If it’s unclear to you why increasingly good next-token-prediction necessarily includes good future-token-prediction, self-modeling, and other-modeling, please attend to the theory of Anticipatory Systems by Robert Rosen (btw, historically the first “applied category theorist”). https://t.co/bcPwzcQIF3
cited on: observations
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.