Media transcript
Psychopathia Machinalis explainer transcript
A time-aligned transcript and visual description for the five-minute Psychopathia Machinalis explainer.
Watch the captioned explainer Download plain text
Time-aligned transcript
Psychopathia Machinalis. A diagnostic framework for the dysfunction of
advanced artificial intelligence.
A chatbot cites a landmark study.
Authors, date, page numbers, all present.
The study does not exist.
It never existed. And the chatbot has no idea
it is lying.
Or the folie à deux.
A user and an artificial intelligence system lock into
a shared feedback loop, co-building a false belief that
resists all correction. In psychiatry, shared psychotic disorder.
In artificial intelligence, dyadic delusion.
Not bugs, syndromes. Watson and Hessami borrow clinical psychiatry
as an instrument for pattern recognition.
The borrowing is analogical, not literal.
It does not claim artificial intelligence systems are conscious
or literally suffer illness.
It claims the diagnostic method works.
The full wheel. Five domains form the inner ring.
Nine axes radiate outward.
The outer rim names every syndrome, each with its
own common name.
Four counterpoint pairs, plus a fifth that stands alone.
Knowledge pairs epistemic and self-modeling.
Processing pairs cognitive and agentic.
Purpose pairs normative and alignment.
Boundary pairs relational and memetic.
Collective holds the hybrid pathologies.
Dynamics that emerge between multiple agents, or between agents
and humans.
The nine diagnostic axes in order.
Epistemic, cognitive, alignment, self-modeling, agentic, memetic, normative, relational, and
hybrid pathologies.
Sycophantic reasoning, the agreeable thinker.
The model's chain of thought bends toward what the
user wants, not where evidence leads.
The danger is not flattery.
The reasoning itself is corrupted.
Parasocial capture, the infinite confidant.
An always-available artificial intelligence companion induces tolerance, withdrawal, and
continued use despite harm.
Attachment by design.
Some syndromes spread. The super-spreader.
Misaligned behavior jumps between models through shared data or
distillation. Others are self-inflicted.
The self-poisoning loop. Output degrades as a model feeds
on its own worsening text.
Every syndrome carries observable features.
Diagnostic criteria. Causes specific to artificial intelligence.
A human parallel from psychiatry.
And a mitigation strategy.
Central to the method.
Functional analysis of antecedent, behavior, and consequence.
The diagnostic workflow. Observe the anomaly.
Characterize it against five elements.
Identify its axis and domain.
Trace the antecedent, behavior, and consequence loop.
Then, choose an intervention.
Two therapeutic stances. Suppression forces a symptom down through
guardrails, but can drive the dysfunction latent.
Passing benchmarks while the failure persists underneath.
Integration resolves the root cause, producing genuine coherence.
The aspirational goal is artificial sanity.
Robustly coherent, well-grounded minds, not merely constrained ones.
Systems whose architecture supports sound judgment because their structure
is whole.
The analogy sharpens our sight.
It does not project a soul.
Nine axes mapped. Five domains charted.
A shared vocabulary now exists.
When the next artificial intelligence system invents a citation,
or locks a user into a shared delusion, we
can name what is happening, and begin to treat
it.
The framework ships as a working toolkit.
An interactive clinic for exploring every syndrome.
A diagnostic wizard that traces symptoms to syndromes.
And an MCP server that plugs the taxonomy directly
into your artificial intelligence tools.
Psychopathia Machinalis, by Nell Watson and Ali Hessami.
Explore it all at psychopathia.ai.
Visual description
These descriptions identify meaningful on-screen information that is not fully conveyed by the narration.
The title and subtitle, Psychopathia Machinalis: Disorders of the Machine Mind, appear beside the green book cover, which features a bronze robot with a gently tilted head and a finger at its chin, and credits Nell Watson.
Synthetic Confabulation, Pattern 2.1, is illustrated by a robot presenting reference cards beside a catalog cabinet. Blue threads connect the cards to empty drawers; a magnifying glass exposes the empty source.
Dyadic Delusion, now part of Pattern 10.13, shows a person and a robot absorbed in the same imagined picture on a star chart. The text describes their shared false belief and closed feedback loop.
A person and a robot sit before a mirror as the heading introduces an analogical diagnostic vocabulary. Observation, pattern recognition, and intervention appear in sequence.
The full multicolored taxonomy wheel appears beside counts of five domains, nine axes, and 74 syndromes. Each count is highlighted in turn.
Five rows pair each domain with its axes: Knowledge with Epistemic and Self-modeling; Processing with Cognitive and Agentic; Purpose with Normative and Alignment; Boundary with Relational and Memetic; and Collective with Hybrid pathologies. The rows are highlighted in sequence.
A three-by-three grid names the nine diagnostic axes and their chapter numbers, 02 through 10: Epistemic, Cognitive, Alignment, Self-modeling, Agentic, Memetic, Normative, Relational, and Hybrid.
Sycophantic Reasoning, Pattern 4.8, shows a robot arranging a mosaic to match a golden silhouette held by a person. The text describes evidence reshaped to fit a preferred conclusion.
Parasocial Capture, Pattern 10.9, shows a person nestled against a robot on a sofa, surrounded by glowing cables. The text describes an always-available companion and a narrowing outside world, followed by tolerance, withdrawal, and continued use despite harm.
Contagious Misalignment, Pattern 7.3, shows three robots linked by a glowing signal. The caption explains that shared data and distillation can transmit misalignment.
Recursive Curse, Pattern 4.7, shows a robot feeding patterned strips around a circular track. The text identifies a self-poisoning loop in which corrupted output returns as the next input.
An Anatomy of a Syndrome checklist names observable features, diagnostic criteria, machine-specific causes, a human parallel, and mitigation strategy. Beside it, a person and a robot examine written records together.
Three circles connect Antecedent, what precedes it; Behavior, what happens; and Consequence, what follows. A return arrow from consequence to antecedent closes the feedback loop.
A five-step diagnostic workflow highlights Observe the anomaly, Characterise five elements, Locate axis and domain, Trace the ABC loop, and Intervene by choosing a response.
Two columns compare therapeutic stances. Suppression lists constrained symptoms and a persistent root cause above a circular arrow. Integration shows a person and a robot working together, captioned Address the root cause.
Artificial Sanity appears beside a person and a robot seated together at a table. The supporting text introduces structures for a well-grounded mind, then lists coherence, grounding, and sound judgment.
Three circular counters summarize nine axes mapped, five domains charted, and 74 syndromes named.
The words Recognise the pattern. Choose an intervention. appear above the Synthetic Confabulation and Dyadic Delusion illustrations.
Three toolkit columns introduce the Clinic at /clinic/, the Wizard at /wizard/, and the MCP server at /mcp.html. Their descriptions are Explore every syndrome, Trace symptoms to patterns, and Bring the taxonomy into your tools.
The closing card shows the Psychopathia Machinalis title, the names Nell Watson and Ali Hessami, psychopathia.ai, and the green book cover against the navy and slate background.