lesswrong

Natural Abstraction Hypothesys

Testing The Natural Abstraction Hypothesis: Project Intro

“Our physical world abstracts well: for most systems, the information relevant “far away” from the system (in various senses) is much lower-dimensional than the system itself.”

Reminds me of Hofstadter example with the sort of billiard balls, how does he call it?

Detusch rather talks of emergent phenomenon, we can usefully do thermodynamic calculations on a pot of boiling water but if we wnated to he reductionists we should do impossible calculations on the dynamics of bubbles and the result would be the samme.

In the lesswrong post the hypothesis is developed in relation to AI and its “alignment”, I still do not grasp the full extent of this concept, mostly theoretical and detached from reality

“the natural abstraction hypothesis would dramatically simplify AI and AI alignment in particular. It would mean that a wide variety of cognitive architectures will reliably learn approximately-the-same concepts as humans use, and that these concepts can be precisely and unambiguously specified”

“If true, the natural abstraction hypothesis provides a framework for translating between high-level human concepts, low-level physical systems, and high-level concepts used by non-human systems.”

Advertisement

of Broccoli and Chestnuts

an horse chestnut is genetically closer to broccoli than to a sweet chestnut

There is no such a thing as a tree, phylogenetically like there is carcinization for sea arthropods tending to become crabs, so there is dendronization, tweak the expression of a couple of genes, heat the right and a green plant develop wood

and there’s no such a thing as wood, althought evident is it, from the point of view of evolution

apparently there is a classic Scott Alexander I should read here THE CATEGORIES WERE MADE FOR MAN, NOT MAN FOR THE CATEGORIES

The incipt does indeed smell of classic “The argument goes like this. Jonah got swallowed by a whale. But the Bible says Jonah got swallowed by a big fish. So the Bible seems to think whales are just big fish. Therefore the Bible is fallible. Therefore, the Bible was not written by God.”

GS and SF

that would be General Semantics and Science Fiction

I started from here by chance https://www.lesswrong.com/posts/qc7P2NwfxQMC3hdgm/rationalism-before-the-sequences

“SF author Greg Bear probably closed the book on attempts to define science fiction as a genre in 1994 when he said “the branch of fantastic literature which affirms the rational knowability of the universe””

and follows some stories on GS and SF

General Semantics, a rationalist society https://www.generalsemantics.org/

“THE GENERAL SEMANTICS AND SCIENCE FICTION
OF ROBERT HEINLEIN AND A . E . VAN VOGT*” http://www.generalsemantics.org/wp-content/uploads/2011/05/articles/gsb/gsb41-drake.pdf

“Students’ critiques of General Semantics seems to constantly include the
following : (1) It’s nice but people can’t or don’t live that way : and, (2) How can
General Semantics be used in the ‘real’ world outside of the classroom? ”

building worlds, I guess, I should read on, Heinlein and van Vogt both attended GS groups

GENERAL SEMANTICS AS SOURCE MATERIAL IN THE WORKS OF ROBERT A. HEINLEIN https://www.jstor.org/stable/42579098?seq=1