Modeling AGI Safety Frameworks with Causal Influence Diagrams
This work addresses the need for clear comparisons among AGI safety frameworks for researchers and practitioners, but it is incremental as it applies an existing method to a new domain.
The paper tackled the problem of comparing AGI safety frameworks by modeling them with causal influence diagrams, resulting in a unified representation that facilitates easy comparison and serves as an accessible visual introduction.
Proposals for safe AGI systems are typically made at the level of frameworks, specifying how the components of the proposed system should be trained and interact with each other. In this paper, we model and compare the most promising AGI safety frameworks using causal influence diagrams. The diagrams show the optimization objective and causal assumptions of the framework. The unified representation permits easy comparison of frameworks and their assumptions. We hope that the diagrams will serve as an accessible and visual introduction to the main AGI safety frameworks.