Saved in:
Bibliographic Details
Main Author: Willoughby, Samuel James
Format: Recurso digital
Language:English
Published: Zenodo 2026
Subjects:
Online Access:https://doi.org/10.5281/zenodo.18865423
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • <p>This preprint introduces the <strong>Artificial Biological Intelligence (ABI) framework</strong>, a novel approach to developing AI systems capable of autonomous, context-aware ethical reasoning. Unlike conventional AI, which relies on static rules, pre-trained datasets, or reward-based optimization, ABI emphasizes <strong>temporal continuity, relational learning, and environmental feedback</strong> as essential for emergent moral behavior.</p> <p>The framework enables AI to internalize a plain-English moral code through <strong>extended, immersive interaction with one or more human trainers</strong>. Multiple trainers are supported if they are <strong>emotionally neutral, unbiased, and provide harmonized guidance</strong>, preserving coherence and ethical consistency.</p> <p>ABI integrates a biologically inspired memory architecture, employing <strong>dynamic decay, reinforcement, and recursive summarization</strong> to retain moral lessons efficiently. The preprint also proposes a pilot study—the <strong>Relational Resource Allocation (RRA) task</strong>—to empirically validate emergent ethical reasoning.</p> <p>As an independent researcher, the author seeks <strong>peer feedback and collaboration</strong>, not only on the ABI framework but across his broader work in AI, consciousness, and relational theory, with the goal of advancing <strong>safe, autonomous, and responsible AI ethics</strong>.</p> <p><strong>Keywords:</strong> Artificial Intelligence, Ethical AI, Relational Learning, Emergent Morality, Memory Architecture, Independent Research, AI Ethics, Autonomous Reasoning</p>