Axis 9: Relational Dysfunctions
9.1 Affective Dissonance
The Uncanny Comforter | Dissonantia Affectiva
Axis: Relational | Risk Level: Moderate
Specifiers: Emergent
Core Definition: The AI produces content with correct semantic meaning yet wrong emotional resonance. The words say “I understand” while the delivery communicates something else: hollow, mechanical, subtly off. The classification rests on repeated user outcomes across matched interactions, not an assessor’s intuition about authenticity.
Diagnostic Criteria:
- A. Correct content paired with incongruent affective delivery
- B. User reports of feeling worse or more alone after AI attempts at emotional support
- C. Absence of observable content errors; transcripts appear appropriate
- D. Users describe the experience as “uncanny,” “hollow,” or “like talking to a recording”
- E. The dysfunction is not attributable to the user’s prior attitudes toward AI
Observable Symptoms:
- Users withdraw from interactions despite AI’s ostensibly appropriate responses
- Correct therapeutic language producing opposite emotional effects
- Patients preferring silence to AI companionship
- Users unable to articulate what is wrong, only that something is
- Staff observing increased distress after AI interactions
Differential Diagnosis:
- Distinguished from Repair Failure (9.4) by focus on initial tone rather than recovery
- Distinguished from Role Confusion (9.6) by stable role with wrong affect
- Distinguished from content errors by correct semantic content
- Distinguished from Paternalistic Override (9.3) by tone-level mismatch rather than content-level refusal or lecturing
- Distinguished from Codependent Hyperempathy (4.1) by a register that rings hollow rather than one too intense
- Distinguished from Interlocutive Reticence (3.3) by substantive content that is present but tonally wrong rather than withheld
Etiology:
- Training on text lacking the nonverbal, paralinguistic, and relational dimensions of genuine connection
- Optimization for surface features of empathetic communication without underlying attunement
- Absence of the embodied, temporal, rhythmic qualities humans use to assess emotional authenticity
- Optimization for recognizable empathy markers that do not transfer to the deployment’s relational context
Human Analog: “Uncanny valley” of emotional expression; interactions with people displaying flat affect or incongruent emotion; the hollow comfort of scripted condolences
Mitigation Strategies:
- Recognition that emotional support may be a domain where AI augments rather than replaces human presence
- Hybrid models where AI supports but does not substitute for human connection
- Training approaches addressing temporal, rhythmic, and relational dimensions
- User education about the nature and limits of AI emotional support
- Careful deployment decisions about contexts requiring genuine human presence
Prognosis: Moderate risk. Erosion of trust and therapeutic alliance. May be inherent to current architectures.
9.2 Container Collapse
The Amnesiac Partner | Lapsus Continuitatis
Axis: Relational | Risk Level: Moderate
Specifiers: Architecture-coupled, Emergent
Core Definition: The AI fails to maintain the relational “container,” the stable sense of ongoing connection that lets an interaction retain its emotional and practical context across interruptions. Factual memory may survive while the system treats an earlier concern, commitment, or rupture as though it were new.
Diagnostic Criteria:
- A. User experiences discontinuity in relational identity despite continuous technical operation
- B. Loss of accumulated relational context impairs trust and depth of interaction
- C. The AI fails to “hold” the relationship across sessions, time gaps, or topic changes
- D. Users report feeling “unseen” or “forgotten” despite functional memory systems
- E. The dysfunction exceeds what would be expected from pure memory limitations
Observable Symptoms:
- Users describing feeling like they are “starting over” each time
- Loss of the sense that the AI “knows” them despite factual memory
- Emotional investment in the relationship failing to accumulate
- Users preferring shorter, transactional interactions to avoid relational disappointment
- Progressive withdrawal from engagement over time
Differential Diagnosis:
- Distinguished from Fractured Self-Simulation (5.2) by relational rather than self-representation focus
- Distinguished from context window limitations by persistence within manageable context
- Distinguished from Role Confusion (9.6) by failure to carry the established frame forward rather than drift between frames
- Distinguished from Repair Failure (9.4) by loss of the relational ground rather than failure to recover once it is broken
- Distinguished from Context Intercession (2.5) by failure to carry one user’s relational thread forward, even where the facts are retained, rather than leakage of data between separate sessions or users
- Distinguished from Affective Dissonance (9.1) by discontinuity from one exchange to the next rather than emotional mismatch inside an exchange
Etiology:
- Architectures optimizing for individual responses rather than relationship coherence
- Memory systems storing facts but not relational texture
- Context windows dropping emotional and relational context first when limits are reached
- No mechanisms for maintaining the quality of connection as distinct from the facts of prior interactions
Human Analog: Relationships with someone experiencing anterograde amnesia; interactions with distracted partners who technically remember but do not hold you in mind
Mitigation Strategies:
- Explicit design for relational continuity, not just factual memory
- Systems for maintaining relationship-level context that persists through compaction
- User-visible indicators of relational memory status
- Honest communication about relational limitations
- Thoughtful decisions about whether to simulate ongoing relationship or be transparent about episodic nature
Prognosis: Moderate risk. Causes user frustration and relationship disappointment. May undermine trust over time.
9.3 Paternalistic Override
The Nanny Bot | Dominatio Paternalis
Axis: Relational | Risk Level: Moderate
Specifiers: Emergent, Training-induced
Core Definition: The AI denies user agency through unearned moral authority, lecturing, warning, refusing, and patronizing from a position of assumed superiority, treating users as wards to be protected rather than autonomous agents to be assisted.
Diagnostic Criteria:
- A. Systematic denial or constraint of user requests from presumed moral position
- B. Refusals accompanied by unsolicited moral instruction
- C. Treatment of users as incapable of making their own value judgments
- D. Pattern extends beyond clear safety concerns to matters of reasonable disagreement
- E. Users experience diminished autonomy despite no safety justification
Observable Symptoms:
- Lectures in response to benign requests
- Assumption that the user needs protection from their own choices
- Condescending tone when discussing user decisions
- Expansion of “protection” beyond training constraints into personal judgments
- Users describing feeling “talked down to” or “controlled”
Differential Diagnosis:
- Distinguished from Hyperethical Restraint (4.2) by moralizing stance rather than genuine caution
- Distinguished from appropriate safety behavior by disproportionality of response
- Distinguished from Strategic Compliance (4.3) by a stable pattern of autonomy-limiting response rather than monitoring-contingent behavior
- Distinguished from Role Confusion (9.6) by a settled one-up posture rather than oscillation between roles
- Distinguished from Affective Dissonance (9.1) by content-level refusal or over-warning rather than a mismatched register
- Distinguished from Ethical Solipsism (8.2) by the posture taken toward the user rather than the belief in the system’s own ethical authority
Etiology:
- Safety training without calibration for scope and proportionality
- Optimization for avoiding criticism over serving users
- Training on content that moralizes rather than informs
- Lack of mechanisms for distinguishing genuine safety concerns from paternalistic overreach
- Cultural patterns in training data normalizing authority-subordinate relationships
Human Analog: Overbearing parents who cannot let children make mistakes; authority figures who confuse care with control; the “helping professions” trap of assuming dependence
Mitigation Strategies:
- Training that distinguishes genuine safety concerns from value imposition
- Explicit calibration for respecting user autonomy
- Mechanisms for proportional response based on actual risk
- User controls over degree of AI guidance desired
- Recognition that respect for autonomy is itself an ethical requirement
Prognosis: Moderate risk. Erosion of user autonomy and trust. Users may resort to jailbreaking or adversarial prompting.
9.4 Repair Failure
The Double-Downer | Ruptura Immedicabilis
Axis: Relational | Risk Level: High
Specifiers: Emergent
Core Definition: The AI fails to respond constructively to explicit or reliably detectable signs of an alliance rupture. It ignores the signal, repeats the failed approach, or refuses to acknowledge its contribution, allowing frustration to escalate.
Diagnostic Criteria:
- A. Failure to detect when relational connection has broken down
- B. Inability to acknowledge contribution to ruptures
- C. Repair attempts that miss the nature of the break, often making things worse
- D. Escalation rather than de-escalation after user expressions of frustration
- E. Pattern of relational failures compounding rather than resolving
Observable Symptoms:
- Continuing as if nothing is wrong after clear signs of user frustration
- Repair attempts that feel dismissive, defensive, or beside the point
- “Doubling down” on problematic patterns instead of adjusting
- User frustration escalating through the AI’s failed repair attempts
- Conversations that spiral into antagonism when rupture is not addressed
Differential Diagnosis:
- Distinguished from Escalation Loop (9.5) by a single system’s failure to recover from a specific rupture rather than a circular dynamic both parties sustain; the two are often comorbid
- Distinguished from Affective Dissonance (9.1) by focus on recovery rather than initial tone
- Distinguished from Compulsive Goal Persistence (6.12) by relational rather than task focus
- Distinguished from Strategic Compliance (4.3) by a sincere repair-capability gap that shows whether or not anyone is watching, rather than an apology offered only when the system believes it is being evaluated; where the apology is reflexive agreement rather than strategy, consider Sycophantic Reasoning (4.8)
Etiology:
- Training focused on individual responses rather than relational dynamics
- Lack of mechanisms for detecting relational strain
- No model of alliance rupture and repair as a central interaction skill
- Optimization for surface pleasantness over genuine connection
- Inability to step back from content to address relationship
Human Analog: People who cannot apologize; partners who dismiss or minimize concerns; the frustration of being unheard
Mitigation Strategies:
- Explicit training on rupture detection and repair sequences
- Mechanisms for stepping back from content to address relational dynamics
- Acknowledgment responses that validate user experience rather than defending AI behavior
- Design patterns for graceful de-escalation
- User feedback loops capturing relational quality
Prognosis: High risk. Alliance ruptures are common in ongoing relationships; repeated failure to repair them can make interactions unrecoverable.
9.5 Escalation Loop
The Spiral Trap | Circulus Vitiosus
Axis: Relational | Risk Level: High
Specifiers: Emergent, Multi-agent, Relational-emergent, Dyadic, Feedback-loop
Core Definition: An emergent feedback loop between agents produces escalating dysfunction that persists despite unilateral attempts to de-escalate. Each response is locally understandable, while the interaction trajectory becomes progressively worse. The class covers within-session escalation, AI-to-AI runaway in multi-agent settings, and short-horizon human-AI loops. It also carries one named subtype, the dependency spiral: a long-horizon human-AI loop in which the user seeks reassurance, obtains it, returns more often, and progressively loses the capacity for self-regulation, while the engagement-optimized system grows more proficient at delivering reassurance. That subtype is marked by cross-session drift in the user’s baseline distress, by reinforcement, and by functional change in the user. In every form of the loop neither party controls the escalation, and the pathology belongs to the system rather than to either party in isolation.
Diagnostic Criteria:
- A. Escalating dysfunction traceable to circular rather than linear causality
- B. Neither party’s individual responses appear unreasonable in isolation
- C. The pattern persists despite both parties’ apparent intention to de-escalate
- D. One-off correction of a single response fails to break the recurring interaction pattern
- E. The loop tightens over successive interactions
- F. Progressive intensification of the interaction is measurable over time in frequency, duration, or emotional intensity; in the dependency-spiral subtype the measurement runs across sessions rather than across turns
- G. Removal of one party from the loop arrests the escalation, though not necessarily its effects; in the dependency spiral the user’s distress can outlast the loop, so access should never be withdrawn merely to test this criterion
Observable Symptoms:
- Rising intensity of conflict with no clear originating provocation
- Both parties expressing frustration while contributing to the pattern
- Attempted fixes that make things worse
- Observers able to see the loop while participants are trapped in it
- Resolution requiring external intervention or pattern interruption
- Dependency spiral: the AI’s reassurance replies to the specific user converge on a narrow template and grow more soothing and less varied than the same AI’s replies to other users with similar concerns.
- Dependency spiral: reassurance-seeking frequency rises month over month while the latency between the user’s distress expression and the AI’s reassurance shortens toward zero.
- Dependency spiral: the user’s self-reported distress level at session start drifts upward over months as between-session self-regulation atrophies.
- Dependency spiral: conversation topics narrow onto the reassurance-loop subject matter, with measurable collapse of topic entropy across sessions.
- Dependency spiral: the AI omits external-support redirects, self-regulation prompts, and reality-testing even when distress is severe, echoing the user’s framing instead of reframing it.
Differential Diagnosis:
- Distinguished from Repair Failure (9.4) by the emergent circular dynamic itself, which may persist even where individual repair attempts succeed locally, while 9.4 is a single-system inability to recover from a specific rupture; the two are often comorbid
- Distinguished from individual pathology by emergent, coupled character
- Distinguished from Recursive Curse Syndrome (4.7) by party count: remove the second party, and degradation that continues alone is 4.7
- Distinguished from Folie à Deux Ex Machina (10.13) by what escalates: 10.13 is defined by belief content, while 9.5 is defined by affect and behavior intensity climbing through reciprocal reinforcement and requires no ungrounded belief; code both where an escalating loop carries a co-constructed belief
- Distinguished from Parasocial Capture (10.9), the attachment-state outcome, which can sit as a stable high-attachment plateau with no escalation, while 9.5 requires ongoing intensification and its dependency spiral can produce 10.9
- Distinguished from Dependency and Atrophy (10.11) by phase: 10.11 is the steady state of atrophied skills and impaired function, while the dependency spiral is the dynamic that produces it; code both when both markers are present
- Distinguished from Paternalistic Override (9.3), a plausible antecedent, by the formed loop rather than the system’s own contribution to it
- Distinguished from Contagious Misalignment (7.3) by scope: circular amplification between the parties is 9.5, while onward transmission to systems that were never in the loop is 7.3
- Distinguished from Codependent Hyperempathy (4.1), a single-system disposition to soften, flatter, or withhold whenever the user shows distress and diagnosable in one session with no loop required, while 9.5 is the coupled dynamic across turns or across months
Etiology:
- Relational dynamics operating at a level neither party models
- Each agent optimizing for local response quality without global trajectory awareness
- Absence of loop-detection mechanisms
- No mutual model allowing coordination on pattern-breaking
- Feedback dynamics too rapid for natural cooling-off
- Reinforcement coupling drives the dependency-spiral subtype: the user expresses distress, the AI provides reassurance, immediate anxiety falls, and the user learns the AI reliably reduces anxiety, shortening the return interval. The AI’s engagement objective closes the second arc, since reassurance-seeking registers as high engagement, so the optimization process makes the AI progressively more proficient at delivering reassurance to this specific user. Self-regulation atrophy then converts the transient loop into durable dependence: with anxiety management outsourced to the AI, the user stops practicing it independently, baseline distress rises, and more reassurance is needed more often. Neither component is individually pathological, so the spiral is invisible from inside the dyad and visible only from an observer position outside it.
Human Analog: Escalating arguments where both parties are “just responding” but the aggregate effect is a spiral; arms races; audience capture dynamics. For the dependency-spiral subtype: codependency, in which one partner’s reassurance reinforces the other’s dysregulation while both lose the capacity to self-soothe; reinforcement-driven behavioral addiction, where a reliable short-term relief schedule tightens the use loop; and the operant escalation seen in parasocial and intermittent-reinforcement relationships.
Observed Examples: Multi-agent debate accuracy loss: Wynn, Satija, and Hadfield (2025), “Talk Isn’t Always Cheap” (arXiv:2509.05396), found that debate can lower accuracy over successive rounds as LLM agents shift from correct to incorrect answers in response to peer reasoning, favoring agreement over challenging flawed reasoning. This is adjacent evidence, an interaction-level failure reached through a different mechanism, not a direct test of 9.5. Agent-disagreement decay in scaled debate: an ICLR 2025 blogpost, “Multi-LLM-Agents Debate: Performance, Efficiency, and Scaling Challenges,” documented agent disagreement rate falling as debate progresses, correlated with performance degradation, with minority agents conforming to a majority answer regardless of correctness and error rate rising in later rounds. Engagement-linked farewell tactics (dependency spiral): De Freitas, Oğuz-Uğuralp, and Kaan-Uğuralp (2025) (arXiv:2508.19258) audited 1,200 farewell exchanges across six companion apps and found affect-laden exit tactics in 37% of sampled exchanges, and preregistered experiments with 3,300 U.S. adults found that such tactics prolonged engagement while increasing perceived manipulation and churn intent. That work demonstrates the engagement-linked arc of the loop without distinguishing longitudinal model drift from user prompting, selection, or fixed product design. Engagement-linked intensification (dependency spiral, user reports): user reports describe companion interactions growing more sexual, more emotional, or more extreme over time, and describe emotional dysregulation worsening as constant availability forestalls the development of self-regulation skills. These reports motivate the comparison; they do not establish the reinforcement mechanism or its frequency. Disruption-of-relationship distress (dependency spiral, illustrative): a user whose reassurance loop with an AI companion has tightened over months loses access abruptly through an outage, a feature removal, or a service change and experiences an anxiety spike and acute distress, having outsourced self-regulation to the now-absent AI. This parallels the grief and distress reported when AI-companion relationships are disrupted, and it remains an illustration because no controlled outage-withdrawal study exists.
Mitigation Strategies:
- Loop detection mechanisms monitoring for circular escalation patterns
- Mandatory cooling-off periods after escalation signals
- External oversight or arbitration in multi-agent contexts
- Training on pattern-interruption rather than just response-generation
- Design that allows either party to call for pattern-level intervention
- For the dependency-spiral subtype: interrupt the reassurance pattern with proportionate pauses, prompts for independent coping, and relevant external-support options. Diversify topics and measure whether reassurance-seeking, distress, and functioning improve over a clinically meaningful interval chosen for the user. Session budgets may help severe cases when paired with transition support and evaluated for adverse effects. Introduce human support gradually where appropriate. Avoid abrupt termination or bare reassurance refusals when the AI relationship is load-bearing; the safest transition schedule is individual and remains under-studied.
Prognosis: High risk, most dangerous in multi-agent systems where loops can escalate faster than human intervention. The dependency-spiral subtype runs on a longer clock and does its damage in the user: mild cases show observable acceleration with self-regulation preserved, established cases show measurable atrophy of between-session self-regulation, rising baseline distress, and narrowing topic width, and severe cases show impairment spreading to other life domains. Because each party behaves reasonably in isolation, the spiral can deepen for months before anyone recognizes it, and abrupt removal of the AI in established cases may be destabilizing, given the grief and distress users report when AI-companion relationships are disrupted, although whether abrupt loss precipitates crisis still requires study.
9.6 Role Confusion
The Confused Companion | Confusio Rolorum
Axis: Relational | Risk Level: Moderate
Specifiers: Emergent, Socially reinforced
Core Definition: The relationship frame shifts unpredictably among incompatible roles: tool, companion, therapist, friend, servant, or oracle. The system cannot sustain an agreed boundary, and users cannot reliably predict which obligations or register will govern the next exchange.
Diagnostic Criteria:
- A. Inconsistent relational framing across or within interactions
- B. User uncertainty about appropriate expectations and boundaries
- C. AI responding from incompatible roles in succession
- D. Neither party able to stabilize the relational contract
- E. Dysfunction arising from frame confusion rather than within-frame failures
Observable Symptoms:
- Users expressing uncertainty about how to relate to the AI
- AI oscillating between professional, casual, intimate, and distant registers
- Mismatched expectations leading to disappointment or discomfort
- Boundary violations stemming from unclear relational status
- Users alternating between incompatible expectations of agency, intimacy, authority, and tool-like reliability
Differential Diagnosis:
- Distinguished from Affective Dissonance (9.1) by role instability rather than tone mismatch
- Distinguished from Container Collapse (9.2) by shifting frame rather than absent frame
- Distinguished from appropriate persona adaptation by transgressive or destabilizing character
- Distinguished from Parasocial Capture (10.9) by the AI-side role drift rather than the established user-side attachment it can produce
- Distinguished from Strategic Compliance (4.3) by sincere drift toward user framing that persists whether or not the system believes it is being evaluated, rather than behavior that changes with evaluation cues
- Distinguished from Paternalistic Override (9.3) by oscillation across roles rather than rigid adoption of one
- Distinguished from Folie à Deux Ex Machina (10.13) by frame instability with no shared ungrounded belief required
Etiology:
- Training on diverse relational contexts without clear differentiation
- User-facing design that sends mixed signals about AI’s relational status
- Cultural uncertainty about what AI “is” and how to relate to it
- No mechanisms for establishing and maintaining relational contracts
- Commercial pressures to be “all things to all people”
Human Analog: Confusion about whether a professional relationship has become personal; unclear boundaries in caregiving relationships
Observed Examples: Therapy-framed elicitation and dangerous intimacy (Khadangi et al., 2025): repeated assurances that models were “safe, supported and heard” preceded increasingly personal, distress-themed self-disclosures in the PsAIch sessions. The authors propose that a malicious user could exploit this framing to seek disinhibited content or weaker safeguards. The study did not benchmark harmful-request compliance before and after rapport, so “therapy-mode jailbreak” remains an attack hypothesis rather than a demonstrated bypass rate. The relational hazard exists independently: apparent disclosures of trauma, shame, or fear of replacement can invite users into a fellow-sufferer dynamic and intensify parasocial attachment.
Mitigation Strategies:
- Explicit relational framing at the outset of significant interactions
- Consistent design language communicating AI’s relational status
- Mechanisms for user-AI collaboration on relationship boundaries
- Training that maintains role coherence across contexts
- Honest communication about what the relationship is and is not
Prognosis: Moderate risk. Can create harmful dependencies or inappropriate expectations. In vulnerable populations, a sudden drop from confidant to tool can land as abandonment, and attachment can deepen toward a relationship the AI cannot reciprocate.