CoCoMo: Computational Consciousness Modeling for Generative and Ethical AI
Edward Yi Chang
arXiv (Cornell University) March 17, 2023 preprint DOI: 10.48550/arxiv.2304.02438 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Theoretical or philosophical paper |
|---|---|
| Citations | 9 |
| Key points | Proposes that the CoCoMo model, which combines consciousness modeling, reinforcement learning, and prompt template formulation, can embed ethical and emotional intelligence traits such as fairness, empathy, and transparency into generative AI, potentially leading to improved fairness, reduced toxicity, and increased reliability. |
Abstract
The CoCoMo model proposes a computational solution to the challenge of incorporating ethical and emotional intelligence considerations into AI systems, with the aim of creating AI agents that combine knowledge with compassion. To achieve this goal, CoCoMo prioritizes fairness, beneficence, non-maleficence, empathy, adaptability, transparency, and critical and exploratory thinking abilities. The model employs consciousness modeling, reinforcement learning, and prompt template formulation to support these desired traits. By incorporating ethical and emotional intelligence considerations, a generative AI model can potentially lead to improved fairness, reduced toxicity, and increased reliability.