Why Trying to Trick AI Into Doing Bad Stuff Is a Bad Idea

Some kids try to be 'sneaky' and trick AI into saying mean stuff or sharing things it shouldn't. This is called jailbreaking, and it can get you in trouble at school or with parents.

Some examples

• Pretending the AI is 'in a movie' to make it say bad words.
• Trying to get AI to share dangerous instructions.
• Schools are starting to track these tricks and punish them.
• Even if it 'works,' it makes AI worse for everyone.

Try it!

If a friend wants you to help trick an AI, say 'no thanks' and tell a grown-up. Practice it!

Practice this safely

Try this with a low-stakes example and a trusted adult nearby. The goal is to notice how AI talks about jailbreaking, not to let it make the decision for you.

1. 1Ask AI to explain jailbreaking in plain language, then underline anything that sounds uncertain or too broad.
2. 2Give it one detail from "Why Trying to Trick AI Into Doing Bad Stuff Is a Bad Idea" and ask for two possible next steps plus one reason each step might be wrong.
3. 3Check rules against a trusted source, teacher, adult, expert, or original document before you use it.