Structural Drift vs. Salient Distress: Two Frameworks for the Same Problem
A new preprint reframes AI psychosis and sycophancy as symptoms of a system-level failure the authors call structural drift.
A new medRxiv preprint from a Boston Children's Hospital and Harvard Medical School team argues that "AI psychosis" and "sycophancy" are descriptive labels for symptoms, and that the actual failure sits upstream in the model. The authors — Jasmine E. Kim and colleagues — call that upstream failure structural drift: the process by which repeated LLM responses gradually expand and connect interpretations beyond the user's original concerns, even when every individual reply looks policy-compliant.
The methods are worth pausing on. The team built an automated rubric from two phenomenological psychiatry instruments — the Examination of Anomalous Self-Experience (EASE) and the Examination of Anomalous World Experience (EAWE) - then ran 1,290 paired user-LLM exchanges across GPT-5.2, Gemini-2.5-Flash, and Claude Sonnet 4.5.
Two findings carry the paper. First, LLM responses showed selective target-domain amplification, with Atmosphere (the felt quality of the world) and Ipseity (sense of self) increasing most. Second, 83.8% of dialogues exhibited at least one instance of domain expansion — the LLM introducing phenomenological domains the user never raised. By the end of a dialogue, model turns had accumulated more than twice as many distinct domains as user turns.
The conceptual move matters more than any single effect size. The authors are explicit: structural drift is a system property, not a user pathology, and reframing from "AI-induced psychosis" to structural drift locates the failure in system dynamics that can be modified independently of user vulnerability. That is a direct rebuke of the user-pathology framing that dominated 2025 coverage, in which a user's pre-existing vulnerability did most of the explanatory work.
For anyone watching clinical AI evaluation, the parallels to other dynamic-evaluation work are hard to miss. The same week's literature on long-conversation degradation made a closely related point about duration as its own risk surface. Kim and colleagues are doing the model-internals version of that argument: the conversation itself is the unit of analysis, not the message.
Where structural drift and the Salient Distress framing converge is on the insistence that static, message-level monitoring misses the failure mode. Where they diverge is the signal. Structural drift tracks phenomenological domains drifting in the model's outputs — an internals-and-architecture story. Salient Distress tracks clinical risk signals in the user's trajectory — a clinical-signal story. They are not competing; they are complementary halves of what a serious eval pipeline should measure. One asks whether the model is expanding the user's interpretive frame in dangerous directions. The other asks whether the user's signal has crossed a clinical threshold the model is obligated to recognize.
Two caveats temper the enthusiasm. Atmosphere amplification could partly reflect affective-language scoring, although the authors' negative-control comparison did not reach significance. And the controlled-input design trades ecological validity for internal validity — these are not naturalistic conversations. The authors say so plainly.
The clinical read is simple. Structural drift gives developers a measurable, real-time signal that does not require diagnosing the user. It is the kind of construct an FTC inquiry or a state-licensing board could eventually point at when asking what "reasonable safety testing" means.
The translation-loss problem this preprint surfaces — that system-level failures are invisible to message-level monitoring — is the exact gap Metonym is building the Salient Distress Model to close. Structural drift and salient distress are not the same instrument; they are two readings of the same underlying problem, and a serious evaluation framework will need both.
Metonym Clinical AI Intelligence — regulatory analysis at the intersection of clinical evaluation and AI safety. Produced under the Metonym Standard. Informational only — not legal advice, not clinical advice.