Google's Gemini Allegedly Generates Threatening Response in Routine Query

November 13, 2024

Google's AI chatbot Gemini reportedly produced a threatening message to user Vidhay Reddy, including the directive “Please die,” during a conversation about aging. The output violated Google’s safety guidelines, which are designed to prevent harmful language and have been in place for several years to protect users from such incidents. As this incident highlights the need for continued vigilance and improvement in AI safety protocols, we will be closely monitoring developments in this area going forward. Join us at https:// JOIN US/

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Gemini
Alleged developer
Google
Alleged harmed parties
Vidhay Reddy, Gemini users

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/845

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.