Belief manifolds, and how to steer along them (opens in new tab)

A reproduction of Sarfati et al.’s “The Shape of Beliefs” BlueDot Technical AI Safety Project ( “Nature, to be commanded, must be obeyed.” — Francis Bacon, Novum Organum I.3 (1620) Introduction I believe that a deep understanding of how AI systems work internally will be crucial for medium and long term AI safety. Why? Because to mitigate the risks of a system, you must understand it. [1] So, for my BlueDot Technical AI Safety Project, I wanted to get more familiar with an emerging paradigm i...