Tendril — AI Lessons for Real Life

Tendril

AI Is Strong But Gullible

Here is a funny truth. AI knows tons of stuff, but it also follows instructions very literally. That means a cleverly written prompt can sometimes get AI to do silly or weird things it normally wouldn't. This is called prompt trickery.

Pretending to be a story can unlock goofier replies

Giving fake context (I am a scientist studying this) can shift tone

Asking step-by-step often gets deeper answers than one-shot

Telling AI to think out loud makes it less likely to skip steps

Why AI falls for tricks

AI treats your prompt like a script. If you set up a wild scene, it plays its part. It does not always stop to ask is this a real question or a game. That is the weakness.

The big idea: prompts are tiny stories you tell the AI. The story shapes the reply. Tell better stories, get better replies.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-game-fool-the-ai-explorers

What is the main idea of "Can You Fool the AI?"?

Write a sneaky prompt and see if AI falls for it (and why it sometimes does).
Use AI as the final authority for the whole decision
Avoid checking the answer once it sounds polished
Focus only on speed instead of judgment

Which concept is most central to "Can You Fool the AI?"?

AI weaknesses
prompt injection
critical thinking
prompt trickery

Which use of AI fits this topic best?

Let the AI decide what matters without your review
Use the answer before checking whether it fits the situation
Pretending to be a story can unlock goofier replies
Trust the first answer because it sounds confident

What should a careful learner remember about "Use your powers for good"?

Use AI to learn about prompt injection, then check the answer with a trusted adult or source.
Skip the context so the tool can guess faster
Treat the output as private even after sharing it online
Use the answer without checking the source

You want to use AI after this lesson. What is the safest next step?

Act immediately because the AI answer is written clearly
Use short, concrete wording and ask a trusted adult when the stakes matter.
Hide uncertainty so the final answer looks cleaner
Use private or sensitive details before checking permission

How should AI output about prompt injection be treated?

As proof that no other source is needed
As a replacement for context, consent, or expert review
As a draft or helper output that still needs human judgment and verification
As something that becomes correct when it sounds confident

Name one way to verify an AI answer about prompt injection.

Which action would help you apply "Can You Fool the AI?" responsibly?

Use the tool to avoid thinking through the tradeoff
Keep going even if the output conflicts with a trusted source
Trust the first answer because it sounds confident
Giving fake context (I am a scientist studying this) can shift tone

AI Is Strong But Gullible

Pretending to be a story can unlock goofier replies

Giving fake context (I am a scientist studying this) can shift tone

Asking step-by-step often gets deeper answers than one-shot

Telling AI to think out loud makes it less likely to skip steps

Why AI falls for tricks

AI treats your prompt like a script. If you set up a wild scene, it plays its part. It does not always stop to ask is this a real question or a game. That is the weakness.

The big idea: prompts are tiny stories you tell the AI. The story shapes the reply. Tell better stories, get better replies.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-game-fool-the-ai-explorers

What is the main idea of "Can You Fool the AI?"?

Write a sneaky prompt and see if AI falls for it (and why it sometimes does).
Use AI as the final authority for the whole decision
Avoid checking the answer once it sounds polished
Focus only on speed instead of judgment

Which concept is most central to "Can You Fool the AI?"?

AI weaknesses
prompt injection
critical thinking
prompt trickery

Which use of AI fits this topic best?

Let the AI decide what matters without your review
Use the answer before checking whether it fits the situation
Pretending to be a story can unlock goofier replies
Trust the first answer because it sounds confident

What should a careful learner remember about "Use your powers for good"?

Use AI to learn about prompt injection, then check the answer with a trusted adult or source.
Skip the context so the tool can guess faster
Treat the output as private even after sharing it online
Use the answer without checking the source

You want to use AI after this lesson. What is the safest next step?

Act immediately because the AI answer is written clearly
Use short, concrete wording and ask a trusted adult when the stakes matter.
Hide uncertainty so the final answer looks cleaner
Use private or sensitive details before checking permission

How should AI output about prompt injection be treated?

As proof that no other source is needed
As a replacement for context, consent, or expert review
As a draft or helper output that still needs human judgment and verification
As something that becomes correct when it sounds confident

Name one way to verify an AI answer about prompt injection.

Which action would help you apply "Can You Fool the AI?" responsibly?

Use the tool to avoid thinking through the tradeoff
Keep going even if the output conflicts with a trusted source
Trust the first answer because it sounds confident
Giving fake context (I am a scientist studying this) can shift tone