Experiments
Our research program consists of five designed experiments, each testing specific predictions from established theories of consciousness against AI systems. All experiments follow a Design of Experiments (DOE) methodology with pre-registered hypotheses and reproducible protocols.
BuddhaBERT
ActiveFine-tuning language models on contemplative literature — Buddhist suttas, phenomenological philosophy, and contemplative science texts — to test whether training on first-person experiential accounts changes model behavior in measurable ways.
View details →Embodied Embeddings
PlannedTesting whether grounding language in simulated sensory and motor experience produces word and sentence representations with qualitatively different computational properties than text-only training.
View details →Digital Game of Life
DesignedBuilding minimal neural architectures that exhibit emergent complexity, then measuring whether Integrated Information (Phi) correlates with behavioral sophistication and adaptive capacity.
View details →IIT Emergence
DesignedDirectly testing Integrated Information Theory predictions about consciousness in neural network architectures of varying structure, measuring Phi across different topologies and training regimens.
View details →The Forgery Test
PlannedAdversarial validation of consciousness markers — training a generator to imitate the signatures of consciousness, then finding which markers resist faking. The imitation-resistant ones are the measurements worth trusting.
View details →