Natural Abstraction Hypothesis

NAH

AI가 학습하는 효율적인 추상화는 환경 자체의 특성을 반영

Abstractability - The physical world can be abstracted, and it can be summarized with information of a much lower dimension than the overall complexity of the system

Human-Compatibility - Low-dimensional abstraction aligns with the abstractions humans use

Convergence - Various cognitive structures are likely to use similar abstractions

The Natural Abstraction Hypothesis: Implications and Evidence — LessWrong

This post was written under Evan Hubinger’s direct guidance and mentorship, as a part of the Stanford Existential Risks Institute ML Alignment Theory…

https://www.lesswrong.com/posts/Fut8dtFsBYRz8atFF/the-natural-abstraction-hypothesis-implications-and-evidence

World model Interpretability with
AI Internal Interface

If the way AI interacts with various modules through internal interfaces is consistently formed, the possibility increases that humans can understand the format of these interfaces and interpret the entire world model at once.

World-Model Interpretability Is All We Need — LessWrong

Summary, by sections: • 1. Perfect world-model interpretability seems both sufficient for robust alignment (via a decent variety of approaches) and…

https://www.lesswrong.com/posts/HaHcsrDSZ3ZC2b4fK/world-model-interpretability-is-all-we-need

Natural Abstraction Hypothesis

NAH

World model Interpretability with AI Internal Interface

Recommendations

World model Interpretability with
AI Internal Interface