Latest / How I Work / (BONUS) Exploding Kittens CEO’s “walking with AI” ritual to unlock ideas.
Transcript
- 0:01Speaker 1: The secret to using AI well might actually be teaching
- 0:05Speaker 1: it to shut up. In this bonus episode, I am
- 0:09Speaker 1: joined by Elan Lee, the brilliant mind behind games like
- 0:12Speaker 1: Exploding Kittens and Throw Throw Burrito. And while you might
- 0:15Speaker 1: expect someone like Elan to use AI to design wild
- 0:19Speaker 1: new worlds or characters, that's not what he does at all. Instead,
- 0:24Speaker 1: he's found a way to make AI his creative spiring partner,
- 0:27Speaker 1: one that never interrupts, never judges, and somehow helps him
- 0:31Speaker 1: think more clearly.
- 0:33Speaker 2: When you're working with AI, you don't let it answer
- 0:39Speaker 2: questions for you. You let it ask you questions.
- 0:42Speaker 1: In this bonus chat, you'll hear how Elan uses AI
- 0:45Speaker 1: to stress test his game ideas, solve tricky design problems,
- 0:49Speaker 1: and even guide his own creative walks. Welcome to How
- 1:00Speaker 1: I Work, a show about habits, rituals, and strategies for
- 1:04Speaker 1: optimizing your day. I'm your host, doctor Amantha Imba. I'm
- 1:12Speaker 1: curious now that the GENII is such a part of
- 1:15Speaker 1: our work lives, and you know, really has been for
- 1:18Speaker 1: like three years now, how has that changed your creative process?
- 1:23Speaker 2: If it all, we don't use it as part of
- 1:26Speaker 2: the creative process, I have asked A. I've said, hey,
- 1:30Speaker 2: I want to come up with a game that has
- 1:31Speaker 2: a duck of cards and it's themed fish, and it
- 1:35Speaker 2: involves something that you throw up in the air and
- 1:37Speaker 2: have to catch it, and the junk that it spits
- 1:39Speaker 2: back is the worst, most awful stuff imaginable. So we've
- 1:43Speaker 2: learned very you know, we tried all those tests and
- 1:45Speaker 2: realized like, okay, this is not what AI is for.
- 1:48Speaker 2: Then we tried it for art. We're like, okay, so
- 1:50Speaker 2: here's a final game. I don't have a good theme.
- 1:53Speaker 2: Come up with one and create all the art, and
- 1:55Speaker 2: it comes up with well you've seen it comes up
- 1:58Speaker 2: with AI art, and so that's useless. So now what
- 2:01Speaker 2: we use it for is kind of an augmentation process.
- 2:05Speaker 2: We'll say, like, here are instructions that we're ready to
- 2:09Speaker 2: send out to these four hundred families. However, once we
- 2:12Speaker 2: do that, we can't test those four hundred families anymore.
- 2:15Speaker 2: So I want to make sure this has the best
- 2:17Speaker 2: chance of success. Dear AI, please read these instructions and
- 2:21Speaker 2: you ask me any questions that will help with clarity,
- 2:24Speaker 2: and it will find edge cases that I never would
- 2:27Speaker 2: have come up within one hundred years. And that's really
- 2:30Speaker 2: really helpful because now I get the most out of
- 2:34Speaker 2: these families because I can only use them each once. Now,
- 2:37Speaker 2: anything that could possibly come up within reason AI has
- 2:41Speaker 2: usually flagged. We've modified the instructions and now we get
- 2:44Speaker 2: wonderful test results that are to the quality of gameplay
- 2:48Speaker 2: and not to these weird edge cases that just distract
- 2:51Speaker 2: from gameplay. So we use it a lot. There. We
- 2:54Speaker 2: use it a lot when we get into a bind
- 2:57Speaker 2: with points. Points in games are this whole weird eCos
- 3:01Speaker 2: It's an economy. It's this miniature economy that exists within
- 3:04Speaker 2: the game, and if inflation gets too high, the game breaks,
- 3:07Speaker 2: and if a recession happens, the game breaks, and if
- 3:09Speaker 2: you run out of resources, the game breaks. Right. Points
- 3:12Speaker 2: are weird because they have to abide by all the
- 3:15Speaker 2: rules of economics, but in this very very micro sense,
- 3:18Speaker 2: and it's different from games games game. So oftentimes we'll
- 3:21Speaker 2: find ourselves in a bind where it's like we hit
- 3:24Speaker 2: this thing where everyone had to get points, but nobody
- 3:27Speaker 2: won because there weren't enough points. And I don't want
- 3:29Speaker 2: to put in infinite points in this game, So how
- 3:32Speaker 2: do we restrict this one little thing? AI is very
- 3:35Speaker 2: good at those problems solving microeconomic issues. Turns out AI
- 3:40Speaker 2: is lovely at that in a way that I don't
- 3:42Speaker 2: want to study, I don't want to get good at.
- 3:43Speaker 2: I'm going to just throw the problem at AI. It
- 3:45Speaker 2: feels a lot like math. Let somebody else solve it.
- 3:47Speaker 1: I love those two examples. Are there any other ways
- 3:51Speaker 1: that you found personally II to be quite useful in
- 3:55Speaker 1: the role that you do.
- 3:56Speaker 2: Yeah. I use AI every day for about two to
- 3:59Speaker 2: three hours a day, and what I do is primarily
- 4:03Speaker 2: I use chatch EPT and I'll put it on voice mode,
- 4:07Speaker 2: and I have this prompt that I used to have
- 4:09Speaker 2: to refeed it, but now it's learned to remember this prompt.
- 4:12Speaker 2: But the prompt basically says, I'm going to go for
- 4:16Speaker 2: a three hour walk and I want you to stay
- 4:18Speaker 2: on the whole time, and I'm going to describe just
- 4:21Speaker 2: what's going through my head. Might be a game design issue,
- 4:24Speaker 2: it might be a company policy issue, it might be
- 4:26Speaker 2: an HR issue. Whatever it is, here's what I'm thinking
- 4:28Speaker 2: about today. And one every time I tell you to
- 4:32Speaker 2: take notes, just record the last thing I said, and
- 4:35Speaker 2: later on give me a transcript of just the parts
- 4:38Speaker 2: that I've said to record, and then two, don't be
- 4:41Speaker 2: scared of silence. Please please please do not fill silence.
- 4:45Speaker 2: Is if I stop talking, that doesn't mean you talk,
- 4:48Speaker 2: that means just hang out. I'm processing and if I
- 4:51Speaker 2: ask you a question, please help me. And if I
- 4:53Speaker 2: ask you for other ideas for something, then please answer.
- 4:56Speaker 2: But your job is not to be the other half
- 4:59Speaker 2: of this conversation. Your job is to let me think
- 5:02Speaker 2: and facilitate that thinking process. And I do that every
- 5:05Speaker 2: single morning, and it's glorious. It's such a wonderful practice
- 5:09Speaker 2: because I come back with this note file that it
- 5:12Speaker 2: generates of exactly how I want to handle the problem
- 5:16Speaker 2: that I was working on.
- 5:18Speaker 1: I want to know more about this, Like with every
- 5:20Speaker 1: walk that you're going on in the morning, are you
- 5:22Speaker 1: starting with a predefined problem or is it sometimes fuzzier
- 5:26Speaker 1: than that.
- 5:27Speaker 2: Yeah, I used to think I had to I would
- 5:29Speaker 2: list out exactly the problem, but I found that as
- 5:33Speaker 2: the engine gets better and better, I can come to
- 5:37Speaker 2: it with some pretty nebulous ideas and sometimes it will
- 5:40Speaker 2: guide me through brainstorming. Again, this is some modifications I
- 5:44Speaker 2: made to the prompt where I'll say, like I'm looking
- 5:46Speaker 2: for a new game idea. I'm vaguely interested by X, Y,
- 5:49Speaker 2: and Z, So help me figure out what I'm trying
- 5:54Speaker 2: to figure out. Don't answer it for me, just ask
- 5:57Speaker 2: me leading questions that will help me work through my
- 6:00Speaker 2: own design process. And it's quite good at that I'm
- 6:03Speaker 2: able to approach it with much less data than I
- 6:06Speaker 2: thought I had to and still come out with a
- 6:08Speaker 2: great result.
- 6:09Speaker 1: That's really interesting how you don't ask it for input.
- 6:12Speaker 1: You're just using it as someone to question you and
- 6:15Speaker 1: extract information from yourself.
- 6:17Speaker 2: If you were.
- 6:17Speaker 1: Giving advice to someone who was looking for help being
- 6:22Speaker 1: more creative, improving their own creative process, and they're not
- 6:25Speaker 1: you and they're not math, like, what advice would you
- 6:27Speaker 1: give them on how to work with AI?
- 6:31Speaker 2: First, you have to fill your own head with raw materials.
- 6:35Speaker 2: You don't have to remember everything, but like you need
- 6:38Speaker 2: to go watch all the movies, and you need to
- 6:40Speaker 2: listen to all the podcasts, and you need to read
- 6:42Speaker 2: all the books and watch all the TV shows and
- 6:44Speaker 2: play all the games. Because you don't have to have
- 6:47Speaker 2: instant recall of these things, but you do need a
- 6:49Speaker 2: lot of raw data in your head kicking around in
- 6:53Speaker 2: there somewhere, and then when you're working with AI, don't
- 7:00Speaker 2: let it answer questions for you. You let it ask
- 7:04Speaker 2: you questions that all of that raw material might be
- 7:07Speaker 2: the answer for, and in particular, you train it to
- 7:11Speaker 2: encourage you to combine things together. I feel like all
- 7:15Speaker 2: my best ideas are really the combination of other people's ideas,
- 7:19Speaker 2: just combined in new and interesting ways. And if you
- 7:23Speaker 2: can get AI to help you focus on those individual
- 7:28Speaker 2: nuggets that are kicking around in your head because you
- 7:30Speaker 2: filled your head with all those things, and then encourage
- 7:32Speaker 2: you to start combining them together, not how to combine them,
- 7:36Speaker 2: just hey, what if you mix those two ideas together?
- 7:40Speaker 2: Suddenly you're brainstorming in a whole new capacity.
- 7:44Speaker 1: What I love about Alan's approach is that he's flipped
- 7:47Speaker 1: the script on AI. Instead of asking it to come
- 7:50Speaker 1: up with ideas, he uses it to ask him better questions,
- 7:54Speaker 1: to help him see what's already in his head and
- 7:57Speaker 1: connect the dots in new ways. So the next time
- 8:01Speaker 1: you're feeling stuck, try this open chat JPT and ask
- 8:05Speaker 1: it to interview you about your problem instead of solving
- 8:08Speaker 1: it for you, you might be surprised by what surfaces,
- 8:12Speaker 1: and if you haven't yet, heard my full conversation with Elan.
- 8:16Speaker 1: I'd highly recommend it, or you dive into creativity, failure
- 8:20Speaker 1: and what it really takes to make great ideas happen.
- 8:23Speaker 1: There is a link to that in the show notes.
- 8:25Speaker 1: If you like today's show, make sure you hit follow
- 8:28Speaker 1: on your podcast app to be alerted when new episodes drop.
- 8:32Speaker 1: How I Work was recorded on the traditional land of
- 8:34Speaker 1: the warrangery people, part of the Cooler Nation.