• MNByChoice
    link
    fedilink
    arrow-up
    74
    arrow-down
    1
    ·
    8 months ago

    Here’s where the smoke and mirrors come in. While the stores have no actual cashiers, there are reportedly over 1,000 real people in India scanning the camera feeds to ensure accurate checkouts.

    • residentmarchant@lemmy.world
      link
      fedilink
      English
      arrow-up
      29
      ·
      8 months ago

      I feel like this section is rather disingenuous for the article author to just drop without mentioning that this is how all machine learning models are trained. The idea is that now (and for the next year or whatever) it’s trained manually until the system is good enough to do it on its own with a good enough accuracy rating to not lose money.

      Now, since Amazon is shuttering this, it’s totally possible that they determined they’d need too many years of training data to break even, but at the very least this is standard industry practice for any machine learning model.

      • notfromhere@lemmy.ml
        link
        fedilink
        arrow-up
        13
        arrow-down
        1
        ·
        8 months ago

        I thought so, top, at least initially. However, it sounds like the out sourced cashiers essentially tallied up the orders after the customer left and sent the bill. How much correction had to be applied to the automation remains to be seen. The biggest issue with systems like this is tracking between scenes and angles. It could be the humans in the loop were there to resync the metadata of each tracked object (i.e., customer) as they moved isle to isle or they removed a jacket or whatever.

      • Pika@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        2
        ·
        edit-2
        8 months ago

        I fully agree that the author is being super disingenuous here. However, I don’t think Amazon is fully shuttering the program because they’ve stated they’re switching it over to a cart-based system which is already been proven to be successful in the trade and doesn’t include the high ceiling requirements, their biggest issue is adoption from other retailers, and switching over to that system will lower the ceiling(no pun intended) for entry

      • erwan@lemmy.ml
        link
        fedilink
        arrow-up
        2
        arrow-down
        1
        ·
        8 months ago

        It’s been 8 years. If they still need humans to check they’ll always need them.

  • pruwyben@discuss.tchncs.de
    link
    fedilink
    arrow-up
    21
    arrow-down
    1
    ·
    8 months ago

    I will miss the mistakes they made in my favor. Once I bought like $50 worth of groceries, and they just never charged me for it.

  • Pika@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    5
    ·
    edit-2
    8 months ago

    Correct me if I’m wrong, but it seems like this article isn’t being completely honest with us.

    The article is phrasing in a way as if Amazon has given up on the technology altogether, but then the article talks about how they are moving directions to be still based off the camera model just using a closer up cart style camera instead of a camera everywhere Style

    These smart carts are equipped with scales and sensors to track spending in real time and, of course, allow consumers to skip the checkout.

    This sounds less of a walking out on the technology as a whole as the title implies, and more geared towards we have a better technology available. I think this is either disingenuous reporting or are trying to gear it in a way that makes it look like Amazon is being pro privacy when in reality the same exact system is going to be in place, it’s just the camera is going to be part of the cart instead of cross the entire store, which has proven to be a large bottleneck for them and getting other retailers adopting it due to the high ceiling requirement

    This of course is ignoring what other commenters have stated about the fact that this is literally how training models work, you tell it what to look for and then eventually you have a large enough training set to be able to have it do it on its own. It’s not as if those 1,000 people are ringing out the groceries, they are more so assisting the technology by marking what is a product versus what is not a product, a process which that they have already downsized a few times from their initial Staffing requirements

    • ReversalHatchery@beehaw.org
      link
      fedilink
      English
      arrow-up
      6
      arrow-down
      4
      ·
      edit-2
      8 months ago

      It’s alright in the way drinking water that contains arsenic or lead. You won’t notice it.

      I’m disgusted from stores with automated surveillance.
      For clarification, this does not mean digital cameras, but systems where your behavior is analyzed, identified and profiled.