11 comments

  • mgaunard 6 minutes ago

    The cost of code actually increased; code debt is being accumulated faster than we can clean it up.

  • cineticdaffodil 24 minutes ago

    Can a llm predict the price of a change to a codebase in tokens and predict the origin of the price, aka cam it see good and bad architecture?

      arjie 11 minutes ago

      Some code bases better than others but the top models can.

      mathgeek 20 minutes ago

      Ask it to do so, would love to know your results.

  • antonvs 16 minutes ago

    The worse problem is blog posts after the cost of writing collapsed.

    Not everything has to be written as though it’s a middle manager’s idea of what makes for a good TED talk.

      nvme0n1p1 3 minutes ago

      I closed the tab after seeing the AI hero image. Good to know I didn't miss anything.

      aplummer 7 minutes ago

      I read this entire article and didn’t sniff AI, plus it had some good insights…?

        sodapopcan a minute ago

        [delayed]

        nwah1 5 minutes ago

        Feels like a human-authored outline that was run through AI to make it into an article.

          hgomersall 2 minutes ago

          Well it contains a typo, so it made a cock up.

  • j45 21 minutes ago

    Software development has always evolved. Sometimes slowly, sometimes quicker.

    LLMs have brought a different unlock, and for everything we're seeing become easier, it allows people learn to use the tools to take on solving problems that couldn't be approached before.