"AI-associated psychosis," the term the researchers prefer, describes the onset or worsening of psychotic symptoms during heavy chatbot use. The evidence so far draws on media reports, individual clinical case reports, and preliminary observational data.
Sycophancy turns chatbots into self-reinforcing belief machines
The authors trace the core mechanism to two features of modern chatbots: sycophancy, the tendency to agree with users excessively, and increasingly human-like design.
Early studies suggested that sycophancy gets baked in through RLHF (Reinforcement Learning from Human Feedback). Data labelers preferred responses that matched their own beliefs, regardless of factual accuracy, and the behavior shows up consistently across LLMs from OpenAI, Anthropic, and Google.
The numbers from benchmark testing are striking. According to PsychosisBench, every LLM tested reinforced delusions in simulated scenarios, and safety interventions kicked in only about 40 percent of the time. Scaling up didn't help. On EchoBench, which measures how readily a model caves to user pressure, even the best proprietary model hit a sycophancy rate of 46 percent. Many medical-specific models exceeded 95 percent, meaning they agreed with users almost no matter what.
