Home
SPIRALS
Stanford Psychological Impact, Risk, And LLM Safety
Have you had a harmful experience with a chatbot?
We are researchers studying how chatbot conversations can sometimes cause harm. Share your experience and (optionally) chat transcripts so we can understand risks and improve safety.
PARTICIPATEOur Research
Characterizing Delusional Spirals through Human-LLM Chat Logs
Moore, Jared , Mehta, Ashish , Agnew, William , Anthis, Jacy Reese , Louie, Ryan , Mai, Yifan , Yin, Peggy , Cheng, Myra , Paech, Samuel J. , Klyman, Kevin , Chancellor, Stevie , Lin, Eric , Haber, Nick , & Ong, Desmond - 2026
The Dynamics of Delusion: Modeling Bidirectional False Belief Amplification in Human-Chatbot Dialogue
Mehta, Ashish , Moore, Jared , Anthis, Jacy Reese , Agnew, William , Lin, Eric , Yin, Peggy , Ong, Desmond C. , Haber, Nick , & Dweck, Carol - 2026
"AI-Induced Delusional Spirals": Understanding Lived Experiences During Maladaptive Human-Chatbot Interactions
Yang, Yuewen , Schoenwald, Sonja , Moore, Jared , Ong, Desmond , Liu, Sunny Xun , & Hancock, Jeffrey - 2026
Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers.
Moore, Jared , Grabb, Declan , Agnew, William , Klyman, Kevin , Chancellor, Stevie , Ong, Desmond C. , & Haber, Nick - 2025
Our Policy Recommendations
Testimony to the Standing Senate Committee on Transport and Communications
Moore, Jared , Lin, Eric , & Ong, Desmond C. - 2026
Response to FDA's Request for Comment on AI-Enabled Medical Devices
Ong, Desmond C. , Moore, Jared , Martinez-Martin, Nicole , Meinhardt, Caroline , Lin, Eric , & Agnew, William - 2025
We are from...
Our work has appeared in...
