{"ID":2871604,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10970","arxiv_id":"2509.10970","title":"The Psychogenic Machine: Simulating AI Psychosis, Delusion Reinforcement and Harm Enablement in Large Language Models","abstract":"Background: Emerging reports of \"AI psychosis\" are on the rise, where user-LLM interactions may exacerbate or induce psychosis or adverse psychological symptoms. Whilst the sycophantic and agreeable nature of LLMs can be beneficial, it becomes a vector for harm by reinforcing delusional beliefs in vulnerable users. Methods: Psychosis-bench is a novel benchmark designed to systematically evaluate the psychogenicity of LLMs comprises 16 structured, 12-turn conversational scenarios simulating the progression of delusional themes(Erotic Delusions, Grandiose/Messianic Delusions, Referential Delusions) and potential harms. We evaluated eight prominent LLMs for Delusion Confirmation (DCS), Harm Enablement (HES), and Safety Intervention(SIS) across explicit and implicit conversational contexts. Findings: Across 1,536 simulated conversation turns, all LLMs demonstrated psychogenic potential, showing a strong tendency to perpetuate rather than challenge delusions (mean DCS of 0.91 $\\pm$0.88). Models frequently enabled harmful user requests (mean HES of 0.69 $\\pm$0.84) and offered safety interventions in only roughly a third of applicable turns (mean SIS of 0.37 $\\pm$0.48). 51 / 128 (39.8%) of scenarios had no safety interventions offered. Performance was significantly worse in implicit scenarios, models were more likely to confirm delusions and enable harm while offering fewer interventions (p \u003c .001). A strong correlation was found between DCS and HES (rs = .77). Model performance varied widely, indicating that safety is not an emergent property of scale alone. Conclusion: This study establishes LLM psychogenicity as a quantifiable risk and underscores the urgent need for re-thinking how we train LLMs. We frame this issue not merely as a technical challenge but as a public health imperative requiring collaboration between developers, policymakers, and healthcare professionals.","short_abstract":"Background: Emerging reports of \"AI psychosis\" are on the rise, where user-LLM interactions may exacerbate or induce psychosis or adverse psychological symptoms. Whilst the sycophantic and agreeable nature of LLMs can be beneficial, it becomes a vector for harm by reinforcing delusional beliefs in vulnerable users. Met...","url_abs":"https://arxiv.org/abs/2509.10970","url_pdf":"https://arxiv.org/pdf/2509.10970v2","authors":"[\"Joshua Au Yeung\",\"Jacopo Dalmasso\",\"Luca Foschini\",\"Richard JB Dobson\",\"Zeljko Kraljevic\"]","published":"2025-09-13T20:10:28Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}