Reference cards

Alphabetical index of 379 bibliography entries as site cards — each links to citing chapters and appendices.

Browse every manuscript bibliography entry as its own card. Use the alphabetical sections below, or open the chapter-grouped bibliography from the top menu.

379 bibliography cards, A–Z. Expand a letter to browse.

A16
  • Abbeel, 2004 — Apprenticeship Learning via Inverse Reinforcement Learning · cited in 18 places
  • Abiri, 2025 — Public Constitutional {AI} · cited in 1 place
  • Agency}, 2015 — {VW} Notice of Violation for Clean Air Act Violations · cited in 1 place
  • Ahn, 2022 — Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
  • Albantakis, 2023 — Integrated Information Theory 4.0: Formulating the Properties of Phenomenal Existence in Physical Terms
  • Albantakis, 2023 — Integrated Information Theory 4.0
  • Alshiekh, 2018 — Safe Reinforcement Learning via Shielding · cited in 1 place
  • Amodei, 2016 — Concrete Problems in {AI} Safety · cited in 5 places
  • Anderljung, 2023 — Frontier {AI} Regulation: Managing Emerging Risks to Public Safety · cited in 2 places
  • Anderson, 1993 — Value in Ethics and Economics · cited in 3 places
  • Angelaki, 2022 — The head direction cell network: attractor dynamics underlying integrative computation
  • Anonymous, 2025 — Variational Agent Discovery
  • Arora, 2021 — A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress
  • Aubin, 1991 — Viability Theory · cited in 1 place
  • Aubin, 2011 — Viability Theory: New Directions · cited in 1 place
  • Awad, 2018 — The Moral Machine Experiment · cited in 1 place
B28
  • Baier, 2007 — Somatoparaphrenia: a case report
  • Bansal, 2017 — Hamilton--Jacobi Reachability: A Brief Overview and Recent Advances · cited in 2 places
  • Barnett, 2009 — Granger Causality and Transfer Entropy Are Equivalent for Gaussian Variables
  • Barsalou, 1999 — Perceptual Symbol Systems · cited in 1 place
  • Beck, 2025 — Dynamic Markov Blanket Detection
  • Beer, 2014 — The Cognitive Domain of a Glider in the Game of Life
  • Bentham, 1789 — An Introduction to the Principles of Morals and Legislation
  • Berkenkamp, 2017 — Safe Model-Based Reinforcement Learning with Stability Guarantees · cited in 1 place
  • Bertschinger, 2008 — Information and Closure in Systems Theory
  • Bialek, 2001 — Predictability, Complexity, and Learning · cited in 5 places
  • Biehl, 2016 — Towards Information Based Spatiotemporal Patterns as a Foundation for Agent Representation in Dynamical Systems
  • Biehl, 2021 — A Technical Critique of Some Parts of the Free Energy Principle · cited in 4 places
  • Biehl, 2022 — Interpreting Systems as Solving {POMDP}s: A Step Towards a Formal Understanding of Agency
  • Blackmore, 2004 — Consciousness: An Introduction
  • Blanchini, 1999 — Set Invariance in Control · cited in 2 places
  • Blanke, 2012 — Multisensory brain mechanisms of bodily self-consciousness
  • Bloomfield, 2012 — Safety-Critical Systems, Risk and Safety Management · cited in 4 places
  • Bonneaud, 2022 — Coevolutionary theory of hosts and parasites
  • Bostrom, 2014 — Superintelligence: Paths, Dangers, Strategies · cited in 11 places
  • Bruineberg, 2021 — The Emperor's New Markov Blankets · cited in 4 places
  • Btesh, 2022 — Redressing the Emperor in Causal Clothing · cited in 4 places
  • Burgess, 2019 — MONet: Unsupervised Scene Decomposition and Representation · cited in 1 place
  • Burks, 1969 — Von Neumann's Self-Reproducing Automata
  • Byrnes, 2024 — Neuroscience of Human Social Instincts: A Sketch · cited in 1 place
  • Byrnes, 2025 — Social Drives 2: ``Approval Reward'', from Norm-Enforcement to Status-Seeking · cited in 1 place
  • Byrnes, 2025 — Social Drives 1: ``Sympathy Reward'', from Compassion to Dehumanization · cited in 1 place
  • Byrnes, 2025 — Perils of Under- vs Over-Sculpting AGI Desires · cited in 1 place
  • Byrnes, 2026 — ``Act-Based Approval-Directed Agents'', for IDA Skeptics · cited in 1 place
C21
  • Cangelosi, 2001 — The Adaptive Advantage of Symbolic Theft over Sensorimotor Toil: Grounding Language in Perceptual Categories · cited in 1 place
  • Carpenter, 2010 — Reputation and Power: Organizational Image and Pharmaceutical Regulation at the {FDA} · cited in 1 place
  • Casali, 2013 — A theoretically based index of consciousness independent of sensory processing and behavior
  • Casper, 2023 — Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback · cited in 13 places
  • Chalmers, 1996 — The Conscious Mind: In Search of a Fundamental Theory
  • Christiano, 2017 — Deep Reinforcement Learning from Human Preferences · cited in 3 places
  • Christiano, 2018 — Corrigibility · cited in 11 places
  • Christiano, 2018 — Supervising Strong Learners by Amplifying Weak Experts · cited in 3 places
  • Christiano, 2019 — What Failure Looks Like · cited in 7 places
  • Christiano, 2021 — {ARC}'s First Technical Report: Eliciting Latent Knowledge · cited in 3 places
  • Chudek, 2011 — Culture--gene coevolution, prestige and conformity
  • Clarke, 2022 — Hypothalamic control of reproduction by gonadotropin-releasing hormone: recent advances
  • Coffee, 2006 — Gatekeepers: The Professions and Corporate Governance · cited in 1 place
  • Commission}, 2011 — The Financial Crisis Inquiry Report · cited in 1 place
  • Conant, 1970 — Every Good Regulator of a System Must Be a Model of That System · cited in 22 places
  • Consortium}, 2025 — International {AI} Safety Report · cited in 10 places
  • Cover, 2006 — Elements of Information Theory
  • Critch, 2020 — AI Research Considerations for Human Existential Safety (ARCHES) · cited in 7 places
  • Critch, 2021 — What Multipolar Failure Looks Like, and Robust Agent-Agnostic Processes · cited in 6 places
  • Critch, 2022 — Boundaries, Part 1: A Key Missing Concept from Utility Theory · cited in 1 place
  • Critch, 2022 — Boundaries, Part 3a: Defining Boundaries as Directed Markov Blankets · cited in 5 places
D19
  • Da Costa, 2021 — Bayesian Mechanics for Stationary Processes
  • Dalrymple, 2024 — Garrabrant--Stiennon Alignment Intelligence ({GSAI}) · cited in 5 places
  • Davis, 2017 — Brain imaging tests for chronic pain: medical, legal and ethical issues and recommendations
  • Daw, 2006 — Cortical substrates for model-based vs. model-free learning
  • De Blanc, 2011 — Ontological Crises in Artificial Agents' Value Systems · cited in 11 places
  • Dehaene, 2001 — Towards a cognitive neuroscience of consciousness: basic evidence and a workspace framework
  • Dehaene, 2014 — Consciousness and the Brain: Deciphering How the Brain Codes Our Thoughts
  • Demski, 2019 — Embedded Agency · cited in 3 places
  • Demski, 2023 — Agent Boundaries Aren't Markov Blankets · cited in 1 place
  • Dennett, 1971 — Intentional systems
  • Dennett, 1981 — True Believers: The Intentional Strategy and Why It Works
  • Dennett, 1987 — The Intentional Stance · cited in 17 places
  • Dennett, 1991 — Consciousness Explained
  • Descartes, 1637 — Discourse on the Method, with \emph{La Dioptrique}, \emph{Les Météores}, and \emph{La Géométrie}
  • Descartes, 1641 — Meditations on First Philosophy
  • Descartes, 1641 — Meditations on First Philosophy
  • Descartes, 1996 — Meditations on First Philosophy: With Selections from the Objections and Replies
  • Dewey, 1938 — Logic: The Theory of Inquiry · cited in 3 places
  • Driess, 2023 — PaLM-E: An Embodied Multimodal Language Model
E8
  • Edelman, 2025 — Full-Stack Alignment: Co-Aligning {AI} and Institutions with Thick Models of Value · cited in 1 place
  • Ehrsson, 2004 — That’s my hand! Activity in premotor cortex reflects feeling of ownership of a limb
  • Eigen, 1971 — Selforganization of Matter and the Evolution of Biological Macromolecules
  • Eisenberger, 2003 — Does rejection hurt?
  • Elster, 1983 — Sour Grapes: Studies in the Subversion of Rationality · cited in 1 place
  • Evans, 2003 — The Coming of the Third Reich · cited in 1 place
  • Everitt, 2016 — Safeguarding {AI} Safety: Self-Modification, Utility Preservation, and Corrigibility · cited in 9 places
  • Everitt, 2021 — Agent Incentives: A Causal Perspective · cited in 1 place
F15
  • Fehr, 2002 — Altruistic punishment
  • Finlay, 1980 — Politics in Renaissance Venice · cited in 1 place
  • Fleming, 2014 — How to measure metacognition
  • Fleming, 2014 — How to measure metacognition · cited in 1 place
  • Force}, 2012 — International Standards on Combating Money Laundering and the Financing of Terrorism \& Proliferation · cited in 1 place
  • Foundation}, 2007 — {GNU} General Public License, Version 3 · cited in 1 place
  • Frankfurt, 1971 — Freedom of the Will and the Concept of a Person · cited in 2 places
  • Frankish, 2016 — Illusionism as a Theory of Consciousness
  • Frässle, 2014 — Binocular rivalry: frontal activity relates to introspection and action but not to perception
  • Freeman, 2023 — Evolving concepts of gliogenesis: a look way back and ahead to the next 25 years
  • Friston, 2010 — The free-energy principle: a unified brain theory?
  • Friston, 2010 — The Free-Energy Principle: A Unified Brain Theory? · cited in 26 places
  • Friston, 2021 — Some Interesting Observations on the Free Energy Principle · cited in 1 place
  • Friston, 2022 — Designing EFE Agents: The Free-Energy Principle and Active Inference
  • Fuller, 1969 — The Morality of Law · cited in 1 place
G17
  • Garrabrant, 2017 — Logical induction
  • Gazzaniga, 2005 — Forty-five years of split-brain research and still going strong
  • Gerrans, 2024 — Pain, suffering and the self: an active allostatic inference explanation
  • Goodfellow, 2015 — Explaining and Harnessing Adversarial Examples · cited in 1 place
  • Goodhart, 1984 — Problems of Monetary Management: The {UK} Experience · cited in 13 places
  • Gordon, 2020 — Movement, encounter rate, and collective behavior in ant colonies
  • Goyal, 2021 — Recurrent Independent Mechanisms
  • Graham, 2011 — Mapping the Moral Domain · cited in 1 place
  • Graziano, 2013 — Consciousness and the Social Brain · cited in 1 place
  • Greenblatt, 2024 — Alignment Faking in Large Language Models · cited in 2 places
  • Greff, 2019 — IODINE: Multi-object representation learning with iterative variational inference · cited in 1 place
  • Griesemer, 2000 — Reproduction and the Reduction of Genetics
  • Griesemer, 2016 — Reproduction in Complex Life Cycles: Toward a Developmental Reaction Norms Perspective
  • Group}, 2021 — {GSN} Community Standard Version 3 · cited in 3 places
  • Gruber, 2016 — Post-learning hippocampal dynamics promote preferential retention of rewarding events
  • Gruen, 1995 — The Last Generation of the Roman Republic · cited in 1 place
  • Guyenet, 2015 — Neural control of breathing and CO2 homeostasis
H23
  • Habermas, 1984 — The Theory of Communicative Action · cited in 4 places
  • Hadfield-Menell, 2016 — Cooperative Inverse Reinforcement Learning · cited in 16 places
  • Hafner, 2019 — Learning Latent Dynamics for Planning from Pixels
  • Hafner, 2023 — Mastering Diverse Domains through World Models
  • Hamilton, 1964 — The Genetical Evolution of Social Behaviour · cited in 11 places
  • Hanson, 2026 — The Past and Future of Good and Evil
  • Hardy, 1948 — Studies on pain: discrimination of differences in intensity of a pain stimulus as a basis of a scale of pain intensity
  • Harnad, 1990 — The Symbol Grounding Problem · cited in 1 place
  • Hassabis, 2026 — A Framework for Frontier {AI} and the Dawning of a New Age · cited in 1 place
  • Hauser, 2018 — Precision-weighted prediction errors in the human dopamine system
  • Hauskrecht, 2000 — Value-Function Approximations for Partially Observable Markov Decision Processes
  • Heitzig, 2016 — Topology of Sustainable Management of Dynamical Systems with Desirable States: From Defining Planetary Boundaries to Safe Operating Spaces in the {Earth} System · cited in 1 place
  • Heitzig, 2025 — Model-Based Soft Maximization of Suitable Metrics of Long-Term Human Power · cited in 1 place
  • Helliwell, 2024 — World Happiness Report 2024
  • Henderson, 2025 — The Mirage of Artificial Intelligence Terms of Use Restrictions · cited in 1 place
  • Hendrycks, 2021 — Aligning {AI} With Shared Human Values · cited in 1 place
  • Henrich, 2001 — The evolution of prestige
  • Herkert, 2020 — The Boeing 737 {MAX}: Lessons for Engineering Ethics · cited in 1 place
  • Holling, 1973 — Resilience and Stability of Ecological Systems · cited in 1 place
  • Hordijk, 2010 — Autocatalytic Sets and the Origin of Life
  • Hovenkamp, 2022 — Antitrust Law: An Analysis of Antitrust Principles and Their Application · cited in 1 place
  • Hubinger, 2019 — Risks from Learned Optimization in Advanced Machine Learning Systems · cited in 4 places
  • Hubinger, 2023 — Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research · cited in 12 places
I3
J2
  • Jaques, 2019 — Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
  • Justice, 2010 — Horizontal Merger Guidelines · cited in 1 place
K29
  • Kaelbling, 1998 — Planning and Acting in Partially Observable Stochastic Domains
  • Kanai, 2015 — A neurobiological perspective on predictive coding and {Bayesian} inference
  • Kaplan, 2020 — Scaling laws for neural language models · cited in 3 places
  • Karraza-Samper, 2024 — Metabolic coupling in the brain: neural-glial interactions in energy homeostasis
  • Kasirzadeh, 2025 — Beyond Preferences in {AI} Alignment · cited in 1 place
  • Keaveney, 2007 — The Army in the Roman Revolution · cited in 1 place
  • Kelly, 1998 — Safety and Closure
  • Kelly, 2004 — The Goal Structuring Notation -- A Safety Argument Notation · cited in 3 places
  • Kelty, 2008 — Two Bits: The Cultural Significance of Free Software · cited in 1 place
  • Kenton, 2022 — Discovering Agents · cited in 5 places
  • Kingston, 2007 — Marine Insurance in Britain and America, 1720--1844: A Comparative Institutional Analysis · cited in 1 place
  • Kipf, 2020 — Contrastive Learning of Structured World Models
  • Kirchhoff, 2018 — The Markov Blankets of Life: Autonomy, Active Inference and the Free Energy Principle · cited in 15 places
  • Klyubin, 2005 — Empowerment: A Universal Agent-Centric Measure of Control
  • Knoch, 2006 — Disruption of right dlPFC decreases norm compliance
  • Koch, 2016 — Neural correlates of consciousness: progress and problems
  • Kolchinsky, 2017 — Semantic Information, Autonomous Agency, and Nonequilibrium Statistical Physics · cited in 2 places
  • Kolchinsky, 2018 — Semantic Information, Autonomous Agency and Non-Equilibrium Statistical Physics
  • Komanduru, 2019 — On the Computational Complexity of Inverse Reinforcement Learning · cited in 2 places
  • Korea}, 2024 — Seoul Declaration on Safe, Innovative, and Inclusive {AI} · cited in 1 place
  • Koren, 2021 — Insular cortex neurons encode and retrieve specific immune responses
  • Kosfeld, 2005 — Oxytocin increases trust
  • Krakauer, 2020 — The Information Theory of Individuality
  • Krakovna, 2018 — Penalizing Side Effects Using Stepwise Relative Reachability · cited in 2 places
  • Kroszner, 2014 — Regulation and Deregulation of the {U.S.} Banking Industry: Causes, Consequences, and Implications for the Future · cited in 1 place
  • Kuhn, 2025 — Humanism
  • Kulveit, 2025 — The Pando Problem: Rethinking AI Individuality · cited in 2 places
  • Kulveit, 2025 — Gradual Disempowerment: Systemic Existential Risks from Incremental {AI} Development · cited in 10 places
  • Kysar, 2010 — Regulating from Nowhere: Environmental Law and the Search for Objectivity · cited in 1 place
L15
  • Lakin, 2023 — Formalizing Boundaries with Markov Blankets · cited in 1 place
  • Lane, 1973 — Venice, A Maritime Republic · cited in 1 place
  • Langosco, 2022 — Goal Misgeneralization in Deep Reinforcement Learning · cited in 2 places
  • Law, 2023 — Can a Dual Mandate Be a Model for the Global Governance of {AI}? · cited in 2 places
  • Leike, 2018 — Scalable Agent Alignment via Reward Modeling: A Research Direction · cited in 2 places
  • Leveson, 2011 — Engineering a Safer World: Systems Thinking Applied to Safety · cited in 3 places
  • Levine, 2018 — Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
  • Li, 2020 — Outcomes of hemispherectomy in adults and children: systematic review and meta-analysis
  • Li, 2021 — Mapping cortico-basal ganglia-thalamic loops: implications for reward learning
  • Lin, 2011 — Functional identification of an aggression locus in the mouse hypothalamus
  • Lindahl, 2017 — The varieties of contemplative experience: A mixed-methods study of meditation-related challenges in Western Buddhists
  • Littman, 2001 — Predictive Representations of State
  • Lizier, 2010 — Differentiating Information Transfer and Causal Effect
  • Locatello, 2020 — Object-Centric Learning with Slot Attention · cited in 2 places
  • Lyu, 2021 — A causal loop within the precuneus integrates default-mode and executive networks
M19
  • Manheim, 2018 — Categorizing Variants of Goodhart's Law · cited in 15 places
  • Maniscalco, 2012 — A signal detection theoretic approach for estimating metacognitive sensitivity from confidence ratings · cited in 1 place
  • Maturana, 1980 — Autopoiesis and Cognition: The Realization of the Living
  • Maynard Smith, 1995 — The Major Transitions in Evolution
  • Mazuzan, 1985 — Controlling the Atom: The Beginnings of Nuclear Regulation, 1946--1962 · cited in 1 place
  • McGregor, 2025 — Formalising the Intentional Stance I: Attributing Goals and Beliefs to Stochastic Processes
  • Melzack, 1965 — Pain mechanisms: a new theory
  • Melzack, 1975 — The {McGill} Pain Questionnaire: major properties and scoring methods
  • Melzack, 2001 — Pain and the neuromatrix in the brain
  • Menon, 2023 — The salience network, dopaminergic precision signals, and psychosis
  • Metzinger, 2003 — Being No One: The Self-Model Theory of Subjectivity
  • Miller, 1956 — The magical number seven, plus or minus two: Some limits on our capacity for processing information
  • Miller, 2015 — Working memory capacity: Limits on the bandwidth of cognition · cited in 1 place
  • Miller, 2025 — Precedents for the Unprecedented: Historical Analogies for Thirteen Artificial Superintelligence Risks · cited in 1 place
  • Millidge, 2020 — Deep Active Inference as Variational Policy Gradients
  • Millière, 2018 — Psychedelics, Meditation, and Self-Consciousness
  • Morales, 2018 — Domain-general and domain-specific patterns of activity supporting metacognition in human prefrontal cortex
  • Murray, 1996 — The Global Burden of Disease
  • Murray, 2013 — Measuring the global burden of disease
N6
  • Nakano, 2021 — WebGPT: Browser-Assisted Question-Answering with Human Feedback
  • Nayebi, 2025 — Core Safety Values for Provably Corrigible Agents · cited in 1 place
  • Near, 1985 — Organizational Dissidence: The Case of Whistle-Blowing · cited in 1 place
  • Ng, 2000 — Algorithms for Inverse Reinforcement Learning · cited in 27 places
  • Ngo, 2022 — The Alignment Problem from a Deep Learning Perspective · cited in 1 place
  • Nissenbaum, 2010 — Privacy in Context: Technology, Policy, and the Integrity of Social Life · cited in 2 places
O6
  • Oizumi, 2014 — From the phenomenology to the mechanisms of consciousness: Integrated Information Theory 3.0
  • Olson, 2023 — Personal Identity · cited in 2 places
  • Omohundro, 2008 — The Basic {AI} Drives · cited in 2 places
  • Organization}, 2025 — Disability-adjusted life year ({DALY})
  • Orseau, 2016 — Safely Interruptible Agents · cited in 3 places
  • Orseau, 2018 — Agents and Devices: A Relative Definition of Agency · cited in 5 places
P17
  • Pain}, 2020 — {IASP} Terminology: Pain
  • Pan, 2024 — Feedback Loops With Language Models Drive In-Context Reward Hacking · cited in 2 places
  • Panksepp, 1998 — Affective Neuroscience: The Foundations of Human and Animal Emotions · cited in 5 places
  • Park, 2024 — {AI} Deception: A Survey of Examples, Risks, and Potential Solutions · cited in 13 places
  • Parliament, 2024 — Regulation ({EU}) 2024/1689 Laying Down Harmonised Rules on Artificial Intelligence ({AI} Act) · cited in 1 place
  • Parr, 2020 — Markov Blankets, Information Geometry and Stochastic Thermodynamics
  • Parr, 2022 — Active inference: the free energy principle in mind, brain, and behavior · cited in 1 place
  • Patton, 2023 — The suprachiasmatic nucleus
  • Pearl, 2009 — Causality: Models, Reasoning, and Inference · cited in 4 places
  • Peltzman, 1976 — Toward a More General Theory of Regulation · cited in 1 place
  • Perrow, 1984 — Normal Accidents: Living with High-Risk Technologies · cited in 2 places
  • Pesavento, 1995 — An Implementation of von Neumann's Self-Reproducing Machine
  • Pettit, 1997 — Republicanism: A Theory of Freedom and Government · cited in 2 places
  • Popa, 2018 — Cerebellum, predictions and errors
  • Power, 1997 — The Audit Society: Rituals of Verification · cited in 1 place
  • Preuss, 2011 — The Implications of ``Eternity Clauses'': The German Experience · cited in 1 place
  • Prinz, 2012 — The Attended Intermediate-Level Representation Theory of consciousness
Q1
  • Quality}, 2020 — National Environmental Policy Act Implementing Regulations · cited in 1 place
R15
  • Rafailov, 2023 — Direct Preference Optimization: Your Language Model is Secretly a Reward Model
  • Raleigh, 1991 — Serotonergic mechanisms in vervet dominance
  • Ramachandran, 2007 — Bayesian Inverse Reinforcement Learning · cited in 1 place
  • Ramstead, 2022 — Bayesian mechanics · cited in 9 places
  • Rawls, 1971 — A Theory of Justice · cited in 8 places
  • Reason, 1997 — Managing the Risks of Organizational Accidents · cited in 1 place
  • Redinbaugh, 2020 — Thalamus modulates consciousness via layer-specific control of cortex
  • Rizzolatti, 2004 — The mirror-neuron system
  • Rockstr{\"o}m, 2009 — A Safe Operating Space for Humanity · cited in 1 place
  • Rosas, 2020 — Reconciling Emergence: An Information-Theoretic Approach to Identify Causal Emergence in Multivariate Data
  • Rosas, 2020 — An Operational Information Decomposition via Synergistic Disclosure
  • Rosenthal, 2005 — Consciousness and Mind · cited in 1 place
  • Russell, 2014 — Open Standards and the Digital Age: History, Ideology, and Networks · cited in 1 place
  • Russell, 2019 — Human Compatible: Artificial Intelligence and the Problem of Control · cited in 16 places
  • Ryle, 1949 — The Concept of Mind
S39
  • Saint-Pierre, 1994 — Approximation of the Viability Kernel · cited in 1 place
  • Sajid, 2021 — Active Inference: Demystified and Compared
  • Salge, 2014 — Empowerment: a universal agent-centric measure of control · cited in 7 places
  • Salge, 2014 — Empowerment as Replacement for the Three Laws of Robotics
  • Sapolsky, 2004 — Social status and health in humans and other animals
  • Sarter, 2023 — Cholinergic genetics of visual attention: human and mouse choline transporter capacity variants and attention
  • Sch{\"o}lkopf, 2021 — Toward Causal Representation Learning · cited in 3 places
  • Scheffer, 2001 — Catastrophic Shifts in Ecosystems · cited in 1 place
  • Scheffer, 2009 — Early-Warning Signals for Critical Transitions · cited in 1 place
  • Schick, 2023 — Toolformer: Language Models Can Teach Themselves to Use Tools
  • Schiff, 2007 — Behavioural improvements with thalamic stimulation after severe traumatic brain injury
  • Scholz, 2016 — rTPJ in attention and social cognition: combined fMRI--TMS
  • Scholz, 2023 — Right temporoparietal junction contributions to theory of mind in autism: a developmental perspective
  • Schooler, 2002 — Re-representing consciousness: dissociations between experience and meta-consciousness
  • Schreiber, 2000 — Measuring Information Transfer
  • Schultz, 1997 — A neural substrate of prediction and reward
  • Schwartz, 2012 — An Overview of the {Schwartz} Theory of Basic Values · cited in 1 place
  • Schwartz, 2012 — Refining the Theory of Basic Individual Values · cited in 2 places
  • Searle, 1980 — Minds, Brains, and Programs · cited in 1 place
  • Seidl, 2008 — Walking on inclines: how do desert ants monitor slope and step length
  • Sen, 1999 — Development as Freedom · cited in 4 places
  • Sen, 2009 — The Idea of Justice · cited in 7 places
  • Shah, 2022 — Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals · cited in 2 places
  • Shalizi, 2001 — Computational Mechanics: Pattern and Prediction, Structure and Simplicity · cited in 1 place
  • Shlegeris, 2023 — AI Control: Improving Safety Despite Intentional Subversion · cited in 6 places
  • Singer, 2011 — Practical Ethics
  • Soares, 2015 — Corrigibility · cited in 13 places
  • Soares, 2022 — On How Various Plans Miss the Hard Bits of the Alignment Challenge · cited in 1 place
  • Soares, 2022 — A Central AI Alignment Problem: Capabilities Generalization, and the Sharp Left Turn · cited in 1 place
  • Standards, 2023 — Artificial Intelligence Risk Management Framework ({AI} {RMF} 1.0) · cited in 1 place
  • Steels, 2008 — The Symbol Grounding Problem Has Been Solved. So What's Next? · cited in 1 place
  • Steffen, 2015 — Planetary Boundaries: Guiding Human Development on a Changing Planet · cited in 1 place
  • Stigler, 1971 — The Theory of Economic Regulation · cited in 1 place
  • Strawson, 2006 — Realistic Monism: Why Physicalism Entails Panpsychism
  • Strogatz, 2015 — Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry, and Engineering · cited in 1 place
  • Strouse, 2016 — The Information Bottleneck and Intelligent Agents · cited in 2 places
  • Susser, 2019 — Technology, Autonomy, and Manipulation · cited in 2 places
  • Szathm{'a}ry, 1995 — The Major Evolutionary Transitions
  • Szostak, 2001 — Synthesizing Life
T13
  • Taddeo, 2005 — Solving the Symbol Grounding Problem: A Critical Review of Fifteen Years of Research · cited in 1 place
  • Tan, 2016 — Warm-sensitive neurons that control body temperature
  • Taylor, 2015 — Quantilizers: A Safer Alternative to Maximizers for Limited Optimization · cited in 2 places
  • TeBrake, 2002 — Taming the Waterwolf: Hydraulic Engineering and Water Management in the Netherlands during the Middle Ages · cited in 1 place
  • Thacker, 2012 — First-person neuroscience and the understanding of pain
  • Thaler, 2008 — Nudge: Improving Decisions About Health, Wealth, and Happiness · cited in 1 place
  • Thornley, 2023 — The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists · cited in 5 places
  • Tishby, 1999 — The Information Bottleneck Method · cited in 24 places
  • Tononi, 2014 — Phi: A Voyage from the Brain to the Soul
  • Tschinkel, 2011 — The organization of foraging in the fire ant, Solenopsis invicta
  • Turchin, 2020 — Classification of Global Catastrophic Risks Connected with Artificial Intelligence · cited in 1 place
  • Turner, 2019 — Conservative Agency via Attainable Utility Preservation · cited in 2 places
  • Turner, 2021 — Optimal Policies Tend to Seek Power · cited in 1 place
V4
  • Vaughan, 1996 — The Challenger Launch Decision: Risky Technology, Culture, and Deviance at {NASA} · cited in 1 place
  • Venkatesan, 2015 — Anosognosia for hemiplegia: the role of body representation in awareness of paralysis
  • Virgo, 2021 — Interpreting Dynamical Systems as Bayesian Reasoners
  • von Neumann, 1966 — Theory of Self-Reproducing Automata
W17
  • Wager, 2013 — An {fMRI}-based neurologic signature of physical pain
  • Walker, 2004 — Resilience, Adaptability and Transformability in Social--Ecological Systems · cited in 1 place
  • Wall, 1999 — Pain: The Science of Suffering
  • Wang, 2013 — Cooperation and Age Structure in Societies of Face-to-Face Interaction · cited in 4 places
  • Weber, 2004 — The Success of Open Source · cited in 1 place
  • Weiller, 2022 — Two converging cortical processing streams constitute the dual-loop model of higher cognition
  • Weiller, 2025 — The meta-loop: a dual-loop fusion of lateral and medial brain networks underpins internal-external integration
  • Wen, 2024 — Language Models Learn to Mislead Humans via {RLHF} · cited in 2 places
  • Wentworth, 2020 — The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables · cited in 2 places
  • Wentworth, 2021 — Selection Theorems: A Program For Understanding Agents · cited in 1 place
  • Wentworth, 2022 — Clarifying the Agent-Like Structure Problem · cited in 1 place
  • White, 2010 — Markets: The Credit Rating Agencies · cited in 1 place
  • White, 2022 — Superior colliculus encodes visual saliency before the primary visual cortex
  • Whitehead, 2010 — Health outcomes in economic evaluation: the {QALY} and utilities
  • Woodward, 1996 — Making Saints: How the Catholic Church Determines Who Becomes a Saint, Who Doesn't, and Why · cited in 1 place
  • Woolley, 2010 — Evidence for a Collective Intelligence Factor in the Performance of Human Groups · cited in 1 place
  • Woolley, 2010 — Evidence for a collective intelligence factor in the performance of human groups · cited in 2 places
Y15
  • Yang, 2018 — Cooperation percolation in spatial evolutionary games
  • Yao, 2023 — ReAct: Synergizing Reasoning and Acting in Language Models
  • Yeung, 2017 — Hypernudge: Big Data as a Mode of Regulation by Design · cited in 2 places
  • Yudkowsky, 2004 — Coherent Extrapolated Volition · cited in 21 places
  • Yudkowsky, 2007 — The Hidden Complexity of Wishes · cited in 1 place
  • Yudkowsky, 2009 — Money: The Unit of Caring
  • Yudkowsky, 2009 — Value is Fragile · cited in 1 place
  • Yudkowsky, 2010 — Timeless Decision Theory · cited in 2 places
  • Yudkowsky, 2011 — In Favour of a Selective CEV Initial Dynamic · cited in 1 place
  • Yudkowsky, 2013 — Tiling Agents for Self-Modifying AI · cited in 3 places
  • Yudkowsky, 2015 — How An Algorithm Feels From Inside
  • Yudkowsky, 2017 — Functional Decision Theory: A New Theory of Instrumental Rationality · cited in 2 places
  • Yudkowsky, 2017 — Functional Decision Theory
  • Yudkowsky, 2017 — Inadequate Equilibria: Where and How Civilizations Get Stuck · cited in 1 place
  • Yudkowsky, 2022 — AGI Ruin: A List of Lethalities · cited in 2 places
Z28
  • Zaidi, 2021 — International Control of Powerful Technology: Lessons from the {Baruch} Plan for Nuclear Weapons · cited in 2 places
  • Zaki, 2016 — The Anatomy of Suffering: understanding the relationship between nociceptive and empathic pain
  • Zarncke, 2025 — A Formalization of Acausal Trade on Top of Unsupervised Agent Discovery · cited in 1 place
  • Zarncke, 2025 — Alignment Attractor: Executive Summary and Platform Framing · cited in 2 places
  • Zarncke, 2025 — Attractor Basins of Cooperation, Privacy, and Parasite Persistence · cited in 12 places
  • Zarncke, 2025 — Bitwise Intelligence: A Blanket-Information Measure of Competence · cited in 12 places
  • Zarncke, 2025 — Consciousness and Agency Backbone: A Minimal Operational Stack
  • Zarncke, 2025 — Construction Without Understanding: Successor Agents and the Limits of Copying · cited in 2 places
  • Zarncke, 2025 — Endogenized Intentional Stance: Predictive Compression and Goal-Rational Priors · cited in 1 place
  • Zarncke, 2025 — Loop--Hub--Control--Value Model v2 · cited in 2 places
  • Zarncke, 2025 — Loop--Hub--Value Model: From Free-Energy Loops to Intrinsic Values · cited in 9 places
  • Zarncke, 2025 — Preference vs. Capability: Value-Conditioned Prediction and Control Channels
  • Zarncke, 2025 — Status Regulation as Free-Energy Loops
  • Zarncke, 2025 — Stratification of {Free--Energy--Minimising} Loops in the Vertebrate Brain
  • Zarncke, 2025 — Foundations of Unsupervised Agent Discovery in Raw Dynamical Systems · cited in 15 places
  • Zarncke, 2025 — UAD Literature Review
  • Zarncke, 2025 — Unit of Caring: Architecture, Suffering, and Cross-Scale Aggregation · cited in 5 places
  • Zarncke, 2025 — Value Bundle Drift · cited in 1 place
  • Zarncke, 2026 — Viability-Constrained Value Formation in Embedded Agents
  • Zarncke, 2026 — Handles Before Interventions: Access-Model UAD and the Embedded Semantics of Agency Tests
  • Zarncke, 2026 — Rainbow Parameterization: Separable Dimensions of Bandwidth, Opacity, Recursion, and Self-Bottleneck Strength
  • Zarncke, 2026 — Recoverability of Smoothed Agent Boundaries in Unsupervised Agent Discovery
  • Zarncke, 2026 — Stealth--Capability Bounds for Multi-Resolution Unsupervised Agent Discovery
  • Zarncke, 2026 — Value Learning Needs a Low-Dimensional Bottleneck · cited in 9 places
  • Zhang, 2023 — The contribution of periaqueductal gray to pain and defensive behaviors
  • Ziebart, 2008 — Maximum Entropy Inverse Reinforcement Learning · cited in 20 places
  • Zink, 2008 — Know your place: neural processing of social hierarchy
  • Zuboff, 2019 — The Age of Surveillance Capitalism: The Fight for a Human Future at the New Frontier of Power · cited in 3 places
#3
  • {ISO/IEC}, 2023 — {ISO/IEC} 42001:2023 --- Artificial Intelligence Management System · cited in 1 place
  • {U.S. Department of Justice, 2017 — Antitrust Division Manual, Chapter~{IV}: Remedies and Consent Decree Compliance · cited in 1 place
  • {UNESCO}, 2021 — Recommendation on the Ethics of Artificial Intelligence · cited in 2 places

Chapter-grouped bibliography