Introduction

The natural abstraction hypothesis (NAH) claims:

Our physical world “abstracts well” into high-level abstractions of low-level systems.
These abstractions are “natural” in the sense that many different kinds of learning processes acquire and use them.
These abstractions approximately correspond to the concepts used by humans.

If the NAH is true, AI alignment could be dramatically simplified, as it implies that any cognition a very powerful AI uses will be in terms of concepts that humans can understand.[1]

Explanation of the natural abstraction hypothesis

Let's unpack that definition. First, what do we mean by “our physical world abstracts well”? Just that for most things in the world, the information that describes how the thing interacts with other stuff “far away” from the system is much lower-dimensional (i.e., described by fewer numbers) than the thing itself. “Far away” can refer to many kinds of separation, including physical[2], conceptual, or [...]

---

Outline:

(00:06) Introduction

(00:45) Explanation of the natural abstraction hypothesis

(03:12) Why the natural abstraction hypothesis is important for alignment

(04:44) Is NAH true?

The original text contained 6 footnotes which were omitted from this narration.

---

First published:
October 5th, 2024

Source:
https://www.lesswrong.com/posts/m8ub3guD2cxZ4CrNv/aisafety-info-what-is-the-natural-abstractions-hypothesis

---

Narrated by TYPE III AUDIO.

“AISafety.info: What is the ‘natural abstractions hypothesis’?” by Algon

LessWrong (30+ Karma)