aiqbench analysis
This paper fundamentally shifts the discourse on machine consciousness by introducing Causal Liability Theory, which argues that linguistic first-person outputs from generative models do not imply actual phenomenal experience. Through rigorous causal audits and activation patching experiments, the authors demonstrate that dissociating behavioral performance from underlying causal bearer structure is experimentally tractable, effectively debunking the "AI Consciousness Fallacy." The work provides a critical theoretical framework for distinguishing between simulated introspection and genuine subjecthood in large language models.
We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consciousness
arXiv:2609.06715v1 Announce Type: new Abstract: The contemporary debate over machine consciousness begins from a concealed assumption: that the object called "AI" already constitutes the kind of entity to which consciousness could belong. This paper challenges that assumption by separating phenomenal consciousness, introspective report, and human projective introspection, then arguing that generative systems can return linguistic traces of human interiority in first-person form without thereby identifying a phenomenal bearer. We call the resulting inference the AI Consciousness Fallacy. We then introduce Causal Liability Theory (CLT). CLT-I proposes liability closure as a criterion for individuating a candidate bearer: a physically continuing process becomes the non-delegable inheritor of constraints generated by its own endogenous discriminations. CLT-II advances the stronger conjecture that liability closure is necessary and sufficient for minimal phenomenal subjecthood. An open-weight causal audit operationalizes CLT-I across multiple model families. Forced discriminations produced persistent downstream divergence; activation patching showed strong causal mediation; live and copied adaptive states were behaviorally identical under matched randomness; and detached reconstruction preserved computational state across process replacement while, by protocol, breaking constitutive continuity and non-delegable inheritance. These results show that CLT-I distinctions are experimentally tractable and can dissociate causal bearer structure from first-person performance. The framework therefore separates consciousness attribution, causal bearer individuation, and the independent metaphysical question of consciousness constitution.
Abstract:The contemporary debate over machine consciousness begins from a concealed assumption: that the object called "AI" already constitutes the kind of entity to which consciousness could belong. This paper challenges that assumption by separating phenomenal consciousness, introspective report, and human projective introspection, then arguing that generative systems can return linguistic traces of human interiority in first-person form without thereby identifying a phenomenal bearer. We call the resulting inference the AI Consciousness Fallacy. We then introduce Causal Liability Theory (CLT). CLT-I proposes liability closure as a criterion for individuating a candidate bearer: a physically continuing process becomes the non-delegable inheritor of constraints generated by its own endogenous discriminations. CLT-II advances the stronger conjecture that liability closure is necessary and sufficient for minimal phenomenal subjecthood. An open-weight causal audit operationalizes CLT-I across multiple model families. Forced discriminations produced persistent downstream divergence; activation patching showed strong causal mediation; live and copied adaptive states were behaviorally identical under matched randomness; and detached reconstruction preserved computational state across process replacement while, by protocol, breaking constitutive continuity and non-delegable inheritance. These results show that CLT-I distinctions are experimentally tractable and can dissociate causal bearer structure from first-person performance. The framework therefore separates consciousness attribution, causal bearer individuation, and the independent metaphysical question of consciousness constitution.
Artificial Intelligence (cs.AI)
arXiv:2609.06715 [cs.AI]
(or arXiv:2609.06715v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.06715 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 303 words
Related coverage
Dharma vs Adharma - The Perplexity of Being Alive
hillpost.in · Aug 25, 2026
Mental causation is not load-bearing
LessWrong · Jun 7, 2026
John Archibald Wheeler, The Physicist Who Made Information A Foundation
Quantum Zeitgeist · Sep 13, 2026
Microsoft AI CEO says AI threats are real, and Anthropic is making it worse
The Verge · Sep 17, 2026