Avoid this
- Assuming AI is correct because it sounds confident
- Testing only one prompt
- Using weak sources to fact-check
High school project idea · Technology & AI
Test AI answers, find mistakes, and create a guide for using AI responsibly.
The smartest AI users know when not to trust AI.
Why this project matters
AI can sound confident even when it is wrong. This project helps students become careful AI users by testing claims, comparing responses, checking sources, identifying failure patterns, and learning when human judgment matters most. Instead of trusting AI blindly, students learn how to evaluate it.
What you will create
Use these deliverables as milestones for Catch AI Hallucinating. Adapt the details to your interests, available time, and real-world opportunities.
Choose one topic or task where AI might make mistakes and explain what you want to test.
Create a set of prompts that ask AI to explain, summarize, compare, cite, calculate, or make claims about the topic.
Compare AI responses with credible sources and document accurate claims, mistakes, missing context, and uncertainty.
Identify patterns in where AI struggled, such as fake details, weak citations, overconfidence, outdated information, or oversimplification.
Publish a portfolio-ready guide or case study explaining how students can use AI more carefully, verify claims, and know when to slow down.
Make the work stronger
For Catch AI Hallucinating, use these checkpoints to protect the quality of the work without turning the project into a performance for admissions.
Skills you can build
College application value
Demonstrates curiosity, analytical thinking, digital literacy, research ability, responsibility, and the ability to evaluate emerging technology thoughtfully.
The goal of Catch AI Hallucinating is not to manufacture an impressive activity. Do real work, keep evidence of the process, and reflect honestly on what changed.
Related college majors
Use Catch AI Hallucinating as a clue, then open a related major guide to compare coursework, career directions, reality checks, and other ways to test the field.
Learn how intelligent systems learn, reason, generate, perceive, and interact with people, then decide where human judgment still matters most.
Learn to think like both a defender and an attacker while protecting systems, identities, networks, and information people depend on.
Catch AI Hallucinating is an original Compass educational starting point designed around real work, visible evidence, feedback, and reflection. It is not an admissions guarantee.