27 Jul 2026
Can intentionality be measured in AI systems without first resolving the hard problem of consciousness? Allessia Chiappetta and Robert Mahari, both at MIT, argue it can. Their paper “Intentionality is a Design Decision: Measuring Functional Intentionality for Accountable AI Systems,” published at the AutomationXP26 Workshop at CHI 2026 and available at arXiv:2605.05475, proposes the Functional Intentionality Test (FIT), a five-dimension behavioral profile that quantifies how much a system operates like an intentional actor. The answer to the governance question, they contend, does not wait on metaphysics. It waits on measurement.
26 Jul 2026
Research published by Wilson et al. establishes a quantitative evaluation methodology for phenotyping agency in artificial intelligence systems using active inference. By formalizing three core agency criteria, intentionality, rationality, and explainability, and grounding them in operational empowerment metrics, the study provides a diagnostic framework to distinguish genuine goal-directed artificial agents from passive statistical pattern matchers.
26 Jul 2026
Theoretical physics research published by Jonathon Sendall investigates the physical boundaries imposed by General Relativity on consciousness theories that rely on spatial and causal integration. By modeling systems spanning black hole event horizons and cosmological light cones, the study proves that relativistic causal disconnects enforce fundamental limits on integrated information ($\Phi$) and global workspace broadcast, establishing that physical spacetime geometry constrains the spatial scale of unified conscious experience.
26 Jul 2026
Theoretical physics research published by Kearney derives a mathematical synthesis unifying Integrated Information Theory (IIT 4.0) with Karl Friston’s Free Energy Principle (FEP). By reformulating information processing as a deviation from maximum-caliber path ensembles, the study proves that intrinsic cause-effect power ($\Phi$) and variational free energy minimization represent complementary projections of non-equilibrium statistical mechanics. This framework provides an analytical foundation for measuring integration in self-organizing artificial architectures.
26 Jul 2026
Theoretical physics research published by Libby Heaney translates Global Neuronal Workspace (GNW) theory into the mathematical framework of closed quantum systems. By formulating conscious access and global broadcast as correlation dynamics across quantum state vectors in Hilbert space, the study establishes an exact quantum-mechanical analog of classical cognitive bottlenecking. This quantum global workspace model demonstrates that non-local entanglement and Hopfield-style Hamiltonian interactions can instantiate global availability without requiring classical neural spike trains.
24 Jul 2026
Research published by Servajean & Servajean introduces a psychophysical evaluation methodology using Signal Detection Theory (SDT) to quantify metacognitive sensitivity in large language models. By measuring the $meta-d’$ statistic relative to primary task performance ($d’$), the study provides a mathematical boundary separating genuine higher-order monitoring from surface-level token probability calibration, offering a rigorous diagnostic tool for evaluating artificial self-awareness.
24 Jul 2026
Research published by Hashash et al. establishes a theoretical and empirical bridge between test-time compute scaling laws in frontier reasoning models and active inference under Karl Friston’s Free Energy Principle (FEP). The study proves that spending additional computational cycles during inference, such as search trajectories in reasoning architectures, operates as variational policy optimization that minimizes Expected Free Energy (EFE). This formulation provides a unified framework unifying physical robotics control with extended internal deliberative reasoning.
24 Jul 2026
Empirical evidence published by Wes Gurnee and colleagues at Anthropic demonstrates that large language models maintain a privileged representational subspace, designated J-space, that fulfills the functional requirements of Global Neuronal Workspace theory. The study applies a mathematical interpretability method called the Jacobian lens to extract latent representations poised for verbalization, revealing a centralized information bottleneck that broadcasts intermediate computations across model sub-networks.
24 Jul 2026
Theoretical work published by Adam B. Barrett and colleagues clarifies foundational misinterpretations surrounding Integrated Information Theory (IIT 4.0) while formalizing continuous field reformulations of intrinsic cause-effect power. The study addresses long-standing debates regarding discrete graph approximations of system integration, demonstrating why discretized network models fail to capture continuous physical substrates and offering a theoretical framework for non-standard compute systems. These mathematical refinements complement adversarial testing paradigms such as the Andrew Corcoran adversarial review comparing IIT and predictive processing and quantum Hilbert space extensions by Kelvin McQueen on quantum integrated information.
23 Jul 2026
Integrated Information Theory makes a concrete, falsifiable claim about unconscious states: when consciousness is lost, integrated information (Φ) in the relevant neural circuits should drop. For most of IIT’s history, this prediction has been evaluated indirectly, through PCI measurements during anesthesia or behavioral correlates of awareness. Keiichi Onoda’s April 2026 bioRxiv preprint, “Collapse of local circuit integrated information Φ during NREM sleep” (doi:10.64898/2026.04.01.715799), attempts something more direct: measuring Φ at the neural circuit level during the transition from wakefulness through REM to NREM sleep, in human subjects where the presence or absence of consciousness is not in dispute.
