• FermiEstimate@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    30
    ·
    5 months ago

    I conclude that scheming is a disturbingly plausible outcome of using baseline machine learning methods to train goal-directed AIs sophisticated enough to scheme (my subjective probability on such an outcome, given these conditions, is ~25%).

    Out: vibes and guesswork

    In: “subjective probability”