Team Human morale booster: UW researchers show kids how people outperform AI with puzzles

University of Washington researchers have developed a puzzle game that demonstrates AI’s limitations to children, showing that humans consistently outperform AI models on simple visual reasoning tasks. The game addresses a critical gap in AI literacy education, helping kids understand that artificial intelligence isn’t the all-knowing technology many perceive it to be.

Why this matters: Children often view AI as “magical” and infallible, especially those who can’t yet fact-check AI responses due to limited reading skills or subject knowledge.

• The visual puzzle format allows non-readers to directly experience AI failures, fostering critical thinking about technology limitations.
• “When it comes to AI technologies in general, there is a huge sense of trust that kids have with these devices,” said UW researcher Aayushi Dangol.

How it works: The game asks children to solve visual puzzles, then prompts them to instruct AI to complete the same task using text hints.

• AI consistently fails even when given specific directions and hints from users.
• The puzzles require abstraction and reasoning skills that humans possess but current AI models lack.
• Multiple AI models are included to show that different systems struggle with the same challenges.

The big picture: The game is based on François Chollet’s 2019 Abstraction and Reasoning Corpus (ARC Puzzle), designed to be easy for humans but difficult for machines.

• It serves as a benchmark for measuring AI capabilities and has been adapted by UW researchers for educational use.
• The tool is available online for anyone to try.

What the kids are saying: Students testing the game at UW’s KidsTeam camp expressed both frustration and enlightenment about AI’s limitations.

• “I don’t think (AI) knows what a border means,” one child observed while playing.
• 10-year-old Zoe Blumenthal reflected: “AI is supposed to be this magical computer mind that can do anything, and instead it is this.”
• The experience led her to appreciate human creativity: “Creativity is something the mind makes up. It doesn’t have to be told information (like AI).”

What researchers think: The game creates valuable learning opportunities by highlighting the gap between AI promises and performance.

• “Clearly, there is this discrepancy between what (AI) is saying and what (AI) is producing,” Dangol noted.
• Jason Yip, who runs UW’s Information School design lab, emphasized the importance of building confidence: “I think it is actually important for people to know even at a young age that the machines aren’t smarter than you, they just do different things and different tasks in this way.”