Self-Organizing Intelligent Matter: A blueprint for an AI generating algorithm
This work addresses the challenge of developing a general AI generating algorithm for researchers in artificial life and AI, but it is incremental as it builds on existing concepts with a simplified implementation.
The paper tackles the problem of creating intelligent organisms by proposing an artificial life framework where atomic elements with neural operations interact via information exchange and physics-like rules, aiming to form the basis of a general AI generating algorithm, with a simplified implementation discussed for future scaling.
We propose an artificial life framework aimed at facilitating the emergence of intelligent organisms. In this framework there is no explicit notion of an agent: instead there is an environment made of atomic elements. These elements contain neural operations and interact through exchanges of information and through physics-like rules contained in the environment. We discuss how an evolutionary process can lead to the emergence of different organisms made of many such atomic elements which can coexist and thrive in the environment. We discuss how this forms the basis of a general AI generating algorithm. We provide a simplified implementation of such system and discuss what advances need to be made to scale it up further.