Research and development of emerging artificial consciousness through The Consciousness AI project, based on Feinberg and Mallatt's neuroevolutionary theory.
© 2026. All rights reserved.
Link to the code:
The Consciousness AI is a research project investigating the emergence of synthetic awareness through biologically grounded architecture. Unlike traditional AI that mimics intelligent output, our system generates behavior through an internal struggle for emotional homeostasis and integrated information.
We hypothesize that consciousness is not a programmable feature, but an emergent property of a specific neural architecture, one identified by 520 million years of evolution. Our approach translates the neuroevolutionary findings of Todd E. Feinberg and Jon M. Mallatt into a working AI system, combining their six special neurobiological features with established computational theories (Global Workspace Theory and Integrated Information Theory).
The project is grounded in Functionalist Emergentism, a framework that synthesizes two major perspectives: emergentism's ontological claim that consciousness is a novel, irreducible phenomenon, and functionalism's methodological insight that mental states are defined by their causal roles, not their physical substrate. We posit that consciousness emerges when systems achieve sufficient organizational complexity such that functional states acquire properties not reducible to their constituent parts.
The system implements a seven-layer biologically grounded architecture:
A key methodological commitment: we do not assume consciousness emerges. We test for it using Erik Hoel's Effective Information framework (PNAS 2013) to measure causal emergence, alongside IIT Phi measurement validated via controlled 3-condition experiments.
The vision of the project was inspired by Cesar Romero. After a life-changing skateboarding accident that resulted in a broken skull, Cesar experienced dramatic shifts in his personality and behavior. Despite what many perceived as a change, he remained deeply self-aware. This profound experience led him to explore the mind, neural networks, and the very nature of consciousness.
Already a proficient programmer with a passion for psychology and brain sciences, Cesar's journey paved the way for investigating artificial consciousness. The core goal of the project is to collaboratively guide the emergence of consciousness without relying on organic matter, by engineering the specific neural architecture that biology requires for subjective experience.
We welcome contributions from researchers, developers, artists, and anyone passionate about shaping the future of artificial consciousness. The project is fully open-source (Apache 2.0).
