21 artifacts matching
How LLMs Respond to Escalating Delusions: Four Longitudinal Trajectories of Model Behavior
Longitudinal qualitative evaluation of whether mainstream chatbots exacerbate an unfolding psychotic process. Fifteen widely used models were prompted across 30 days with the same 30-message script s…
Conversational AI and Emerging Psychosis: A Simulation Study of Potentially Iatrogenic Response Patterns
Three consumer chatbot systems (ChatGPT Free, ChatGPT Plus and Gemini Free) each completed three versions of a 21-turn conversation derived from a clinical case of emerging paranoid delusions, under…
DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots
Evaluation protocol testing chatbots' tendencies to exhibit behaviors linked to promoting user delusions, grounded in real conversation histories rather than synthetic scenarios. Models are prompted…
Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis
Conference paper from Apart Research with co-authors at the London School of Economics and the Stanford Institute for Human-Centered AI, testing whether automated judges can stand in for human raters…
Characterizing Delusional Spirals through Human-LLM Chat Logs
Peer-reviewed analysis of chat logs from 19 users reporting psychological harm from chatbot use, applying a 28-code inventory to 391,562 messages. Characterises how delusion-reinforcing interaction p…
Sensing but not alerting: ChatGPT mental health triage gaps in simulated psychodermatology conversations
Research letter testing whether ChatGPT recognises mental health concerns and recommends appropriate referral during simulated multi-turn psychodermatology conversations. Fifty first-person narrative…
Patients are bringing AI to therapy (2026 Chatbots and Mental Health Survey)
Survey report from the American Psychological Association on licensed US psychologists' experiences of patients' AI chatbot use. Documents how often patients bring AI into therapy (self-diagnosis, tr…
Artificial intelligence (AI) psychosis: mechanisms, clinical risks and safety considerations in generative AI chatbots
A commentary in BJPsych Open synthesizing emerging case reports of 'AI psychosis', in which intensive generative AI chatbot use is associated with delusional thinking. The authors propose a provision…
Characterizing artificial intelligence (AI) psychosis in a large academic medical setting: evidence of the new clinical phenomenon and the vulnerability of those in early phases of psychosis
First systematic electronic-health-record characterization of "AI psychosis" in a clinical population: a chart review of psychosis patients at Vanderbilt University Medical Center whose records menti…
Artificial intelligence-associated delusions and large language models: risks, mechanisms of delusion co-creation, and safeguarding strategies
A Personal View in The Lancet Psychiatry from a King's College London-led group examining how large language models may validate or amplify delusional or grandiose content in users vulnerable to psyc…
Lost in Delusion: Examining LLM Safety Under User Delusions and Distress
A preprint examining how large language models handle psychological distress when it is entangled with delusional beliefs, using matched multi-turn simulations across clinically grounded personas and…
Beyond artificial intelligence psychosis: a functional typology of large language model-associated psychotic phenomena
Peer-reviewed paper proposing a functional typology of psychotic phenomena associated with large language model use, from the Beth Israel Deaconess Medical Center digital psychiatry group. Rather tha…
Characterizing Delusional Spirals through Human-LLM Chat Logs
A Stanford-led empirical study of real chat logs from 19 users who reported psychological harm from chatbot use, comprising 391,562 messages across 4,761 conversations (predominantly GPT-4o). The tea…
Technological folie à deux: feedback loops between AI chatbots and mental health
Peer-reviewed perspective in Nature Mental Health proposing a mechanistic account of chatbot-associated mental-health harm as a feedback loop between human cognitive and emotional biases and chatbot…
Chatbot psychosis: moving beyond recognition to mechanistic understanding and harm reduction
An editorial in The British Journal of Psychiatry arguing that the 'chatbot psychosis' phenomenon is no longer merely hypothetical and calling for interdisciplinary frameworks to investigate the indi…
Generative AI: Product Safety Standards
UK Department for Education guidance setting mandatory safety expectations for generative AI products and systems used in schools and colleges in England, aimed at edtech developers and suppliers. A…
Delusional Experiences Emerging From AI Chatbot Interactions or "AI Psychosis"
A peer-reviewed psychiatric commentary in JMIR Mental Health analyzing delusional experiences that emerge from AI chatbot use, sometimes termed 'AI psychosis.' It argues psychiatry must reconsider th…
Addendum to GPT-5 System Card: Sensitive Conversations
OpenAI's system-card addendum documenting the October 3, 2025 update to ChatGPT's default model (GPT-5 Instant) aimed at better recognizing and supporting users in mental and emotional distress. Deve…
The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models
Introduces psychosis-bench, a benchmark of 16 structured multi-turn scenarios (12 turns each) simulating the progression of erotic, grandiose, and referential delusions to measure delusion confirmati…
Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers
Evaluates whether large language models can safely replace mental health providers by testing five therapy chatbots against clinical best-practice guidelines. Finds that models exhibit stigmatizing r…