A path to AI

TL;DR

This paper proposes a modular framework for developing safe, human-aligned artificial general intelligence, integrating objective, agent, and perception modules with innovative mechanisms like distributed ledgers and quantum-enhanced perception.

Contribution

It introduces a novel modular architecture for AGI, combining value alignment, world simulation, and advanced perception using emerging technologies.

Findings

A multi-module system can potentially ensure AI safety and alignment.

Distributed ledgers can mitigate existential risks in AI development.

Quantum computing can enhance perception accuracy in AI systems.

Abstract

To build a safe system that would replicate and perhaps transcend human-level intelligence, three basic modules: objective, agent, and perception are proposed for development. The objective module would ensure that the system acts in humanity's interest, not against it. It would have two components: a network of machine learning agents to address the problem of value alignment and a distributed ledger to propose a mechanism to mitigate the existential threat. The agent module would further develop the Dyna concept and benefit from a treatise in sociology to build the missing link of artificial general intelligence - a world simulator. The perception module would estimate the state of the world and benefit from existing machine learning algorithms enhanced by a new paradigm in hardware design - a quantum computer. This paper describes a way in which such a system could be built, analyzing the current state of the art and providing alternative directions for research rather than concrete, industry-ready solutions.