Sign inSign in
ConceptSystems & CS

Model alignment

An approach to agent security where the AI model itself is trained to behave safely and want the right things.
as Somesh Jha defines itUniversity of Wisconsin-Madison
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Lecturers

1

    Connections

    4

    The lectures that define it or assume it, and the concepts next to it.

    Concepts3

    1 lecturer. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.