• HubertManne@piefed.social
    link
    fedilink
    English
    arrow-up
    16
    ·
    1 day ago

    this type of thing really shows llm’s to me. its great at creating this busy work but not so much with fixing it. so it can find them and we know microsoft is all in on ai coding, but it does not seem to help fixing them quickly. they are spending so much money to muck things up more and make more expense.

    • 3abas@lemmy.world
      link
      fedilink
      English
      arrow-up
      7
      arrow-down
      2
      ·
      21 hours ago

      That’s not what they’re saying. They’re saying llms are getting so good at revealing vulnerabilities that they have to put focus and effort on finding and fixing them before external malicious actors do.

      Yeah it’s faster to find a bug than to refactor a whole codebase to fix it, they’re still using llms to speed up fixing the bugs. If you believe them, anyway.

      I do. Their software stacks were so shit and bloated and had many owners with different visions and understanding of what code does what and why and they rely on being closed source to survive penetration, I do believe llms are finding vulnerabilities left and right, and focused refactoring to address legacy human slop can take time, even for a super competent llm that does it correctly in one shot.

      • MangoCats@feddit.it
        link
        fedilink
        English
        arrow-up
        1
        ·
        16 hours ago

        they rely on being closed source to survive penetration

        M$ always has.

        But even open source relied a great deal on the volume and complexity of their code base to survive penetration… until now.

    • MangoCats@feddit.it
      link
      fedilink
      English
      arrow-up
      2
      arrow-down
      1
      ·
      16 hours ago

      its great at creating this busy work but not so much with fixing it

      Actually, if you know what needs fixing, LLMs can accelerate the fixing process quite a bit too.

      The problem is: LLMs don’t know what they don’t know, so they’ll declare “good enough” and it’s up to the LLM operator to call BS and give them additional context to ensure they keep going until ALL the applicable concerns are addressed.