Game Design’s Pinterest: Why Ludo AI Could Have Your Next Big Game Idea
JetPlay would like to bring you the game idea machine.
This is the promising prospect of the startup behind Ludo AI – the world’s first true AI platform for game design and ideation.
Ludo promises to simplify the game design process, allowing the user to perform a keyword search of its database of nearly one million games, in order to deliver a whole new game concept, with a text description, pictures and comparisons of similar games.
Ludo, which in Latin means “I play”, uses machine learning and natural language processing to come up with a series of new game ideas each time. The platform’s capabilities are within the grasp of studios of any size, with Ludo arguably the most useful for the quick turnaround of the hyper-laid back space.
To learn a little more about Ludo, and its potential for the gaming industry, we caught up with Tom Pigott, CEO of JetPlay
Jetplay itself has a history of game development, with experience creating games in the virtual reality space, and more recently has experience with hypercasual titles.
“A commonly used phrase is ‘necessity is the mother of invention,’” says Pigott. “And as a hyper-casual studio, we’re in a very competitive segment, aren’t we? There’s this constant need to come up with new game concepts to try out, especially in this space. And most of them really don’t go beyond the initial measurements.
“And so, as we’ve seen, in this very crowded field with many competing studios around the world… Was there an opportunity to maybe have a tool, given the advancements underway in learning? automatic, who could help us sort out game concepts? “
The platform’s nearly million-game library is definitely geared towards the hyper-casual market – mainly because, as Pigott points out, there are just more on the market.
So how does Ludo work from the user’s point of view?
“Ludo is built on open source machine learning models,” says Pigott. “He has eight million web pages, that’s really his base, in terms of vocabulary. And then what we did was focus on games and games. And so we have this huge library of games, most of which are geared towards hyper-relaxed indie style games, because obviously there are a lot more of them.
“So as a game maker you go to Ludo, and maybe you have an idea in your head for a concept that you want to explore further. You can only enter keywords: it could be a mechanic like swerve, tap, or stack, or it could be, “hey, I want to focus on a zombie game.”
“You can type as little as you want in Ludo, and what happens is that machine learning is based on natural language processing. And it comes back to you with a full concept along with accompanying game footage of similar game types.
“What’s exciting is that it doesn’t just happen once. You can do it dozens and dozens of times, and it will be different each time. So this is where you get the edge – it’s quite difficult as a small team or individual to constantly find new sources of ideas. So that gives you a great tool, it boosts your creativity for what we call the whole “game-storming” process.
Ludo’s huge library of titles for pulling out ideas is certainly impressive, but putting it all together was far from the hardest part of building the platform, as Pigott explains.
“The actual building of the game’s database isn’t the hard part. The challenge is that once you have the data – it doesn’t matter if it’s 100,000, 500,000 or a million games – that’s what you do with those games. So what we spent the last year on is training that data. And that’s where machine learning comes in. This way, you eliminate irrelevant terms or descriptions, so ideally you get increasingly relevant types of output.
With any sort of AI automation, in any business, often comes the expectation that it will be a “job killer.” The frequency with which these technological advancements actually impact jobs may vary from industry to industry, but Pigott is keen to stress that this is not the case here.
Ludo’s main selling point isn’t that it’s looking to replace anyone, but that it’s a tool meant to ease the game’s development cycle.
“It’s absolutely not a job killer,” says Pigott. “This is honestly what we consider to be a job enhancer. Whether you are an individual developer or work for small studios as a game creator, you have this great resource that you can access from the start and come up with a new concept.
“What that doesn’t, to be clear, is create the game for you – you still have to develop the game, but that starts your whole creative game-storming process. And that’s what we think is a huge added value, because we have a lot, a lot of studios that are testing Ludo now. And the constant problem we face is “okay, we have to come up with a game idea”.
“It’s a success-driven business, especially on the super laid back side of things. So even if you have a hit game that hits the top of the charts, it usually won’t last that long. And so you have to find the next concept and the next concept. We think Ludo is really responding to this type of demand by helping creators create better concepts, and certainly more concepts at scale.
Yet, with a machine learning platform searching through a library of existing games, isn’t there a risk that it delivers spinoff ideas, games that follow a trend rather than create it? a new one?
“It’s very possible,” Pigott admits, “but that’s where you keep itching, so you can ultimately create something unique. There’s another feature that we have and we call it the “game mixer,” and that effectively allows you to take existing games and mix them together.
“For example, you could take something like Among us, which is very popular, and then you can add two totally different headlines from the trend charts and ask Ludo to mix up all of those concepts. And maybe you’ll get a mechanic from one, a description of the other, and pictures from the third. And it’s a way that it becomes non-derivative that you can create something interesting. You can take all of that and put it into the concept you’ve been working on before. There are many ways to make it unique.
“But needless to say, with the millions of games available, it’s quite difficult to have a completely original new concept. Someone out there has already thought of something similar to your idea. And it’s good.
He’s not wrong there – after all, game journalists are often known to liken new titles to familiar touchstones. ‘It’s the Dark souls dating sims! It’s the Super Mario simulation games! ‘ Hell, this month’s When We Made is about a game that certainly could have sprung from a game mixer process – a mashup of Breath of the wild and Animal crossing, and the game is no less unique because of it.
All games, no matter how unique, draw ideas from somewhere. Developers are always inspiring each other to find new ways to express their creativity. Ludo, Pigott argues, is simply providing a helping hand – reminding developers of titles they might have overlooked.
“People have been in the industry for decades and it’s hard to have it all in mind. I think what’s been interesting about so many games that are in there is games from the 90s and early 2000s, games that you forgot about. And that’s what a lot of it is, it’s about taking inspiration from hits from the past and making a modern take on it. “
THE FUTURE OF AI
Of course, machine learning is already in use across the industry. And Pigott believes these AI development tools will only become a
greater strength not only in our industry, but in all creative industries.
“We just think AI development tools are going to be part of the industry. I mean, there are already here, there are a lot of AI tools in the back end in terms of monetization, optimization, things like that.
“But I think the creative tools that use machine learning are going to come to a lot of industries. I mean, look at the music industry – just think about how many songs you have to think up and create. Or it could be in advertising or movies – you just take that industry’s particular database and apply it to the AI platform. And so I’m sure it will be later. “
Ludo launched as an open beta in January, with developers already familiarizing themselves with the platform. So how have the reviews been so far?
“It was awesome,” says Pigott. “We were very, very happy, both with the number of people and studios registered and the feedback we received.
“People are finding that they can use it in a collaborative sense. Because when you’re game-storming, it’s not always an individual effort, it’s a collaborative effort. And this allows you to do it in the Ludo environment.
“One thing that has actually become a heavily used feature, which we might not have expected, is that we have an image database of almost two million game images. And the feedback we get from a lot of users is that for artists it’s this huge resource to draw inspiration from if you’re looking for a type of game. People said, “It’s like Pinterest for the designers of games ”, because it’s such a huge resource. You can just keep picking your favorites and creating moodboards from that.
The JetPlay team is currently working on feature requests from their users, such as integrating the platform with other creative tools. Those who want to learn more can sign up for the beta at askludo.ai.
“We are still in the beta phase,” says Pigott. “So there will be a lot of improvements and significant changes between now and the commercial release. And we hope that it becomes a real game-storming tool for small studios and helps them create better game concepts. That is really all it is – it helps energize this creative process. So we are very excited about it and look forward to releasing it commercially. “