From cacophony to hierarchy: a principled framework for assessing AI consciousness
cs.AI, cs.CY
Submitted: 2026-09-28
Updated: 2026-09-29
Comments: 150 pages, 43 figures, 6 tables. Interactive tool: https://ai-cognition.org/cacophony-tool/ ; code: https://github.com/arvomm/cacophony-public-code [v2 Fixed misc references where the bibliography details didn't match the intended reference, including Hoel (2026); Goldstein (2024), and others. Thank you to Hoel for flagging this issue.]
Code: https://github.com/arvomm/cacophony-public-code
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Where is the Mind? Persona Vectors and LLM Individuation
- Unplugging a Seemingly Sentient Machine Is the Rational Choice -- A Metaphysical Perspective
- Are Biological Systems More Intelligent Than Artificial Intelligence?
- Large Language Models Report Subjective Experience Under Self-Referential Processing
- Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
- Report on Candidate Computational Indicators for Conscious Valenced Experience
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks
- Introduction to Artificial Consciousness: History, Current Trends and Ethical Challenges
- A Case for AI Consciousness: Language Agents and Global Workspace Theory
- Language Models Represent Space and Time
- A Disproof of Large Language Model Consciousness: The Necessity of Continual Learning for Consciousness
- Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
- Taking AI Welfare Seriously
- The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
- Mechanisms of Introspective Awareness
- Emergent Linear Representations in World Models of Self-Supervised Sequence Models
- Functional Emotions or Situational Contexts? A Discriminating Test from the Mythos Preview System Card
- The inner screen model of consciousness: applying the free energy principle directly to the study of conscious experience
- The Copernican Argument for Alien Consciousness; The Mimicry Argument Against Robot Consciousness
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems