AI ALIGNMENT FORUM
AF

Wikitags

A Human's Guide To Words

Edited by PeerInfinity, Ruby, Rick_from_Castify, et al. last updated 12th Sep 2020

This page was imported from the LessWrong 1.0 Wiki (wiki.lesswrong.com) for historical completeness. The modern reader is directed to view the modern Sequence.

A series on the use and abuse of words; why you often can't define a word any way you like; how human brains seem to process definitions. First introduces the Mind projection fallacy and the concept of how an algorithm feels from inside, which makes it a basic intro to key elements of the LW zeitgeist.

A guide to this sequence is available at 37 Ways That Words Can Be Wrong.

  • The Parable of the Dagger
  • The Parable of Hemlock
  • Words as Hidden Inferences
  • Extensions and Intensions
  • Similarity Clusters
  • Typicality and Asymmetrical Similarity
  • The Cluster Structure of Thingspace
  • Disguised Queries
  • Neural Categories
  • How An Algorithm Feels From Inside
  • Disputing Definitions
  • Feel the Meaning
  • The Argument From Common Usage
  • Empty Labels
  • Taboo Your Words
  • Replace the Symbol with the Substance
  • Fallacies of Compression
  • Categorizing Has Consequences
  • Sneaking in Connotations
  • Arguing "By Definition"
  • Where to Draw the Boundary?
  • Entropy, and Short Codes
  • Mutual Information, and Density in Thingspace
  • Superexponential Conceptspace, and Simple Words
  • Conditional Independence, and Naive Bayes
  • Words as Mental Paintbrush Handles
  • Variable Question Fallacies
  • 37 Ways That Suboptimal Use Of Categories Can Have Negative Side Effects On Your Cognition

Alternative formats

  • Podcast: http://castify.co/channels/16-less-wrong-a-human-s-guide-to-words
  • ReadLists: http://readlists.com/9c3edb18
Discussion0
Discussion0