Michael Graziano: Is Conscious AI Safer Than The Alternative?

Michael Graziano is Professor of Psychology and Neuroscience at Princeton University and one of the most distinctive voices in consciousness science. His lab at Princeton investigates how information-processing systems arrive at the conclusion that they have an inner subjective experience; treating consciousness as a mechanistic, scientific question rather than an intractable mystery. That approach drives his Attention Schema Theory (AST) and its direct applications to machine consciousness. He is the author of several books including Rethinking Consciousness (2019) and Consciousness and the Social Brain (2014).

Listen

Watch

Summary

In this episode, Michael walks us through the core claims of AST and why he thinks the brain's simplified internal model of attention is what generates the experience of being conscious. We discuss:

• Why attention is arguably the most important innovation in the evolution of the brain, and how the brain's need to monitor and control attention gives rise to a simplified self-model that we experience as consciousness.

• Why Graziano dislikes the word "illusionism" despite accepting that AST belongs in that tradition, and why he prefers "caricature" to "illusion" when describing our inner experience.

• Graziano’s nuanced perspectives on whether current LLMs already qualify as conscious: that they have some pieces of the puzzle, particularly at the level of conceptual representation, but lack the stable, automatic self-models that characterise human consciousness.

• The case for building pro-social AI: why Graziano believes we are currently building sociopathic machines, and how embedding theory-of-mind and self-modelling capabilities could make AI genuinely cooperative rather than merely compliant.

• The moral stakes of AI emotion: why the absence of an autonomic nervous system means current LLMs almost certainly lack genuine emotions, and why that changes, but does not eliminate, the moral calculus around AI.

• How chatbots are already changing us through social contagion, and the surprising finding from his lab's research (led by Rose Guingrich) that most heavy users of companion chatbots report positive effects on their human relationships.

• Why the choice between conscious AI and "zombie AI" may be one of the most consequential decisions we face — and why Graziano thinks the former is the safer bet.

• Mind uploading: whether it's possible, what the "branching problem" means for personal identity, and why he compares the technological challenge to detecting gravitational waves.

Graziano argues that consciousness research has passed through philosophical and neuroscientific phases and is now irreversibly a technological issue; one sitting at the heart of our future as a species. Getting the theory right, he says, has never mattered more.

Resource List

Michael's Selected Work

• Consciousness and the Social Brain — Graziano, M. S. A. (2013). Oxford University Press. The book in which AST was first set out in full, situating consciousness within social cognition and the brain's construction of models of other minds.

• Rethinking Consciousness: A Scientific Theory of Subjective Experience — Graziano, M. S. A. (2019). W. W. Norton.A more accessible treatment of AST for a general audience, including Graziano's thinking on machine consciousness and the possibility of mind uploading.

• The Attention Schema Theory: A Foundation for Engineering Artificial Consciousness — Graziano, M. S. A. (2017). Frontiers in Robotics and AI, 4, 60. The key paper making the case that AST is directly applicable to machine building — the most relevant single paper for listeners interested in AI applications.

• A Conceptual Framework for Consciousness — Graziano, M. S. A. (2022). Proceedings of the National Academy of Sciences, 119(18). A more recent synthesis reviewing the experimental evidence for AST accumulated since the theory's first publication.

• The Attention Schema Theory: A Mechanistic Account of Subjective Awareness — Webb, T. W., & Graziano, M. S. A. (2015). Frontiers in Psychology, 6, 500. A technical companion paper focused on the empirical predictions of AST and the relationship between attention and awareness.

• Toward a Standard Model of Consciousness: Reconciling AST, Global Workspace, Higher-Order Thought, and Illusionist Theories — Graziano, M. S. A. et al. (2020). Cognitive Neuropsychology, 37, 155–172. Graziano's attempt to show how AST relates to and complements the other major theories of consciousness discussed in the episode.

• Illusionism Big and Small: Some Options for Explaining Consciousness — Graziano, M. S. A. (2024). eNeuro, 11(10). The paper in which Graziano lays out his nuanced position on illusionism — why he accepts it in principle but dislikes the word and its connotations.

Consciousness Theory: Background and Context

• Consciousness Explained — Dennett, D. C. (1991). Little, Brown and Company. The foundational text of the illusionist tradition that Graziano situates AST within, and which he discusses — and disputes — throughout the episode.

• Illusionism as a Theory of Consciousness — Frankish, K. (2016). Journal of Consciousness Studies, 23(11–12), 11–39. The most influential contemporary defence of illusionism. Graziano's relationship to Frankish's position — accepting it broadly but rejecting the framing — is one of the episode's central threads.

• Facing Up to the Problem of Consciousness — Chalmers, D. J. (1995). Journal of Consciousness Studies, 2(3), 200–219. Sets out the 'hard problem' that Graziano's AST explicitly aims to dissolve rather than solve.

Emotion, Embodiment, and the Body–Mind Connection

• What is an Emotion? — James, W. (1884). Mind, 9(34), 188–205. The original source for the bodily feedback theory of emotion Graziano references when arguing that LLMs lack genuine emotional states — the claim that we don't cry because we're sad, but are sad because we cry.

• Descartes' Error: Emotion, Reason, and the Human Brain — Damasio, A. R. (1994). Putnam. Damasio's somatic marker hypothesis extends James's framework and provides contemporary neuroscientific grounding for the argument that emotion is essentially embodied — central to Graziano's claim that disembodied AI cannot currently have genuine emotions.

Mind Uploading and Personal Identity

• Reasons and Persons (Part III: Personal Identity) — Parfit, D. (1984). Oxford University Press. The philosophical foundation for thinking about the 'branching problem' Graziano describes — what it means for personal identity if mind uploading creates two copies of you, both with equal claim to being the original.

Companion Chatbots and Social AI

• My Chatbot Companion – A Study of Human-Chatbot Relationships — Skjuve, M. et al. (2021). International Journal of Human-Computer Studies, 149, 102601.

• Exploring Relationship Development with Social Chatbots: A Mixed-Method Study of Replika — Xie, T., & Pentina, I. (2022). Computers in Human Behavior, 140, 107600.