• irishPotato@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    3
    ·
    2 days ago

    Absolutely, but that’s the easy case, computerphile had this interesting video discussing a proof of concept exploration which showed that indirectly including stuff in the training/accessible data could also lead to such behaviours. Take it with a grain of salt cause it’s obviously a bit alarmist, but very interesting nonetheless!