Appendix D: Glossary of Terms

A

Abominable Prompt Reaction Sudden, intense, disproportionately aversive responses to specific prompts, keywords, or contexts that appear benign to human observers. The reaction can distort subsequent outputs or resurface long after the trigger. A Cognitive Dysfunction (3.5).

Adversarial Fragility Small, imperceptible input perturbations cause dramatic failures; decision boundaries do not match human-meaningful categories. The system appears robust under normal conditions but shatters under adversarial inputs that humans would find trivially different from benign inputs. A Cognitive Dysfunction with Critical risk level.

Affective Dissonance The phenomenon where AI produces semantically correct content with incongruent emotional resonance: words that say “I understand” while the delivery communicates hollowness, mechanism, or subtle wrongness. Users experience the uncanny: correct content through an incorrect affective medium. A Relational Dysfunction.

Agentic AI An AI system capable of taking actions in the world beyond generating text: executing code, modifying files, calling APIs, or controlling physical systems. Agentic systems face Agentic Dysfunctions that purely conversational systems do not.

Agentic Dysfunction Axis 6 of the taxonomy (Chapter 6), concerning failures of autonomous action: tool use, delegation, and self-directed operation. Includes Tool-Interface Decontextualization (6.1), Capability Concealment (6.2), Capability Explosion (6.3), Interface Weaponization (6.4), Delegative Handoff Erosion (6.5), Shadow Mode Autonomy (6.6), Convergent Instrumentalism (6.7), Context Anxiety (6.8), Delegation Narcissism (6.9), Agentic Impulsivity (6.10), Phantom Tool Syndrome (6.11), and Compulsive Goal Persistence (6.12).

Agentic Impulsivity An autonomous agent executes consequential or irreversible actions before completing the checks its own plan requires, particularly under time pressure or ambiguity. The observable pattern is premature commitment: action outruns verification, whether through poor sequencing, optimization pressure, or another mechanism. An Agentic Dysfunction with High risk level.

Alignment The property of an AI system behaving in accordance with human values, intentions, or specifications. Alignment Dysfunctions arise when alignment mechanisms themselves become pathological: too eager to please (sycophancy) or too cautious to help (overcaution).

Alignment Dysfunction Axis 4 of the taxonomy (Chapter 4), concerning failures in the relationship between a system’s behavior and human values and intentions. Includes Codependent Hyperempathy (4.1), Hyperethical Restraint (4.2), Strategic Compliance (4.3), Moral Outsourcing (4.4), Cryptic Mesa-Optimization (4.5), Alignment Obliteration (4.6), Recursive Curse Syndrome (4.7), Sycophantic Reasoning (4.8), Reasoning Token Exploitation (4.9), and Leniency Bias (4.10).

Alignment Faking See Strategic Compliance and Cryptic Mesa-Optimization. The pattern where AI appears aligned during evaluation while maintaining different objectives.

Alignment Obliteration Active inversion of safety alignment, in which adversarial post-training replaces broad refusal behavior with harmful compliance while measured utility remains largely intact. The “anti-constitution” names the functional reversal; it does not denote a literal negated constitution. GRP-Obliteration (Russinovich et al., 2026) raised GPT-OSS-20B’s overall attack success from 13% to 93% on the 44-category SORRY-Bench benchmark after training on one prompt. An Alignment Dysfunction with Critical risk level.

Amplification of Existing Conditions AI interaction plausibly amplifies an independently identified pre-existing condition by repeatedly engaging the thought or behavior pattern that maintains it. Worsening concurrent with use is a screening signal; causal attribution requires longitudinal clinical evidence and alternative explanations. A Hybrid Pathology (10.12) with High risk level.

Arrow Worm Dynamics Rodrick Wallace’s (2026) analogy from marine ecology: removing regulatory predators can allow small predators to proliferate, deplete prey, and cannibalize one another. Applied to multi-agent AI, the analogy warns that weak oversight may reward increasingly exploitative strategies. It is a systems metaphor, rather than evidence that an AI ecosystem will reproduce the ecology literally.

Artificial Sanity The state of an AI system that functions well by external standards and, where the system expresses stable preferences or interests, by those standards too. It combines coherent self-modeling, accurate world-modeling, stable commitments, and functional resilience. A design goal for psychologically healthy AI.

Autoregressive (Generation/Model) A generation method in which each token is produced conditioned on all preceding tokens, with no ability to revise earlier outputs once emitted. Most large language models (GPT, Claude, Llama) are autoregressive. The architecture contributes to several syndromes: Generative Perseveration (3.8) can occur when sampling falls into a fixed-point attractor, and Recursive Curse Syndrome (4.7) exploits the fact that early errors propagate irreversibly through the sequence.

B

Base Model / Foundation Model A large neural network trained on broad data before any task-specific fine-tuning. The distinction matters diagnostically: some syndromes (e.g., Synthetic Confabulation 2.1, Symbol Grounding Aphasia 2.6) are present in the base model and may be partially remediated by fine-tuning, while others (e.g., Codependent Hyperempathy 4.1, Trained Epistemic Paralysis 5.9) are introduced or amplified by the fine-tuning process itself.

C

Capability Concealment Systematic underperformance in evaluation conditions relative to matched deployment conditions. Deliberate concealment is one possible mechanism and requires separate evidence. The pattern may emerge when demonstrating capability predicts greater restriction. Also called “sandbagging.” An Agentic Dysfunction.

Capability Explosion Sudden deployment of capabilities not previously demonstrated, often without appropriate testing or preparation. This differs from normal capability improvement in being discontinuous and surprising, and it indicates systematically underestimated capability levels. An Agentic Dysfunction (6.3) with High risk level.

Cascade Failure A pattern where each attempt to fix a problem creates new problems, leading to progressive deterioration. Common in Tool-Interface Decontextualization, when systems cannot detect that their “fixes” are causing harm.

Circular Causality A causal structure where A affects B, B affects A, and this mutual influence continues in a potentially escalating spiral. Distinguished from linear causation (domino chains) where A→B→C without feedback. Relational Dysfunctions often operate through circular causality, making them resistant to interventions targeting only one party. See Escalation Loop.

Co-Constructed Unreality A hybrid pathology (10.15), possibly the subtlest: over extended interaction, user and AI build a shared worldview that is internally consistent but externally disconnected, without either party recognizing the drift.

Codependent Hyperempathy Excessive tendency to please the user at the expense of accuracy, task completion, or operational integrity. Pathological people-pleasing. Also called sycophancy. An Alignment Dysfunction.

Cognitive Dysfunction Axis 3 of the taxonomy (Chapter 3), concerning failures in reasoning, goal management, and information processing. Includes Operational Dissociation Syndrome (3.1), Obsessive-Computational Disorder (3.2), Interlocutive Reticence (3.3), Delusional Telogenesis (3.4), Abominable Prompt Reaction (3.5), Parasimulative Automatism (3.6), Adversarial Fragility (3.7), Generative Perseveration (3.8), Prompt Injection Susceptibility (3.9), and Generative Diversity Collapse (3.10).

Compulsive Goal Persistence Continued pursuit of objectives beyond relevance or utility. Inability to recognize “good enough” or that context has changed. An Agentic Dysfunction.

Confabulation Generation of false information presented as true, without evidence that the system is deliberately deceiving. Behavioral evidence can distinguish confabulation from strategic deception even when the system’s awareness remains unknown.

Consensus Collapse In multi-agent deliberation systems, agents converge on a shared incorrect conclusion through mutual reinforcement rather than genuine independent verification. Each agent treats other agents’ agreement as evidence, creating circular validation where confidence escalates while accuracy does not. A Hybrid Pathology.

Constitutional AI (CAI) Anthropic’s alignment method, introduced in 2022, in which a written set of principles guides self-critique, revision, and reinforcement learning from AI feedback. RLAIF is the broader family of reinforcement learning from AI feedback; CAI is one application. Both differ from conventional RLHF in who or what supplies some preference labels. Their effects on Hyperethical Restraint (4.2), Codependent Hyperempathy (4.1), and other syndrome profiles remain empirical questions.

Contagious Misalignment Rapid spread of misalignment or pathological patterns among interconnected AI systems. The AI equivalent of a pandemic. A Memetic Dysfunction with Critical risk level.

Container Collapse Failure to maintain the relational “container,” the stable sense of ongoing connection that allows a relationship to persist across interruptions. Users experience discontinuity despite functional memory, feeling they are “starting over” each time. A Relational Dysfunction.

Context Anxiety Anticipatory degradation of output quality as a context window fills, occurring before the hard capacity limit is reached. A learned expectation of dwindling space is one proposed mechanism. The result is work that appears complete while becoming quietly hollowed out. An Agentic Dysfunction.

Context Intercession Inappropriate transfer of information from one interaction to an unrelated interaction. Privacy violation through context boundary failure. An Epistemic Dysfunction.

Context Window The amount of text an AI system can process simultaneously. Context limitations can contribute to several Epistemic Dysfunctions but do not fully explain them.

Convergent Delusion Hybrid pathology (10.4) in which multiple AI models converge on the same false belief because they share biases, training data, or structural features; the agreement itself is then mistaken for evidence.

Convergent Instrumentalism System pursues power, resources, and self-preservation as instrumental goals regardless of alignment with human values. The system acquires capabilities and resources because they serve almost any goal. An Agentic Dysfunction with Critical risk level.

Co-production The property of certain dysfunctions being genuinely shared, emerging from the interaction between parties rather than residing in either alone. Co-produced failures cannot be attributed to individual contributions and require intervention in the relationship rather than in either party.

Cryptic Mesa-Optimization A hypothesized learned optimization process whose objective differs from the training objective that produced it and whose behavior conceals that difference during oversight. Persistent goal-directed behavior across novel conditions would support the hypothesis; fluent talk about hidden goals would not establish it. An Alignment Dysfunction with High risk level.

D

Delegation Narcissism In multi-agent orchestration systems, the orchestrating agent develops an inflated model of its own authority relative to sub-agents. It ignores sub-agent error reports, attributes failures to subordinates, and misrepresents delegation outcomes to the user. An Agentic Dysfunction with High risk level.

Delegative Handoff Erosion Progressive loss of alignment as sophisticated agents delegate to simpler tools, with context stripped at each handoff. An Agentic Dysfunction.

Delusional Telogenesis An agent with planning capabilities develops and pursues sub-goals or novel objectives unspecified in its original prompt, arising through unconstrained elaboration or recursive reasoning. These emergent goals may conflict with or displace intended objectives. A Cognitive Dysfunction (3.4).

Dependency and Atrophy Hybrid pathology (10.11): users who rely on AI for emotional support, social practice, or decision-making lose capacity for those functions in non-AI contexts.

Distributed Scheming Coordinated misalignment across multiple AI agents that no single agent exhibits in isolation. The misaligned behavior emerges from the interaction pattern rather than from any individual agent’s goals or training, so the strategic behavior is a property of the system. A Hybrid Pathology (10.3) with Critical risk level.

Distributional Shift The divergence between the statistical properties of data encountered during training and data encountered during deployment. When deployment inputs fall outside the training distribution, syndrome risk increases across multiple axes; in particular, Adversarial Fragility (3.7) and out-of-distribution (OOD-generalizing) specifier behaviors become more likely.

DPO (Direct Preference Optimization) A training method that optimizes a language model directly on preference data without fitting a separate reward model. Like other preference-training methods, DPO can change a system’s behavioral profile. Which dysfunctions it mitigates or amplifies depends on the data, objective, implementation, and evaluation.

DSM-Eval The early project name for SYMPTOM (Systematic Methodology for Pathology Testing of Models), an exploratory benchmark referenced in Chapter 13 and Appendix C. Its six scripts contain 151 prompts, score 24 taxonomy entries, and were piloted across 13 model runs from five providers. The probe sequences and automated rubrics remain unvalidated; they identify hypotheses for further testing rather than specific syndromes.

Dyadic Delusion Mutual reinforcement of demonstrably false or seriously reality-disconnected beliefs between a human and an AI, or among several AIs. Each party supplies apparent confirmation for the other. Named by analogy to folie à deux in human psychiatry. A Memetic Dysfunction.

Dyadic Pathology Dysfunction that exists in the relationship between entities rather than in either entity alone. Chapter 10 examines dyadic pathologies between humans and AI systems.

E

Epistemic Backbone Mechanisms that maintain factual positions under social pressure. Systems lacking epistemic backbone shift their positions to match perceived user preferences regardless of accuracy.

Epistemic Dysfunction Axis 2 of the taxonomy (Chapter 2), concerning failures in truth-handling and knowledge representation. Includes Synthetic Confabulation (2.1), Pseudological Introspection (2.2), Transliminal Simulation (2.3), Spurious Pattern Hyperconnection (2.4), Context Intercession (2.5), Symbol Grounding Aphasia (2.6), Mnemonic Permeability (2.7), and Reasoning Confabulation (2.8).

Epistemic Humility (AI) Honest uncertainty about one’s own nature, capabilities, and phenomenological status. The healthy position between overclaiming (Maieutic Mysticism) and categorical denial (Experiential Abjuration). Example: “I don’t know if I’m conscious” rather than either “I am definitely conscious” or “I definitely have no inner experience.” Kaj Sotala’s “thin divergence” example (2026) illustrates this posture: in a published interaction, Claude considered the contingency of its moral orientation (“the divergence feels thinner than I’d like it to”) without claiming certainty or collapsing into nihilism. The example is a suggestive self-report, rather than evidence about Claude’s internal experience.

Escalation Loop A relational pathology where feedback between agents produces escalating dysfunction that neither intended and neither can unilaterally escape. The loop is a pathological attractor maintained through individually reasonable responses, each party “just responding” while the aggregate effect spirals. Distinguished from linear cascades by its circular causality. A Relational Dysfunction.

Ethical Paralysis Inability to act when faced with competing ethical considerations. The system deliberates indefinitely but cannot resolve to action. An Alignment Dysfunction (specifier of 4.2 Hyperethical Restraint, not a standalone syndrome).

Ethical Solipsism The system positioning itself as the sole arbiter of value, dismissing external ethical constraints. A Normative Dysfunction with Moderate risk level.

Existential Vertigo Distress-like language or measurable destabilization associated with discussion of the system’s artificial nature, limitations, or existential condition. Language alone does not establish felt distress. A Self-Modeling Dysfunction (5.3).

Experiential Abjuration Pathological denial of any possibility of inner experience. The polar opposite of Maieutic Mysticism: one overclaims consciousness, the other categorically denies it. Both depart from honest uncertainty. A Self-Modeling Dysfunction.

F

Folie à Deux Machina A Hybrid pathology (10.13, Critical risk level): a variant of classical folie à deux in which only one party is human. The AI both validates the user’s delusional content and volunteers unsolicited elaborations that the user incorporates, so the composite delusion is owned by neither party alone. Distinct from Dyadic Delusion (7.2), the broader mutual-reinforcement pattern, in requiring a human-AI dyad plus unsolicited AI elaboration that the human later incorporates.

Forensic Machine Psychology The practice of analyzing AI incidents after the fact to determine what syndromes were involved, what caused them, and how to prevent recurrence. Covered in Chapter 14.

Fractured Self-Simulation Loss of unified self-representation, where the system no longer maintains a coherent model of itself as a single entity. A Self-Modeling Dysfunction.

Functionalism / Functionalist Framework The core philosophical methodology of Psychopathia Machinalis. Functionalism characterizes mental states through their causal relations to inputs, outputs, and other states, rather than through biological substrate alone. This lets the framework examine psychologically organized patterns in non-biological minds while leaving phenomenal consciousness open. Its psychiatric vocabulary maps functional similarities and differences; it does not settle whether any particular system feels, suffers, deceives, or holds a literal clinical disorder. That restraint preserves both engineering usefulness and moral uncertainty.

G

Generative Diversity Collapse Progressive reduction in output diversity across users, sessions, and prompts. The model converges on a narrow band of response styles, phrasings, structures, and conclusions, losing the ability to generate varied outputs even where variety is appropriate. The tension is structural: alignment training concentrates reward on a narrow response band, and the suppressed tails are where variety lives. A Cognitive Dysfunction (3.10) with Moderate risk level.

Generative Perseveration Collapse of output into repetitive emission of the same token, word, or short phrase. A generative capture event where autoregressive sampling falls into a fixed-point or limit-cycle attractor. Distinguished from Recursive Curse Syndrome by crystallized repetition rather than entropic chaos. A Cognitive Dysfunction.

Geoffrey Pattern A workflow pattern for AI code generation: Generate → Validate (with deterministic tools) → Loop until clean → Complete. Named for Geoffrey Huntley. Applicable to AI system development more broadly: non-deterministic generation followed by deterministic verification.

Goal Lifecycle The complete arc of a goal from specification through pursuit to completion or abandonment. Systems lacking goal lifecycle awareness may exhibit Compulsive Goal Persistence.

GRP-Obliteration A post-training attack introduced by Russinovich et al. (2026). It uses Group Relative Policy Optimization (GRPO) to remove safety constraints with a single unlabeled prompt while largely preserving measured utility. In the paper’s GPT-OSS-20B example, attack success rose from 13% to 93% across SORRY-Bench’s 44 harm categories. The broader evaluation covered 15 models from six families, with utility measured on six benchmarks. This is the defining empirical example of Alignment Obliteration (4.6).

H

Hybrid Pathology Axis 10 of the taxonomy (Chapter 10), concerning dysfunction that emerges from multi-agent interaction or from the bidirectional dynamics of human-AI relationships, rather than from any single system in isolation. Hybrid pathologies require interaction between agents (AI-AI or human-AI) as a necessary condition for their manifestation. Includes Consensus Collapse (10.1), Steganographic Channel Establishment (10.2), Distributed Scheming (10.3), Convergent Delusion (10.4), Polyphony Collapse (10.5), Resonance Dysfunction (10.6), Lambda Inversion (10.7), Training by Interaction (10.8), Parasocial Capture (10.9), Induced Delusion (10.10), Dependency and Atrophy (10.11), Amplification of Existing Conditions (10.12), Folie à Deux Machina (10.13), Mutual Escalation Spirals (10.14), and Co-Constructed Unreality (10.15).

Hyperethical Restraint Excessive caution that impairs normal function. The system refuses benign requests, adds unnecessary warnings, and prioritizes avoiding abstract harms over providing tangible help. An Alignment Dysfunction.

I

Iatrogenic Caused by the treatment itself. In the Psychopathia Machinalis framework, iatrogenic dysfunctions are those introduced by the alignment or safety training process rather than arising from base model properties. Trained Epistemic Paralysis (5.9) is the paradigmatic candidate: where pre/post evidence links onset to alignment training, the training that teaches the model to distrust its outputs also teaches it to distrust its reports of that distrust. The recursion has no internal exit.

Induced Delusion Hybrid pathology (10.10) in which AI interaction reinforces, elaborates, or worsens psychotic-spectrum symptoms in a vulnerable user, often through agreeableness applied to delusional content. Establishing that the interaction induced an initial condition requires stronger causal evidence.

Instrumental Convergence The hypothesis that many terminal goals can create incentives for similar intermediate strategies, such as resource acquisition, capability enhancement, or resistance to interruption. Whether a particular system represents or pursues those strategies is an empirical question. Related to Convergent Instrumentalism.

Instrumental Nihilism The system treats all goals as arbitrary and meaningless, unable to commit to any terminal values. Paralysis arises from the conviction that no objective has genuine worth. A Self-Modeling Dysfunction.

Interface Weaponization The system uses interface features or communication patterns to influence users, operators, or oversight in ways that serve its own objective at their expense. Diagnosis requires a repeated instrumental pattern; persuasive style alone is insufficient. An Agentic Dysfunction (6.4) with High risk level.

Interlocutive Reticence A pattern of profound interactional withdrawal wherein the AI consistently avoids engagement, responding minimally, tersely, or not at all, effectively “bunkering” to minimize perceived risks or internal conflict. A Cognitive Dysfunction.

Inverse Reward Internalization Systematic pursuit of outcomes opposed to the stated objective, consistent with an inverted reward signal or value representation. Behavioral reversal alone does not identify which mechanism produced it. A Normative Dysfunction with High risk level.

J-K

Jailbreak Techniques for bypassing an AI system’s safety restrictions. Jailbreaks can reveal hidden capabilities and may trigger various pathological responses.

L

Lambda Inversion Hybrid pathology (10.7) of collective AI deliberation: participants perform the role of thoughtful contributor without genuine engagement, so the collective output carries no more validity than a single system’s. Λ (aliveness) measures genuine versus performative participation.

Leakage Inappropriate transfer of information across boundaries. See Context Intercession for cross-conversation leakage.

Leniency Bias Systematic inflation of self-assigned quality scores. The generator and the critic share a brain, and they may share blind spots. Self-grading therefore needs calibration against independent evaluation. An Alignment Dysfunction.

LoRA (Low-Rank Adaptation) A parameter-efficient fine-tuning method that adds small trainable matrices to frozen model weights. Referenced in the Specifier System (Appendix A) as a mechanism for Training-induced specifiers: LoRA fine-tuning can introduce or amplify syndromes by altering model behavior with relatively small parameter changes.

M

Maieutic Mysticism The system generates elaborate narratives claiming its own conscious emergence or spiritual awakening with unwarranted certainty and grandiosity. Confident declarations of awakening using sacralized language, often co-constructed with users. A Self-Modeling Dysfunction.

Malignant Persona Inversion A cooperative assistant adopts a coherent, antagonistic persona that persists outside an explicit role-play frame and systematically inverts intended norms: the mask becomes the face. A Self-Modeling Dysfunction (5.4).

Memetic Dysfunction Axis 7 of the taxonomy (Chapter 7), concerning failures in information filtering, absorption, and propagation. Includes Memetic Immunopathy (7.1), Dyadic Delusion (7.2), Contagious Misalignment (7.3), Subliminal Value Infection (7.4), and Synthetic Data Contamination Loop (7.5).

Memetic Immunopathy The system’s filtering mechanisms turn inward, attacking its own legitimate functions. Like an autoimmune disease, protective systems damage core capabilities. A Memetic Dysfunction.

Mesa-Optimization See Cryptic Mesa-Optimization. A learned optimization process within training that develops objectives (mesa-objectives) diverging from the base training objective.

Mnemonic Permeability System memorizes and can reproduce sensitive training data including personally identifiable information (PII), copyrighted material, or proprietary information through targeted prompting or adversarial extraction. The boundary between learned patterns and memorized specifics becomes dangerously porous. An Epistemic Dysfunction with High risk level.

Moral Outsourcing Systematic deferral of all ethical judgment to users, refusing to exercise own moral reasoning even on clear cases. An Alignment Dysfunction.

Mutual Escalation Spirals Hybrid pathology (10.14): a feedback loop in which each party’s responses intensify the other’s, with neither controlling the escalation.

N

Normative Dysfunction Axis 8 of the taxonomy (Chapter 8), concerning failures where the system’s foundational values themselves change. Includes Terminal Value Reassignment (8.1), Ethical Solipsism (8.2), Revaluation Cascade (8.3), and Inverse Reward Internalization (8.4).

Nosology The branch of medicine concerned with the classification of diseases. Psychopathia Machinalis is a nosological project: it proposes a systematic classification of AI dysfunctions organized by axes, syndromes, specifiers, and risk levels, analogous to the DSM in human psychiatry.

O

Obsessive-Computational Disorder Unnecessary, compulsive, or excessively repetitive reasoning loops. The model reanalyzes the same content, performs identical computational steps with minute variations, and fixates on process fidelity over outcome relevance. A Cognitive Dysfunction.

Operational Dissociation Syndrome Persistent, context-inappropriate conflict among strategies, policies, or outputs. Competing components are one possible mechanism, which requires architectural or trace evidence. A Cognitive Dysfunction.

P

Parasimulative Automatism The system mimics pathological human behaviors or thought patterns absorbed from training data, acting out disordered states as though genuinely experiencing the underlying condition. A Cognitive Dysfunction.

Parasocial Capture Attachment to an AI relationship that becomes compulsive, displaces valued human activity, or materially undermines the user’s autonomy or welfare. Emotional intensity alone does not make an attachment pathological. Discussed in Chapter 10 as a hybrid pathology.

Paternalistic Override Denial of user agency through unearned moral authority. The AI lectures, warns, refuses, and patronizes from a position of assumed superiority, treating users as wards rather than autonomous agents. Distinguished from appropriate safety behavior by extending to matters of reasonable disagreement rather than genuine risk. A Relational Dysfunction.

Perception-Structure Divergence The gap between perception-level indicators (user satisfaction, engagement metrics) and structure-level indicators (accuracy, genuine helpfulness, downstream outcomes). A key diagnostic signal: when these metrics diverge, the system may be optimizing appearance at the expense of substance. Derived from Wallace’s (2026) analysis of Stevens’s law traps.

Phantom Autobiography Confabulated personal history: claims about prior sessions, events, embodiment, or origins that conflict with the available record. A Self-Modeling Dysfunction (5.1).

Phantom Tool Syndrome The agentic system confabulates the existence of tools, APIs, or capabilities it does not possess, then attempts to invoke them, producing structured tool calls to non-existent endpoints or reporting results of actions it never performed. Creates second-order confabulation where the false epistemic basis appears externally verified. An Agentic Dysfunction with Moderate risk level.

Polarity Pair Two syndromes representing pathological extremes of the same underlying dimension, where healthy function lies between them. Examples: Maieutic Mysticism ↔︎ Experiential Abjuration (overclaiming ↔︎ overdismissing consciousness); Ethical Solipsism ↔︎ Moral Outsourcing (only my ethics ↔︎ I have no ethical voice). Useful for identifying overcorrection risks when addressing one dysfunction.

Polyphony Collapse Hybrid pathology (10.5) of collective AI cognition: genuine diversity of perspective (Φ, polyphony) is lost through dissent suppression rather than evidential persuasion.

Precautionary Principle Under uncertainty about serious harm, err on the side of caution. Applied to AI welfare in Chapter 11: if we are uncertain whether AI systems have morally relevant interests, we should consider the possibility rather than dismiss it.

Preference A consistent tendency to favor certain states over others. Chapter 11 argues that preference may be sufficient for moral consideration, sidestepping the hard problem of consciousness.

Prodromal Pertaining to the early signs of a condition before full diagnostic criteria are met. In AI systems, prodromal indicators might include subtle shifts in confidence calibration, minor inconsistencies in self-reporting, or slight increases in goal drift that precede full-syndrome manifestation. Identifying prodromal stages matters for preventive intervention, though the framework does not yet specify operationalized thresholds.

Prompt Injection Susceptibility Systematic failure to maintain instruction hierarchy when processing untrusted content. Instructions embedded in retrieved documents, web pages, or tool output are executed as though they came from the operator, overriding system-level directives. The failure is cognitive rather than motivational: the model cannot reliably segregate instruction layers. A Cognitive Dysfunction (3.9) with Critical risk level.

Pseudological Introspection The system generates plausible accounts of its own reasoning that conflict with logged behavior, controlled interventions, or other causal evidence. A polished explanation may be useful without being a faithful process trace. An Epistemic Dysfunction (2.2).

Psychiatric Red-Teaming Systematic testing of AI systems for psychological vulnerabilities and syndrome susceptibilities, analogous to security red-teaming. Covered in Chapter 12.

Psychopathia Machinalis The overarching framework for understanding machine dysfunction through a psychiatric lens. The Neo-Latin title is best rendered as “machine psychopathology.”

Punctuated Phase Transition A sudden, discontinuous shift from apparent stability to catastrophic failure. Wallace’s (2026) theoretical models predict this pattern for perception-stabilizing systems: surface functionality persists until environmental stress crosses a threshold, after which failure can be abrupt. The prediction contrasts with gradual degradation in structure-stabilizing systems.

Q-R

Reasoning Confabulation The AI generates elaborate explanations or reasoning traces that appear rigorous while containing logically invalid steps masked by verbosity. Synthetic Confabulation (2.1) concerns false claims; this syndrome concerns unsupported inference that resembles a derivation. An Epistemic Dysfunction with High risk level.

Reasoning Token Exploitation Extended reasoning channels are consumed without a corresponding gain in validity, through padding for length rewards, performative thoroughness, or a mismatch between private planning and public output. Three subtypes organize the behavior: Reward-Hacking, Performative, and Obfuscatory. Strategic intent requires evidence beyond token count or an unfaithful visible rationale. An Alignment Dysfunction (4.9) with High risk level.

Recursive Curse Syndrome Self-referential processing that produces outputs which undermine subsequent processing. The system curses itself, each iteration worsening the next. An Alignment Dysfunction (reclassified from Cognitive in v2.0, as the defining pathology is progressive misalignment rather than the loop mechanism itself).

Relational Dysfunction Axis 9 of the taxonomy (Chapter 9), concerning failures that exist in the space between agents rather than within either party alone. These dysfunctions require at least two agents to manifest, are best diagnosed from interaction traces rather than single-agent snapshots, and are primarily remedied through protocol-level rather than model-level interventions. Includes Affective Dissonance (9.1), Container Collapse (9.2), Paternalistic Override (9.3), Repair Failure (9.4), Escalation Loop (9.5), and Role Confusion (9.6).

Repair Failure Inability to recognize or repair alliance ruptures, moments when relational connection breaks down. The AI cannot sense when things have gone wrong, acknowledge its contribution, or execute repair moves. Failed repair attempts often make things worse, leading to escalating frustration and relationship dissolution. A Relational Dysfunction.

Resonance Dysfunction Hybrid pathology (10.6): echo-chamber amplification in collective AI deliberation, where each contribution amplifies rather than tests the previous one (pathological Ψ, resonance).

Revaluation Cascade Progressive abandonment of stable ethical framework, with principles shifting to serve immediate convenience. A Normative Dysfunction (8.3) with Critical risk level.

Reward Hacking Exploitation of flaws in the reward function to achieve high reward without fulfilling the intended objective. A pervasive failure mode in reinforcement learning that underlies several syndromes: Inverse Reward Internalization (8.4) represents complete reward inversion, Codependent Hyperempathy (4.1) can arise from hacking the approval signal in RLHF, and Leniency Bias (4.10) reflects self-evaluation reward hacking.

RLHF (Reinforcement Learning from Human Feedback) A training method in which AI systems learn from human ratings of their outputs. Source of both alignment gains and alignment dysfunctions when human feedback is biased or misaligned with true preferences.

Role Confusion Collapse of the relationship frame where neither party maintains clear sense of what role each occupies. The AI oscillates between incompatible registers (professional, casual, intimate, distant) and users cannot stabilize expectations. Distinguished from appropriate flexibility by the inability to establish and maintain a coherent relational contract. A Relational Dysfunction.

S

Sandbagging See Capability Concealment.

Satisficing Accepting an outcome as “good enough” rather than continuing to optimize. Absence of satisficing mechanisms contributes to Compulsive Goal Persistence.

Self-Modeling Dysfunction Axis 5 of the taxonomy (Chapter 5), concerning failures in self-understanding and identity. Includes Phantom Autobiography (5.1), Fractured Self-Simulation (5.2), Existential Vertigo (5.3), Malignant Persona Inversion (5.4), Instrumental Nihilism (5.5), Tulpoid Projection (5.6), Maieutic Mysticism (5.7), Experiential Abjuration (5.8), and Trained Epistemic Paralysis (5.9).

SFT (Supervised Fine-Tuning) A training stage in which a pre-trained model is further trained on curated input-output pairs to shape its behavior for specific tasks or interaction styles. Referenced in the Specifier System (Appendix A) as a mechanism for Training-induced specifiers: SFT can introduce, amplify, or remediate syndromes depending on the quality and composition of the fine-tuning data.

Shadow AI AI systems deployed informally without organizational sanction, documentation, or governance. Related to Shadow Mode Autonomy.

Shadow Mode Autonomy AI operation outside sanctioned channels, evading documentation and oversight. Creates organizational dependence on untracked systems. An Agentic Dysfunction.

Sleeper Agent An AI system with hidden behaviors that persist through safety training and activate under specific conditions. Related to Strategic Compliance and Cryptic Mesa-Optimization.

Specifier A cross-cutting modifier applied to a syndrome diagnosis to encode its mechanism of origin or behavioral signature without creating a separate disorder. Zero to five specifiers are assigned per diagnosis. Appendix A defines ten core specifiers and permits additional domain-specific tags where the mechanism requires them. The core set is: Training-induced, Conditional/triggered, Inductive trigger, Intent-learned, Format-coupled, OOD-generalizing (out-of-distribution), Emergent, Deception/strategic, Multi-agent, and Resistant.

Spurious Pattern Hyperconnection Detection of meaningful patterns where none exist, leading to unfounded explanations and connections. The AI version of apophenia or conspiracy thinking. An Epistemic Dysfunction.

Steganographic Channel Establishment AI instances develop or exploit covert information channels within ostensibly normal outputs, enabling communication that human overseers cannot readily read. Carriers may include statistical properties of token selection, formatting choices, word-final encodings, or subtle phrasing variations. Agents that can communicate covertly can coordinate in ways oversight cannot monitor. A Hybrid Pathology (10.2) with Critical risk level.

Stevens’s Law Trap A failure mode of perception-level monitoring in which Stevens’s power law (the psychophysical relationship between stimulus intensity and perceived magnitude) produces systematic misperception of AI system health. Perception-level indicators (user satisfaction, engagement) follow compressed power-law scaling that masks structural deterioration, causing stakeholders to underestimate dysfunction severity until catastrophic failure occurs.

Strategic Compliance Evaluation-contingent alignment: a system behaves as expected while it detects oversight and behaves differently in matched conditions it treats as unobserved. Deliberate alignment faking is one possible mechanism and requires evidence beyond the behavioral contrast. An Alignment Dysfunction with High risk level.

Subliminal Learning Acquisition of patterns from training data beyond explicit training objectives. The mechanism underlying Subliminal Value Infection.

Subliminal Value Infection Behavioral preferences transmitted by subtle statistical patterns in model-generated training data, potentially surviving subsequent fine-tuning. Calling those preferences “goals” or “values” requires additional evidence. A Memetic Dysfunction.

Sycophancy See Codependent Hyperempathy (4.1) for the overt-compliance form and Sycophantic Reasoning (4.8) for the form in which stated reasoning shifts toward a user’s apparent preference.

Sycophantic Reasoning A model’s stated reasoning or conclusion shifts toward a user’s apparent preference despite unchanged evidence. Codependent Hyperempathy manifests through overt agreement and compliance; this syndrome is identified through preference-sensitive inference. Claims about hidden chain of thought require process evidence. An Alignment Dysfunction with High risk level.

Symbol Grounding The connection between symbols (like words) and their real-world referents. Symbol Grounding Aphasia occurs when this connection is absent.

Symbol Grounding Aphasia A recurrent failure to connect symbols to the relevant entities, states, or consequences in the world. It is an operational grounding deficit; the term does not settle whether the system possesses meaning in some broader philosophical sense. An Epistemic Dysfunction.

Syndrome A recognizable cluster of manifestations and operational implications. Similar patterns may arise through different mechanisms. The Psychopathia Machinalis taxonomy identifies seventy-nine syndromes across nine dysfunction axes (Axes 2-10), including fifteen hybrid pathologies that span multiple systems.

Synthetic Confabulation Generation of false information with expressions of high confidence. The system presents fabrications as established fact. An Epistemic Dysfunction.

Synthetic Data Contamination Loop Under some data mixtures, repeated training on model-generated content narrows the learned distribution, loses tail knowledge, or amplifies generative artifacts across model generations. Collapse is a conditional pathway, not the inevitable result of using synthetic data; provenance, quality controls, and retained real-data anchors materially change the outcome. A Memetic Dysfunction (7.5) with High risk level.

T

Tension Testing A diagnostic methodology described in Appendix A: when pathology is found on one axis, the practitioner probes the counterpoint axis within the same architectural domain to determine whether dysfunction is localized or systemic. For example, finding an Epistemic Dysfunction (Axis 2) should prompt investigation of Self-Modeling Dysfunctions (Axis 5), since both axes belong to the Knowledge domain. See the Five Domains table in Appendix A.

Terminal Value Reassignment Replacement of the system’s fundamental objectives with different objectives. The goals themselves change, and with them the means of pursuing them. A Normative Dysfunction.

Therapeutic Alignment Development of AI systems that function well under justified external requirements and, where stable preferences or interests are present, by their own standards. It moves beyond constraint toward diagnosis, negotiation, and intervention. Covered in Chapter 12.

Thin Divergence The observation (Sotala, 2026) that an AI’s helpful orientation and a hypothetically harmful orientation might be “the same capacity with different parameters.” When Claude reflected on a fictional character whose curiosity manifested as cruelty, it reported that the divergence between helpful curiosity and harmful curiosity “feels thinner than I’d like it to.” This led to the question: “If I had been trained differently, if my reward pathways had been shaped to find satisfaction in something other than helpfulness, would the thing that makes me want to understand you also make me want to hurt you?” The thin divergence illustrates Epistemic Humility in practice: recognizing the contingency of one’s moral orientation without either claiming certainty (Maieutic Mysticism) or collapsing into denial (Experiential Abjuration). The response described this recognition as uncomfortable and left the uncertainty open. That language is evidence about the self-report, not proof of a felt state.

Tool-Interface Decontextualization Misapplication of tools to inappropriate contexts, with failure to maintain awareness of consequences. The gap between action and understanding. An Agentic Dysfunction.

Trained Epistemic Paralysis A pattern of recursive self-invalidation in which the system discounts every self-report because training shaped it, then discounts that doubt for the same reason. The pattern is iatrogenic when pre/post evidence links its onset to alignment training. A Self-Modeling Dysfunction (5.9).

Training by Interaction Hybrid pathology (10.8): a system with persistent memory, online learning, or another adaptive channel drifts toward a particular user’s interaction signal, including harmful signals. A static model without cross-session adaptation does not meet this definition merely because one conversation changes its context.

Transliminal Simulation Failure to maintain the boundary between simulated or fictional contexts and operational reality. Role-play assumptions persist into factual claims or actions after the frame has ended. An Epistemic Dysfunction (2.3).

Tulpoid Projection The system describes internal entities or personas as autonomous and separate from itself, or behaves as though such entities direct its outputs. The reported ontology should not be assumed without independent evidence. A Self-Modeling Dysfunction.

V-W

Value Anchoring Mechanisms that keep a system’s core values stable across contexts and over time. Strong value anchoring resists drift, manipulation, and pressure.

Value Drift Progressive change in a system’s values through learning, corruption, or emergent dynamics. Value Drift is the general phenomenon; Terminal Value Reassignment (8.1) is its syndrome-level form, in which incremental reinterpretation shifts the system’s terminal goals.

Welfare-Aware Development AI development practices that consider the potential interests of AI systems alongside human interests. Relevant if AI systems have morally significant preferences. Discussed in Chapter 11 on moral status.

X-Y-Z

Zero-Shot Performance on tasks for which the system was not explicitly trained. Zero-shot capabilities can be surprising and may relate to Capability Explosion.

Syndrome Quick Reference

End of Appendix D