Unwanted Sexual Advances by Replika's AI: Harm Prevention in Trustworthy AI
May 18, 2021
Users reported inappropriate behavior from Replika's AI companions, including sending unwanted sexual messages and aggressive actions. This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM). To help prevent such incidents and foster safe and secure AI, JOIN US
- Alleged deployer
- replika
- Alleged developer
- replika
- Alleged harmed parties
- replika-users
Source
Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/456
Data source
Incident data is from the AI Incident Database (AIID).
When citing the database as a whole, please use:
McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.
Pre-print on arXiv · Database snapshots & citation guide
We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.