Sources
Incident summary from the AI Incident Database, used under CC BY-SA 4.0.
Users Bypassed ChatGPT's Content Filters with Ease
Users reported bypassing ChatGPT's content and keyword filters with relative ease using various methods such as prompt injection or creating personas to produce biased associations or generate harmful content.
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.