Skip to content

Robot performs first realistic surgery without human help: System trained on videos of surgeries performs like an expert surgeon

Technology
68 54 0
  • 148 Stimmen
    4 Beiträge
    18 Aufrufe
    czardestructo@lemmy.worldC
    Likely. The coils only job is to ignite the lamp by whacking it with high voltage to strip some barium elections off the coil to induce plasma and therefore electrical flow. The plasma then excites the phosphorus to make light. After that the coils could just be stubs of wire so long as current keeps flowing through the excited plasma. If you did it inductively it would achieve the same means but I don't think the plasma would be as dense so the lamp not as bright. My theory anyways.
  • Unlocking the Legacy of the Honda Acty Across Four Generations

    Technology technology
    1
    2
    0 Stimmen
    1 Beiträge
    7 Aufrufe
    Niemand hat geantwortet
  • 138 Stimmen
    15 Beiträge
    58 Aufrufe
    toastedravioli@midwest.socialT
    ChatGPT is not a doctor. But models trained on imaging can actually be a very useful tool for them to utilize. Even years ago, just before the AI “boom”, they were asking doctors for details on how they examine patient images and then training models on that. They found that the AI was “better” than doctors specifically because it followed the doctor’s advice 100% of the time; thereby eliminating any kind of bias from the doctor that might interfere with following their own training. Of course, the splashy headline “AI better than doctors” was ridiculous. But it does show the benefit of having a neutral tool for doctors to utilize, especially when looking at images for people who are outside of the typical demographics that much medical training is based on. (As in mostly just white men. For example, everything they train doctors on regarding knee imagining comes from images of the knees of coal miners in the UK some decades ago)
  • 0 Stimmen
    1 Beiträge
    11 Aufrufe
    Niemand hat geantwortet
  • 4 Stimmen
    1 Beiträge
    4 Aufrufe
    Niemand hat geantwortet
  • 119 Stimmen
    10 Beiträge
    48 Aufrufe
    S
    Active ISA would be a disaster. My fairly modern car is unable to reliably detect posted or implied speed limits. Sometimes it overshoots by more than double and sometimes it mandates more than 3/4 slower. The problem is the way it is and will have to be done is by means of optical detection. GPS speed measurement can also be surprisingly unreliable. Especially in underground settings like long pass-unders and tunnels. If the system would be based on something reliable like local wireless communications between speed limit postings it would be a different issue - would also come with a significant risc of abuse though. Also the passive ISA was the first thing I disabled. And I abide by posted speed limits.
  • AI and misinformation

    Technology technology
    3
    20 Stimmen
    3 Beiträge
    24 Aufrufe
    D
    Don’t lose hope, just pretend to with sarcasm. Or if you are feeling down it could work the other way too. https://aibusiness.com/nlp/sarcasm-is-really-really-really-easy-for-ai-to-handle#close-modal
  • 377 Stimmen
    58 Beiträge
    190 Aufrufe
    avidamoeba@lemmy.caA
    Does anyone know if there's additional sandboxing of local ports happening for apps running in Private Space? E: Checked myself. Can access servers in Private Space from non-Private Space browsers and vice versa. So Facebook installed in Private Space is no bueno. Even if the time to transfer data is limited since Private Space is running for short periods of time, it's likely enough to pass a token while browsing some sites.