Content Filtering Quiz

5 questions Pass: 70% +25 pts (50 with Pro)

Quiz covering Input and Output Safety

What you'll be asked

  1. What is the primary purpose of an input content filter in an AI system?
  2. Which of the following describes a 'jailbreak' attempt in the context of input safety?
  3. When implementing output filtering, why is it often necessary to inspect the model's response before displaying it to the user?
  4. What is a 'False Negative' in the context of content filtering?
  5. Which strategy is most effective at mitigating 'indirect prompt injection' vulnerabilities?

Answers and explanations come after you submit.