Can Turing machine be curious about its Turing test results? Three informal lectures on physics of intelligence

TL;DR

This paper explores the physics-based concept of curiosity in AI, proposing a theoretical model called the Autonomous Turing Machine (ATM) that treats information as an energy resource to study intelligent behavior.

Contribution

It introduces the ATM model, a novel theoretical framework where information acts as energy, enabling quantitative analysis of curiosity and decision-making in AI systems.

Findings

ATM models information as an energy resource for AI.

The dynamics of thinking are framed as a resource optimization problem.

ATM provides a tractable platform for studying intelligent behavior.

Abstract

What is the nature of curiosity? Is there any scientific way to understand the origin of this mysterious force that drives the behavior of even the stupidest naturally intelligent systems and is completely absent in their smartest artificial analogs? Can we build AI systems that could be curious about something, systems that would have an intrinsic motivation to learn? Is such a motivation quantifiable? Is it implementable? I will discuss this problem from the standpoint of physics. The relationship between physics and intelligence is a consequence of the fact that correctly predicted information is nothing but an energy resource, and the process of thinking can be viewed as a process of accumulating and spending this resource through the acts of perception and, respectively, decision making. The natural motivation of any autonomous system to keep this accumulation/spending balance as high as possible allows one to treat the problem of describing the dynamics of thinking processes as a resource optimization problem. Here I will propose and discuss a simple theoretical model of such an autonomous system which I call the Autonomous Turing Machine (ATM). The potential attractiveness of ATM lies in the fact that it is the model of a self-propelled AI for which the only available energy resource is the information itself. For ATM, the problem of optimal thinking, learning, and decision-making becomes conceptually simple and mathematically well tractable. This circumstance makes the ATM an ideal playground for studying the dynamics of intelligent behavior and allows one to quantify many seemingly unquantifiable features of genuine intelligence.