**Links to**: [[Language models]], [[Language]], [[04 Concepts as pre-dictions]], [[Semantic attractor]], [[Pattern]], [[Reference]], [[Metaphor]], [[Analogy]], [[Intuition]], [[Cognition]], [[Logic]], [[Invention]], [[Virtual]], etc. See also: [[Chunk]].   ### To parse is to _process chunks_, to consume segments, and (in most cases, therefore) to produce an output, to _compute_.^[At least, as we currently see it, because information flow has directionality and cannot be destroyed.] However, both _chunk_ and _parse_ can sometimes be confused (e.g., when encounters with new patterns occur).   We use this word, sometimes literally and sometimes metaphorically, to refer to the way(s) in which _chunked_ (i.e., predictable; patterned) information becomes _consumed_ (and therefore stabilized into categories, structures, types, etc.). In psycholinguistics, _parsing_ is terminologically used in this way, too: it implies distinction by conceptual categorization as well as the incremental understanding of meaning as applied via syntax; increasing abstraction. We also use the word _chunk_ technically but flexibly (sometimes interchanged with _parse_), both can be applied to any system which filters (language) data, human or otherwise. The reason _chunk_ and _parse_ can be interchangeably used is because sometimes we may parse an already predicted chunk, and sometimes parsing implies novel chunking. The metaphor is particularly apt in our current scenario: both human systems and LLMs have **information capacity limitations** that make chunking necessary, and parsing possible. Humans, in the flesh, have memory and physiological limits (I suspect _the infinite_ does not (always) make us go insane because we eventually always fall asleep and/or die) and LLMs have “context windows” and “attention mechanisms” to enable parsing. Both humans and machines segment continuous streams of information into discrete units allowing for processing, and although the underlying mechanisms may differ significantly, the metaphor is employed in order to run into their differential effects and explore, precisely, how it is that they are different. This strategy borrows from the productive generativity that has been the “animal as machine” or “mind as machine” historical metaphor. Saying how they are alike signals, often, how they differ, leading to new concepts and ways to interact with reality.   ### Examples Please notice how interpretation changes in terms of **predictive** and **generative** effects when we switch out _parse_ for _chunk_ in the examples below. Chunking implies inventing, discovering or establishing a standard as a pattern, whereas parsing implies consuming that pattern (which can lead to novel ways of chunking). 1. Given the way the Solar system functions, we are given to parse years (even though a year is already a highly abstract structure, not a given), months, weeks, the day as hours, etc.; 2. We parse geological time and history as eras, epochs, and ages; 3. We parse music as beats, measures, and movements; 4. We parse organic development as stages; 5. We parse narratives as starting and ending; meaning as (literary) genres, movements, and traditions, impressions, emotions, semantics, intuitions, words and syntax, and parse speech as phonemes, morphemes, sentences; text as paragraphs, chapters, and volumes; 6. We parse conversations as greetings, topics, strategies, purposes, closings; arguments as premises and conclusions; 7. We parse organisms as kingdom, phylum, class, order, genus, and species; 8. We parse chemical elements as the periodic table; 9. We parse knowledge as disciplines, fields, and specializations; 10. We parse mental conditions as diagnostic categories; 11. We parse legal systems as civil, criminal, and administrative, etc.; 12. We parse astronomical objects as planets, stars, galaxies, clusters, and everything (unknown) in between; 13. We parse complex visual patterns into structured ones, such as symmetries; (thereby greatly reducing uncertainty, see also: [[Symmetry]]); 14. We parse faces as organized features; societies as classes, castes, or socioeconomic strata; social interactions as formal and informal; familiar, estranged and otherwise unrelatable; kinship as family trees and other relational terms; 15. We parse political systems as democracies, autocracies, and other forms; religious practices and systems as rituals, beliefs, and institutions. 16. Etc.