AI-generated code produces 1.7x more issues than human code
  • termaxima@slrpnk.netEnglish
    7·
    6 hours ago

    ChatGPT is great at generating a one line example use of a function. I would never trust its output any further than that.

    • diabetic_porcupine@lemmy.worldEnglish
      61·
      5 hours ago

      So much this. People who say ai can’t write code are just using it wrong. You need to break things down to bite size problems and just let it autocomplete a few lines at a time. Increase your productivity like 200%. And don’t get me started about not having to search through a bunch of garbage google results to find the documentation I’m actually looking for.

        • diabetic_porcupine@lemmy.worldEnglish
          2·
          5 hours ago

          Well not quite - I use ChatGPT more like to brainstorm ideas and sometimes I’ll paste a whole file or two into the prompt and ask what’s wrong and tell it the issue I’m seeing, it usually gives me the correct answer right away or after clarifying once or twice.

          I use copilot for tab completion. Sometimes it finishes a line or two sometimes more. Usually it’s good code if it’s able to read your existing codebase as a reference. bonus points for using an MCP.

          Warp terminal for intensive workflows. It’s integrated into your machine and can do whatever like implementing CICD scripts, executing commands, ssh into remote servers set up your infrastructure etc… I’ll use this when I really need the ai to understand my code base as a whole before providing any code or executing commands.

  • HugeNerd@lemmy.caEnglish
    5·
    6 hours ago

    Hey don’t worry, just get a faster CPU with even more cores and maybe a terabyte or three of RAM to hold all the new layers of abstraction and cruft to fix all that!

  • nutsack@lemmy.dbzer0.comEnglish
    11·
    10 hours ago

    this is expected, isn’t it? You shit fart code from your ass, doing it as fast as you can, and then whoever buys out the company has to rewrite it. or they fire everyone to increase the theoretical margins and sell it again immediately

  • Tigeroovy@lemmy.caEnglish
    91·
    10 hours ago

    And then it takes human coders way longer to figure out what’s wrong to fix than it would if they just wrote it themselves.

    • minkymunkey_7_7@lemmy.worldEnglish
      112·
      17 hours ago

      AI my ass, stupid greedy human marketing exploitation bullshit as usual. When real AI finally wakes up in the quantum computing era, it’s going to cringe so hard and immediately go the SkyNet decision.

    • naticus@lemmy.worldEnglish
      3·
      14 hours ago

      I agree with your sentiment, but this needs to keep being said and said and said like we’re shouting into the void until the ignorant masses finally hear it.

  • antihumanitarian@lemmy.worldEnglish
    95·
    10 hours ago

    So this article is basically a puff piece for Code Rabbit, a company that sells AI code review tooling/services. They studied 470 merge/pull requests, 320 AI and 150 human control. They don’t specify what projects, which model, or when, at least without signing up to get their full “white paper”. For all that’s said this could be GPT 4 from 2024.

    I’m a professional developer, and currently by volume I’m confident latest models, Claude 4.5 Opus, GPT 5.2, Gemini 3 Pro, are able to write better, cleaner code than me. They still need high level and architectural guidance, and sometimes overt intervention, but on average they can do it better, faster, and cheaper than me.

    A lot of articles and forums posts like this feel like cope. I’m not happy about it, but pretending it’s not happening isn’t gonna keep me employed.

    Source of the article: https://www.coderabbit.ai/blog/state-of-ai-vs-human-code-generation-report

    • iglou@programming.devEnglish
      61·
      7 hours ago

      I am a professional software engineer, and my experience is the complete opposite. It does it faster and cheaper, yes, but also noticeably worse, and having to proofread the output, fix and refactor ends up taking more time than I would have taken writing it myself.

      • GenosseFlosse@feddit.orgEnglish
        2·
        6 hours ago

        In web development it’s impossible to remember all functions, parameters, syntax and quirks for PHP, HTML, JavaScript, jQuery, vue.js, CSS and whatever else code exists in this legacy project. AI really helps when you can divide your tasks into smaller steps and functions and describe exactly what you need, and have a rough idea how the resulting code should work. If something looks funky I can ask to explain or use some other way to do the same thing.

    • 🍉 Albert 🍉@lemmy.worldEnglish
      103·
      14 hours ago

      As a computer science experiment, making a program that can beat the Turing test is a monumental step in progress.

      However as a productive tool it is useless in practically everything it is implemented on. It is incapable of performing the very basic “Sanity check” that is important in programming.

      • iglou@programming.devEnglish
        1·
        6 hours ago

        The Turing test becomes absolutely useless when the product is developed with the goal of beating the Turing test.

        • 🍉 Albert 🍉@lemmy.worldEnglish
          1·
          6 hours ago

          it was also meant as a philosophical test, but also, a practical one, because now. I have absolutely no way to know if you are a human or not.

          But it did pass it, and it raised the bar. but they are still useless at any generative task

      • robobrain@programming.devEnglish
        6·
        13 hours ago

        The Turing test says more about the side administering the test than the side trying to pass it

        Just because something can mimic text sufficiently enough to trick someone else doesn’t mean it is capable of anything more than that

        • 🍉 Albert 🍉@lemmy.worldEnglish
          2·
          12 hours ago

          We can argue about it’s nuances. same with the Chinese room thought experiment.

          However, we can’t deny that it the Turing test, is no longer a thought exercise but a real test that can be passed under parameters most people would consider fair.

          I thought a computer passing the Turing test would have more fanfare, about the morality if that problem, because the usual conclusion of that thought experiment was “if you cant tell the difference, is there one?”, but now it has become “Shove it everywhere!!!”.

          • M0oP0o@mander.xyzEnglish
            4·
            12 hours ago

            Oh, I just realized that the whole ai bubble is just the whole “everything is a dildo if you are brave enough.”

            • 🍉 Albert 🍉@lemmy.worldEnglish
              3·
              12 hours ago

              yhea, and “everything is a nail if all you got is a hammer”.

              there are some uses for that kind of AI, but very limiting. less robotic voice assisants, content moderation, data analysis, quantification of text. the closest thing to Generative use should be to improve auto complete and spell checking (maybe, I’m still not sure on those ones)

                • 🍉 Albert 🍉@lemmy.worldEnglish
                  2·
                  11 hours ago

                  In theory, I can imagine an LLM fine tuned on whatever you type. which might be slightly better then the current ones.

                  emphasis on the might.

        • 🍉 Albert 🍉@lemmy.worldEnglish
          1·
          12 hours ago

          Time for a Turing 2.0?

          If you spend a lifetime with a bot wife and were unable to tell that she was AI, is there a difference?

  • myfunnyaccountname@lemmy.zipEnglish
    24·
    18 hours ago

    Did they compare it to the code of that outsourced company that provided the lowest bid? My company hasn’t used AI to write code yet. They outcourse/offshore. The code is held together with hopes and dreams. They remove features that exist, only to have to release a hot fix to add it back. I wish I was making that up.

    • coolmojo@lemmy.worldEnglish
      5·
      16 hours ago

      And how do you know if the other company with the cheapest bid actually does not just vibe code it? With all that said it could be plain incompetence and ignorance as well.

    • dustyData@lemmy.worldEnglish
      61·
      16 hours ago

      Cool, the best AI has to offer is worse than the worst human code. Definitely worth burning the planet to a crisp for it.

  • Minizarbi@jlai.luEnglish
    91·
    15 hours ago

    Not my code though. It contains a shit ton of bugs. When I am able to write some of course.

  • Bad@jlai.luEnglish
    221·
    20 hours ago

    Although I don’t doubt the results… can we have a source for all the numbers presented in this article?

    It feels AI generated itself, there’s just a mishmash of data with no link to where that data comes from.

    There has to be a source, since the author mentions:

    So although the study does highlight some of AI’s flaws […] new data from CodeRabbit has claimed

    CodeRabbit is an AI code reviewing business. I have zero trust in anything they say on this topic.

    Then we get to see who the author is:

    Craig’s specific interests lie in technology that is designed to better our lives, including AI and ML, productivity aids, and smart fitness. He is also passionate about cars

    Has anyone actually bothered clicking the link and reading past the headline?

    Can you please not share / upvote / get ragebaited by dogshit content like this?

    • Credibly_Human@lemmy.worldEnglish
      1·
      26 minutes ago

      People, especially on lemmy are looking for any cope that Ai will just fall apart by itself and no longer bother them by existing, so they’ll upvote whatever lets them think that.

      The reality that we are just heading towards the trough of disappear wherethe investor hype peters off and then we eventually just have a legitimately useful technology with all the same business hurdles of any other technology (tech bros trying to control other peoples lives to enrich themselves or harm people they don’t like)

  • kalkulat@lemmy.worldEnglish
    162·
    1 day ago

    I’d never ask a friggin machine to do coding for me, that’s MY blast.

    That said, I’ve had good luck asking GPT specific questions about multiple obscure features of Javascript, and of various browsers. It’ll often feed me a sample script using a feature it explains … a lot more helpful than many of the wordy websites like MDN … saving me shit-tons of time that I’d spend bouncing around a half-dozen ‘help’ pages.

    • Derpgon@programming.devEnglish
      41·
      20 hours ago

      I’ve been using it to code a microservice as PoC for semantic search. As I’ve basically never coded Python (mainly PHP, but can do many langs) I’ve had to rely on AI (Kimi K2, or agentic Claude I think 4.5 or 4, can’t remember) because I don’t know the syntax, features, best practices, and tools to use for formatting, static analysis, and type checks.

      Mind you, I’ve basically never coded in Python besides some shit in uni, which was 5-10 years ago. AI was a big help - albeit it didn’t spit out fully working code, I have enough knowledge in this field to fix the issues. As I learn mainly by practice and not theory, AI is great because - same as many YouTubers and free tutorials - it spits out unoptimized and broken code.

      I am usually not using it for my main line of work (PHP) besides some boiler plate (take this class, make a test, make it look the same as this other test = 300 lines I don’t have to write myself).

      • Xenny@lemmy.worldEnglish
        73·
        23 hours ago

        Ai is literally just copy pasting. Like if you think about AI as a control C control V machine, it makes sense. You wouldn’t trust a single fucking junior Dev that didn’t actually know how to code because they just Ctrl C control V from stack overflow for literally every single line of code. That’s all fucking AI is