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.

  • Zoboomafoo@slrpnk.net
    link
    fedilink
    English
    arrow-up
    9
    arrow-down
    1
    ·
    9 months ago

    one technique even backfired, teaching the AI to recognize its triggers and better hide its bad behavior from the researchers.

    They get more human by the day