Discussion: Objective Robustness and Inner Alignment Terminology

📖 Description

In the alignment community, there seem to be two main ways to frame and define objective robustness and inner alignment. They are quite similar, mainly differing in the manner in which they focus on the same basic underlying problem. We'll call these the objective-focused approach and the generalization-focused approach. We don't delve into these issues of framing the problem in [Empirical Observations of Objective Robustness Failures](https://www.lesswrong.com/posts/iJDmL7HJtN5CYKReM/empirical-observations-of-objective-robustness-failures), where we present empirical observations of objective robustness failures. Instead, we think it is worth having a separate discussion of the matter. These issues have been mentioned only infrequently in a few comments on the Alignment Forum, so it seemed worthwhile to write a post describing the framings and their differences in an effort to promote further discussion in the community.

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://www.alignmentforum.org/posts/pDaxobbB9FG5Dvqyv/discussion-objective-robustness-and-inner-alignment