See how NTU students from diverse fields experiment with artificial intelligence (AI) to push the boundaries of learning and redefine what is possible
by Tan Zi Jie, Kenny Chee + ChatGPT
IN COMPUTATIONAL THINKING
If someone says “You think like a robot,” would you take it as a compliment?
However you feel about it, the ability to break down complex problems into step-by-step solutions, is an essential skill. It’s called computational thinking and involves identifying patterns and designing algorithms, all of which will help you navigate the technology-saturated future.
By making and solving maze problems on computer science education platform 3D Maze, Renaissance Engineering Programme (REP) students have picked up computation thinking and python programming in an engineering computation module.
In 3D Maze, students use simple “blocks” of code to programme a player’s movement within a maze game. Click to see how it’s done.
3D Maze was developed by Prof Ong Yew Soon in 2015. Recently, it bagged an award in the Global MOOC and Alliance Awards 2023. The tool by the NTU professor is so effective that it was augmented and used to train over 3,000 first-year students in core digital skills since last semester.
In addition, the team behind 3D Maze added a generative AI layer to assignments to teach students how to craft prompts for AI models.
Students learn programming and AI skills by building and solving maze games on 3D Maze, an award-winning learning platform created by NTU’s Prof Ong Yew Soon.
Make your maze with ChatGPT
In one assignment, first-year students use ChatGPT to solve a complex maze puzzle from 3D Maze. Guided by their instructor, they first convert the 3D maze problem into text, for example, using a grid of symbols and letters like “11111” to describe the maze layout.
Then, through experimenting with different prompts on ChatGPT, they co-create a “solvable maze” that a player can enter and exit.
First-year students craft a solvable maze with AI.
Use AI to learn coding
In the upcoming semesters, more OpenAI features such as ChatGPT will be added to 3D Maze to better serve the 6,000 undergraduates who use it each year.
While ChatGPT is widely known as an LLM that checks grammar or whips up dinner recipes, it is also able to generate simple code and spot errors like missing semicolons in a line of code.
When using 3D Maze, students with limited programming knowledge will get step-by-step guidance from ChatGPT, while those with programming skills can use the GenAI tool to improve their code or come up with better solutions.
How we used ChatGPT
We ran drafts of each of the stories in this cover feature through ChatGPT, using it to condense, rewrite or edit paragraphs and sentences.
😊: ChatGPT swiftly explained technical concepts and did so accurately as the lines containing them were fact-checked with the real experts.
🤣: For one iteration of the TCM article, it kept associating TCM with magic spells and potions. It was hilarious.
How we used DALL-E
It visualised the students’ AI projects from text prompts.
😊: DALL-E offers an endless array of styles; try “lofi vibes” to get charming, aesthetic visuals.
Kenny
Zi Jie
This story was published in the Jan-Feb 2024 issue of HEY!. To read it and other stories from this issue in print, click here.
