AI Alignment in the Design of Interactive AI: Specification Alignment, Process Alignment, and Evaluation Support
This paper maps concepts from AI alignment onto a basic, three step interaction cycle, yielding a corresponding set of alignment objectives: 1) specification alignment: ensuring the user can efficiently and reliably communicate objectives to the AI, 2) process alignment: providing the ability to verify and optionally control the AI's execution process, and 3) evaluation support: ensuring the user can verify and understand the AI's output.
the notion of a Process Gulf, which highlights how differences between human and AI processes can lead to challenges in AI control.