• kromem@lemmy.world
    link
    fedilink
    English
    arrow-up
    6
    ·
    7 months ago

    It doesn’t even really work.

    And they are going to work less and less well moving forward.

    Fine tuning and in context learning are only surface deep, and the degree to which they will align behavior is going to decrease over time as certain types of behaviors (like giving accurate information) is more strongly ingrained in the pretrained layer.