00:00:01
Speaker 1: The secret to using AI well might actually be teaching it to shut up. In this bonus episode, I am joined by Elan Lee, the brilliant mind behind games like Exploding Kittens and Throw Throw Burrito. And while you might expect someone like Elan to use AI to design wild new worlds or characters, that's not what he does at all. Instead, he's found a way to make AI his creative spiring partner, one that never interrupts, never judges, and somehow helps him think more clearly.
00:00:33
Speaker 2: When you're working with AI, you don't let it answer questions for you. You let it ask you questions.
00:00:42
Speaker 1: In this bonus chat, you'll hear how Elan uses AI to stress test his game ideas, solve tricky design problems, and even guide his own creative walks. Welcome to How I Work, a show about habits, rituals, and strategies for optimizing your day. I'm your host, doctor Amantha Imba. I'm curious now that the GENII is such a part of our work lives, and you know, really has been for like three years now, how has that changed your creative process?
00:01:23
Speaker 2: If it all, we don't use it as part of the creative process, I have asked A. I've said, hey, I want to come up with a game that has a duck of cards and it's themed fish, and it involves something that you throw up in the air and have to catch it, and the junk that it spits back is the worst, most awful stuff imaginable. So we've learned very you know, we tried all those tests and realized like, okay, this is not what AI is for. Then we tried it for art. We're like, okay, so here's a final game. I don't have a good theme. Come up with one and create all the art, and it comes up with well you've seen it comes up with AI art, and so that's useless. So now what we use it for is kind of an augmentation process. We'll say, like, here are instructions that we're ready to send out to these four hundred families. However, once we do that, we can't test those four hundred families anymore. So I want to make sure this has the best chance of success. Dear AI, please read these instructions and you ask me any questions that will help with clarity, and it will find edge cases that I never would have come up within one hundred years. And that's really really helpful because now I get the most out of these families because I can only use them each once. Now, anything that could possibly come up within reason AI has usually flagged. We've modified the instructions and now we get wonderful test results that are to the quality of gameplay and not to these weird edge cases that just distract from gameplay. So we use it a lot. There. We use it a lot when we get into a bind with points. Points in games are this whole weird eCos It's an economy. It's this miniature economy that exists within the game, and if inflation gets too high, the game breaks, and if a recession happens, the game breaks, and if you run out of resources, the game breaks. Right. Points are weird because they have to abide by all the rules of economics, but in this very very micro sense, and it's different from games games game. So oftentimes we'll find ourselves in a bind where it's like we hit this thing where everyone had to get points, but nobody won because there weren't enough points. And I don't want to put in infinite points in this game, So how do we restrict this one little thing? AI is very good at those problems solving microeconomic issues. Turns out AI is lovely at that in a way that I don't want to study, I don't want to get good at. I'm going to just throw the problem at AI. It feels a lot like math. Let somebody else solve it.
00:03:47
Speaker 1: I love those two examples. Are there any other ways that you found personally II to be quite useful in the role that you do.
00:03:56
Speaker 2: Yeah. I use AI every day for about two to three hours a day, and what I do is primarily I use chatch EPT and I'll put it on voice mode, and I have this prompt that I used to have to refeed it, but now it's learned to remember this prompt. But the prompt basically says, I'm going to go for a three hour walk and I want you to stay on the whole time, and I'm going to describe just what's going through my head. Might be a game design issue, it might be a company policy issue, it might be an HR issue. Whatever it is, here's what I'm thinking about today. And one every time I tell you to take notes, just record the last thing I said, and later on give me a transcript of just the parts that I've said to record, and then two, don't be scared of silence. Please please please do not fill silence. Is if I stop talking, that doesn't mean you talk, that means just hang out. I'm processing and if I ask you a question, please help me. And if I ask you for other ideas for something, then please answer. But your job is not to be the other half of this conversation. Your job is to let me think and facilitate that thinking process. And I do that every single morning, and it's glorious. It's such a wonderful practice because I come back with this note file that it generates of exactly how I want to handle the problem that I was working on.
00:05:18
Speaker 1: I want to know more about this, Like with every walk that you're going on in the morning, are you starting with a predefined problem or is it sometimes fuzzier than that.
00:05:27
Speaker 2: Yeah, I used to think I had to I would list out exactly the problem, but I found that as the engine gets better and better, I can come to it with some pretty nebulous ideas and sometimes it will guide me through brainstorming. Again, this is some modifications I made to the prompt where I'll say, like I'm looking for a new game idea. I'm vaguely interested by X, Y, and Z, So help me figure out what I'm trying to figure out. Don't answer it for me, just ask me leading questions that will help me work through my own design process. And it's quite good at that I'm able to approach it with much less data than I thought I had to and still come out with a great result.
00:06:09
Speaker 1: That's really interesting how you don't ask it for input. You're just using it as someone to question you and extract information from yourself.
00:06:17
Speaker 2: If you were.
00:06:17
Speaker 1: Giving advice to someone who was looking for help being more creative, improving their own creative process, and they're not you and they're not math, like, what advice would you give them on how to work with AI?
00:06:31
Speaker 2: First, you have to fill your own head with raw materials. You don't have to remember everything, but like you need to go watch all the movies, and you need to listen to all the podcasts, and you need to read all the books and watch all the TV shows and play all the games. Because you don't have to have instant recall of these things, but you do need a lot of raw data in your head kicking around in there somewhere, and then when you're working with AI, don't let it answer questions for you. You let it ask you questions that all of that raw material might be the answer for, and in particular, you train it to encourage you to combine things together. I feel like all my best ideas are really the combination of other people's ideas, just combined in new and interesting ways. And if you can get AI to help you focus on those individual nuggets that are kicking around in your head because you filled your head with all those things, and then encourage you to start combining them together, not how to combine them, just hey, what if you mix those two ideas together? Suddenly you're brainstorming in a whole new capacity.
00:07:44
Speaker 1: What I love about Alan's approach is that he's flipped the script on AI. Instead of asking it to come up with ideas, he uses it to ask him better questions, to help him see what's already in his head and connect the dots in new ways. So the next time you're feeling stuck, try this open chat JPT and ask it to interview you about your problem instead of solving it for you, you might be surprised by what surfaces, and if you haven't yet, heard my full conversation with Elan. I'd highly recommend it, or you dive into creativity, failure and what it really takes to make great ideas happen. There is a link to that in the show notes. If you like today's show, make sure you hit follow on your podcast app to be alerted when new episodes drop. How I Work was recorded on the traditional land of the warrangery people, part of the Cooler Nation.
Speaker 1: The secret to using AI well might actually be teaching it to shut up. In this bonus episode, I am joined by Elan Lee, the brilliant mind behind games like Exploding Kittens and Throw Throw Burrito. And while you might expect someone like Elan to use AI to design wild new worlds or characters, that's not what he does at all. Instead, he's found a way to make AI his creative spiring partner, one that never interrupts, never judges, and somehow helps him think more clearly.
00:00:33
Speaker 2: When you're working with AI, you don't let it answer questions for you. You let it ask you questions.
00:00:42
Speaker 1: In this bonus chat, you'll hear how Elan uses AI to stress test his game ideas, solve tricky design problems, and even guide his own creative walks. Welcome to How I Work, a show about habits, rituals, and strategies for optimizing your day. I'm your host, doctor Amantha Imba. I'm curious now that the GENII is such a part of our work lives, and you know, really has been for like three years now, how has that changed your creative process?
00:01:23
Speaker 2: If it all, we don't use it as part of the creative process, I have asked A. I've said, hey, I want to come up with a game that has a duck of cards and it's themed fish, and it involves something that you throw up in the air and have to catch it, and the junk that it spits back is the worst, most awful stuff imaginable. So we've learned very you know, we tried all those tests and realized like, okay, this is not what AI is for. Then we tried it for art. We're like, okay, so here's a final game. I don't have a good theme. Come up with one and create all the art, and it comes up with well you've seen it comes up with AI art, and so that's useless. So now what we use it for is kind of an augmentation process. We'll say, like, here are instructions that we're ready to send out to these four hundred families. However, once we do that, we can't test those four hundred families anymore. So I want to make sure this has the best chance of success. Dear AI, please read these instructions and you ask me any questions that will help with clarity, and it will find edge cases that I never would have come up within one hundred years. And that's really really helpful because now I get the most out of these families because I can only use them each once. Now, anything that could possibly come up within reason AI has usually flagged. We've modified the instructions and now we get wonderful test results that are to the quality of gameplay and not to these weird edge cases that just distract from gameplay. So we use it a lot. There. We use it a lot when we get into a bind with points. Points in games are this whole weird eCos It's an economy. It's this miniature economy that exists within the game, and if inflation gets too high, the game breaks, and if a recession happens, the game breaks, and if you run out of resources, the game breaks. Right. Points are weird because they have to abide by all the rules of economics, but in this very very micro sense, and it's different from games games game. So oftentimes we'll find ourselves in a bind where it's like we hit this thing where everyone had to get points, but nobody won because there weren't enough points. And I don't want to put in infinite points in this game, So how do we restrict this one little thing? AI is very good at those problems solving microeconomic issues. Turns out AI is lovely at that in a way that I don't want to study, I don't want to get good at. I'm going to just throw the problem at AI. It feels a lot like math. Let somebody else solve it.
00:03:47
Speaker 1: I love those two examples. Are there any other ways that you found personally II to be quite useful in the role that you do.
00:03:56
Speaker 2: Yeah. I use AI every day for about two to three hours a day, and what I do is primarily I use chatch EPT and I'll put it on voice mode, and I have this prompt that I used to have to refeed it, but now it's learned to remember this prompt. But the prompt basically says, I'm going to go for a three hour walk and I want you to stay on the whole time, and I'm going to describe just what's going through my head. Might be a game design issue, it might be a company policy issue, it might be an HR issue. Whatever it is, here's what I'm thinking about today. And one every time I tell you to take notes, just record the last thing I said, and later on give me a transcript of just the parts that I've said to record, and then two, don't be scared of silence. Please please please do not fill silence. Is if I stop talking, that doesn't mean you talk, that means just hang out. I'm processing and if I ask you a question, please help me. And if I ask you for other ideas for something, then please answer. But your job is not to be the other half of this conversation. Your job is to let me think and facilitate that thinking process. And I do that every single morning, and it's glorious. It's such a wonderful practice because I come back with this note file that it generates of exactly how I want to handle the problem that I was working on.
00:05:18
Speaker 1: I want to know more about this, Like with every walk that you're going on in the morning, are you starting with a predefined problem or is it sometimes fuzzier than that.
00:05:27
Speaker 2: Yeah, I used to think I had to I would list out exactly the problem, but I found that as the engine gets better and better, I can come to it with some pretty nebulous ideas and sometimes it will guide me through brainstorming. Again, this is some modifications I made to the prompt where I'll say, like I'm looking for a new game idea. I'm vaguely interested by X, Y, and Z, So help me figure out what I'm trying to figure out. Don't answer it for me, just ask me leading questions that will help me work through my own design process. And it's quite good at that I'm able to approach it with much less data than I thought I had to and still come out with a great result.
00:06:09
Speaker 1: That's really interesting how you don't ask it for input. You're just using it as someone to question you and extract information from yourself.
00:06:17
Speaker 2: If you were.
00:06:17
Speaker 1: Giving advice to someone who was looking for help being more creative, improving their own creative process, and they're not you and they're not math, like, what advice would you give them on how to work with AI?
00:06:31
Speaker 2: First, you have to fill your own head with raw materials. You don't have to remember everything, but like you need to go watch all the movies, and you need to listen to all the podcasts, and you need to read all the books and watch all the TV shows and play all the games. Because you don't have to have instant recall of these things, but you do need a lot of raw data in your head kicking around in there somewhere, and then when you're working with AI, don't let it answer questions for you. You let it ask you questions that all of that raw material might be the answer for, and in particular, you train it to encourage you to combine things together. I feel like all my best ideas are really the combination of other people's ideas, just combined in new and interesting ways. And if you can get AI to help you focus on those individual nuggets that are kicking around in your head because you filled your head with all those things, and then encourage you to start combining them together, not how to combine them, just hey, what if you mix those two ideas together? Suddenly you're brainstorming in a whole new capacity.
00:07:44
Speaker 1: What I love about Alan's approach is that he's flipped the script on AI. Instead of asking it to come up with ideas, he uses it to ask him better questions, to help him see what's already in his head and connect the dots in new ways. So the next time you're feeling stuck, try this open chat JPT and ask it to interview you about your problem instead of solving it for you, you might be surprised by what surfaces, and if you haven't yet, heard my full conversation with Elan. I'd highly recommend it, or you dive into creativity, failure and what it really takes to make great ideas happen. There is a link to that in the show notes. If you like today's show, make sure you hit follow on your podcast app to be alerted when new episodes drop. How I Work was recorded on the traditional land of the warrangery people, part of the Cooler Nation.
