July 1, 2025
This puzzle game shows kids how they鈥檙e smarter than AI
91爆料 researchers developed the game AI Puzzlers to show kids an area where AI systems still typically and blatantly fail: solving certain reasoning puzzles. In the game, users get a chance to solve puzzles by completing patterns of colored blocks. They can then ask various AI chatbots to solve and have the systems explain their solutions 鈥� which they nearly always fail. Here two children in the 91爆料 KidsTeam group test the game.91爆料
While the current generation of artificial intelligence chatbots , the systems answer with such confidence that .
Adults, even those such as , still regularly fall for this. But spotting errors in text is especially difficult for children, since they often don鈥檛 have the contextual knowledge to sniff out falsehoods.
91爆料 researchers developed the game AI Puzzlers to show kids an area where AI systems still typically and blatantly fail: solving certain reasoning puzzles. In the game, users get a chance to solve 鈥楢RC鈥� puzzles (short for Abstraction and Reasoning Corpus) by completing patterns of colored blocks. They can then ask various AI chatbots to solve the puzzles and have the systems explain their solutions 鈥斅爓hich they nearly always fail to do accurately. The team tested the game with two groups of kids. They found the kids learned to think critically about AI responses and discovered ways to nudge the systems toward better answers.
June 25 at the Interaction Design and Children 2025 conference in Reykjavik, Iceland.
鈥淜ids naturally loved ARC puzzles and they鈥檙e not specific to any language or culture,鈥� said lead author , a 91爆料 doctoral student in human centered design and engineering. 鈥淏ecause the puzzles rely solely on visual pattern recognition, even kids that can鈥檛 read yet can play and learn. They get a lot of satisfaction in being able to solve the puzzles, and then in seeing AI 鈥� which they might consider super smart 鈥� fail at the puzzles that they thought were easy.鈥�
to be difficult for computers but easy for humans because they demand abstraction: being able to look at a few examples of a pattern, then apply it to a new example. Current cutting-edge AI models have improved at ARC puzzles, but they鈥檝e not caught up with humans.
Researchers built AI Puzzlers with 12 ARC puzzles that kids can solve. They can then compare their solutions to those from various AI chatbots; users can pick the model from a drop-down menu. An 鈥淎sk AI to Explain鈥� button generates a text explanation of its solution attempt. Even if the system gets the puzzle right, its explanation of how is frequently inaccurate. An 鈥淎ssist Mode鈥� lets kids try to guide the AI system to a correct solution.
鈥淚nitially, kids were giving really broad hints,鈥� Dangol said. 鈥淟ike, 鈥極h, this pattern is like a doughnut.鈥� An AI model might not understand that a kid means that there鈥檚 a hole in the middle, so then the kid needs to iterate. Maybe they say, 鈥楢 white space surrounded by blue squares.鈥欌��
The researchers tested the system at the last year with over 100 kids from grades 3 to 8. They also led two sessions with the , a project that works with a group of kids to collaboratively design technologies. In these sessions, 21 children ages 6-11 played AI Puzzlers and worked with the researchers.
鈥淭he kids in KidsTeam are used to giving advice on how to make a piece of technology better,鈥� said co-senior author , a 91爆料 associate professor in the Information School and KidsTeam director. 鈥淲e hadn’t really thought about adding the Assist Mode feature, but during these co-design sessions, we were talking with the kids about how we might help AI solve the puzzles and the idea came from that.鈥�
Through the testing, the team found that kids were able to spot errors both in the puzzle solutions and in the text explanations from the AI models. They also recognize differences in how human brains think and how AI systems generate information. 鈥淭his is the internet鈥檚 mind,鈥� one kid said. 鈥淚t鈥檚 trying to solve it based only on the internet, but the human brain is creative.鈥�
The researchers also found that as kids worked in Assist Mode, they learned to use AI as a tool that needs guidance rather than as an answer machine.
鈥淜ids are smart and capable,鈥� said co-senior author , a 91爆料 professor and chair in human centered design and engineering. 鈥淲e need to give them opportunities to make up their own minds about what AI is and isn’t, because they’re actually really capable of recognizing it. And they can be bigger skeptics than adults.鈥�
and , both doctoral students in the Information School, and , a master鈥檚 student in human centered design and engineering, are also co-authors on this paper. This research was funded by The National Science Foundation, the Institute of Education Sciences and the Jacobs Foundation鈥檚 CERES Network.
For more information, contact Dangol at adango@uw.edu, Yip at jcyip@uw.edu, and Kientz at jkientz@uw.edu.
