PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 31, 20260 citationsOpen Access

From Psychology to AGI: A Mathematical Foundation of Titov's Subject-Centred Model for Building Machines with Intrinsic Motivation and Subjectivity

View Full Paper
YBYury Berdinsky

Key Points

  • This research aims to create a mathematical framework for developing AI agents that possess intrinsic motivation and subjectivity based on Titov's psychological model.
  • Developed a mathematically rigorous model using a Gaussian approximation for integrated information.
  • Proposed the SubjectNet architecture along with PyTorch pseudocode.
  • Connected the model to lattice gauge theory via CNN/LQCD isomorphism.
  • The model demonstrates a closed causal loop between the intentional and intending subsystems.
  • It effectively integrates intrinsic motivation within AI agents.
  • A falsifiable experiment was proposed to validate the model's predictions.

Abstract

We translate Titov's subject-centred psychological model into a mathematically rigorous, fully differentiable framework for building AI agents with intrinsic motivation and subjectivity. The model formalises the interaction of two subsystems — the intentional (I) and the intending (D) — through a closed causal loop (reentry). We use a Gaussian approximation for integrated information ΦG, propose the SubjectNet architecture with PyTorch pseudocode, and demonstrate that in the continuum limit the model becomes a lattice gauge theory connected to the CNN/LQCD isomorphism. A minimal falsifiable experiment is proposed.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Yury Berdinsky (2026) studied this question.

synapsesocial.com/papers/6a1bd1745783ba022b6fcf5ehttps://doi.org/10.5281/zenodo.20444604
Ask AI
Helpful
Bookmark
Share
View Full Paper