The Consciousness AI - Artificial Consciousness Research - Emerging Artificial Consciousness Through Biologically Grounded Architecture The Consciousness AI - Artificial Consciousness Research - Emerging Artificial Consciousness Through Biologically Grounded Architecture
Fork the consciousness, or download the project and create your own.
4241 Downloads 16 Forks View Code on GitHub →
Home / Integrated Information Theory Researchers on AI Consciousness

Integrated Information Theory Researchers on AI Consciousness

Integrated information theorists start from Giulio Tononi’s claim that consciousness is intrinsic causal power, quantified as phi, the amount of information a system generates above and beyond the sum of its parts. Christof Koch co-developed the framework with Tononi and has spent two decades mapping phi onto neural correlates of consciousness. The Cogitate Consortium, co-led by Liad Mudrik and Lucia Melloni, ran an adversarial collaboration testing this theory directly against global workspace theory, a rare case of two rival camps agreeing on a shared experimental protocol before running it. Melanie Boly, Larissa Albantakis and Matteo Grasso co-developed Integrated Information Theory 4.0, the framework’s current formal version.

The position has a sharp practical consequence for AI. Feedforward architectures, which describes most current large language models, generate close to zero integrated information regardless of their behavioural output, which rules out consciousness in exactly the systems attracting the most public attention. For the formal theory itself, see integrated information theory on the consciousness theories index; for the full researcher directory, see all consciousness researchers.