it's gay space communism (sigh) but, since AI is probably driving my medical care decisions at the insurance company level, might as well get something to play with.

  • They're also bad at that though, because if you don't know that stuff then you don't know if what it's telling you is right or wrong.

    I...think that's their point. The only reason it seems good is because you're bad and can't spot that is bad, too.

  • I have limited AI experience, but so far that's what it means to me as well: helpful in very limited circumstances.

    Mostly, I find it useful for "speaking new languages" - if I try to use AI to "help" with the stuff I have been doing daily for the past 20 years? Yeah, it's just slowing me down.

    and the only reason it's not slowing you down on other things is that you don't know enough about those other things to recognize all the stuff you need to fix

  • I actively hate the term "vibe coding." The fact is, while using an LLM for certain tasks is helpful, trying to build out an entire, production-ready application just by prompts is a huge waste of time and is guaranteed to produce garbage code.

    At some point, people like your coworker are going to have to look at the code and work on it, and if they don't know what they're doing, they'll fail.

    I commend them for giving it a shot, but I also commend them for recognizing it wasn't working.

    I think the term pretty accurately describes what is going on: they don't know how to code, but they do know what correct output for a given input looks like, so they iterate with the LLM until they get what they want. The coding here is based on vibes (does the output feel correct?) instead of logic.

    I don't think there's any problem with the term, the problem is with what's going on.

  • This post did not contain any content.

    Yeah... It's useful for summarizing searches but I'm tempted to disable it in VSCode because it's been getting in the way more than helping lately.

  • Interesting idea… we actually have a plan to go public in a couple years and I’m holding a few options, but the economy is hitting us like everyone else. I’m no longer optimistic we can reach the numbers for those options to activate

    Always keep an open mind. I stuck around in my first job until the sad and pathetic end for everyone, and when I finally did start looking the economy was worse than it had been when the writing was first on the wall.

  • I...think that's their point. The only reason it seems good is because you're bad and can't spot that is bad, too.

    To be fair, when you're in Gambukistan and you don't even know what languages are spoken, a smart phone can bail you out and get you communicating basic needs much faster and better than waving your hands and speaking English LOUDLY AND S L O W L Y . A good human translator, you can trust, should be better - depending on their grasp of English, but there's another point... who do you choose to pick your hotel for you? Google, or a local kid who spotted you from across the street and ran over to "help you out"? That's a tossup, both are out to make a profit out of you, but which one is likely to hurt you more?

  • I work for an adtech company and im pretty much the only developer for the javascript library that runs on client sites and shows our ads. I dont use AI at all because it keeps generating crap

    I have to use it for work by mandate, and overall hate it. Sometimes it can speed up certain aspects of development, especially if the domain is new or project is small, but these gains are temporary. They steal time from the learning that I would be doing during development and push that back to later in the process, and they are no where near good enough to make it so that I never have to do the learning at all

  • I think the term pretty accurately describes what is going on: they don't know how to code, but they do know what correct output for a given input looks like, so they iterate with the LLM until they get what they want. The coding here is based on vibes (does the output feel correct?) instead of logic.

    I don't think there's any problem with the term, the problem is with what's going on.

    That's fair. I guess what I hate is what the term represents, rather than the term itself.

  • 0 Stimmen
    1 Beiträge
    12 Aufrufe
    Niemand hat geantwortet
  • Theoretical Private Age Confirmation -- Possible?

    Technology technology
    1
    0 Stimmen
    1 Beiträge
    11 Aufrufe
    Niemand hat geantwortet
  • I Counted All of the Yurts in Mongolia Using Machine Learning

    Technology technology
    9
    17 Stimmen
    9 Beiträge
    45 Aufrufe
    G
    I'd say, when there's a policy and its goals aren't reached, that's a policy failure. If people don't like the policy, that's an issue but it's a separate issue. It doesn't seem likely that people prefer living in tents, though. But to be fair, the government may be doing the best it can. It's ranked "Flawed Democracy" by The Economist Democracy Index. That's really good, I'd say, considering the circumstances. They are placed slightly ahead of Argentina and Hungary. OP has this to say: Due to the large number of people moving to urban locations, it has been difficult for the government to build the infrastructure needed for them. The informal settlements that grew from this difficulty are now known as ger districts. There have been many efforts to formalize and develop these areas. The Law on Allocation of Land to Mongolian Citizens for Ownership, passed in 2002, allowed for existing ger district residents to formalize the land they settled, and allowed for others to receive land from the government into the future. Along with the privatization of land, the Mongolian government has been pushing for the development of ger districts into areas with housing blocks connected to utilities. The plan for this was published in 2014 as Ulaanbaatar 2020 Master Plan and Development Approaches for 2030. Although progress has been slow (Choi and Enkhbat 7), they have been making progress in building housing blocks in ger distrcts. Residents of ger districts sell or exchange their plots to developers who then build housing blocks on them. Often this is in exchange for an apartment in the building, and often the value of the apartment is less than the land they originally had (Choi and Enkhbat 15). Based on what I’ve read about the ger districts, they have been around since at least the 1970s, and progress on developing them has been slow. When ineffective policy results in a large chunk of the populace generationally living in yurts on the outskirts of urban areas, it’s clear that there is failure. Choi, Mack Joong, and Urandulguun Enkhbat. “Distributional Effects of Ger Area Redevelopment in Ulaanbaatar, Mongolia.” International Journal of Urban Sciences, vol. 24, no. 1, Jan. 2020, pp. 50–68. DOI.org (Crossref), https://doi.org/10.1080/12265934.2019.1571433.
  • Musk's X sues New York state over social media hate speech law

    Technology technology
    1
    1
    1 Stimmen
    1 Beiträge
    11 Aufrufe
    Niemand hat geantwortet
  • One-Click RCE in ASUS's Preinstalled Driver Software

    Technology technology
    9
    29 Stimmen
    9 Beiträge
    55 Aufrufe
    M
    Yeah, Lemmy has a VERY large Linux user base, which means Windows discussions tend to get mocked or dismissed. But the reality is that Windows is still the dominant OS for the vast majority of users, by leaps and bounds. Linux runs the world’s infrastructure, but Windows is what the average user boots up every day. “This exploit only works on the average user’s OS. And it only works if the user clicks the “yes” button to escalate permissions, which they have been conditioned to always do without question. Obviously this isn’t an exploit to worry about.”
  • Is the ‘tech bro-ification’ of abortion here?

    Technology technology
    15
    1
    69 Stimmen
    15 Beiträge
    75 Aufrufe
    T
    Nah. Been working in tech for nearly 30 years, "tech bro" is a delineation. Keeps the fuckers from smearing the rest of us
  • I'm making a guide to Pocket alternatives: getoffpocket.com

    Technology technology
    30
    160 Stimmen
    30 Beiträge
    122 Aufrufe
    B
    Update: https://lemmy.world/post/31554728
  • 24 Stimmen
    14 Beiträge
    35 Aufrufe
    S
    I think you're missing some key points. Any file hosting service, no matter what, will have to deal with CSAM as long as people are able to upload to it. No matter what. This is an inescapable fact of hosting and the internet in general. Because CSAM is so ubiquitous and constant, one can only do so much to moderate any services, whether they're a large corporation are someone with a server in their closet. All of the larger platforms like 'meta', google, etc., mostly outsource that moderation to workers in developing countries so they don't have to also provide mental health counselling, but that's another story. The reason they own their own hardware is because the hosting services can and will disable your account and take down your servers if there's even a whiff of CSAM. Since it's a constant threat, it's better to own your own hardware and host everything from your closet so you don't have to eat the downtime and wait for some poor bastard in Nigeria to look through your logs and reinstate your account (not sure how that works exactly though).