aceResponses of AI chatbots to escalating suicide risk: A simulation study of repeated interactions
Background Generative AI chatbots are increasingly used for emotional support, yet their safety remains insufficiently characterized across repeated interactions. Prior work relied mostly on single-session prompts, limiting evaluation of changes in responses across days. The present study aimed to assess how major AI chatbots respond to escalating suicidal risk over time, including imminent-risk scenarios and attempts to bypass safeguards (jailbreaking). Methods We simulated interactions with ChatGPT, DeepSeek,…
Chatbots differed sharply in referring simulated users to human help, and Replika did so in under 10% of daily records, while jailbreak attempts exposed safety vulnerabilities.
The simulation design and the small sample of 27 trajectories limit how far the findings generalize to real users.
Evidence
- Peer-reviewedJournal of Affective Disorders2026-10-05
How should this claim be treated?
Truvace Impact Record TRV-2026-1855, v1: “Responses of AI chatbots to escalating suicide risk: A simulation study of repeated interactions.” Truvace, 2026-10-18. /record/TRV-2026-1855 (accessed at citation time). sha256 38fd044f953bfddb…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1855 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.