universal_ai_as_imitation

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision		 Previous revision
universal_ai_as_imitation [2026/03/08 19:37] – pedroortegauniversal_ai_as_imitation [2026/03/08 20:59] (current) – pedroortega
Line 6: Line 6:
 {{ ::uai-imitation.webp?nolink&800 |}} {{ ::uai-imitation.webp?nolink&800 |}}
  
-====== Universal Artificial Intelligence as Imitation (General Audience Summary) ======+====== Universal Artificial Intelligence as Imitation ======
  
 Download: Paper - {{ ::universal_ai_imitation_general_audience.pdf |General Audience Version}} Download: Paper - {{ ::universal_ai_imitation_general_audience.pdf |General Audience Version}}
Line 17: Line 17:
 //Keywords: universal imitation, counterfactual action, third-party action, evidence-transfer, interface.// //Keywords: universal imitation, counterfactual action, third-party action, evidence-transfer, interface.//
  
-===== Introduction: cooking instruction and learning next steps from consequences =====+===== Introduction: learning next steps from consequences =====
  
 A common task is learning to cook with a chef. The learner attempts a step, and the kitchen replies with structured evidence: aroma shifts, sound changes, browning, viscosity, texture, and taste, as well as brief corrections or confirmations from the chef. Over repeated trials, competence takes the form of an internal rule: a compact explanation of why some interventions succeed and others fail, and a way to generalize beyond the demonstrated cases. In this setting, success is not naturally described as optimizing a standalone score in isolation. It is better described as learning what tends to //happen after// a chosen step, and using that relationship to produce good outcomes in dishes the learner has not seen before. A common task is learning to cook with a chef. The learner attempts a step, and the kitchen replies with structured evidence: aroma shifts, sound changes, browning, viscosity, texture, and taste, as well as brief corrections or confirmations from the chef. Over repeated trials, competence takes the form of an internal rule: a compact explanation of why some interventions succeed and others fail, and a way to generalize beyond the demonstrated cases. In this setting, success is not naturally described as optimizing a standalone score in isolation. It is better described as learning what tends to //happen after// a chosen step, and using that relationship to produce good outcomes in dishes the learner has not seen before.
  • universal_ai_as_imitation.1772998631.txt.gz
  • Last modified: 2026/03/08 19:37
  • by pedroortega