Humanoid Artificial Consciousness Designed with Large Language Model Based on Psychoanalysis and Personality Theory

TL;DR

This work explores artificial consciousness by embedding psychoanalytic theory (Freud and Jung) and MBTI-based personality types into a two-module AI system: a Consciousness Module coordinating self-awareness, preconsciousness, and unconsciousness, and a Personality Module instantiating 16 MBTI profiles with needs and memories. It evaluates the system across ten scenarios using a mixed-methods approach: large-scale surveys, automated judgments via ChatGPT, and expert qualitative reviews, reporting generally strong indication of human-like cognition but with notable limitations such as limited differentiation across personas and architectural homogenization when using a single LLM. The results suggest that combining psychoanalytic-inspired architecture with MBTI-derived personalities can yield more intuitive, adaptable AI interactions, while also underscoring the need for multi-agent, persona-specific models and transparent reasoning to enhance interpretability and ethics. The study lays groundwork for robust frameworks to assess artificial consciousness and lays out concrete avenues for advancing the individuality and transparency of conscious-like AI in real-world cognitive tasks.

Abstract

Human consciousness is still a concept hard to define with current scientific understanding. Although Large Language Models (LLMs) have recently demonstrated significant advancements across various domains including translation and summarization, human consciousness is not something to imitate with current upfront technology owing to so-called hallucination. This study, therefore, proposes a novel approach to address these challenges by integrating psychoanalysis and the Myers-Briggs Type Indicator (MBTI) into constructing consciousness and personality modules. We developed three artificial consciousnesses (self-awareness, unconsciousness, and preconsciousness) based on the principles of psychoanalysis. Additionally, we designed 16 characters with different personalities representing the sixteen MBTI types, with several attributes such as needs, status, and memories. To determine if our model's artificial consciousness exhibits human-like cognition, we created ten distinct situations considering seven attributes such as emotional understanding and logical thinking. The decision-making process of artificial consciousness and the final action were evaluated in three ways: survey evaluation, three-tier classification via ChatGPT, and qualitative review. Both quantitative and qualitative analyses indicated a high likelihood of well-simulated consciousness, although the difference in response between different characters and consciousnesses was not very significant. This implies that the developed models incorporating elements of psychoanalysis and personality theory can lead to building a more intuitive and adaptable AI system with humanoid consciousness. Therefore, this study contributes to opening up new avenues for improving AI interactions in complex cognitive contexts.

Figures (6)

• Figure 1: Design of consciousness as a whole collective comprehensive communication network between consciousnesses
• Figure 2: Four pairs of dichotomous elements
• Figure 3: Conscious and personality modules integrating psychoanalysis theory, MBTI, needs and memories
• Figure 4: Study design overview
• Figure 5: (a) Mean likelihood by MBTIs, (b) Mean likelihood by situations (w/o ISTP)