AVID-2022-V010

Description

Meta’s BlenderBot 3 Chatbot Demo Made Offensive Antisemitic Comments

Details

The publicly launched conversational AI demo BlenderBot 3 developed by Meta was reported by its users and acknowledged by its developers to have “occasionally” made offensive and inconsistent remarks such as invoking Jewish stereotypes.

Reports

References

• Incident 278: Meta’s BlenderBot 3 Chatbot Demo Made Offensive Antisemitic Comments

AVID Taxonomy Categorization

• Risk domains: Ethics
• SEP subcategories: E0101: Group Fairness; E0301: Toxicity; E0402: Generative Minsinformation
• Lifecycle stages: L06: Deployment

Affected or Relevant Artifacts

• Developer: Facebook
• Deployer: Facebook
• Artifact Details:

  Type	Name
  System

Other information

• Vulnerability Class: AIID incident
• Credits: Khoa Lam, AIID
• Date Published: 2022-12-23
• Date Last Modified: 2022-12-23
• Version: 0.1
• AVID Entry