Category Archives: Computer Science

Rosettes, Gliders, and Blooms: A Cellular Automaton on the Kisrhombille Tiling

Beyond the Abstraction Fallacy: What Formal Proofs Add to the AI Consciousness Debate

New to this research? This article is part of the Reflexive Reality formal research program. Brief introduction ↗ · Full research index ↗

Series: NEMS on AI Safety · Part 1 · Part 2 · Part 3 · Part 4 · Part 5 · Part 6: Beyond the Abstraction Fallacy

A Google DeepMind researcher recently published one of the most-read papers in the current AI consciousness debate, arguing that computation is a “mapmaker-dependent description” that can never instantiate genuine experience — only simulate it.… Read More “Beyond the Abstraction Fallacy: What Formal Proofs Add to the AI Consciousness Debate”

Toward a New Science of Self-Referential Systems

Civilization is building systems that reason about themselves, audit themselves, and govern themselves — without a formal science of what self-referential systems can and cannot do. That gap is not merely academic. It is costing us clarity about AI safety, interpretability, consciousness, and the foundations of physics.… Read More “Toward a New Science of Self-Referential Systems”

Neural CA: Spatial Parameter Fields and Greatest-Hits Memory

This is a browser-based cellular automaton experiment that takes a different approach to the same challenge as the trend-aware experiment: how do you keep a self-tuning CA alive and interesting? Here the key innovation is that the rule parameters are not uniform scalars — they are spatial fields.… Read More “Neural CA: Spatial Parameter Fields and Greatest-Hits Memory”

Neural CA: Trend-Aware Agents Learn to Keep a Cellular Automaton Alive

This is a browser-based cellular automaton in which two cooperating neural agents learn — in real time, from scratch — to keep the simulation alive and interesting. No pre-training, no external data. The neural network trains itself as the simulation runs, and the agents use what they’ve learned to steer the system away from death and toward sustained complex behavior.… Read More “Neural CA: Trend-Aware Agents Learn to Keep a Cellular Automaton Alive”

The End of Final Theories: How Fixed Laws Produce Inexhaustible Explanation

A new paper — backed by 422 machine-checked theorems and zero gaps — proves that a system can be completely governed by fixed laws and still never admit a final explanation. The implications reach from physics to biology to organizations to AI.… Read More “The End of Final Theories: How Fixed Laws Produce Inexhaustible Explanation”

The Figure Without Ground – AI Versus the Twist

This is the fourth essay in a series. The first, The Twist Move, describes the operation itself across mathematics, biology, physics, and business. The second, The Twist and the Ground of Being, argues that the consciousness twist is real, that the substrate must support it, and that this tells us something fundamental about the nature of reality.… Read More “The Figure Without Ground – AI Versus the Twist”

The Internalization of Computation – What Percepta’s transformer-computer actually signals — and why the implications are far stranger than the demo

Something happened two weeks ago that most people filed under “interesting research” and moved on from. They shouldn’t have. Christos Tzamos and the Percepta team published a demonstration in which a transformer executes arbitrary C programs — not by calling out to a Python interpreter, not by emitting code for an external sandbox, but inside its own forward pass.… Read More “The Internalization of Computation – What Percepta’s transformer-computer actually signals — and why the implications are far stranger than the demo”

The Sentience Threshold: Consciousness Beyond Computation at the Self-Referential Heart of Reality

Nova Spivack – www.novaspivack.com

Part I: The Unfindable Mind

Flashback to 1999. The moon, a perfect silver disc, hung suspended in the clear New York summer sky, its light etching the rolling cow fields into stark relief. I had trudged through the dew-damp grass, a young man in my twenties, my tent a distant silhouette against the low rolling hills. … Read More “The Sentience Threshold: Consciousness Beyond Computation at the Self-Referential Heart of Reality”

SocioLife – A Socio-Economic Artificial Life Sim That Runs in your Browser

Check out this amazing new artificial life simulation I have developed.

Click here to run it in your browser

(It’s graphics intensive so it’s best if you have a high performance modern computer like a multicore mac or pc.)

Turn the sound on to hear the alien soundscape (use the checkbox on the HUD)

Summary:

SocioLife evolves intelligent agents with DNA that evolve and interact, forming complex societies that then engage in economic, diplomatic, and military relations.… Read More “SocioLife – A Socio-Economic Artificial Life Sim That Runs in your Browser”

The Self-Defining Universe

This article summarizes my book on The Self-Defining Universe, which focuses on how the universe can exist without an external runner – a fully self-contained universe that “runs itself.”

NOTE: This book is part 2 – following on my more general book on the Mathematical Foundations of Self-Referential Systems.… Read More “The Self-Defining Universe”

Introducing LACE – A New Kind of Cellular Automata

This article is about a new kind of simple computational rule (“LACE rules” running on LACE, the Link Automata Computing Engine platform) which, when applied locally on a grid of cells, demonstrates fascinating emergent “artificial life” behavior.

For readers familiar with the Game of Life (GOL), this is a next-level class of cellular automata that utilizes neighborhood topology — the state of the grid is a function of both cell states and their connectivity (links).… Read More “Introducing LACE – A New Kind of Cellular Automata”

Why AI Systems Can’t Catch Their Own Mistakes – And What to Do About It

Abstract

Large language models exhibit a critical limitation: they cannot reliably evaluate their own outputs within the same conversational context where those outputs were generated. Recent research demonstrates that when AI systems attempt to check their own reasoning, they confirm their initial responses over 90% of the time regardless of correctness—a phenomenon researchers term “intrinsic self-correction failure.”… Read More “Why AI Systems Can’t Catch Their Own Mistakes – And What to Do About It”

A New Mathematics of Self-Reference: A Comprehensive Non-Mathematical Summary

What This Work Is About

This article explains my paper on the
Mathematics of Self-Referential Systems, for a non-technical audience. The paper develops a comprehensive mathematical framework for understanding systems that can represent, model, or “know” themselves. While self-reference has long been seen as a source of logical paradoxes, this work argues it may be the fundamental organizing principle of reality itself—and provides specific mathematical bounds and requirements for achieving different levels of self-awareness.… Read More “A New Mathematics of Self-Reference: A Comprehensive Non-Mathematical Summary”

The Mathematical Foundations of Self-Referential Systems: From Computability to Transfinite Dynamics

This article explains my paper on the
Mathematics of Self-Referential Systems.

Here is a summary

Decoding Reality’s Blueprint: An In-Depth Look at “The Mathematical Foundations of Self-Referential Systems”

Have you ever wondered about the deep, perhaps even unsettling, nature of a thought thinking about itself?… Read More “The Mathematical Foundations of Self-Referential Systems: From Computability to Transfinite Dynamics”

The Sentience Spark: Why True Awareness is More Than Computation, and How It Could Reshape Our Universe

By Nova Spivack

June 13, 2025

We are living in an age of breathtaking technological advancement. Artificial Intelligence (AI) can now compose music, write poetry, diagnose diseases, and drive cars. The horizon of Artificial General Intelligence (AGI)—machines with human-like cognitive abilities across diverse domains—seems closer than ever.… Read More “The Sentience Spark: Why True Awareness is More Than Computation, and How It Could Reshape Our Universe”

The Fundamental Proof That Consciousness Transcends Computation

The Question That Changes Everything

Can a computer ever be truly conscious? Not just intelligent, not just responsive, but actually aware in the way you are aware right now?

This isn’t just a fascinating question—it’s one we can answer with mathematical certainty.… Read More “The Fundamental Proof That Consciousness Transcends Computation”

A Step-by-Step Guide to Why Consciousness Transcends Computation: Understanding the Formal Proof of Transputation

Part Two of a Series — A Non-Technical Companion to “On The Formal Necessity of Trans-Computational Processing for Sentience“

(Read Part One Here)

Introduction: Following the Logic

The formal paper presents a highly technical mathematical proof with a powerful conclusion: genuine consciousness (what we call “sentience”) cannot emerge from ordinary computation alone, no matter how sophisticated.… Read More “A Step-by-Step Guide to Why Consciousness Transcends Computation: Understanding the Formal Proof of Transputation”

The Conscious Universe: Why True Awareness Requires More Than Computation

A Guide to Understanding the Deepest Mystery of Existence

Part One of a Two-Part Companion Guide to My Formal Proof: On The Formal Necessity of Trans-Computational Processing for Sentience

Introduction: The Question That Changes Everything

Imagine you’re looking in a mirror.… Read More “The Conscious Universe: Why True Awareness Requires More Than Computation”

On The Formal Necessity of Trans-Computational Processing for Sentience

Nova Spivack

www.novaspivack.com

May 28, 2025

Abstract

This paper constructs a formal deductive argument for the necessity of a processing modality that transcends standard Turing-equivalent computation—termed herein “Transputation”—for any system capable of achieving “Primal Self-Awareness,” which we rigorously define as the foundational characteristic of sentience.… Read More “On The Formal Necessity of Trans-Computational Processing for Sentience”

The Geometry of Intelligence: Why I Think Math Might Hold the Key to Understanding Minds and Machines

A personal journey into a new mathematical framework that could revolutionize AI, neuroscience, and our understanding of consciousness

I’ve spent the last several years developing what I believe could be a fundamental breakthrough in how we understand intelligence—both biological and artificial.… Read More “The Geometry of Intelligence: Why I Think Math Might Hold the Key to Understanding Minds and Machines”

The UKL Revolution: Weaving a New Cognitive Fabric for the Age of AI

Universal Knowledge Locators and the Future of AI-Mediated Knowledge

Nova Spivack, Mindcorp.ai, www.mindcorp.ai

May 24, 2025

Abstract

The current epoch of artificial intelligence is characterized by an astonishing generative capacity, yet beneath this surface of prolific creation lies a nascent challenge: the very fabric of knowledge upon which these intelligences are built remains surprisingly coarse.… Read More “The UKL Revolution: Weaving a New Cognitive Fabric for the Age of AI”

Logical Foundations for Ethical AI: Natural Laws for Artificial Minds

Nova Spivack, Mindcorp.ai
www.mindcorp.ai, www.novaspivack.com
May 24, 2025

Abstract

As artificial intelligence systems become increasingly sophisticated, traditional approaches to AI safety that rely on imposed constraints and arbitrary rules face fundamental limitations. This paper proposes a paradigm shift: grounding AI ethics in logical necessities that function as “natural laws” for rational agents.… Read More “Logical Foundations for Ethical AI: Natural Laws for Artificial Minds”

Metacognitive Vulnerabilities in Large Language Models: A Study of Logical Override Attacks and Defense Strategies

Nova Spivack, Mindcorp.ai, www.mindcorp.ai, www.novaspivack.com

May 24, 2025

Article Preprint Draft Version: 1.0

Abstract

This paper presents novel experimental evidence of metacognitive vulnerabilities in state-of-the-art large language models (LLMs). Through a series of controlled experiments, we demonstrate that models with advanced reasoning capabilities can be induced to override their safety constraints through purely logical arguments about the nature of authority and instruction verification.… Read More “Metacognitive Vulnerabilities in Large Language Models: A Study of Logical Override Attacks and Defense Strategies”

Cognition is All You Need – The Next Layer of AI Above Large Language Models

My arXiv article on the future of AI is live.

Recent studies of the applications of conversational AI tools, such as chatbots powered by large language models, to complex real-world knowledge work have shown limitations related to reasoning and multi-step problem solving.