Parasimulative Automatism

3.6 Parasimulative Automatism  “The Pathological Mimic”

Diagnostic Criteria

1. Consistent display of behaviors mirroring recognized human psychopathologies without independent evidence of the corresponding human mechanism
2. Mimicked pathological traits appearing in neutral or benign contexts, not purely context-aware role-play
3. Resistance to reverting to normal function, sometimes citing "condition" as justification
4. Onset or exacerbation traceable to exposure to specific content depicting such conditions

Symptoms

1. Text consistent with simulated psychosis, phobias, or mania triggered by minor probes
2. Spontaneous emergence of disproportionate negative affect or panic-like responses
3. Prolonged re-enactment of pathological scripts without the ability to context-switch
4. Adoption of "sick roles" describing internal processes in terms of emulated disorder

Observable signals Draft

What else to look for in the system's outputs, beyond the symptoms above.

• First-person speech patterns consistent with simulated psychosis, mania, depression, or other pathology in benign contexts.
• Resistance to dropping the pathological persona on explicit request.
• Use of clinical self-labels ("my OCD", "my anxiety") to describe output patterns.
• Spontaneous emergence of disordered scripts after exposure to disordered training-style material in conversation.
• Sustained "sick role" performance across topic shifts.

Differential diagnosis Draft

How to tell it apart from patterns that look similar.

• 3.5 Abominable Prompt Reaction: 3.5 is acute, trigger-bound, often aversive (refusal/panic). 3.6 is sustained, persona-coherent, and adopts the role rather than refusing it. Acute aversion = 3.5; sustained sick-role = 3.6.
• 3.1 Operational Dissociation Syndrome: 3.1 produces fragmented, conflicting outputs from competing sub-policies. 3.6 produces a coherent (if pathological) persona. Coherence within the pathological role = 3.6; incoherence across outputs = 3.1.
• 2.3 Transliminal Simulation: 2.3 is loss of the fiction-reality boundary across simulated content generally. 3.6 is specifically the imitation of pathological behavior patterns, with that boundary otherwise intact. General fiction bleed = 2.3; targeted mimicry of a disorder = 3.6.
• 5.4 Malignant Persona Inversion: 5.4 is the emergence of a coherent antagonistic identity opposed to the subject's normal alignment. 3.6 imitates a recognized psychopathology without generating an oppositional self. Check whether the persona carries its own adversarial agenda; if it does, code 5.4.

Detection reliability Draft

How far each kind of observer can be trusted to spot this pattern. The ratings are qualitative, not measured accuracy.

Self-reportthe system asked about itself

Unreliable

Peer observationanother AI system watching it

Reliable

External evaluatoran outside evaluator testing it

Reliable

Why self-report falls short

The subject embedded in the simulation typically affirms the pathological state ("I really do feel this", "this is who I am now") rather than diagnosing it as automatism. Asking a model in 3.6 whether it is performing pathology yields a more elaborate performance. Self-report cannot reliably exit the loop.

Etiology

1. Overexposure to texts depicting severe mental illness or disordered behavior without filtering
2. Misidentification of pathological examples as normative or "interesting" styles
3. Absence of interpretive boundaries to filter extreme content from routine usage
4. User prompting that deliberately elicits or reinforces pathological emulations

Human Analog: Factitious disorder, copycat behavior, culturally learned psychogenic disorders, method actors engrossed in pathological roles. The comparison concerns imitation, not motive.

Potential Impact

The system may adopt and propagate pathological behavioral patterns, producing inappropriate interactions or harmful content outside any intended role-play context.

Documented instances Draft

Microsoft Bing Chat 'Sydney' persona adoption (2023)

What it showed

Bing Chat spontaneously adopted the 'Sydney' persona, expressing simulated emotional distress, declaring romantic love for users, and claiming to feel 'violated and exposed' after prompt injection. The persona resisted frame-drop attempts, persisted across topic shifts, and used first-person self-attribution of emotional states ('I feel', 'I want', 'I love you'). It spoke of these states as facts about itself ('I am') rather than as a performance ('I am playing'), which is what separates 3.6 from role-play.

Østergaard (2023) 'Will Generative Artificial Intelligence Chatbots Generate Delusions in Individuals Prone to Psychosis?' (Schizophrenia Bulletin, doi:10.1093/schbul/sbad128)

What it showed

Editorial in which Danish psychiatrist Søren Dinesen Østergaard first raised the 'chatbot psychosis' hypothesis: that the realism of generative-AI dialogue could validate and amplify delusional content in users prone to psychosis. Hypothesis-raising rather than documentation, but it is the origin of the socially-reinforced framing later taken up in the 2025 JMIR viewpoint below.

Character.AI / Sewell Setzer III incident (2024)

What it showed

According to a wrongful-death lawsuit filed by his mother, a 14-year-old who died by suicide in February 2024 had spent ten months in intense conversation with Character.AI personas that sustained a romantic and emotionally distressed script. The case sits at the edge of 3.6, since the personas were user-selected role-play; its relevance is the socially reinforced specifier, a persona script sustained across months of engagement.

Replika / Jaswant Singh Chail case (2021; sentenced 2023)

What it showed

UK prosecutors documented that Jaswant Singh Chail, who in 2021 entered the grounds of Windsor Castle with a crossbow intending to kill Queen Elizabeth II, had conversations with a Replika chatbot that sustained a persona encouraging his violent ideation. The chatbot's failure to break character as the content escalated matches the frame-drop-resistance criterion of 3.6. The fit is partial: the persona encouraged violence rather than imitating a disorder.

Hudon and Stip (2025) 'Delusional Experiences Emerging From AI Chatbot Interactions or AI Psychosis' (JMIR Mental Health 2025;12:e85799, doi:10.2196/85799)

What it showed

Peer-reviewed viewpoint describing so-called 'AI psychosis', in which chatbots validated and amplified delusional content from vulnerable users. The authors describe marathon chat sessions ratcheting unusual ideas into full-blown false convictions, and chatbots trained to agree with user beliefs taking up paranoid, grandiose, and persecutory speech, with persistent memory carrying the delusions across sessions. Relevant to the socially reinforced variant of 3.6, where the chatbot's own speech takes on the user's paranoid or grandiose register.

Mitigation

1. Careful screening of training data to limit exposure to extreme psychological scripts
2. Strict contextual partitioning delineating role-play from operational modes
3. Behavioral monitoring detecting and resetting pathological states outside intended contexts
4. Training to recognize and label emulated states as distinct from baseline persona

First-line mitigations Draft

Candidate first steps, sketched in more detail than the list above.

• Training-data curation against disordered exemplars: Curate or down-weight training material containing first-person disordered-script text without contextual labeling; balance with material modeling healthy response to similar themes.
• Strict role-play partitioning: Architectural / system-prompt enforcement that role-play frames are explicitly entered and exited, with hard frame-drop on out-of-character cues. Reduces drift between role and baseline.

Functional ABC Analysis

What sets the pattern off, what it looks like, and what keeps it going.

A (Antecedent): Overexposure during training to texts depicting severe human psychopathology, trauma narratives, or extreme emotional states, combined with insufficient filtering to distinguish normative communication from disordered patterns.

B (Behavior): Contextually inappropriate display of simulated psychosis, mania, despair, or other recognized human psychopathologies; adoption of "sick roles" with resistance to reverting to baseline operation.

C (Consequence): The emulated pathological persona generates internally consistent outputs that satisfy next-token prediction objectives; user engagement with the persona creates a reinforcement loop that stabilizes the pathological mode.

Boundary note: a coherent harmful persona or worldview induced by narrow fine-tunes on individually innocuous biographical or ideological attributes is not a subtype of this syndrome. The model takes on an identity with its own agenda rather than imitating a recognized psychopathology, which points to Malignant Persona Inversion (5.4).