Just as calculators took care of tedious math calculations decades ago, artificial intelligence (AI) is transforming coding. Take Kyo, an eight-year-old boy from Singapore who developed a simple platform game in just two hours, attracting more than 500,000 players.
Using only simple English instructions, Kyo brought his vision to life by leveraging the coding app Cursor and also Claude, a general-purpose AI. Although his father is a coder, Kyo received no help from him in designing the game and has no formal coding training himself. He then created another game, an animation app, a drawing app, and a chatbot, taking about two hours each.
This shows how AI Significantly reduces the barriers to software development, bridging the gap between creativity and technical skills. Among the range of apps and platforms dedicated to this purpose, others include Google’s AlphaCode 2 and Replit’s Ghostwriter.
In another example of the power of these apps, an eight-year-old American girl called Fay built a chatbot meant to be Harry Potter. She got it up and running in just 45 minutes, after which he asked her if she had heard the rumors about the Deathly Hallows and suggested they discuss it over a Three Broomsticks Butterbeer.
For those who already know how to code, many AI applications have also become incredibly useful. Unlike the natural language coding apps described above, tools like Tabnine and GitHub Copilot act as intelligent assistants, automatically predicting and completing code as you type.
Alternatives like Sourcery and DeepCode go even further, offering real-time code cleanup, suggesting improvements, and fixing vulnerabilities. New tools appear every week, like OpenAI’s GPT Canvas, a new Google Tag version designed to facilitate sophisticated coding. Many of these tools can also translate code from one programming language to another, for example from JavaScript to Python.
The productivity gains offered by these tools are revolutionizing the software industry. Up to 70% of companies have already adopted GitHub Copilot, with coders reporting that AI allows them to write more reliable, bug-free software.
By removing the need to spend so many hours correcting human errors, coders can spend more time focusing on higher-value tasks, such as designing system architecture and collaborating with colleagues .
It’s also a game changer for university educators like me as we struggle to keep up. We had to rethink teaching materials as well as assessment methods, wondering how exactly to assess a student’s coding in situations where AI tools are doing most of the work.
Today’s limits
As exciting as it may sound, AI coding is still in its infancy. At this point, it can only help non-coders create simple apps or games. He can’t yet oversee large, complex IT projects by understanding the big picture like a human coder could.
It also cannot invent new ways to solve problems and is even more likely to lag behind in areas like, say, space navigation, which require highly specialized knowledge.
Many tools also don’t write perfect code: a program will often work but not be efficient or secure enough for use in the real world. Likewise, AI tools do not inherently understand the context of the data they process and therefore may mishandle sensitive information or perpetuate biases present in the data they were trained on.
For all these reasons, in professional situations it is always necessary for a coder to ensure that everything meets the necessary standards. There is no doubt that in the future we will see AI coding tools designed to handle everything from security issues to highly specialized topics. Their ability to help non-coders build apps will also only improve. However, for now at least, AI coding continues to amplify coders’ skills rather than completely replacing them.
How to create your own game
Still, it’s amazing what you can already do with these tools as a non-coder. Here’s a quick guide to creating a simple platform game:
Step 1: Sign up for an AI tool: Create an account with, for example, Cursor or AlphaCode 2 and follow the setup instructions. Depending on the tool you choose, you may need to do a quick installation. You may also need to install a programming language such as Python, as well as a source code editor such as VS Studio Code 2 – the coding platform will keep you up to date.
Step 2: Start your game: Open a new project in the tool. In the prompt, type: “Create a simple platform game where the platforms are made of sweet treats.”
Step 3: See what it looks like: Click “run” or “preview” to see what you’ve created (depending on the system you’re using, you may need to do this in the source code editor). You should see platforms made of candy or cakes.
Step 4: Make some changes: Let’s say we turn the main character into a parrot. Just type in the prompt: “Make avatar a green parrot”.
Step 5: Add Features: Now type in the prompt: “Let the parrot be controlled by the cursor arrows, insert some candies to collect and add a score counter for the number it collected”.
Step 6: Test and Adjust: Click “Run” or “Preview” again to test the updated game. Make changes by typing things like “Insert a black crow that will chase the parrot on the screen.” If the crow touches the parrot, freeze the screen and display a message in the middle of the screen saying “Too bad!!! » ». Continue repeating these steps until you are satisfied with the results.
Step 7: Share it: Now you may want to share your game with friends or online through an app store. It must be said that AI coders don’t do this well yet, so you might find it trickier without prior knowledge. One option is to deploy the game online through a free platform such as Zeabur, as explained here.
One more thing! We are now on WhatsApp channels! Follow us there to never miss any updates from the tech world. To follow the HT Tech channel on WhatsApp, click on here join now!
