I’m currently pulling together a bunch of sources – that are mostly recent – on the topic of LLMs and their use in software development. Some are peer-reviewed studies. Some are i…

studies show a clear trend – output is up (more code, more commits, bigger diffs), but outcomes don’t reflect that trend. If anything, the average team is taking longer to ship worse software

  • chicken@lemmy.dbzer0.com
    15·
    16 hours ago

    LLMs cannot distinguish between recent and out-of-date information in the context, and information in the model itself, learned during training (“dominant priors”), can often “outweigh” information we give it

    LLM inference is more accurate when we give them examples (demonstrations) rather than just describing what we want.

    Deep neural networks, including LLMs, struggle to learn patterns with long-range dependencies, at any scale of model. They will always be “driving in fog”, with local, short-range probabilities crowding out long-range ones. In case you were wondering why they suck at the “big picture” – probabilistically, it’s a blur.

    I’d guess that what all this stuff adds up to is, sustainable use of LLMs as a coding tool for nontrivial projects calls for an entirely reworked set of software development practices to conform to its limitations effectively, but the people in charge really really want and believe it to be a drop-in efficiency boost, and a big mess results. This reminds me a lot of the articles and arguments I’ve read over the years about low level vs high level programming languages and frameworks. Probably will play out a similar way.

    • douglasg14b@lemmy.world
      2·
      4 hours ago

      A lot of tokens tends to help move the needle, building in guardrails, sophisticated review of both in process work & final outputs, and consensus helps raise the bar considerably.

      That and sane, universally consistent, well structured, low tech debt, organizationally elegant, systematically evolved codebases. Something the grand majority of teams don’t have to begin with.

      Nevermind being well documented, with excellent opinionated linting and static type enforcement configurations, with robust CI checks. More things many projects don’t seem to have.

      Turns out that giving AI poorly engineered and maintained codebases just amplifies the poor engineering and low rigor already present. Something that’s endemic to our industry.