• andyburke@fedia.io
    link
    fedilink
    arrow-up
    16
    arrow-down
    15
    ·
    4 months ago

    You know what we do in engineering when we need to understand a system a lot of the time? We instrument it.

    Please explain why this can’t be instrumented. Please explain why the trace data could not be analtzed offline at different timescales as a way to start understanding what is happening in the models.

    I’m fucking embarassed for CS lately.

    • Scubus@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      17
      ·
      4 months ago

      … but they just said that it can. You check it, and you will receive gibberish. Congrats, your value is .67845278462 and if you change that by .000000001 in either direction things break. Tell me why it ended up at that number. The numbers, what do they mean?

    • Match!!@pawb.social
      link
      fedilink
      English
      arrow-up
      17
      arrow-down
      4
      ·
      4 months ago

      That field is called Explainable AI and the answer is because that costs money and the only reason AI is being used is to cut costs

      • wizardbeard@lemmy.dbzer0.com
        link
        fedilink
        English
        arrow-up
        4
        arrow-down
        3
        ·
        4 months ago

        Thank you. I am fucking exhausted from hearing people claim these things are somehow magically impossible when the real issue is cost.

        Computers and technology are amazing, but they are not magic. They are the most direct piece of reality where you can reliably say that every single action taken can be broken into discrete steps, even if that means tracing individual CPU operations on data registers like an insane person.