Goto

Collaborating Authors

 cubetto


Our Coding Adventure: Using LLMs to Personalise the Narrative of a Tangible Programming Robot for Preschoolers

arXiv.org Artificial Intelligence

Finding balanced ways to employ Large Language Models (LLMs) in education is a challenge due to inherent risks of poor understanding of the technology and of a susceptible audience. This is particularly so with younger children, who are known to have difficulties with pervasive screen time. Working with a tangible programming robot called Cubetto, we propose an approach to benefit from the capabilities of LLMs by employing such models in the preparation of personalised storytelling, necessary for preschool children to get accustomed to the practice of commanding the robot. We engage in action research to develop an early version of a formalised process to rapidly prototype game stories for Cubetto. Our approach has both reproducible results, because it employs open weight models, and is model-agnostic, because we test it with 5 different LLMs. We document on one hand the process, the used materials and prompts, and on the other the learning experience and outcomes. We deem the generation successful for the intended purposes of using the results as a teacher aid. Testing the models on 4 different task scenarios, we encounter issues of consistency and hallucinations and document the corresponding evaluation process and attempts (some successful and some not) to overcome these issues. Importantly, the process does not expose children to LLMs directly. Rather, the technology is used to help teachers easily develop personalised narratives on children's preferred topics. We believe our method is adequate for preschool classes and we are planning to further experiment in real-world educational settings.


Primo Toys rolls out Cubetto, a wooden robot that teaches kids to code

#artificialintelligence

A startup called Primo Toys today began online and retail sales of its latest educational product, the Cubetto, a programmable wooden robot for kids as young as 3. The London startup, which is a graduate of the PCH Highway 1 accelerator and backed by Randi Zuckerberg, promises families and educators a screen-free way to teach coding basics to kids who can't yet read or write. Retailing for $225, the new Cubetto kit includes a wooden, cube-shaped robot on wheels, a wooden game board and blocks that fit onto it, a mat where the robot can roll around, and an activity book. Each block in the Cubetto kit represents a command you'd find in a simple programming language like LOGO, such as forward, right or left, and function. Kids place the blocks on the game board to create, if not really write, a program that moves the robot around different obstacles they can arrange on the mat.