PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 17, 20260 citationsOpen Access

Recursive Cognitive Externalization (RKE)Priority Registration — AbstractAndreas EhstandORCID: 0009-0006-3773-7796

View Full Paper
AEAndreas Ehstand

Key Points

  • The aim is to register the concept of Recursive Cognitive Externalization for cognitive representation creation.
  • Conceptual framework for Recursive Cognitive Externalization is proposed.
  • Structured interactions between humans and large language models (LLMs) are emphasized.
  • Future methodology and implementation details are noted for publication.
  • The paradigm offers unique cognitive self-modeling opportunities.
  • Facilitates novel interpersonal cognitive access through enhanced representation.
  • Distinct from traditional AI personalization and knowledge management methods.

Abstract

Recursive Cognitive Externalization (RKE)Priority Registration — AbstractAndreas EhstandORCID: 0009-0006-3773-7796 February 2026AbstractThis document registers the concept of Recursive Cognitive Externalization (RKE) — a paradigmfor the creation of persistent, updatable representations of individual cognitive architectures throughstructured human-LLM interaction. RKE is distinct from existing approaches to AI personalization,knowledge management, digital twinning, and reflective practice. The paradigm enables novel forms ofcognitive self-modeling and interpersonal cognitive access. Methodology and implementation arereserved for future publication.License: CC BY-ND 4.0 InternationalKeywords: Cognitive Externalization, Human-LLM Interaction, Self-Modeling, Exocortex, RecursiveCo-AdaptationCitation: Ehstand, A. (2026). Recursive Cognitive Externalization (RKE): Priority Registration. Zenodo.© 2026 Andreas Ehstand. All rights reserved.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Andreas Ehstand (2026) studied this question.

synapsesocial.com/papers/699405494e9c9e835dfd6127https://doi.org/10.5281/zenodo.18652024
Ask AI
Helpful
Bookmark
Share
View Full Paper