Suppose our old friends Alice and Bob decide to undertake an art project. Alice will draw a bunch of random purple and green lines on a piece of paper. That will be Alice's picture (A). She’ll then make a copy, erase all the purple lines, and send the result as a message (M) to Bob. Bob then generates his own random purple lines, and adds them to the green lines from Alice, to create Bob's picture (B). The two then frame their two pictures and hang them side-by-side to symbolize something something similarities and differences between humans something. Y’know, artsy bullshit.

Now, suppose Carol knows the plan and is watching all this unfold. She wants to make predictions about Bob's picture, and doesn’t want to remember irrelevant details about Alice's picture. Then it seems intuitively “natural” for Carol to just remember where all the green lines are (i.e. the [...]

---

Outline:

(03:22) What Are Natural Latents? How Do We Quickly Check Whether Something Is A Natural Latent?

(03:30) Alice and Bob's Art Project

(05:05) Generalization

(06:24) Dogs

(08:53) Why Are Natural Latents Useful?

(09:13) Minimal Relevant Information

(11:58) Maximal Robust Information

(15:10) More Examples

(15:36) Toy Probability Examples

(15:40) Anti-Example: Three Flips Of A Biased Coin

(17:12) 1000 Flips Of A Biased Coin

(18:12) Ising Model

(21:07) Physics-Flavored Examples

(21:12) Gas (Over Space)

(22:16) Non-Isolated Gas

(24:23) Gasses In Systems

(25:24) Rigid Bodies

(27:24) Phase Change

(28:04) Other Examples

(28:08) “Clusters In Thingspace”

(32:45) Social Constructs: Laws

(36:06) Takeaways

The original text contained 2 footnotes which were omitted from this narration.

---

First published:

Source:

Narrated by TYPE III AUDIO.