papers

Publications (45)

cs.AI2024

Metagoals Endowing Self-Modifying AGI Systems with Goal Stability or Moderated Goal Evolution: Toward a Formally Sound and Practical Approach

Ben Goertzel

We articulate here a series of specific metagoals designed to address the challenge of creating AGI systems that possess the ability to flexibly self-modify yet also have the prope…

cs.MA2022

A Reputation System for Market Security and Equity

Anton Kolonin, Deborah Duong, Ben Goertzel +4

We simulate a reputation system in a market to optimise the balance between market security and market equity. We introduce a method of using a reputation system that will stabilis…

cs.AI2024

PLN and NARS Often Yield Similar strength confidence Given Highly Uncertain Term Probabilities

Ben Goertzel

We provide a comparative analysis of the deduction, induction, and abduction formulas used in Probabilistic Logic Networks (PLN) and the Non-Axiomatic Reasoning System (NARS), two…

cs.AI2023

Generative AI vs. AGI: The Cognitive Strengths and Weaknesses of Modern LLMs

Ben Goertzel

A moderately detailed consideration of interactive LLMs as cognitive systems is given, focusing on LLMs circa mid-2023 such as ChatGPT, GPT-4, Bard, Llama, etc.. Cognitive strength…

cs.AI2020

Grounding Occam's Razor in a Formal Theory of Simplicity

Ben Goertzel

A formal theory of simplicity is introduced, in the context of a "combinational" computation model that views computation as comprising the iterated transformational and compositio…

cs.AI2018

A Reputation System for Artificial Societies

Anton Kolonin, Ben Goertzel, Deborah Duong +1

One approach to achieving artificial general intelligence (AGI) is through the emergence of complex structures and dynamic properties arising from decentralized networks of interac…

cs.MA2022

A Liquid Democracy System for Human-Computer Societies

Anton Kolonin, Ben Goertzel, Cassio Pennachin +4

Problem of reliable democratic governance is critical for survival of any community, and it will be critical for communities powered with Artificial Intelligence (AI) systems upon…

cs.LO2025

Homomorphic Encryption of Intuitionistic Logic Proofs and Functional Programs: A Categorical Approach Inspired by Composite-Order Bilinear Groups

Ben Goertzel

We present a conceptual framework for extending homomorphic encryption beyond arithmetic or Boolean operations into the domain of intuitionistic logic proofs and, by the Curry-Howa…

cs.CL2014

Learning Language from a Large (Unannotated) Corpus

Linas Vepstas, Ben Goertzel

A novel approach to the fully automated, unsupervised extraction of dependency grammars and associated syntax-to-semantic-relationship mappings from large text corpora is described…

cs.AI2020

What Kind of Programming Language Best Suits Integrative AGI?

Ben Goertzel

What kind of programming language would be most appropriate to serve the needs of integrative, multi-paradigm, multi-software-system approaches to AGI? This question is broached vi…

cs.SI2018

Reputation System for Online Communities (in Russian)

Anton Kolonin, Ben Goertzel, Deborah Duong +2

Understanding the principles of consensus in communities and finding ways to optimal solutions beneficial for entire community becomes crucial as the speeds and scales of interacti…

cs.AI2025

Intensional Inheritance Between Concepts: An Information-Theoretic Interpretation

Ben Goertzel

This paper addresses the problem of formalizing and quantifying the concept of "intensional inheritance" between two concepts. We begin by conceiving the intensional inheritance of…

cs.AI2017

Toward a Formal Model of Cognitive Synergy

Ben Goertzel

"Cognitive synergy" refers to a dynamic in which multiple cognitive processes, cooperating to control the same cognitive system, assist each other in overcoming bottlenecks encount…

cs.AI2021

Paraconsistent Foundations for Quantum Probability

Ben Goertzel

It is argued that a fuzzy version of 4-truth-valued paraconsistent logic (with truth values corresponding to True, False, Both and Neither) can be approximately isomorphically mapp…

cs.AI2020

Combinatorial Decision Dags: A Natural Computational Model for General Intelligence

Ben Goertzel

A novel computational model (CoDD) utilizing combinatory logic to create higher-order decision trees is presented. A theoretical analysis of general intelligence in terms of the fo…

cs.AI2021

Architecture of Automated Crypto-Finance Agent

Ali Raheman, Anton Kolonin, Ben Goertzel +2

We present the cognitive architecture of an autonomous agent for active portfolio management in decentralized finance, involving activities such as asset selection, portfolio balan…

cs.AI2021

The General Theory of General Intelligence: A Pragmatic Patternist Perspective

Ben Goertzel

A multi-decade exploration into the theoretical foundations of artificial and natural general intelligence, which has been expressed in a series of books and papers and used to gui…

cs.AI2022

A meta-probabilistic-programming language for bisimulation of probabilistic and non-well-founded type systems

Jonathan Warrell, Alexey Potapov, Adam Vandervorst +1

We introduce a formal meta-language for probabilistic programming, capable of expressing both programs and the type systems in which they are embedded. We are motivated here by the…

cs.CR2025

PICO: Secure Transformers via Robust Prompt Isolation and Cybersecurity Oversight

Ben Goertzel, Paulos Yibelo

We propose a robust transformer architecture designed to prevent prompt injection attacks and ensure secure, reliable response generation. Our PICO (Prompt Isolation and Cybersecur…

cs.NE2021

Info-Evo: Using Information Geometry to Guide Evolutionary Program Learning

Ben Goertzel

A novel optimization strategy, Info-Evo, is described, in which natural gradient search using nonparametric Fisher information is used to provide ongoing guidance to an evolutionar…

cs.AI2020

Embedding Vector Differences Can Be Aligned With Uncertain Intensional Logic Differences

Ben Goertzel, Mike Duncan, Debbie Duong +5

The DeepWalk algorithm is used to assign embedding vectors to nodes in the Atomspace weighted, labeled hypergraph that is used to represent knowledge in the OpenCog AGI system, in…

cs.AI2021

Patterns of Cognition: Cognitive Algorithms as Galois Connections Fulfilled by Chronomorphisms On Probabilistically Typed Metagraphs

Ben Goertzel

It is argued that a broad class of AGI-relevant algorithms can be expressed in a common formal framework, via specifying Galois connections linking search and optimization processe…

cs.MA2019

A Reputation System for Multi-Agent Marketplaces

Anton Kolonin, Ben Goertzel, Cassio Pennachin +4

We present an exploration of a reputation system based on explicit ratings weighted by the values of corresponding financial transactions from the perspective of its ability to gra…

cs.CC2026

Prime Successor Irreducibility: Turing Machine Complexity, Kolmogorov Complexity, and Weakness-Based Formulations

Ben Goertzel, Bill Lauritzen

We develop conjectures and theorems expressing the idea that the prime sequence exhibits computational irreducibility in the transition from one prime to its successor. Informally,…

cs.AI2017

Symbol Grounding via Chaining of Morphisms

Ruiting Lian, Ben Goertzel, Linas Vepstas +2

A new model of symbol grounding is presented, in which the structures of natural language, logical semantics, perception and action are represented categorically, and symbol ground…

cs.CL2023

An Evaluation of GPT-4 on the ETHICS Dataset

Sergey Rodionov, Zarathustra Amadeus Goertzel, Ben Goertzel

This report summarizes a short study of the performance of GPT-4 on the ETHICS dataset. The ETHICS dataset consists of five sub-datasets covering different fields of ethics: Justic…

quant-ph2010

Constructing quantum circuits for maximally entangled multi-qubit states using the genetic algorithm

Zheyong Fan, Hugo de Garis, Ben Goertzel +2

Numerical optimization methods such as hillclimbing and simulated annealing have been applied to search for highly entangled multi-qubit states. Here the genetic algorithm is appli…

cs.AI2025

ActPC-Geom: Towards Scalable Online Neural-Symbolic Learning via Accelerating Active Predictive Coding with Information Geometry & Diverse Cognitive Mechanisms

Ben Goertzel

This paper introduces ActPC-Geom, an approach to accelerate Active Predictive Coding (ActPC) in neural networks by integrating information geometry, specifically using Wasserstein-…

cs.PL2021

Reflective Metagraph Rewriting as a Foundation for an AGI "Language of Thought"

Ben Goertzel

MeTTa (Meta Type Talk) is a novel programming language created for use in the OpenCog Hyperon AGI system. It is designed as a meta-language with very basic and general facilities f…

cs.AI2017

Humanoid Robots as Agents of Human Consciousness Expansion

Ben Goertzel, Julia Mossbridge, Eddie Monroe +2

The "Loving AI" project involves developing software enabling humanoid robots to interact with people in loving and compassionate ways, and to promote people' self-understanding an…

cs.CC2026

A Quantale-Weakness Route to via CD Evidence Normalization and Gauge-Buffered Locked Ensembles

Ben Goertzel

We present a proof architecture for \(P \neq NP\) based on an upper--lower clash in polytime-capped conditional description length. We construct an efficiently samplable family of…

cs.AI2020

Folding and Unfolding on Metagraphs

Ben Goertzel

Typed metagraphs are defined as hypergraphs with types assigned to hyperedges and their targets, and the potential to have targets of hyperedges connect to whole links as well as t…

cs.CL2020

Guiding Symbolic Natural Language Grammar Induction via Transformer-Based Sequence Probabilities

Ben Goertzel, Andres Suarez Madrigal, Gino Yu

A novel approach to automated learning of syntactic rules governing natural languages is proposed, based on using probabilities assigned to sentences (and potentially longer word s…

cs.SI2019

A Reputation System for Marketplaces - Viability Assessment

Anton Kolonin, Ben Goertzel, Cassio Pennachin +3

In this work we explore the implementation of the reputation system for a generic marketplace, describe details of the algorithm and parameters driving its operation, justify an ap…

cs.AI2017

Cost-Based Intuitionist Probabilities on Spaces of Graphs, Hypergraphs and Theorems

Ben Goertzel

A novel partial order is defined on the space of digraphs or hypergraphs, based on assessing the cost of producing a graph via a sequence of elementary transformations. Leveraging…

cs.AI2026

A Motivational Architecture for Conversational AGI

Anna Mikeda, Ben Goertzel

Motivational architectures in cognitive AI have largely been designed for physical agents regulating bodily needs. Conversational agents operate in a different regime: their sensor…

quant-ph2025

Efficient Quantum-Safe Homomorphic Encryption for Quantum Computer Programs

Ben Goertzel

We present a lattice-based scheme for homomorphic evaluation of quantum programs and proofs that remains secure against quantum adversaries. Classical homomorphic encryption is lif…

cs.AI2020

Maximal Algorithmic Caliber and Algorithmic Causal Network Inference: General Principles of Real-World General Intelligence?

Ben Goertzel

Ideas and formalisms from far-from-equilibrium thermodynamics are ported to the context of stochastic computational processes, via following and extending Tadaki's algorithmic ther…

cs.AI2019

Distinction Graphs and Graphtropy: A Formalized Phenomenological Layer Underlying Classical and Quantum Entropy, Observational Semantics and Cognitive Computation

Ben Goertzel

A new conceptual foundation for the notion of "information" is proposed, based on the concept of a "distinction graph": a graph in which two nodes are connected iff they cannot be…

cs.LG2017

Metalearning for Feature Selection

Ben Goertzel, Nil Geisweiller, Chris Poulin

A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated p…

cs.AI2023

OpenCog Hyperon: A Framework for AGI at the Human Level and Beyond

Ben Goertzel, Vitaly Bogdanov, Michael Duncan +10

An introduction to the OpenCog Hyperon framework for Artificiai General Intelligence is presented. Hyperon is a new, mostly from-the-ground-up rewrite/redesign of the OpenCog AGI f…

cs.LO2023

Meta-MeTTa: an operational semantics for MeTTa

Lucius Gregory Meredith, Ben Goertzel, Jonathan Warrell +1

We present an operational semantics for the language MeTTa.

cs.AI2024

ActPC-Chem: Discrete Active Predictive Coding for Goal-Guided Algorithmic Chemistry as a Potential Cognitive Kernel for Hyperon & PRIMUS-Based AGI

Ben Goertzel

We explore a novel paradigm (labeled ActPC-Chem) for biologically inspired, goal-guided artificial intelligence (AI) centered on a form of Discrete Active Predictive Coding (ActPC)…

cs.AI2021

Paraconsistent Foundations for Probabilistic Reasoning, Programming and Concept Formation

Ben Goertzel

It is argued that 4-valued paraconsistent truth values (called here "p-bits") can serve as a conceptual, mathematical and practical foundation for highly AI-relevant forms of proba…

cs.AI2020

Uncertain Linear Logic via Fibring of Probabilistic and Fuzzy Logic

Ben Goertzel

Beginning with a simple semantics for propositions, based on counting observations, it is shown that probabilistic and fuzzy logic correspond to two different heuristic assumptions…