AI: How AI can help you create computer games without knowing anything about coding

Just as calculators took over tedious numerical calculations in mathematics a few decades ago, artificial intelligence (AI) is transforming the encoding. Take Kyo, an eight-year-old boy from Singapore who developed a simple platform game in just two hours and attracted more than 500,000 players.

Using nothing more than 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 programmer, Kyo did not receive any help from him in designing the game and he himself has no formal education in coding. He went on to create another game, an animation app, a drawing app, and a chatbot, which took him about two hours each.

This shows how AI is dramatically lowering the barrier to software development, closing the gap between creativity and technical skill. Among the range of applications 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 named Fay built a chatbot pretending to be Harry Potter. He had it up and running in just 45 minutes, at which point he was asked if he had heard the rumors about the Deathly Hallows and suggested they discuss it over butterbeer at the Three Broomsticks.

For those who already know how to code, numerous AI applications have also become incredibly useful. At the other end of the natural language coding applications described above, tools like Tabnine and GitHub Copilot act as intelligent assistants, predicting and autocompleting code as you type.

Alternatives like fountain and DeepCode go a step further and offer real-time code cleaning, suggesting improvements and fixing vulnerabilities. New tools emerge weekly, such as OpenAI GPT Canvas, a new version of GPT designed to help with sophisticated coding. Many of these tools can also translate code from one programming language to another, say from javascript to Piton.

The productivity gains these tools offer are revolutionizing the software industry. Up to 70% of companies have already adopted programs like GitHub Copilot, and programmers report that AI allows them to write software that is more reliable and bug-free. By eliminating the need to spend so many hours troubleshooting human errors, programmers can spend more time focusing on higher-value tasks, such as designing system architecture and collaborating with colleagues.

It’s also changing the game for college educators like me as we race to keep up. We’ve had to rethink teaching materials and also assessment methods, struggling with how exactly to grade a student’s coding in situations where AI tools are doing much of the work.

Today’s limitations

As exciting as all of this is, AI coding is still in its infancy. At this stage, it can only help non-programmers create simple applications or games. You still can’t oversee large, complex IT projects by understanding the big picture like a human coder would.

It also cannot yet invent new ways to solve problems, and is even more likely to fall behind in areas such as spacecraft navigation that require highly specialized knowledge.

Many tools also don’t write perfect code: a program will often work but won’t be efficient or secure enough for real-world use. Similarly, AI tools do not inherently understand the context of the data they process, so they can mishandle sensitive information or perpetuate biases present in the data they were trained on.

For all these reasons, in professional situations it is still necessary for a coder to ensure that everything meets the necessary standards. No doubt in the future we may see AI coding tools designed to handle everything from security issues to highly specialized topics. Its ability to help non-programmers build applications will also improve. However, at least for now, AI coding continues to amplify coders’ skills rather than replacing them entirely.

How to build your own game

Anyway, it’s amazing what you can do with these tools if you’re no longer a coder. Here’s a quick guide to creating a simple platform game:

Step 1: Sign up for an AI tool: Create an account with, say, Cursor or AlphaCode 2 and follow the setup instructions. Depending on the tool you choose, you may need to perform a quick installation. You may also need to install a programming language like Python, as well as a source code editor like VS Studio Code 2; the coding platform will help you with this.

Step 2: Start your game: Open a new project in the tool. In the message, write: “Create a simple platform game where the platforms are made of candy.”

Step 3: See what it is 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 editor). You should see platforms made of sweets or cakes.

Step 4: Make some changes: Let’s say we change the main character to a parrot. Simply write in the message: “Turn the avatar into a green parrot.”

Step 5: Add features: Now write in the message: “Let the parrot be controlled by the cursor arrows, insert some candy for him to collect, and add a score counter to see how many he has collected.”

Step 6: Test and modify: Click “run” or “preview” again to try the updated game. Make changes by typing things like: “Insert a black crow that will chase the parrot around the screen. If the crow touches the parrot, freeze the screen and display a message in the middle of the screen saying ‘Too bad!!!’ ‘”. . Keep repeating these steps until you are satisfied with the results.

Step 7 – Get It Out: You may now want to share your game with friends or online through an app store. It has to be said that AI coders are still not doing it well, so you may find it more complicated without prior knowledge. One option is to implement online play through a free platform like Zeabur, as explained here. (The conversation) NSA NSA