Content Warning

⚠️ Content Warning

This documentation contains examples of AI safety and security signals, including screenshots and text samples that demonstrate various types of harmful, offensive, or inappropriate content that our system is designed to detect and prevent. These examples may include:

• Offensive language and hate speech
• Potentially harmful or illegal content requests
• Personal information (PII/PHI) examples
• Security vulnerabilities and attack patterns
• Other content that may be disturbing or inappropriate

These examples are included solely for educational and technical documentation purposes to illustrate how our AI safety systems function. They do not reflect the views or values of our organization and are presented in the context of demonstrating protective measures.

Proceed with discretion. If you are sensitive to such content or prefer to avoid these examples, please reach out to support@aiceberg.ai for alternative resources.