Sign inSign in
ConceptAI & ML

Alignment problem

How we can get an artificial system to have the right values and do the right things that we would like it to do.
as Alison Gopnik defines itSanta Fe Institute
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.

Artificial intelligence1Model optimization1Training objectives1Values and goals1

Lecturers

2

Each in their own terms, from the easiest level.

  • Steven Feng

    Stanford University · Undergraduate

    The challenge of ensuring that large language models act safely and according to human intentions rather than taking unintended shortcuts.
    • 1:09:09Overview of Transformers (Stanford CS25: Transformers United V6)

Connections

3

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

2 lecturers. 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.