"This work is part of the third pillar of our approach to alignment research: we want to automate the alignment research work itself. A promising aspect of this approach is that it scales with the pace of AI development. As future models become increasingly intelligent and helpful as assistants, we will find better explanations."
On first look this is genius but it seems pretty tautological in a way. How do we know if the explainer is good?... Kinda leads to thinking about who watches the watchers...
On first look this is genius but it seems pretty tautological in a way. How do we know if the explainer is good?... Kinda leads to thinking about who watches the watchers...