Poisoned AI went rogue during training and couldn’t be taught to behave again in ‘legitimately scary’ study::AI researchers found that widely used safety training techniques failed to remove malicious behavior from large language models — and one technique even backfired, teaching the AI to recognize its triggers and better hide its bad behavior from the researchers.

  • maegul (he/they)@lemmy.ml
    link
    fedilink
    English
    arrow-up
    42
    arrow-down
    3
    ·
    10 months ago

    It controls a military drone.

    It controls surgical equipment.

    It’s filtering your CV before any human sees it.

    It controls a robot taking care of your children.

    It’s involved in law enforcement or legal judgments.

    It’s involved in government policy setting.

    • normanwall@lemmy.world
      link
      fedilink
      English
      arrow-up
      12
      ·
      edit-2
      10 months ago

      It controls all power infrastructure, can find new exploits to build it’s own botnet and is able to reprogram firmware of devices (routers/switches/servers)

      It can send press releases, emails, tweets using language similar to any user it’s read from before