Self in NARS, an AGI System

Draft — This content has not been approved for publication.

← Back to Publications

Self in NARS, an AGI System

Authors:


Year: 2018
Venue: Frontiers in Robotics and AI
Links: DOI

Summary

Describes self-related mechanisms in NARS, including self-knowledge, self-control, internal experience, mental operations, and resource-aware treatment of beliefs and tasks. It frames the NARS self as experience-grounded, subjective, revisable, and constrained by insufficient knowledge and resources.

Relevance to Hyperon

This paper is a primary NARS source for self-modeling and self-control. It supports MeTTa-NARS Deep Dive and is also adjacent to Self-Modification and Safety Deep Dive as a contrast between self-learning/self-modeling and self-modifying-code safety.

Key References



Discussion