#138 Data Science & AI in the Gaming Industry

Hi, I'm Maggie, VP of Curriculum at datacamp and I know firsthand how overwhelming it can be to keep up with the rapid changes in data and AI. But staying ahead doesn't have to be hard. That's why our curriculum team has curated the best learning content to help you and your team stay ahead, covering everything from data and AI literacy for busy executives to cutting edge generative AI for developers, and everything in between. Whether you're upskilling yourself or your team, we make learning practical, engaging and flexible. It just works. Power your data and AI transformation journey on datacamp.com.

We are living very exciting time because we are just beginning to scratch the surface of everything that could be done with data science in games and this is still a very new adventure for a lot of studios and I feel like with ChatGPT4 and other improvements in AI there is so much potential, so many things that could potentially be done to make it better for everyone.

Hello everyone. Welcome to Data Framed. I'm Adele, data evangelist and educator at Data Camp, and if you're new here, Data Framed is a weekly podcast in which we explore how individuals and organizations can succeed with data and AI. A lot of the time at Data Framed, I have the privilege to talk to data leaders and practitioners about one of my biggest passions, which is obviously data science. But today is even more delightful because I get to further understand the intersection of two of the biggest topics I'm most passionate about, which is data and video games. For those who are not aware, the video games industry is bigger in market value than the music and movies industries combined. And the video games industry is a rare industry that combines both creativity, art direction, incredibly high quality production, but also an extremely mature approach, technology and data Data informs a lot what we see in video games from the quality of video games, the accessibility of maps and worlds, and even the go to market as video games are launched. This is why I'm thrilled to have Marie de la Selc on today's episode. Marie is an accomplished games industry professional with over a decade of experience. She started off her career as a data analyst and has since risen through the ranks to become a data leader.

In the gaming industry.

She's worked at companies such as Ubisoft, Warner Bros. And most recently at Eidos, the company most well known for games such as Guardians of the Galaxy and Tomb Raider. Throughout the episode, we discuss how data science can be used in gaming. Unique challenges data teams face in gaming, from really low data volumes to massive changes to production schedules and even game vision. We also spoke about the difference between AI as we know it in data science and AI and gaming, which informs how NPCs behave in a video game world and a lot more topics. If you enjoyed this episode, make sure.

To subscribe to the show, share it.

With your friends, give us a review and comment. It goes a long way in making sure the show successful. And now on to today's episode.

Marie de Lazerque, it's great to have you on the show.

Nice to meet you, Very happy to be there.

So you've been at the intersection of data science and gaming for more than 10 years now. So maybe to set the stage for our conversation. Let's say I'm playing Guardians of the galaxy on my PS5. What role did Data science or is playing or Data science is playing in making sure that I'm having a great experience.

So of course I can't reveal anything that would be NTA related. But on a general basis what is going to be happening is the data that is being generated by players when they are playing is being collected pre like launch and after launch to help developers actually understand how people are playing the game and if what they had in mind is actually what is happening in the game. So there is a lot of different ways data science can be used to make sure this happen. You can use data science to optimize the system of the game. For instance, you can use AI to test the game automatically to see if there is any kind of issues. And of course in my team there are also data analysts and they were working with data scientists to provide, you know, any kind of like report and dashboard to better understand what we were observing in terms of behaviors.

So that's really great. You know, in a lot of ways there's a lot of different use cases or areas where data science provides a lot of value in gaming. You had quite a few different data teams in gaming. Maybe walk us through the different types of areas within a game where data science and machine learning play a big role in delivering value.

What is very interesting about data science is how versatility is it encompass so many different applications. In my previous job we actually had like an AI team. We also had people inside of the development team working on those kind of things and we had like our machine learning people in my team working on different things related to business. So in a game we can just discuss of for instance the AI that are actually being developed to help a player having fun by engaging with NPCs that are well defined, but also being able to defeat enemies that are an actual challenge. So there is more and more data being used during development to be able to achieve those kind of goals. And there is also optimizing anything, like the sound of the game or the graphics, how to use machine learning and data science to actually help in those kind of challenges. And we've been using also on our side, data science to determine how people are actually reacting to everything that was related to the game. So reviews and people like journalists are publishing different reviews. We were able to extract information from those and say, okay, so this is what people are actually talking about and this is the sentiment that is actually associated to them. So what kind of things could you do based on those kind of things? So there is so many possible applications and different people being specialized in those specific areas.

That's very cool. And as a gamer myself, it's very nice to see the applications of data science across the chain of gaming, from development to the actual AI behind the NPCs and even after release, because the community aspect of gaming is such a huge important element that makes or breaks the success of a game. So understanding the pulse of the fans, what they want, et cetera, is really important. So I want to maybe pause on a few use cases that you talked here about. Let's maybe discuss, you know, early in development. I'm very keen on discussing what goes into AI development for an npc. But first let's talk about development. There's a lot of data science use cases that go into QA testing, into making sure that the game is running smoothly, it releases bug free. We've seen a lot of disasters in the industry, for example, where games were released prematurely with a lot of bugs. We've seen a lot more attention nowadays being applied towards QA testing for games. Maybe walk us through an example of how that looks like in action. What is a process of setting up a data driven QA process?

So this particular aspect of things, we were actually working with the AI team to develop those agents. So it was not my team, but we were working with them to be able to provide the dashboard and everything. But the idea is you can basically teach an agent to do different kind of actions or to learn from its environment and find stuff by themselves. And then you can deploy them in a version of the game or any kind of place you would like to improve. So they would be able to just play and they will generate data, basically. And using this data you will be able to determine, oh, it looks like this seems to be a problem. So for instance, if you see your agents are Always falling in the same hole again and again. Okay, maybe there is a problem and we should just get rid of this because it's very confusing and it's a problem. And the idea is you can generate so many of them and they can do almost anything in the game, so it's easier for them to find very specific issues that would be difficult to find for a human. And you can make them work during the night when you are basically sleeping. So there is a lot of very interesting things that could be done to improve the game based on this kind of agents just playing it and fighting Edge case and providing us with all of the data they are generating when they play so we can analyze the data after that and say, okay, so this is what we observe. So there is more and more companies, I think, that are going to use this kind of qa, not going to replace a QA professional, because a QA professional is absolutely necessary to understand, interpret the data, see if he's seeing the same kind of issues. But it's a tool in their disposition basically to help.

That's very fascinating in a lot of ways.

You mentioned here, I think two main.

Use cases or value drivers behind this is one, you uncover potential bugs within a game by looking at that data, but you also make a game better by uncovering potential issues in the level design.

You mentioned here.

If a bot continuously falls in a hole, then there's probably something wrong with the level design that needs to be improved. Maybe unpacking a bit the methodology. Are these reinforcement learning agents that are being used or are they programmed relatively more strictly? What is the methodology behind these tools?

So from what we were able to see working with this team in particular, they started with something very simple. So just to be able to implement the agent and see how it was reacting in the world. Because the reality is it's very complex to deploy an agent in a game. And so first it was very much rules that were predetermined for the AI and say, okay, we would like you to learn how to, I don't know, like do four steps and hit something. But the idea was in the long term for this to be actually reinforcement learning. So bots being able to learn from their environments and do actions by themselves.

Yeah, that's very fascinating and related to this agent design. And AI is actually the NPC AI that is developed, let's say you're playing Call of Duty, you're playing your favorite action game, how the enemies attack you, where they hide, the level of difficulty, that is all predetermined as well. Maybe walk us through that type of AI when it comes to applications in gaming. What's the process of that?

So this one is not, I would say in my particular bag of expertise this is usually taken care of by a development team itself. So there is people specialized like programmers, scripter and so on and so forth that are dedicated to doing these kind of things. But I think more and more there is going to have collaboration between those specific people and data scientists that would be able to say, okay, so instead of scripting a certain number of things, you can actually use a reinforcement learning model to be able to dictate basically the behaviors of all of those. But I don't think we are there just yet. I haven't seen a lot of people doing it just yet. But I know it's something that is more and more discuss because obviously there is so many possible applications.

And you mentioned another set of use cases here being actual commercial use cases. On being able to understand what the community engagement been like for a game, being able to understand how the game is being played after the game release so that there are further optimization. Maybe walk us through these use cases in a bit more detail. What does it take to set up these types of use cases pre launch?

What is interesting, I was discussing for instance the opportunity to optimize a game system. So there is a lot of system in the game, there is a lot of fight since economic system, combat system, all of those kind of things. And the idea is before the game is being released, it's always interesting to get people to actually play and generate data. So we have an idea how to analyze those. And so we were having people in pre launch coming and doing exactly this. And the idea was also for us, it was what we had in mind at least to use actually those bots, the one I was talking about, to generate as many of them as we could and let them play and see how they were interacting with the game and where the system was actually failing. So it could be, for instance, they are collecting far too many resources and there is no challenge for them to purchase anything. It could be, oh, you want the boss to be defeated in no less than 10 minutes. And they like most of the time, the players and those bots, they are able to defeat it in like three minutes. So there is a problem there. So those with the inside of the game like the optimization of the game. But there were also, as you were saying, business aspects to what we were doing. And this one was for instance having developing a tool that was allowing Us to scrap the reviews from journalists and people you know are reviewing the game. So on Metacritic, for instance, or Steam or any of this kind of stuff, and being able after that to do some topic modeling on it to determine what kind of things will actually be discussed in the game and what sentiment was being associated to that. So this is very important for marketing, for instance, to have an idea what are people saying at the moment, what are they discussing, what kind of sentiment is being associated with that and using it. So we had a dashboard and everything, the model has been deployed and we were able to use it.

I think it's very fascinating from your perspective. You sit as a leader within the industry and it seems like you need to have strong collaboration with almost everyone within a gaming organization, whether that's the engineering department, the creative studio, who wants a boss battle to be 10 minutes or around that vicinity of time. You need to be able to provide them like good direction over what makes a challenging boss battle, but also to the commercial teams, finance and marketing and be able to be supportive to them. So maybe let's start on the development and creative side of the coin. What does a good collaboration look like for a data science leader in this space to be able to understand what are the true requirements, requirements for a game to be successful? How can I inform the agenda? Walk me through the challenges there and how you've seen modes of success.

Yeah, so this is very much the art of everything. So you need to have everyone on board with you and you need to prove to all of those people that what you are doing is actually being useful to them. Because developing a game is difficult. It requires a lot of time, a lot of effort, a lot of money. And basically what we were trying to achieve is we are there for you. So we are going like we need to collaborate and anything we do, it's to answer the questions you have and help you meet your objectives. So the team we had was very much in the middle of, as you were saying, a lot of teams. So we were working with user research, we were working with marketing, with PR and the game development team. And so to be able to keep open communication with all of those people, we're basically using the Agile methodology. So we are working on two to three weeks sprint and during the sprint we were collecting any requirements, making sure they were actually met at the end of the sprint and so on and so forth. And what we were doing also to be able, for instance to make sure we were align with the development cycle of a game, was actually asking to be Part of some of their more important meetings. So being able to say, hey, could we be there when you are developing features? Could we be there when you are having some of your Sprint meetings and so on and so forth and making sure that the information was actually circulating between everyone.

And maybe as someone who's managing a team, how do you split your time between coordination with other teams versus actually working with your team and being a contributor yourself? How, what's the time split there? Because it strikes me as that there's a lot of coordination that needs to happen there.

There is a lot of coordination and this is why you have all of those different roles in a team. You are going to have like data analysts and data scientists and so on and so forth. Those people are actually doing the CR of the work and they are like transforming the requirements into actual deliverables. But everyone was actually participating in this collaboration. So basically we are the data scientist, data analyst, directly embedded into the development team. So this way they were able to collect any kind of requirements and work on them as soon as possible and as efficiently as possible. So I would say on my side, I was trying to coordinate as much as I could also and it was taking a lot of time. So it was basically one of the core activity, making sure, okay, what has been discussed, where are we in term of what we need to deliver? Are those people aware of what we are working on at the moment? And so on and so forth. So as a director manager, it's a lot of time that you have to actually dedicate to this. But at least the communication was not just me coordinating everything. Like everyone was actually talking to the team directly and reporting to the team what new information layout so we can coordinate together. I don't know if it makes sense, but yeah, that's the way we're doing it.

It definitely makes sense. And you mentioned something is that making games is hard. It's very hard, right? Like anyone who is not necessarily aware of the gaming industry, for context, the gaming industry is bigger than the movie industry in the music industry combined, right? And making games like your favorite games like Grand Theft Auto or Call of Duty or Rockstar or like for example Red Dead Redemption, right? They take eight to nine years sometimes in creation of like development time crunch. It's quite a lot of effort to create a game and oftentimes there's creative direction changes that happen mid games right throughout the development cycle. How does that affect the data team? How are you able to be agile and be flexible when there are major shifts that happen in the creative direction of a game.

Okay, so this is a very good question and we were affected by this a lot, obviously, because it's not just, it's impacting everything, it's impacting the planning of the project. When we are going to have Playtest, what kind of features are going to stay or what kind of features are going to be cut, all of this kind of things. So this is why, first and foremost I was saying I want people to be part of the meetings where game designers and others are actually having this discussion so we have a chance to adjust as soon as the information is being delivered to like it's being known and we have to basically have those. Like this is why we have our sprint and this is why we are agile, having those meetings where we say, okay, so this is the new situation, this is what is going to remain, what's, what is going to go away, what's the new priority for each of those. And of course, as you were saying, all of this is not just the dev team, it's everyone, including people working in the background. So when we have to do those kind of things, it impacts our metrics, it impacts our documentation, it impacts what kind of like metrics is being implemented and will have to change, but also which one are going to be decommissioned and which one are going to need a new implementation which requires dev time for it to happen. So we are very used to this, which is why it's not necessarily impacting us too hard because we expect them, we expect those kind of things to happen. And this is why we have also like this coordination with the dev team to say, okay, during a sprint we need dev to spend time for us to for instance implement the metrics and so on and so forth. For a data science, for the data science aspect of things, it's also very hard because when the game is changing, suddenly your models are not working as they should work and you have to sometimes start again from scratch because new features are suddenly appearing, others are just going to get out completely of the game and so on and so forth. So basically you have to keep track of all of that and you have to be able to adapt, retrain your model, like ask people to play the game and if you have them, like set up some bots and see what's happening. It's very challeng challenging. It's very challenging. And it's costly also it's quite expensive because training a model and like putting in production is not. It's costly in terms of how much time it's Taking, but also using the data to train the model and so on, so forth. So what we do is there is phase in a project where this is more likely to happen than others. So we know, for instance, we're not going to develop a very complex data model for anything that is at the very beginning of a project, we are going to wait for it to be more mature and more stable to start doing any of this kind of stuff. Before that it's going to be more. We try to see how we can like even deploy anything, put everything in place in terms of pipeline, put everything in place in term of being able to work with the data.

This is extremely fascinating, you know, especially given I think one of my two favorite industries are data science and gaming. So I'm really enjoying this conversation. And in a lot of ways the creative aspect and creative changes. Right. Puts an additional wrinkle to the data science challenges because there's not necessarily a lot of data on that new feature. When you create and deploy a model, what are the challenges? How do you avoid or how do you solve that challenge for not a lot of data, let's say early in the development process and the QA process, you want to create a machine learning model that's trained on the environment or something along those lines. What do you do when there's a lot of data scarcity because there's not a lot of players that have played the game so far.

Absolutely. See, this is the biggest challenge we had because data science and all of those models, they require a lot of data to be able to start beginning to do something. And when you have only like 10 to 30 people playing during playtests, it makes it very difficult. So this is why we had this ide, but it was not deployed yet when I was, before I left to actually use those bots. So those AI agents that are going to be able to play the version of the game that is actually available in a way that is relatively similar to a player. So you can generate a lot of them and all of those, they are going to send metrics. And those metrics, you can use them to determine, okay, what seems to be like the most important features and so on and so forth. But yes, datasense in pre launch, it's. Yeah, it's not always easy if what you're looking for is improving anything related to player playing the game. It's easier for stuff like, you know, graphics of audio or any of those kind of things because you can generate data easily. But yeah, that's at least it was what we were trying to achieve and I hope that it could work in the future.

So that's really great. And we've been talking quite a lot about what happens like data science use cases and specificities and challenges pre launch when the game is being developed. But maybe let's talk about it as well post launch. So one aspect that I imagine is extremely difficult and challenging when setting up these types of data science use cases is getting a lot of data from players when millions of players around the planet are playing at the same time and trying to understand and unearth insights from that data. So the way I see it is that there's a lot of challenges on the data collection side, like how do you actually set up that streaming platform to get a lot of data in, to be able to ingest it and transform it. But then is what do you look for when you improve, to actually improve a game? So let's maybe start in that first puzzle. Here is what are the challenges related to data collection when you have millions of players streaming data to the cloud and you're able to collect that data and store it.

So data collection is actually not so much of an issue because we have pipelines, we have a system to collect the metrics, define them, implement them, and this is being tested before the game is released. So we are ready when suddenly we have millions of people coming and providing all of this data. We decide which metrics we are keeping, which one. We are not keeping this kind of stuff, and then we have access to them directly. So we're using Google BigQuery and Google Cloud services to be able to achieve this. So it was not us, it was the data engineer and the magician on the DevOps team. These people do stuff I don't understand, but I'm very happy because it works. And the idea is unlike a lot of team from which when the game is released, it's released like it's done. Congratulations, you did your work for us. It's actually like marketing and all of this team work is actually starting because suddenly we are looking into all of those KPIs to make sure the game is actually performing as we were expecting. We are looking into, okay, so what we saw during the pre launch when we were trying to improve the system, has it been effectively corrected or not? In terms of player behaviors, are we seeing new things that we have not identified? We are doing also data science, for instance, segmentation of failure. So we are going to try to determine, fine, who is playing our game, what kind of category of players we have Based on what they are actually doing inside of the game. So for instance, oh, there is a category of people that looks like they are very engaged, they are doing absolutely everything in the game, while others are barely touching the surface. And how many of those people we have. And we are going to try to predict stuff like activity which we can expect it to change or to stay the same based on if we are going to do any kind of event. Of course we are discussing and working with the sales team to see, okay, could we have like a very simple prediction model just to have like an idea of, okay, what we can expect as a baseline in the coming weeks, for instance, and see how we adjust based on that. So there is a lot of things we were looking into in terms of, of a business, but also like player behaviors and understanding how the game was performing.

And if you wanted to choose what is a more challenging time for the data science team would be pre launch or post launch. In terms of the type of use cases as well as the level of technical expertise needed to unearth these insights.

I would say everything should be in place and everything should be working for the release of the game. So all of your pipeline, all of your model, all of your this, they should be ready, up and running. Even if after that you need to make modification, you need to retrain stuff and so on and so forth. I would say it's more challenging pre launch because you don't have a lot of data and you are basically putting everything in place, hoping it's going to work. Once the game is released there is new challenge. True, you suddenly have a lot of data so you need to be sure your model able to absorb all of that. It's going to cost more money because suddenly you are training and you are deploying model on millions of people data. So maybe you will have to sample for those kind of things. There is obviously the fact that with more data there is new behaviors that maybe you didn't catch up when you were on pre launch, so so on and so forth. But once you have everything in place, the kind of issues you will have is usually easier to tackle than when you are building everything up from scratch.

And you mentioned here a lot of insights that you uncover from player tests after the game is launched. How does the communication flow look like then with the creative teams, how often do they update the game after that, what does that process look like?

So it all depends on the kind of games. Obviously if it's a live game or if it's a game you put in a Box and just sell on the counter. But usually what's going to happen, we are going to have a live dashboard with all of those KP's that are needed to follow up on the game. There is going to have reports also. So for instance, for Guardians, we made a series of six reports and those were presented to like the high level executive, but also the producer of the game and all those kind of things. We make also custom reports for people having specific question regarding one aspect of the game or two. And this way we are making sure people can follow up on the game and follow up on what's happening inside of the game, answer questions. And sometimes those kind of questions can come very far away after the launch, which is very interesting. If someone is developing a game that seems to be similar to the game we developed in the past, they're going to come to us and say, hey, could you do some, some specific reports? Marketing obviously is going to want to know what's happening in term of player activity, for instance, if they decide to do any kind of event. So for instance, you're putting your game on the game pass. Okay, how many more people did you get? And it allows you to say, okay, maybe how many of those people would have paid if we had not made this specific thing? So there is a lot like we are trying to keep everyone informed because this is extremely important. People working on the game took time to actually discuss with us and provide time for us to have metrics in the game and so on and so forth. And for us it's super. They know, okay, this is the result of everything you did. Like you can now see how the game is working and what people are doing.

This is really great. And there's a couple of things that you mentioned here that I would like to further unpack. So you mentioned the marketing question of let's say the game is on game pass. Should we have kept the game out of game pass, yes or no? When it comes to the data coming there, how important is the console maker, developer ecosystem? How do they provide you that data? Where do you get that data from Microsoft? What does that look like?

I have to say, I'm always extremely astonish at how unwilling most of those console developers are to actually provide data in a format that would allow us to go further into the analysis we would like to do on our side. We know we get the data from the game directly, we are going to get information about how many people are doing what and so on and so forth. Of course, it's completely unanimous. Like it's completely GDPR complain and everything for the cells. It's not us that we're collecting this information. It was marketing or finance and from my understanding most of the time those information were coming into a different kind of format on Excel Extract and it was not even this person has made this purchase. It's going to be a conglomerate like each like months. This is how much you would have sell, which was a challenge to do a prediction and stuff like this.

Yeah. Interestingly, Netflix follows a similar model. Not a lot of people know how much their movies have been downloaded. For example, let's say you are a comedian on Netflix. You don't know how much your special.

Has been streamed, which is puzzling me so much because those are our players basically ourselves. We should be able to collect information at people level because this is important for us. But in the console industry it's not working this way. On the PC side, I think it's far much easier if I understand well, because Steam and so on and so forth, they are letting you get access to all of this kind of information. But yeah, it's a challenge this one, like for the sales I have to sell account solely. It's a challenge too.

It's an interesting space. And then the other question that I wanted to ask you here as well, which is you mentioned something that's very specific that I think we can go on a tangent here and discuss quite a lot, which is it depends on the type of the game, right? If it's a live game, if it's a off the counter game and you can even go into more detail here. Is this sports simulator? Is it a first person shooter? Is it a game like Hades for example, example, that is developed over time. Right. So that also has a lot of wrinkles when it comes to what type of data science you do. So maybe walk us through the relationship between the type of game and what type of data science you do on the game. What does that relationship look like?

Yeah, absolutely. So a live game part by definition will be updated as it goes. But there is going to have events, but there is also going to have a lot of patches of constant development past the official release date, which means there is far much more opportunity for a data analysis and data science team to actually have an impact on the game because they can provide those reports and use those models to actually provide information to the dev, answer their questions and so on, so forth and make recommendation to improve certain aspect of the game in term of whatever you want. Like it could be the revenue, it could be the retention, it could be the acquisition, it could be a lot of different aspects based on what the PM or anyone that is concerned needs and wants when a game is being released as a box. Basically it's a bit different because the new iteration of that game or the DLC you're going to release are going to be sparse or very far away in time. So you are going to be able to still learn a lot of things because it's going to inform any kind of like similar project and also what kind of return on investments you had just simply based on like the number of people paying, how much they're staying, if they are like abandoning the game and so on and so forth. But the kind of things you will do is not necessarily going to be as immediate, let's say in terms of the impact on the game and a.

Lot of ways as well that will also determine what goes into a sequel of a game in case the sequel is being developed. So I was for example, I played God of War then God of War 2 directly after each other and you could see that there were some quality of life improvements that were done on really small things that would have most likely been informed by data science and by analyzing player data.

Player data, absolutely. So it's interesting because it might be less immediate, let's say, but it's still very important because very often a project like you know, a studio is not going to have like just one game in development and that's it and then we start a new one. There is multiple games being developed at the same time. And so what you learn from one of those games you just released you can use to determine what could possibly happen for the others. Especially knowing that most of the studios are specialized into a certain type of game. So even if it's not exactly the same IP or the same game, there is just things you can learn from what you just did.

This is super useful. Now Marie, as we close out our conversation, I'd be risk not to talk to you about generative AI. If you look back also like two years ago when GPT3 was released, one of the first crazy use cases of GPT3 was actually a game use case which was a form of Dungeons and Dragons type role based playing game which is through text that is essentially auto generated each time you run a playthrough. We've seen a lot of cool use cases in game design from creating assets in Unreal Engine to creating audio assets as well to even creating player interactions and having a dialogue agents. So do you see this becoming more and more used in gaming in the next few years.

No one can predict the future, but I think any studio that is a little bit serious about data and how they want to use them to improve their game is going to use this kind of tool because it's so powerful. One of the things it could be used just to start would be generating dialogues for the npc, barks for the enemies, any of this kind of stuff that is usually painful to do and, and could just be automated so people that are developing like a narrative, the game can focus on more interesting stuff. There is so many ways it could give the feeling of a more vivid world through the kind of experience it provides. I'm already using it for a lot of like, teach me like I'm a five year old stuff and it's impressive, like you feel like you are talking to someone even if obviously it's not the case.

It's very impressive indeed. And I think what's even more exciting for what this means for the future of gaming is what this means for the future of indie gaming in a lot of ways. If a two team developer team are able to create incredibly high quality dialogues, incredible high quality assets with the use of AI, then this only means better games for everyone in the future as well. So this is a pretty interesting space to follow.

And it's not the only application because you know you could ask him to generate quotes for you. It's pretty impressive. I was looking in at it and you can just say, could you provide me, I have this question, I want to do these things. I would like you to generate some codes in Blur program and it actually does it. So I have to say it's so much faster and easier than just go to Stacker Overflow and trying to find a bit of code that is going to help you. So I feel like it's going to maybe reduce some, some development time potentially also by providing help to programmers and anyone who needs those kind of things.

I couldn't agree more. Now Marie, as we wrap up our conversation today, do you have any final words to share with the audience before we end our chat?

Yes, I would say that we are living very exciting time because we are just beginning to scratch the surface of everything that could be done with data science in games. And this is still a very new adventure for a lot of studios and I feel like with ChatGPT4 and other improvements in AI there is so much potential, so many things that could potentially be done to make it better for everyone. But I think there is still the barrier of the habits. There is some inner C yet because it's very new. It's. It's not something that people are used to think about when they are developing a game. So I think we will have to actually consider it seriously and provide the resource and time that is needed for them to be implemented.

That is very great. Marie. Thank you so much for coming on Data Frame. I really appreciate it.

Thanks to you. It was, it was a very good time. Speaking.

I had a blast. I love talking about gaming any day of the week and let alone talking about data science. Yeah.

Yep.

I appreciate it.

Thank you. SA.