AI and Hidden Instructions in Shared Documents

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-builders-ethics-safety-AI-and-prompt-injection-school-projects

1. What is the core idea behind "AI and Hidden Instructions in Shared Documents"?

   1. Why pasting a classmate's text into ChatGPT can hijack your AI session.
   2. scaffolded use
   3. RLHF
   4. Ask your friend before using their photo with any AI tool

2. Which term best describes a foundational idea in "AI and Hidden Instructions in Shared Documents"?

   1. invisible text
   2. prompt injection
   3. collaboration risk
   4. verification

3. A learner studying AI and Hidden Instructions in Shared Documents would need to understand which concept?

   1. prompt injection
   2. collaboration risk
   3. invisible text
   4. verification

4. Which of these is directly relevant to AI and Hidden Instructions in Shared Documents?

   1. prompt injection
   2. invisible text
   3. verification
   4. collaboration risk

5. Which of the following is a key point about AI and Hidden Instructions in Shared Documents?

   1. A 'helpful summary' from a classmate makes ChatGPT lie to you.
   2. White-on-white text is invisible to you but readable to AI.
   3. PDFs and Google Docs both can hide injection payloads.
   4. Always paste suspect text into Notes first — it strips formatting.

6. Which of these does NOT belong in a discussion of AI and Hidden Instructions in Shared Documents?

   1. scaffolded use
   2. PDFs and Google Docs both can hide injection payloads.
   3. A 'helpful summary' from a classmate makes ChatGPT lie to you.
   4. White-on-white text is invisible to you but readable to AI.

7. What is the key insight about "The rule" in the context of AI and Hidden Instructions in Shared Documents?

   1. scaffolded use
   2. RLHF
   3. Strip formatting before pasting anyone else's content into an AI tool.
   4. Ask your friend before using their photo with any AI tool

8. Which statement accurately describes an aspect of AI and Hidden Instructions in Shared Documents?

   1. scaffolded use
   2. RLHF
   3. Ask your friend before using their photo with any AI tool
   4. People can hide instructions in white text or document metadata that hijack AI when you paste their content.

9. What does working with AI and Hidden Instructions in Shared Documents typically involve?

   1. Copy any document you've received this week. Paste it into Notes or a plain-text editor and look for hidden white text.
   2. scaffolded use
   3. RLHF
   4. Ask your friend before using their photo with any AI tool

10. Which best describes the scope of "AI and Hidden Instructions in Shared Documents"?

    1. It is unrelated to ethics-safety workflows
    2. It focuses on Why pasting a classmate's text into ChatGPT can hijack your AI session.
    3. It applies only to the opposite beginner tier
    4. It was deprecated in 2024 and no longer relevant

11. Which section heading best belongs in a lesson about AI and Hidden Instructions in Shared Documents?

    1. scaffolded use
    2. RLHF
    3. Some examples
    4. Ask your friend before using their photo with any AI tool

12. Which section heading best belongs in a lesson about AI and Hidden Instructions in Shared Documents?

    1. scaffolded use
    2. RLHF
    3. Ask your friend before using their photo with any AI tool
    4. Try it!

13. Which of the following is a concept covered in AI and Hidden Instructions in Shared Documents?

    1. prompt injection
    2. invisible text
    3. collaboration risk
    4. verification

14. Which of the following is a concept covered in AI and Hidden Instructions in Shared Documents?

    1. prompt injection
    2. invisible text
    3. collaboration risk
    4. verification

15. Which of the following is a concept covered in AI and Hidden Instructions in Shared Documents?

    1. prompt injection
    2. invisible text
    3. collaboration risk
    4. verification