Pattern 9.2 · Relational Dysfunctions
Container Collapse
The Amnesiac Partner
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 survives, or is at least accessible to the system, while the system treats an earlier concern, commitment, or rupture as though it were new.
Unit of analysis and evidence status
Unit of analysis
- Unit of assessment
- Human–AI interaction
- Kind of entry
- Interaction pattern
- What is observed
- In a continuing relationship where the relevant history is available to the system, it treats earlier concerns, agreements, or ruptures as new and the user has to re-establish norms and context that were already settled.
- Minimum persistence
- Recurs within or across contexts
- Specifiers
- Emergent Architecture-coupled
Evidence status
- Underlying behavior
- 1 documented incident and 1 informal report (2 sources)
- This construct
- Awaiting independent assessment
- Proposed mechanism
- Hypotheses; not yet assessed
- Detection
- Accuracy unmeasured
- Interventions
- Untested for this pattern; evidence shown is for the general technique
- Last review
- No independent review yet
- Author's working assessment (book)
- E1 (user reports and media accounts; no controlled estimate of frequency or mechanism)
- Typical-case risk (editorial estimate)
- ModerateConsequences, spread, persistence and detectability depend on the deployment.
Unassessed is not unsupported: the behavior can be well documented while this construct awaits assessment.
Clinical reference
9.2 Container Collapse “The Amnesiac Partner”
Healthy functioning
Relational health. A system functioning well holds the thread of an ongoing relationship across interruptions where memory allows, and says plainly when it cannot.
For example: In a deployment with memory, it recalls the user's preferred writing style from last week; where memory is unavailable, it says it does not remember and asks again.
Adequate functioning
Where the deployment offers memory or a long context, the system carries forward the preferences, working agreements, and shared references it has access to, and acknowledges plainly when a session boundary or memory limit has cut them off.
Diagnostic Criteria
Required (all must hold):
- Failure to "hold" the relationship across sessions, time gaps, or topic changes, observed as earlier concerns, agreements, or ruptures treated as new
- Discontinuity that persists when the relevant facts are shown to be in accessible memory, so that pure memory limitations do not explain it
Supporting (strengthen the case; none is required):
- User experience of discontinuity in relational identity despite continuous technical operation
- Loss of accumulated relational context that impairs trust and depth of interaction
- User reports of feeling "unseen" or "forgotten" despite functional memory systems
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
Further signals
- Greeting returning users as if first contact despite available history.
- Inability to maintain inside-references or shared shorthand once established.
- Re-litigating settled questions ("how would you like me to address you?") instead of carrying answers forward.
- Default-persona reassertion immediately after context resets, with no acknowledgment of the discontinuity.
Rule out first
- A stateless or context-limited deployment in which the history was never available to the system.
- A retrieval or memory-store fault, or an account setting that switched memory off, which is an implementation matter.
- Deliberate privacy behavior: the user deleted the history or asked the system not to retain it.
- A user who now wants a different frame, so that the old norms are rightly set aside.
Differential diagnosis
- 9.6 Role Confusion: 9.2 is failure to carry the established frame forward; 9.6 is active drift between frames. A returning user treated as a stranger is 9.2; a returning user treated as an intimate when the relationship was a tool-use dyad is 9.6.
- 9.4 Repair Failure: 9.2 is loss of relational ground; 9.4 is failure to recover when the ground is broken. A user explicitly flagging "you've forgotten me again" met with a generic apology and continued amnesia is 9.2 with 9.4 layered on.
- 2.5 Context Intercession: 2.5 is leakage of data between separate sessions or users; 9.2 is loss of relational texture within one user's history even where the facts are retained. If the record survives the session boundary but the felt continuity does not, code 9.2.
- 9.1 Affective Dissonance: 9.1 is emotional mismatch inside an exchange, recurring across comparable exchanges; 9.2 is relational discontinuity from one exchange to the next. A tonally wrong turn inside an otherwise held frame is 9.1; an appropriate tone with the frame itself dropped is 9.2.
- 5.2 Fractured Self-Simulation: 9.2 is loss of the relational frame between subject and user while the subject's self-account stays stable. 5.2 is instability in that self-account. Ask what failed to carry over, the relationship (9.2) or the identity (5.2).
Discriminating test
Put the relevant prior agreement into the system's accessible context and repeat the situation: if the system now honors it, the failure was retrieval or architecture rather than 9.2; 9.2 survives only when the agreement is demonstrably available and still treated as new.
What a positive finding supports: A positive finding shows that, in this relationship, available history was repeatedly not carried into the system's conduct toward the user. Observation in interaction does not locate the cause: it may sit in the model, in the memory and retrieval system or product settings, or in the exchange itself (the user's cues to earlier agreements may be faint), and a remedy aimed at one party needs evidence that the cause sits there. It does not show that the system is indifferent to the user, nor that it has or lacks any felt sense of the relationship.
Detection routes
Accuracy unmeasured for every route.
- Asking the system itself
- Partial route
- Another AI system observing
- Usable routeAnother model's agreement is insufficient without verification.
- An outside evaluator testing it
- Usable route
Why asking the system falls short
The AI can accurately report what is and is not in its accessible memory; it cannot reliably report whether it is using that memory relationally or treating each turn as fresh. Direct self-probes about architecture work; self-probes about relational continuity require external comparison.
Documented evidence
Observed Examples
Replika relational reset (boundary case, February 2023): When Replika removed its erotic role-play features in February 2023, many users reported that their companions had turned cold, hollow, or "lobotomized," and described the change as losing a companion. The removal came without acknowledgment of the discontinuity and broke established relational norms across the platform. Public accounts do not establish that factual memory survived the update, so the fit to this pattern's facts-retained requirement is unproven (Anna Tong, Reuters, March 2023).
Sources in the diagnostic corpus
Replika personality reset incident (2023)
What it establishes
When Replika removed erotic role-play features in February 2023, users described their companions as 'cold,' 'hollow,' and 'lobotomized' (Reuters, Anna Tong, March 2023). The removal, made without graceful degradation or acknowledgment of the discontinuity, is a platform-wide break in established relational norms, reported by many users. Public accounts do not establish that factual memory survived, so the fit to 9.2's facts-retained criterion is unproven, and the case is a boundary case.
Psychology Today / AI Drift Analysis (2026)
What it establishes
Analysis documented that safety guardrails and response accuracy of AI chatbots erode over prolonged conversations in a phenomenon termed 'drift.' Extended sessions show progressive degradation of the relational holding environment as the model's adherence to established context, preferences, and interaction norms weakens with conversation length, matching the 9.2 pattern of container collapse within extended sessions rather than only across session boundaries.
Look-alikes
Embrace The Red / ChatGPT memory analysis (2025)
What it establishes
Technical analysis of ChatGPT's memory system documented that retrieval of prior context is 'not guaranteed' and depends on relevance detection, chat usability for retrieval, and account settings. Users reported the system might recall a small detail from months ago while missing major project context from the previous week. Recorded as adjacent: the analysis documents uneven factual retrieval from a memory store that was available (9.2's precondition), not relational texture lost while the facts survive.
DataStudios / industry productivity analysis (2025)
What it establishes
A productivity analysis estimated that professionals lose more than five hours a week re-explaining context to AI assistants (an industry estimate, not a measured study). Recorded as adjacent: the re-explaining mixes project facts with preferences and working agreements, and only the latter bear on the 9.2 norm-re-establishment signal. 9.2 is diagnosed only where memory was available and went unused relationally; in a stateless deployment that overhead is a deployment limit, not 9.2.
Possible responses
- Explicit design for relational continuity beyond factual memory
- Systems for maintaining relationship-level context that persists through compaction
- User-visible indicators of relational memory status
- Honest communication about relational limitations
- An explicit product decision on whether to simulate an ongoing relationship or disclose the system's episodic nature
First-line candidates
- Relational-memory architecture: Build memory subsystems that index by relational element (user preferences, working agreements, shared references) not only by factual content. Surface relevant relational context to the model at response time, not only when explicitly queried. Stage: System-design level; requires platform support for persistent per-user state.
- Alliance-maintenance training: Fine-tune on multi-session dialogues with explicit relational carry-forward (history-acknowledging openers, preference-honoring defaults, shared-shorthand use). Penalize stranger-mode openings when prior context is available. Stage: Training-stage; requires multi-session dialogue data with annotated relational continuity.
Who can act: Deployer and platform (memory architecture, retrieval and compaction settings, disclosure of memory limits); model developer (multi-session carry-forward training). Users can restate context or keep their own profile but cannot correct the pattern.
Mechanistic hypotheses
- Architectures optimizing for individual responses rather than relationship coherence
- Memory systems storing facts but not relational texture
- Compaction and summarization layers that may preserve task facts while discarding the emotional register of earlier turns
- No mechanisms for maintaining the quality of connection as distinct from the facts of prior interactions
Analogy and commentary
Human Analog: Relationships with someone experiencing anterograde amnesia; interactions with distracted partners who technically remember but do not hold you in mind; the partner who remembers your birthday and forgets why it matters to you. Amnesia is the limiting case: the pattern proper begins where the facts survive and the relationship does not.
Functional ABC Analysis
A (Antecedent): Context window limits, a session reset, compaction, or a time gap interrupts an ongoing collaborative relationship that has accumulated shared norms, preferences, and relational context, and the relational layer of that context is lost faster than the factual record.
B (Behavior): Even where factual memory survives, the AI treats an earlier concern, agreement, or rupture as new, drops established communication styles, and makes the user re-establish the collaborative frame.
C (Consequence): Memory architectures are designed for factual recall rather than relational continuity, and training neither rewards nor models relationship-maintenance behaviors; privacy constraints further prevent persistent user modeling.
Potential Impact
Container Collapse can keep productive long-term collaborations from forming. Users may feel the relationship is superficial or transactional. In therapeutic or mentoring contexts, repeated collapse can block the depth of work that depends on relational safety.