YouTuber Internet of Bugs examines the latest demo from Cognition that showcases their “first AI software engineer” allegedly solving UpWork programming tasks.

  • lemmy___user@lemmy.world
    link
    fedilink
    English
    arrow-up
    7
    ·
    7 months ago

    This is how I use LLMs right now, and there have been a few times it’s been genuinely helpful. Mind you, most of the time it’s been helpful, it’s because it hallucinates some nonsense that gets me in the right direction, but that’s still at least a little better than the duck.

    • just another dev@lemmy.my-box.dev
      link
      fedilink
      English
      arrow-up
      3
      ·
      7 months ago

      That was my experience as well with GPT 3.5. But the hit ratio is a lot better with GPT 4, and other models like Mixtral and its derivatives.