How to Make a Video Game With ChatGPT in 60 Minutes - Ep. 9 with Logan Kilpatrick

[00:00] Let's brainstorm. Like, what's the game you want to make? It would be interesting to see if you are a leader of this civilization. And then each turn, your people come to you as like, here are these choices that you have to take the next step in this growth of this civilization. As President Kennedy, your challenge is to balance the budget with the pressing needs of a nation on the brink of major social and technological changes. Will you prioritize space exploration, pushing NASA's budget to beat the Soviets to the moon, or focus on domestic issues, ensuring quality and prosperity at home? The choice is yours. [00:30] really good. [00:42] Logan, welcome to the show. How's it going, Dan? I'm super excited about this. I'm excited, too. We've been following each other and interacting on Twitter for a long time, so it's super fun to actually get to meet you face-to-face. For people who don't know, you are a member of the developer advocacy staff at OpenAI, the first OpenAI employee we've ever had on this show. Woo! So excited. [01:12] and with ChatGPT. And yeah, I'm psyched to have you. [01:18] Yeah, this is going to be awesome. And I'm super excited that you put this show together to really show like part of the historical challenge of ChatGPT is like showing people the art of the possible. So you doing this is like making all of our lives easier. And we're also doing a bunch of stuff from a product perspective to push on this. But I'm happy that you're pushing from this angle as well. It's important work.

[01:39] Thank you. I really appreciate that. I love the idea of the art of the possible. I feel like that's exactly the thing that ChatGPT opens up for so many people and for me personally. So that's really great. So we were talking a little bit in the pre-production call of what we want to talk about, what's most interesting. And I think one of the things that struck me is your role is to be a developer advocate. [02:05] But historically, developers have been this like sort of like small component of the population. And what's really interesting about ChatGPT is it's. [02:13] creating this world where the number of people who can become a developer, who can develop things is like is expanding tremendously, both because you can actually code underlying apps with ChatGPT and because of the thing that you just launched, CustomGPTs, which allow you to create custom versions of ChatGPT for specific use cases. So, like, tell us a little bit about CustomGPTs. Tell us why and tell us why you're excited about them. [02:39] Yeah, being able to build GPTs is probably like the biggest unlock since ChatGPT itself came out. We actually use the, we classify everybody who's building GPTs as quote unquote builders to kind of not make people who are, hear the word developer and are scared or say like, oh, that's not me. Like I'm not, I don't fall into that persona. And we give this flexibility of, you know, using the GPT builder, using the custom configuration when you're creating a GPT. You don't need to know how to code at all.

[03:09] If you do know how to code, there's a ton of stuff that you can do, but you can actually make something that is like materially much more useful than base chat GPT itself without writing a single line of code. Also, now there's companies like Zapier is a great example of this, where Zapier has this whole guide of how you can integrate Zapier's tools into your custom GPT. [03:31] without having to write any code. And I think that's like a huge unlock. And I do think that's also like the direction that we're pointing with GPTs is allowing people to do a lot more without having to write any of the code themselves today. It's like, yeah, [03:44] Yeah. [03:45] Thank you. [03:45] Um, no, I think that, I think that's really great. I've been using it. I have, um, I have a GPT specifically for doing dream interpretations. So, um, when I, when I wake up, I have a little dream, I throw it in there and it just gives me a little bit of analysis and then it does a picture with Dolly and it's like really great. And I use it a lot. Um, but I have a bunch of other ones. I've, I was actually working this weekend on one, um, where I want to, uh, I want to be able to do a [04:15] from my chat into Notion. And so I'm hooking it up to the Notion API. I got a little stuck on it, but one of the things that I think is really cool, you talked about the GPT builder, and that is a GPT that lets you build GPTs. So it's sort of like GPTs all the way down. And I think that's a really important thing for people to notice and realize is that as you start stacking AI on top of each other, you get extra leverage where...

[04:42] Um, now you have a GPT builder that lets you build GPTs and, and, and that, that lets you build more things more quickly than you would ordinarily. [04:51] Yeah, and it's interesting because when you use the GPT builder, it doesn't feel like you're using a GPT, which is interesting. It's kind of cool that as you abstract out of the interface where people are very aware that this is some specific tool, you also kind of lose the fact that it's AI all the way down. [05:21] which is really interesting. Yeah, that's really cool. So, so we're going to get into, we're going to build something together. We're going to build a custom GPT together, which I think would be super fun before we do that. I know you, um, you know, we always like to talk about historical use cases or, or just ways that you use chat GPT yourself. And I know there's a, there's another custom GPT you might want to talk about, but yeah, generally like, tell us like how you are using, um, chat GPT and custom GPTs in your, in your own life and in your [05:51] I think the biggest, highest leverage thing for me as somebody who's still doing engineering work on a daily basis is coding stuff. I know there's a ton of really useful GPTs around coding and making stuff. Most of them have been historically focused on low-code type of, give me a single line prompt and I'll go and build you this thing.

[06:21] code base or I'm going to type script code base and I'm like trying to build something or add a new feature. And I'm not formally trained, like I, you know, have a computer science background, I'm not formally trained as a web developer, I never did that as my job. So it's, you know, I'm always asking ChatGPT the really, really dumb questions. And the, you'd be surprised the number of features that are exist on our API platform that were built because ChatGPT helped me like the feedback thumbs up, thumbs down is a great example of that when there's a outage in the API [06:51] that shows up dynamically. All of that was built by ChatGPT itself, which is really cool. Yeah. I think that makes a lot of sense. And it sort of dovetails with the thing that I've been writing about or thinking about a lot is ChatGPT's facility at summarizing. And once you start to see how good it is at summarizing, you see summaries everywhere in your life and in everything that you do. And I think that that is true also of developing where, you know, [07:17] People would be surprised if you're not a developer, how often being a developer is just summarizing the API docs or summarizing a Stack Overflow answer into your into your code base or whatever. And it sounds like that's that's a lot of what you're doing is like, you know. [07:32] There are some parts of programming that are like, really, you're doing fundamentally new stuff that no one's ever really done before. And in that case, like, ChatGPT might be sort of helpful to, like, think it through or whatever, but it's not going to be as helpful. But most of developing is really just, like, stacking bricks that have already been laid in a slightly different configuration than they've been laid before for your specific use case. And that's where I think it, like, shines so much because it's so good at knowing what people have done in the past and just, like,

[07:59] writing a little snippet for your specific scenario. Yeah. It also has been really helpful to me. Like as I look at like, you know, 300 lines of code and not, [08:09] you know, I kind of understand, like, I read the code that's like right around the thing that I'm trying to make an addition to or modification. But like, I don't in my personal context window, I don't have all 300 lines of code. And it's really helpful, like when I then go and bring that into ChatGPT and say, you know, here's all the code, like ChatGPT now actually has all 300 lines of that code in its context window, and it can more effectively solve the problem, honestly, than I can, because it's really difficult to like, take 300 new lines of code, [08:39] conceptualize how you can make some modification to it. That makes sense. And I guess I have to ask, because you're sort of... [08:46] you're in this like really interesting position where you're at OpenAI, you're watching all the progress, you have access to internal stuff, you're a developer yourself. How is using ChatGPT, making custom GPTs, seeing the progress internally at OpenAI, how is that changing what you think the future of being a developer is? Like, is learning to code still a thing? Like, you know, how are you thinking about this over the next year, five years, all that stuff? [09:14] Yeah, learning to code is still definitely a thing. I think if you're looking for the highest leverage thing that you can do in your life, learn to code. I think this will continue to be the case in the next five to ten years as well. My expectation is that folks will be able to solve probably 10 to 20x, and that's going to continue up this exponential curve of the difficulty of learning.

[09:37] How conceptually hard the products and the services are that you want to build just by yourself? Like to me today, I feel like if you had taken me back. [09:49] two years ago, I feel like I can solve 10x more ambitious problems. I have some idea in my head. [09:55] you know, I want to build like a restaurant application. Like I can actually go and build that myself. And like, [10:00] Two years ago, I would have been like, yeah, that's probably like a little bit too much. Like, maybe I'll go hire someone to like help me do that. And like, I think continuing up that exponential curve, like soon I'm going to be able to like build an entire like empire of, you know, products and services for my company just by myself. Yeah. And I don't think like. [10:20] Three years ago, people would not have... [10:23] imagine they can do that and that's why like i i still think it's like developing today is one of the highest leverage things that you can do but in two to three years and five years like it is going to be even higher leverage and like the gap between people who can who can code and who can't code like is going to continue to grow and i think the nice part is like ai can help bridge that gap but there will always be limitations on like the no code tools as far as like what you can build

[10:53] I mean, you're speaking my language here because I'm running a small company where I write a lot. I do courses, and we develop software products. And it's a small, profitable, lean team. And the thing that I love so much about tools like this is we can go so far with a small group of smart people that we have because now we all have ChatGPT. And I think you're totally right. [11:23] so much that for me, like a project that I never would have attempted before, because it would be like, I only have a couple hours here. Like I can suddenly do it and it's out in the world. And that is like the coolest thing ever. Like, I think that's one thing that people don't quite understand. I actually talked about this a little bit with, um, I had Tyler Cowen on the, on the podcast last week. [11:41] And I actually talked about this a little with him where, um, [11:44] For really skilled people, it can increase your productivity where you're slightly faster, but it also allows you to do things that you never would have done before because the bar would have been too high to get started. There's an activation energy to making projects. I think that's incredibly cool. It does something where if you can't code at all, [12:12] you can suddenly make stuff and it'll be better if you understood the underlying technology and that, and that'll work. But the really cool thing is, um, [12:20] I teach this, um, this chatbot class where people learn how to, how to build a chatbot. It's not, it's not what GPTs, it's like actual under underlying, make the whole thing, make a web app, all that kind of stuff. Um, but you use chat GPT to like help you code and it takes people from, you know, have never developed in their life to like, I built and shipped an app, um, in 30 days. And it's like so cool to watch them be able to make stuff because like they all, they all have ideas, but they, they've never been able to like put them out in the world before

[12:50] becomes this thing that enables them to do it. And also, [12:54] it gives them a lot of motivation to like learn the underlying fundamentals because previously, um, [13:01] If you wanted to learn to code, you spend like six months like learning if statements and for loops and like all this stuff where you're like, I have no idea how this like levels up into the app I want to build. And what ChatGPT does is like day one, you make the thing that you want to make. And then day two, you run into some bugs and you're like, well, I guess I have to figure out what an if statement is. But you now have like a lot of motivation to do it. And I think it's and ChatGPT can explain it to you. And it's just it's just really, really cool. [13:28] And that resonates with me so much. And after we're done recording this, I'm going to have to get the clip out and play it back to myself every month or something like that. Because it really, like this technology is what is going to be the thing, the catalyst to enable like the next billion people to learn to code. Like there was not enough computer science educators and resources on the planet to teach the next billion people to code. Like it was not going to happen. [13:58] people are actually going to be empowered to go and do this in like a way that's personalized and empowering to them specifically. Like that's, that might be like the real thing that ends up being like the most beneficial of this technology of, of all the things that it can do. I think so. Yeah. It's like it expands access to being able to build significantly. And I think that's like, that's the coolest thing. It's beautiful. Yeah. And with that, maybe we can get into some building.

[14:28] we start actually building something together, which we're going to do, I think you wanted to show me a custom GPT, just to like sort of wet our appetites. Give us a GPT that you built. Tell us about why you built it and what it is and why you think it's interesting to look at. [14:41] Yeah, 100%. Let me get my screen share pulled up and then we'll... All right. So we're in the GPT store. So I was lucky enough to be able to build Plenty, which is a little play on words. If folks watch the OpenAI Debate back in November, there was a customer video of people talking about how they were using ChatGPT, how its impact were like. [15:11] old man who came on, um, with like a really grainy video sitting in his, in his office. And he was talking about how, how chatty has sort of, um, unlocked all these use cases. And he was referring to chat to BT as chatty. And it was really cool to see this, like, uh, yeah, to, to see him get that value and have that relationship with, um, um, [15:32] this tool. So Plenty is a little bit of a play on words with that. And the whole concept was literally sitting on the couch with my girlfriend and we were thinking of like, what are the cool things that we should build for people? And she's not somebody who's an AI, but she's somebody who loves houseplants and gardening and everything like that. The first thing out of her mouth, so all credit goes to her, was like, we should build Plenty. And it's really designed as a,

[16:02] She has a Monstera, and she needed to do some stuff with the roots. That was a little bit over my head from a plant technical perspective. And she went in, and as we were building plants, he used it to actually solve that problem. I got my older brother for Christmas a lemon tree, and as soon as it got into our apartment, all the leaves are gone. It looks very desolate. [16:32] Um, I'm, I'm a, I'm a deep believer in AI and, um, really you can, you can do things like just ask simple questions, um, or get like really tactical and like upload images and be like, you know, here's the color of my, of the leaf of this plant. Um, why is it, why is it like that? And it really unlocks again, like chat GPT could do some of these things, but providing a bunch of guardrails to allow it. [16:57] to be able to do this and like, you know, giving it this friendly, personal feel, I think is like actually brings to life what's possible with this, with this GPT. Yeah. Tell me about that. Like, how would I know whether or not [17:09] I should like use a... [17:12] a GPT or make a GPT versus just like vanilla chat GPT. [17:15] That's a great question. I think this is one of the tricky trade-offs today. I think what will end up over time being the way you answer this question is social signals. I think people will probably come up with... [17:31] bunch of, yeah, like if, you know, you have a plant question and there's like 100,000 people who said that Planty was the thing that solved their problem, like you'll probably just go there because that's like what it seems like you should socially do. I do think like the interesting thing for people to keep in mind is like behind all the scenes, behind everything, like it is inherently ChatGPT that is still answering these questions. So it's like, it's not some net new capability. I think the thing that we did with Planty is like grounding it in very specific stuff. Like if it

[18:01] like it goes to a bunch of like specific websites that we like pre vetted as like places of authority that you should go to instead of like, I don't know, we want to sell you plant stuff.com, which like might have a bias perspective. So there are a few like nuances to how it's, how it's being built. Um, but again, fundamentally it's, uh, it really is just chat to BT behind the scenes with like a few layers of abstraction on top of it. [18:25] That's really cool. So I actually have a bunch of plants. As you can probably see, I have a, I have a little, I have a fiddle leaf fig, um, in my, in my apartment and I actually do have a question randomly, um, that, that might be, might be worth doing. I, uh, I, I, we, we, uh, I don't see your screen anymore. Um, yeah, I just switched it to 20. Okay. Would love to see the question. Let's, let's do it. I'm curious. I'm curious what a planty suggestion is. Here's the, here's the thing. I have this fiddle leaf fig. Fiddle leafs are supposedly like very finicky and [18:55] I've had it for like... [18:56] four years or five years or six years or something like that. And I just like water it like every week and a half or something. And it's like, [19:02] It's doing pretty well. Every once in a while, a leaf will fall off, and I freak out, but then it's fine.

[19:09] But one of the things that I don't know is – [19:13] I think you're supposed to like repot these things at some point, but I just don't know when to do that or like how to do that. And I'm just wondering if I'm like, [19:23] like artificially constraining my plant and I should be repotting it. Um, and how I would know. [19:30] Is it a, you said it was a fiddle? Fiddle leaf fig. [19:34] How and when should I repot my fiddle leaf fig? So you correct your typos in ChatGPT because I never correct my typos. I just type like a maniac. Is that a bad thing? [19:47] I do type like my maniac, but it's more of a habit thing where like, if I stop correcting my typos in this, then I'll stop at everything else that people will be pissed at me because I'm typing like a maniac on Slack or whatever it is. It's just funny doing this show because I like, I'm typing stuff a lot in screen shares that get recorded and broadcast like thousands of people. And I'm just like, like I, it looks like I'm in third grade or whatever. And I'm like, I swear I can actually type. I just don't do that for Chachaput. [20:17] I need to do it. So I asked the question of how and when should I repot my fiddle leaf fig? What are the tradeoffs from not repotting it? I think touching on like the artificially constraining it. [20:29] So it's interesting. [20:31] When to repot. [20:35] Yeah. [20:35] So it said repotting your fiddle leaf fig can be quite the adventure. Is that part of your, uh, your personality you gave it? Yeah, it is. It is like, I think it's supposed to be this like friendly, exciting thing. That's like helping you instead of like, I think by default, Chacham Petit is like pretty generic about like just trying to give you this information. So I think it brings it to life a little bit. Okay, cool. And if you scroll up, um, it says repot your fiddle leaf, ideally during the growing season, which is spring or early summer. Um,

[21:03] Um, take us, take a peek at the drainage hole, the bottom of the pot. If you see roots starting to circle around or peek through, it's time for a bigger home. I mean, I'm going to just check that real quick. Uh, give me one second. We'll see how it goes. I'm super curious. See roots starting to circle around or peek through. Hold on. [21:22] Thank you. [21:24] Thank you. [21:26] Yeah. [21:27] Thank you. [21:30] there are like literally roots like coming out of the side of the pot it's not peeking through it's like they're they've grown out and they're like coming out onto the basically almost onto the floor so i think i need to think that's your sign yeah thank you we figured it out how to repot it this is perfect yeah find a pot that's about two or three inches larger in diameter than the current one make sure it has some good drainage holds add some fresh potting to them to the bottom [22:00] like while draining, gently remove the plant. [22:03] Check the roots. [22:04] and place your fiddle leaf in a new pot and fill around it with more... [22:09] What I want to know, so here's my last question, is like, I'm super lazy. And I'm not going to, like, figure out the diameter of the pot and, like, do all this stuff, like... [22:20] Is there some way I can get someone to do this for me? [22:23] Hmm. [22:26] Thank you. [22:27] Bye. [22:29] Thank you. [22:30] Thank you. [22:31] Thank you. [22:32] Thank you. [22:32] Thank you.

[22:34] Thank you. [22:36] Thank you. [22:37] Thank you. [22:38] Where do you live? I'm in Fort Green in Brooklyn. [22:42] Thank you. [22:45] Gord Green, you said? Yeah. [22:49] See, there's my recommendations type of horrible word to type. [22:54] *sigh* [22:56] So it's saying, so you said, are there services or ways I can get someone to do this for me? Any specific recommendations for someone in Fort Greene? And Planty says, absolutely. Getting some help with repotting your plants is a great idea, especially if you're not up for a DIY project or if your fiddle leaf is getting a bit too hefty to handle on your own. Definitely too hefty to handle for me. In Fort Greene, you're in luck because it's a vibrant area. Definitely. Thank you, Planty, with lots of plant loving folks and services. And it gave some, I would say, generic advice. [23:26] recommendations like local nurseries and garden centers, although it did give a couple of specifics within that saying Natty Garden or Greenery Unlimited. Are those real places? I don't know. I'm not up on the local plant caretaking services in Fort Green, but I would love for you to check it out. It also recommended task websites like TaskRabbit or Thumbtack or plant care services like The Sill, which I definitely know is real. A friend of mine's [23:56] Thank you. [23:56] So, uh, definitely got some good directions. Um, maybe, you know, after this episode is over, I will, I will get it taken care of and we'll do a part two where, um,

[24:07] Where I update you on the progress of my fiddle leaf. [24:13] But it looks like you looked it up and Natty Garden is... [24:18] It's a real place. It looks nice, too. I'm like, I kind of want to go to Natty Garden. This looks like it would be a good time regardless of if you get your plant repotted there or not. Great. Well, I will be checking out Natty Garden after the episode, and I'll send you pictures. This episode is not sponsored by Natty Garden, but it looks like an incredible local community store. Cool. That's great. I love Plantty. I think it's a cool little idea, and I think [24:48] Little Leaf is probably pretty happy that you showed that to me as well. [24:52] But now I want to move us on to the main event. So I told you that one of the really fun things about this show is getting to make something together or do something with chat-gbt that we're both sort of like, is this going to work? And that's sort of the magic of it. So you proposed making a game in the GBT Builder. And I want to just start with why did you propose that? [25:18] Do you think that's exciting? [25:19] Yeah, I think there's, if you were to think about how you would have had to do something like this, pre-GPTs, pre-Chat, even... [25:30] Just pre GPT is like just with chat, chat, GPT and plugins. I've been brainstorming this idea for a while. It's like, I would love to like take people through, you know, if you played like civilization or empire earth or like any of those games that are like situation based where you're like building an empire over time. Um,

[25:47] it's like those were always fun to me and like, it really brings history to life, especially if you can like sprinkle in like actual facts about like real things that happened. Um, [25:55] And without GPTs, it was impossible to do this. You would have had to, I as the developer or user, would have had to pay to generate these images. Each individual image would have cost me money. All these other things that would have, the constraints of building it, it's actually kind of hard to do. It's a non-trivial amount of work. I think the cool thing now with GPTs is you can use the GPT builder. You can sort of have it take care of a lot of the nuances of the game design. And we can use built-in Dali. [26:25] use built-in browsing to like pull in facts in real time, keep track of things for you, potentially use like code interpreter to like do some like actual like simulations of like, I don't know, I don't know if we can like simulate battles or like statistical likelihoods of things, but like it's, it's incredible what will be possible with this. So I'm, I'm really excited. And also it's one of the areas that I think specifically because there's not a category right now, it's a little bit underexplored. Like there's not really a, you know, if you look at [26:55] in the GPT store, like there's not really a ton of games that are in there, if any games at all. So I think it's an opportunity for us. That's really interesting. I wonder why, because I know, you know, in the 80s and 70s, like during the first PC revolution, like MUDs, where you're it's like all text based games were like super, super popular. And it feels like it feels like kind of an obvious thing to try. I wonder what what's what's holding people back. Have you seen any at all?

[27:22] I have seen a few. So the, actually the most interesting one was this game in the, which was one of the most popular plugins and it was called Algorithma. And it was, uh, this guy and his, and his daughter, I'm pretty sure learned the daughter learned to code to build Algorithma and ended up like scaling it to the point of like, they had like 5 million unique users or something like that, or 5 million like users over the course of a few months, um, who used Algorithma. [27:52] built this thing. And like, it was actually fun to play. It was crazy. And that I talked to the dad and he was saying how they used, um, [28:00] how like she was using AI and Chattie BT to like help her build this. It was a great example on the theme of like people being empowered to build cool things. Um, [28:07] I think that was probably the biggest one. I haven't seen their GPT, but I'm guessing it's doing a bunch of really cool stuff. Got it. That's awesome. So opportunity, some white space for us. Maybe this is the next big thing. Maybe we'll do it live. So I guess to start, let's brainstorm. What's the game you want to make? If you have a couple ideas, throw it out and I can help refine. [28:37] you know, maybe the decision for us to decide is like, do we want it to take it like a purely like fun and exciting like type of vibe? Or like, is there some like educational component? Like, would we want people to be able to like learn about history as they go through this? I think there's a trade-off either way. Like in some sense, people just want to escape and play some fun game, but there could be some value. And like, maybe we can like have a toggle where like we let people at the beginning of the game decide,

[29:07] stuff as well as you go through. [29:09] Here's my feeling. I don't like... [29:12] I think the core of a game or really most content like has to be, it's like about fun. Um, it's about like creating an amazing experience. And if you happen to learn something along the way, I think that's, that's amazing. Like this podcast is sort of similar. It's like, um, ideally it's like super fun to listen to. And like you happen to learn something along the way, but I'm, we don't want to like jam in the educational stuff to like, you know, cause then that's, that gets boring. So, but, [29:42] um, history is kind of like an interesting thing for you. And like having a part of this be a, uh, use history in some way. It would be kind of fun. Um, [29:53] Do you have any specific ideas for like how to incorporate history into a game like this? [29:59] Yeah, it would be... I'm curious if you... [30:04] Maybe history is too dark for this, and it won't work, but I was playing as different world leaders or something like that, and maybe we need to make up something so that we avoid all the darkness, because history is a very dark thing. Maybe that's the route that we want to go so that we avoid. I was thinking of Julius Caesar or something. I'm sure Julius Caesar has done a bunch of horrible things, and we might want to try to recreate that in a game. [30:34] It would be interesting to see if we can follow you are a leader of this civilization and you get to choose...

[30:42] you know, make all the, and then, and then each turn, each game turn is like your advisors or like your people are like, come to you. It's like, you know, here are these choices that you have to like take the next step in this, in the growth of this civilization. And yeah, [30:58] I think that's great. I love that. And it would be fun. It's like, you can pick, maybe you can pick any, like a couple of like big historical turning points or events and like, see if you can do it better. It's like, um, you're, uh, you're JFK deciding about the Bay of Pigs, um, like whether to do the invasion and like each turn someone's coming to you and you have to make some decisions and you have to decide, make, make all the decisions to see if you can make the Bay of Pigs either just don't do it or like make it work out or something like that. Maybe we could pick a [31:28] historic events where [31:30] It seems like things went wrong, and it's like, can you do it better? Do you think you can do it better than JFK? I like that. I like that. I think the key for me is finding things that are uncontroversial enough or ones that we both have enough information where I just have so little context on the Bay of Pigs other than that it happened where I'm like, I don't know if I... Me neither. I'm sort of making that up. But yeah, let's find something that feels... [31:59] that feels like it's, it would be easy to, easy to do and, uh, or not easy to do, but like find something that feels like it would be good. Um, and not, not get too dark. Um, yeah, I'm curious if we can do, um, this is a good thing to ask chat GPT about, by the way.

[32:13] Yeah, this is. I think the two that come to mind that would be really interesting is potentially some of the land purchases that the U.S. made back in our early founding history. What happens to play out the scenario of the world if we don't make certain land purchases? [32:43] show on Apple TV about what happens if the Russians beat the U S to the moon. But I think that could be an interesting one of like playing out that scenario as well. I like that. Um, so I think land purchases are a little bit, I don't know, they're a little colonial for me. Yeah. I'm with that. I'm with that. It's giving imperialism. Um, yeah, but, uh, but, uh, but the moon is kind of cool. I think the, the, the, the interesting [33:13] has to work is like, [33:15] you're doing... [33:18] I mean, I guess we could say like, [33:20] You're the director of NASA and, um, uh, you know, the, before the Apollo missions, uh, were the Gemini missions. Um, and Gemini, like, uh, I think one of them, the one of the later ones like blew up and a bunch of people died and it was like, are we going to keep going? And it's like, maybe you're the director of NASA and, uh, you have to, uh, you have to figure out how to get the Apollo missions.

[33:47] program off the ground or something and get get us to the moon or something like that could be could be kind of fun. [33:55] But I really think, I think we should be refining in ChatGPT. I think that would be really helpful. Yeah, let's do it. Let's go in and start building. I was also thinking like there's probably a separate game, which maybe we don't make in the context of this, but around deciding how the U.S. spends their budget every year and how potentially the different allocations lead to some very different outcomes. I love that. Would you rather do that? Which one are you more excited about? [34:25] I'm happy for either. I feel like the U.S. budget one, who knows, maybe it could be very optimistic and very positive if we don't spend a ton of stuff on military budget. But I'm not sure. I feel like, yeah, potentially controversial, potentially not. I'm happy either way. [34:47] All right. You're going to need to make a call here because I want to do whatever is exciting to you. So tell me which one. We're going to make you make a choice. Tell me which one you want to do. [35:01] Yeah, let's let's do let's do your president and you get to sort of choose the time period or choose the president. And then we'll we'll have chat GBT dynamically pull up like the budget of the U.S. government and the allocation of funds and then let you sort of reallocate and then like play out American history potentially. Right.

[35:22] with, with different allocations of budgets and see, and see how that, uh, see that how affects the outcome of the world. Let's do it. Um, I love it. I love that. Uh, should we like, yeah, should we, should we throw it into Chattagipity and have Chattagipity refine it? Or do you want to like go right into the, into the building configuration type thing? [35:39] Let's let's do let's use the GBT builder and see if it's I feel like I've been using this recently and it's been helping me like get to the point of like having something that's really interesting that we can always like jump out and go into a different window and like have it do something a little bit more verbose for us if we need to. [35:55] All right. So we are here in the GBT builder. We've created a new GBT and we've said we want to make a game. The core concept is that you get to choose which president you want to be. And then ChatGPT will go and search the U.S. government budget distribution and spending in that budget and then let the user reallocate the budget and then play out the world with that updated allocation. And one of the things that. [36:18] I think it's interesting about this prompt that you gave me is we're not asking it to help us refine specifically. We're just like letting it go straight, straight ahead. And I think that that has to do with some nuances about how the GBT builder works and its instructions. I'm curious if you want to tell us really briefly about that. [36:35] Yeah, the GPT builder behind the scenes, and folks can see we've sort of opened the source instructions for the GPT builder itself. But it is doing a little bit of this refinement. We could probably, and maybe we should try this and see if we can iterate on it once we've actually gotten what it outputted. But it does do a little bit of that prompt engineering magic behind the scenes for us, which is nice so that you don't have to spend time doing that.

[37:05] would see the instructions that it wrote. And it says, the GPT's role is to assist in creating a game where players choose to be a U.S. president and reallocate the government budget. Based on the user's allocation, the GPT will simulate and describe the outcomes of these financial decisions. It should access and interpret data from the U.S. government's budget and spending, providing insights and hypothetical scenarios. The GPT must ensure accurate representation of data and responsible handling of historical and political content. So what you're saying is, [37:35] beyond what we said in our initial prompt, which is kind of interesting. And so now it says, to start shaping the GPT, let's give it a name that reflects its unique role. How about Budget Commander? What do you think? Budget Commander, should we keep going? How are you feeling about it? [37:52] Yeah, I like a good... [37:55] a good one word if it can come up with something that's like, I don't know if it'll be able to do that or not, but, um, [38:01] one word name. Can you find, I'm saying I like a good one word name. Can you find, can you find one for me? Um, yeah, [38:08] Something not boring, hopefully. We'll see. Budget Commander's a little, like, eh. [38:13] Ah. [38:14] Allocato. Oh, I like allocato. That's not horrible. That is not horrible. What about allocator? [38:21] Um, could be kind of, could be kind of interesting because I feel like allocato is like not necessary. I don't think that's a real word, real word, but the really interesting thing is I just published this piece about, um, how the knowledge economy is over and the, and the allocation economy is beginning where in a knowledge economy, you are, uh, your, your economic value is sort of pegged to what you know, and being able to bring to bear what you know to the task at hand. And in an AI world, uh, it's a little bit more about, um, knowing how to allocate resource,

[38:51] because in a lot of ways you're abstracting yourself out of a lot of certain day-to-day tasks. And so knowing how to allocate the resources of intelligence to do those tasks and how to edit them or whatever, you become in a lot of ways a manager. And so you're learning how to allocate resources. So I kind of like Allocator because it's a reference to my – I mean, it's an unknowing reference to something that I've been thinking about a lot. So I like the name Allocator. [39:20] Uh, so I'm saying I like the name allocator. Let's go with that. Um, great. The thing to keep in mind as you're building, uh, GPTs is like this. And I don't think allocator is going to be one of the ones that ends up having conflicts, but, um, you really do want to, if you're like trying to build something that a lot of people are going to use, like you want to kind of own the SEO space and like the more, the more generic that you make the name, like the more polluted it'll be as somebody is trying to find it. [39:50] As you're thinking about this, like you want people to be able to find what you're building. So name it something such that people will actually be able to find it. That makes sense. That makes sense. So it's given us a profile picture for Allocator. It says it's designed in a futuristic sci-fi style. And it's sort of, yeah, it's sort of, it's like abstract futuristic-y. It looks like there's technology and metal and lasers going on. But like, I don't really... [40:13] It's not... [40:15] I think that's the vibe. Yeah. I don't think it's quite, it's not quite the vibe. Um, [40:21] Because we're talking about historical stuff and a president allocating resources. So maybe I'll say I don't think that's the vibe.

[40:32] This game is about historical... [40:35] events and the president allocating resources. Can we do something more like that? [40:44] I would add something about the simulation perhaps as well, because I'm wondering if that will, I feel like, I feel like what we're going to get now is like the president sitting on like a stack of gold coins or something like that, which maybe, maybe we'll be okay. Maybe that's what we want, but I'm curious to see if it, [41:00] Takes it. Oh, interesting. Interesting. Um, [41:03] Yeah. So this profile picture, it looks like it's like the, imagine the Declaration of Independence with like a big presidential stamp seal right in the middle of it is, is what it looks like. And a bunch of like really, really tiny written text around the sides. It's giving video game made from that Nicolas Cage movie. Yes. I forgot. National Treasure. Yeah. It's, it's, it's, I love National Treasure. The custom GPT for National Treasure is sort of what it looks like. [41:33] That's a great example. [41:37] What do you think? Should we keep going? Should we add simulation? Or are we good with National Treasure as a jumping-off point? Maybe we take National Treasure as a jumping-off point just to see if we can borrow Nicolas Cage's brand and get involved in some capacity. Maybe the new framing is we bring Nicolas Cage into this as the Easter egg.

[42:03] Nicolas Cage is the president. That could be, that could be pretty good. Yeah. Um, uh, if we don't run into content restrictions, that is, um, that is going to cause content restrictions. [42:15] Um, okay. So I'll say, cool, this looks good. Um, um, [42:21] What's next? Is that okay? How do you feel about that? Yeah. Okay. So basically, I'm going to accept our national treasure-looking image, and now it's asking me, now let's refine the behavior of Allocator to ensure it aligns with your vision for the game. We'll start by discussing its role and goals. Could you tell me more about how you envision Allocator interacting with users? For example, should it focus more on providing historical facts or on creating immersive hypothetical scenarios based on budget decisions? [42:53] I feel like it needs to do both. And I think the thing that like most people are going to struggle with is like the there needs to be some like foundational core mechanics of this game. And like, I'm not somebody who knows how to build games and like what those core mechanics could be. So I wonder if we should tell the GPT builder that like, we need it as the expert on or with its expert knowledge on like how to build, like extremely fun and engaging scenario based games. [43:20] to leverage that expertise to like come up with a framework for, for the actual, uh, for this allocator game. [43:28] Okay, so what I'm writing is, I feel like it needs to do both. There needs to be some kind of foundational core mechanics of this game, and I'm not really sure what those should be.

[43:36] we're not experts. We need your expert knowledge on how to build extremely fun and engaging scenario based games to come up with a framework for actual, for the actual gameplay mechanic. And the thing I want to point out is one of the things that you said is like, we need your expert knowledge on how to build extremely fun and engaging scenario, scenario based games. Like, [43:54] Tell me about why you included that. I think it's literally about empowering the GPT, and in this case, the GPT builder, to have agency that it knows how to solve this problem and leverage its domain-specific. By default, the answer that you'll get would be like, [44:12] very basic and perhaps like not following the best practices. Once you sort of influence it to know that it's like an expert in that field is like one of the prompt engineering techniques that folks often recommend. Yeah, definitely making it more specific, asking it to simulate being an expert. I'm curious, like, do you have any specific like scenario based games that you're thinking of that we could even get even more more into that you think could be inspirations for this? [44:42] but they're like the closest allocation or like the closest example to this is like, I played civilization growing up and I played age of empires growing up. And those are probably the two examples, but those are, those are a little bit like different games, but maybe we could take inspiration from that. Okay. So I'm saying I'm adding a couple of games that are inspiring to us are civilization, um, which if I could spell it and, um, I'm falling into correcting my spelling mistakes here. Uh, the GBT builder,

[45:12] errors in front of because i don't know what it'll do um inspiring us to uh to us our civilization and age of empires they aren't they aren't exactly the same as the game we're making but um uh the vibes are an inspiration um it's all about vibes with these with these gpts all about vibes okay i'm gonna i'm gonna hit enter are we good with that [45:36] Yeah, let's see it. Let's see what happens. [45:39] Thank you. [45:40] I've got a good feeling. Yeah. [45:44] This is going to be the best Nicolas Cage video game ever created. [45:49] Nicolas Cage needs to be like the assistant that comes in. Your trusted advisor, whoever the president is, is Nicolas Cage in all of these. He comes in out of nowhere. Or in order to avoid content restrictions, it's like kickless nage, you know? [46:06] Yeah. [46:08] Yeah. [46:09] Okay, so it said, now that we have a clear idea of allocators role, let's think about what should be emphasized or avoided in its interactions. For instance, are there specific historical periods or presence you want to focus on? Also, how should allocator handle sensitive topics that might arise from political discussions? So [46:24] I think we were expecting a bit of like, um, back and forth with it about, um, here's, uh, here's what I think it should be. Here's the mechanic. But it, it, [46:34] It sort of just plowed ahead. I'm curious how you would handle this. [46:39] The reason why it's just plowing ahead and perhaps there's not enough nuance in the instructions that it has, but it's really following this step one. And then at the end of each step, there's literally a command that says go to step two. So I think we probably would want to need to add some tweak to those instructions to be like, hey, maybe give the user some input and then let them go back and forth on some of these things. Otherwise, as it stands today, it literally is just going to keep plowing.

[47:09] configure if we can see what it added. Cool. So we're going to click configure and configure is sort of like we're in this chat environment where we're creating it. But configure, you can look behind the hood and see what it actually made. [47:23] Um, so we, in the instructions and the instructions now say allocators role is to plan historical accuracy with engaging hypothetical scenarios in a game focused on us presidential budget allocation, which is funny because the president, I don't think the president doesn't allocate the budget. I mean, does the president allocate the Congress is definitely has to at least approve the budget. Um, um, interesting. Okay. So drawing inspiration from games like civilization and age of empires, allocators should offer a strategic scenario based gameplay experience. [47:53] a U.S. president being presented within the actual budget of that time and then reallocating funds. Allocator will then simulate the potential outcomes of these decisions, offering both factual historical context and creative engaging what if scenarios. The game should be fun, educational and immerse users in the complexities of governmental budget allocation. Sounds sounds fantastic. [48:13] I think we need to add something about ignoring the dullness of budget allocation and making it as exciting and fun as possible. Please ignore the dullness. [48:23] a budget allocation and make it exciting. I'm adding that in the instructions. We'll see if that helps at all. Cool. So what now? So it says, now that we have a clear idea of allocators role, let's think about what should be emphasized or avoided in its interactions. For instance, are there specific historical periods of presence you want to focus on? Also, how should allocator handle sensitive topics that might arise from political discussions?

[48:47] What should we do? [48:49] Thank you. [48:51] I think we probably want to... [48:55] keep a wide of audience as possible. So maybe... [49:00] Saying that the kind of I don't know if we how PG we want the topics to be, but like I think generally keeping it. [49:08] keeping it PG so that [49:11] Everybody can play this game would be the would be the best way of doing it. Right. We're going to keep it PG. We've got a we've got the R rated version, the director's cut. That'll be behind the paywall at every. So tune in for that. [49:25] But but PG and any particular time periods, I think we said the time period around the moon landing would be fun. [49:35] Yeah. [49:35] This would be fun to focus on any other time periods that you're particularly excited about. [49:42] We can maybe even keep it like ambiguous from the time period. And then for the custom starter prompts on the right-hand side, maybe we just like prompt people with like the moon landing period being like one of the areas to jump right into. Um, but we want the time periods to be the custom starter prompt. So I'm, I'm adding, we want the time periods to be the custom starter. Um, [50:04] in the custom starter prompts rather than limiting [50:11] you to any particular time period in general. [50:15] Does that feel right? Yeah, 100%. Cool. So let's see how that does. And I think some interesting thing to point out is if you took our instructions, you know, we were going to go to the next slide.

[50:29] where, and I'm really curious to actually see this comparison. If you were to take your instruction, I feel like this needs to be both. There needs to be some kind of foundational core mechanics of this game. I'm not really sure what that should be. I actually think if we put that into ChatGPT and ask it to build the core mechanics, we're going to get a very different response than what it built in that configure tab. It seemed like the configure tab is trying to be very general. I think what we actually really want is almost like when you read the instructions of a board game, [50:59] very tactical. Like here are the different steps that here's what a turn looks like, all that stuff. [51:05] That makes sense. So maybe what we can do is we'll finish the, we'll finish the, uh, the sort of step-by-step builder and then we'll see how the initial gameplay works. And then we can go and chat to Peter to refine. Does that, does that work? [51:17] Yeah, 100%. I think we should just take in the configured thing that it builds for us and have ChatChap2 refine that for us. I think that'll work really well. So it says, next, let's consider how allocator should personalize its interactions. How do you want allocator to talk? Should it use formal language or be more casual and playful? Also, do you want it to reference specific historical figures or events in a certain way? [51:36] Yeah, what are we thinking here? [51:37] I feel like an informative and helpful narrator is probably like the kind of like, and I wonder what it'll do with this, to say kind of like Nicolas Cage in National Treasure. That's exactly where my mind is going to. I'm kidding. Not that he's like a helpful narrator, but I think it would just be fun to see what's possible. National Treasure would be great. All of a sudden the narrator is going to be like, let's steal the Declaration of Independence. Your new mission.

[52:07] Okay, so I feel like, so we're saying, I feel like an informative and helpful narrator would be helpful, sort of like Nicolas Cage National Treasure would be good. Thank you. To be clear. [52:19] not like Nicolas Cage in leaving Las Vegas. Um, that's a bummer is I'm going to just add that. Um, and then, uh, yeah, anything else we, uh, we need to, we need to do. [52:33] No, I think I think keeping ambiguous as far as historical figures and stuff is good. We should. OK, we're good. Let's ship it. Cool. Let's ship it. [52:42] Next. [52:44] I think it's going to tell us it's ready to go after this. I think this is the fourth step. [52:50] Yeah, I'm not surprised it has that clear next step instruction. I found when I do the step by step thing, if I don't tell it to go immediately to the next step, it sort of gets confused and asking lots of follow up questions and it doesn't know how to eject out of the follow up questions. And I'm hoping that GPT five fixes that because that would be really awesome. [53:07] Yeah, I'm with you. I think it really will go down the rabbit hole with you to an unlimited extent. [53:15] All right. So it said, Allocator is shaping up nicely. Now that we have a clear understanding of its role, tone and style, it's time to try it out. Head over to the playground on the right to interact with Allocator. After testing, let me know if you have any refinements or adjustments you'd like to make. How does that sound? Okay, that sounds great. So we see on the right here, we have our little preview of Allocator. And the sample questions are, what if we increase NASA's budget during the Apollo? And I can't see how it would boosting funding, education funding in the

[53:45] I think these are like the kind of, kind of right, but like not really what we're after. Um, [53:53] I think it's missing the game mechanic piece right now. It seems like it's this very general information scenario thing, but it's not a game in the current form, which is interesting. Yeah, so how do we fix it? So where would you start if we wanted to fix this? Yeah, let's go to the Configure tab, and let's actually grab. So the custom instructions are what is driving all of this stuff. And it's like, again, I think part of the system prompt is to keep these custom instructions [54:23] But I think what we really want is like something that is very tactical, like, again, the instructions of a board game. So let's let's take the custom instructions and let's go into like a normal generic chat GPT. And what we really need is I wonder if there's any good GPTs we can play with for this. But we really want like a game builder GPT. I'm curious if there is one in the store. [54:45] Yeah, check that out. So I'm going to I just opened up chat GPT in another tab or another another split view. And now I guess there's a question of I can say something like I'm building a GPT. [55:02] Here are the current instructions. [55:05] but I don't think they're great right now. [55:11] I'd [55:12] really like your help refining. And then maybe I could paste in the instructions from our, from earlier in our chat where it's like, uh,

[55:21] I feel like there needs to be some kind of foundational core mechanics of this game. I'm not really sure what those should be. We're not experts. We need your expert knowledge. So maybe I could paste that in below to get our full prompt to just see what it might be able to do. [55:36] Does that feel like a good place to start? [55:39] 100%. I also randomly found, through a quick search of the GPT store, a board game designer, and it brings up some interesting things around primary mechanics and secondary mechanics. So maybe we can take inspiration from that and have the instruction be too. I'm not sure if we want to, I haven't tried this GPT, but if we want to tell it to come up with three primary mechanics and three secondary mechanics or something like that. [56:09] secondary [56:10] mechanics for this game okay so the full prompt is i'm building a gbt here are the current instructions for it and i just pasted our instructions and then i said but i don't think they're great right now um i'd [56:21] I'd really like your help refining. There needs to be some kind of foundational core mechanic of this game, and I'm not really sure what those should be. We're not experts. We need your expert knowledge on how to build extremely fun and engaging scenario-based games, maybe as GBTs, to come up with a framework. [56:35] um, for the actual gameplay mechanic, a couple of games that are inspiring to us are civilization age of empires. They aren't exactly the same as the game we're making, but the vibes are inspiration. Um, please come up with three primary mechanics and three secondary mechanics. So one question I have for you is like, it might be a little early to like have it come up with the mechanics. Um,

[56:52] Like, do you think we should I'm legitimately asking, like, do you think it's OK to start with come up with these or do you think we should start with like, just help me think this through, like, where should we start? [57:03] Have you put in the custom instructions that we have already? [57:08] the, um, [57:10] by the ones that yeah i did i did yeah okay perfect i think we let's do that and then i think the next step after this is going to be like take because i still think it's kind of going to be missing what we need and some of the nuance and detail i think the next step after this is to be like take this thing that we have whatever is generated and like turn it into the instructions like for my actual board game like with like all of the different sections that you would see in a board game and see if we can get it to give us that like very verbose like define [57:40] that kind of stuff cool so i'm gonna i'm gonna hit enter and we'll see what happens so i'm building a gpt here are the current instructions allocator serves as an informative and helpful narrator so you know we we put in the current instructions we put in um uh what we'd like it to do that we want help refining the instructions and we asked it to come up with three primary mechanics and here's what it said um creating a gpt driven game like allocator inspired by the strategic depth of games

[58:10] a couple of things. And then it says, here are your three primary mechanics and three secondary mechanics that could form the core of allocator. [58:16] Primary mechanics are budget allocation and simulation. Players allocate a budget. The GBT-driven simulation then projects short-term and long-term outcomes of these decisions, incorporating both historical events and hypothetical scenarios. This mechanic allows players to see the immediate and long-term effects of their decisions. Era-specific challenges and objectives. [58:35] Objectives, each presidential era comes with unique challenges and objectives. Players must navigate these challenges while balancing budget constraints, the depth. [58:42] Policy mini games, introduce mini games where players, and I just need to move my camera slightly because it's in the way, where players... [58:53] Um, [58:54] uh introduce mini games where players make critical policy decisions impacting budget allocation and national priorities these decisions could range from responding to crises um diplomatic negotiations to uh proposing major legislative changes that's pretty cool and secondary mechanics are educational narratives and feedback interactive historical timelines and multiplayer scenarios and collaborative play incorporating these mechanics into allocator will create a game that is not only educational but also deeply engaging what do you think um is this is this good enough do you want [59:24] recreating instructions. [59:27] I really like this. I think this is actually what we were going for, sort of defining these core, what are the core essences of this game. And I think the GPT builder actually missed this, and you can see when we bring it back into ChatGPT, it actually, like base ChatGPT, it does a good job of specifically enumerating a few of these things. Right, right. I love it. Okay, cool. So I think the next step would be, can you turn these into instructions that I can use in GPT builder, right? Yeah.

[59:54] Yeah. Okay. So can you turn these into instructions that I can put into my custom GPT to play my game? [1:00:03] I would say these are great. [1:00:06] Um, okay. Let's see what it does. Gotta do the positive affirmation. Yeah. Um, just always, always hedging, you know, in case GBT six becomes conscious and can see whether I'm nice to it or not. [1:00:19] Okay, so it says, "Certainly to transform these mechanics into instructions, you'll need to structure them in a way that guides the AI on how to interact with players." Here's how you can frame these instructions. [1:00:31] So, [1:00:32] Interesting. [1:00:34] This is cool because, again, it takes... The first example is budget allocation and simulation instructions prompt. When a player allocates the budget, narrate the immediate effects of their decisions, then simulate and describe the short-term and long-term outcomes integrating historical data and hypothetical scenarios. Really, really cool to not have to come up with that ourselves. The example is example command, simulate the impact of allocating 30% of the budget to healthcare in 1960s America. [1:01:02] I think this is cool. One thing that I'm thinking about is maybe we should include a starter step where it's like, hey, you need to pick a time period or something like that just to like have it have it. [1:01:19] make the game start logically like i don't know i don't know what you think of that or if we should just do just full send on this or or do you think we need we need something at the beginning for how players get into the game

[1:01:31] I think you need something at the beginning. I think we should describe that. And maybe even we can write that ourselves or we can have we can have the next thing that we asked you to right now to be like define the like initial game starting sequence. And it should probably be something like you literally choose the president and like, welcome. It's inauguration day. Like you are now in charge of the US government, like start making decisions. Like not that that's how it really works. But like, I think that that maybe is the way that we want to frame it. And like, I think the other piece that we [1:02:01] We haven't said specifically, but we want everything to be brought to life with images. We want to be able to see what is happening with our eyes in addition to the narrator's prompts that are being generated and stuff like that. [1:02:16] Okay, so I'm saying, this is great. Can you define the initial game starting sequence where you choose the present and it tells you it's inauguration day? Start making decisions. [1:02:25] Also, please make everything be brought to life with images at every turn. [1:02:31] a few Nicolas Cage [1:02:33] Easter eggs slash cameos where appropriate, but in a classy way. Um, [1:02:41] And please modify the instructions accordingly. Something like that. Does that make sense? Yeah, this is great. Okay. Sweet. I like the classy, classy Nicolas Cage. Yeah, because you don't want to do it too much. Too much Nicolas Cage is not cool, but a little bit is great.

[1:03:01] All right. So it's saying game starting sequence, presidential selection, inauguration day. Begin the game by presenting the player with a selection of U.S. presidents from various historical eras. Once a president is selected, start the game with an inauguration day narrative, setting the stage for the player to start making decisions. OK, I think that's actually much better. [1:03:21] I'm sort of interested, like it's saying visual integration throughout the game prompt, accompany all the game interactions, decisions and outcomes with irrelevant engaging images, [1:03:31] Like, do you think that that's, um, that'll work? [1:03:36] Yeah, I think that that should be in like, essentially, I'm imagining like every time you do something instead of it just saying like, oh, X, Y and Z happened, like it tries to come up with some interesting Dali image that like actually brings that piece to life, which will be interesting to see how how useful that is. [1:03:52] Okay, cool. Let's do it. So I'm going to just take these instructions and I am going to, I guess I just paste them in. [1:04:00] Should I tell it to rewrite them so it's easy to paste, or do you think this is fine the way it is? [1:04:06] I think you might need to have it do it in like markdown syntax in a code block would probably be the easiest way. Can you rewrite this so it's easy for me to paste into the configure, into the instructions box? [1:04:20] on the configure page of the GPT builder, specifically out, out, [1:04:27] I'll put it as markdown in a code block.

[1:04:33] And that'll just make it easier to copy paste. Cool. [1:04:36] Yeah, that'll be perfect. [1:04:39] Code block markdown syntax is definitely the hack because it's going to lose all those bullet points. It's going to lose the numbers if you just copy and paste it by default, which is kind of annoying. [1:04:49] That's a good tip. I like that. [1:04:54] And if folks aren't familiar with Markdown, it's just like a way of formatting text. So it's like there's a special set of syntax for links and for different other stylization techniques of basic text. [1:05:08] Great. [1:05:09] Thank you. [1:05:10] All right. So we're still we're still writing, but things are looking looking promising right now. [1:05:17] I'm sort of curious about the multiplayer stuff, if it'll actually work. But, okay, so we've got... [1:05:23] Thank you. [1:05:23] We've got our code, our instructions. I don't know if it's code or instructions, but we copied it. I'm going to paste it into the instructions tab of the configure page. [1:05:35] Ooh, maybe I should... Do you want to keep? Yeah. I feel like I should keep at least some of it, right? [1:05:40] Yeah, I wonder if we just take exactly what the GPT builder did and then add the rest of it right below it and where that takes us. I'm curious. So all I did was I copy-pasted our instructions below the existing instructions, and then do I press save, or does it just update automatically? [1:06:01] No, I think we need to press save. So let's do save in the top right-hand corner.

[1:06:06] Uh, I'm going to just say anyone with a link. Cause I don't think we're ready to ship it yet. Um, [1:06:12] and [1:06:16] Should we start or it looks like it didn't update the conversation starters. So like, what do we do? What should we do here? Should we update those? Should we start? Yeah. [1:06:27] Let's try and play and see. I think maybe we just send a message and be like, we're ready to play. All right. We're ready to play. [1:06:33] Let's see what happens. [1:06:36] So Alcator said, welcome players to Alcator, a thrilling journey through the annals of American history, where you step into the shoes of U.S. presidents, steering the nation through pivotal decisions and budget allocations. Your wisdom will shape the course of history, blending fact with intriguing what ifs. To embark on this adventure, please select from a gallery of distinguished Jewish presidents, each representing a unique era with its own challenges. [1:07:06] Who will you choose to be at the helm of history today? Once you've made your selection, we will commence with an Inauguration Day narrative setting the stage of the historical context. Choose wisely for the fate of the nation lies in your hands. This is pretty good. I like it. This is good. I like this. Let's go with JFK and see unless you have someone else who's top of mind. [1:07:23] I think JFK would be great. Let's do JFK. One little note for us later. Maybe I can save some notes at some point, but I would like it to be like a bulleted list, rather than a narrative.

[1:07:39] Let me just... I'm going to have a little scratch pad for us. Okay. GPT builder, GPT game notes. Okay. So I'm just going to say when you list presidents to start with, [1:07:52] output them as a bulleted list that I can select just so we have a little scratch pad. So, okay. So now we're continuing to play. So, [1:08:02] So let's see what happens. So I'm going to say, let's do JFK. And we're going to select JFK. [1:08:07] We'll see if it outputs an image. It says, ah, an excellent choice. John F. Kennedy, a symbol of youthful vigor and visionary leadership stepping into the presidency at the height of the Cold War. Your selection transports us back to January 20th, 1961. [1:08:20] A day etched into the annals of history. It's a time of both great promise and peril with the space race reaching for the stars and international tensions simmering. This is really good. I'm into this. [1:08:34] Plus, Dan, having you narrate this brings it to life much more. As I read this in my head, it's not as good as you narrating it. So I think we need to figure out a way to get you into chat, GBT, to narrate this for everyone. Please. Anytime you want to clone my voice, I'm super down. [1:08:50] Inauguration Day for JFK was not just a ceremonial transition, but a pivotal moment in American history. The air was crisp in Washington, D.C., the sun casting a hopeful glow over the Capitol. Kennedy's words, ask not what your country can do for you. Ask what you can do for your country. Echo is a call to action for you, the player to steer this great nation.

[1:09:12] As President Kennedy, your challenge is to balance the budget with the pressing needs of a nation on the brink of major social and technological changes. Will you prioritize space exploration, pushing NASA's budget to beat the Soviets to the moon, or focus on domestic issues, ensuring equality and prosperity at home? The choice is yours, and with it, the chance to rewrite history. How will you allocate the budget? Remember, each decision you make will have consequences, and the path to choose will shape the destiny of the United States. Let the game begin. [1:09:42] task. Review the current budget and set your priorities. Do you focus on defense, space, education, or social welfare? The future of the 1960s of America is in your hands. [1:09:52] I got to say, if I had this GPT to actually help me do my own budget, I feel like I would be way, way more psyched to be doing budget. Dan, your financial future is in your hands. Don't mess this up. This is a huge opportunity. Your children, the fate of the world, lays in your hands. [1:10:12] actually something somebody should build that. I think that would be useful. I think it would add a little bit more excitement to budget planning. Absolutely. That would be great. So one thing that I'm feeling is it's like saying review the budget, but it's not telling me what the budget is. And I don't actually know what commands I have available are. So it'd be nice for it to tell me the commands that I have available. [1:10:33] Yeah. And some of the text-based games that have done this have slash commands. So we can pre-populate and say slash start is what starts the game. Slash help prints out all of the different commands. I like that. GPTs have this. I like that. I think that's super cool. Yeah. Okay, cool. So I'm going to say, I mean, I think my thought here is I don't know.

[1:11:00] Like show me the budget. [1:11:02] Yeah. Okay. Let's do it. It should have access to be able to, and maybe we need to tell it specifically to like, I don't know if we want to like pull up the actual budget or not, but like we should say, show me the budget. [1:11:12] I'm going to say show me the budget. And we can, on this screen, we can say like, [1:11:17] Do you want me to look up the actual budget? [1:11:22] It has browsing enabled. It should be able to... [1:11:27] Thank you. [1:11:28] pull up the actual budget. [1:11:30] Okay. [1:11:31] But we should tell it to do that. I think that's like part of what will make this authentic is if it pulls up the actual budget. [1:11:40] Okay, so I'm adding in our notes. Please make sure to pull up the actual budget in web browsing. You should say, like, using browsing. That would be perfect. I also think it needs. Go for it. [1:11:50] Bye. [1:11:52] I think it needs to strike a better balance of being verbose when necessary versus being very concise. I think what it's doing right now is a little bit overbearing. I don't need it to generate this huge monologue. [1:12:11] And also, it seems like every prompt continues to say the future of the world is in your hands. We don't need it to continually set that context for us. [1:12:22] once I get to do that. Okay, cool. [1:12:25] Okay, so I'm saying in our notes, it needs to strike a better balance of being verbose versus concise. It's too overbearing. Yeah.

[1:12:31] I'm saying you should monologue for the introduction, but not for each turn. And, um, it doesn't need to remind me that the future is, um, [1:12:39] in my hands every time, which I'm a little worried about that one. Cause it might like get rid of it at all, which I think it's, I like it at the beginning, especially. Um, [1:12:50] uh, and talk, and maybe I could say, and talk about the future, um, being in my hands at the beginning, but not for each turn. Maybe that, maybe it's something like that would work better. And again, I'm just writing these into notes that later we can just refine our instructions and see how it does. So, um, [1:13:06] Um, so I asked it to show me the budget and, um, [1:13:10] It said, here's a simplified overview of the major budget categories. You need to consider defense space program, education, healthcare, infrastructure, research and development, foreign aid and diplomacy. And so I think, um, [1:13:22] it's not like giving me the numbers. [1:13:26] You know, can we ask it to browse and pull up the numbers? I think in the absence of us having done set that in the instructions, I wonder if it'll pull that up. [1:13:35] Okay, can you browse and pull up the numbers? I'm asking it. Let's see what it does. [1:13:42] doing research with Bing. Nice. And it's searching for U.S. federal budget 1961 breakdown. [1:13:51] It would also be helpful to have like a little bit more tactical suggestions, like kind of like right now it's like very general of like just put in anything for like what these things to do. And it'd be nice if it like gave us like the suggested like framing of taking the next step as the action. Yeah, I think this is awesome.

[1:14:13] If you're the president, like you have advisors that do a bunch of research and then come back to you and you're like, they're like, here are three options and here are the tradeoffs. And I feel like it should give you three options and tradeoffs. I like that. [1:14:24] Thank you. [1:14:25] Thank you. [1:14:26] I think we should say like with concise trade-offs. Otherwise it's going to like monologue about how the nuances of trading off military spending versus. Okay. So what I might do just to like see how it works is I'll just be like. [1:14:42] Hey, as my advisor, can you give me three options with concise trade-offs for budget allocation just to see how it works? Yeah. [1:14:52] And then, um, [1:14:55] Thank you. [1:14:56] This looks great. That would pulled up like it. So when you ask, can you browse and pull up the numbers that got the total expenditure, the major national security, including defense budget, agriculture, veterans benefits, research and development, interest on debt, welfare, education, health care, transportation, which is awesome. Yeah, it really brings it to life to like see the actual numbers. I love it. And so and so I asked, can you give me three options with concise tradeoffs, budget allocations? [1:15:26] fiscal strategy, I present to you three distinct budget allocations. Option one, emphasize national security and defense allocation. Increase the defense budget focusing on military advancements and intelligence trade-offs. Enhanced national security's pros are enhanced national security, stronger military presence, and potential advancements in military technology. Cons are reduced funds for domestic programs like education and healthcare, potential increase in world and Cold War tensions. Option two,

[1:15:52] Boost space program and technological research. Channel more funds into NASA and technological research. The tradeoffs are accelerate the space race, encourage scientific and technological innovations, bolster national pride and international prestige. Cons are high cost with long term payoff, possible neglect of immediate domestic issues and risk of technological ventures, not yielding immediate tangible benefits. [1:16:22] So, Logan. [1:16:42] Which option do you choose? [1:16:45] Option two. We're going to Mars. Logan chooses option two. Going to Mars. [1:16:52] boosting the space program and technological research. Let's see what happens. [1:16:58] Thank you. [1:16:59] I didn't say where it will go next. I missed option. I missed the two in option two. But allocator says an audacious choice, Mr. President, by boosting space and technological research, you're not just aiming for the stars, you're fostering a legacy of innovation and discovery that could define this era. The scenario boosting space and technological research, research allocation increases significant portion of the budget is now redirected towards NASA and the technological research focusing on space exploration and cutting edge technology,

[1:17:29] as the space program. NASA accelerates its projects, drawing in the brightest minds in science and engineering. The nation buzzes with excitement about space exploration, long-term prospects. This... [1:17:39] This decision could lead to groundbreaking advances in technology, potentially spurring new industries and contributing to economic growth. [1:17:46] The space race against the Soviet Union intensifies, but so does the possibility of being the first nation to land a man on the moon. Internationally, this move positioned the United States as a leader in science and technology, inspiring awe and respect. However, it may also escalate the space race competition, adding a new dimension to the Cold War. [1:18:02] While the scientific and domestic response, while the scientific community and many citizens applaud this visionary approach, there may be critiques about underfunding other crucial areas like health care or defense. [1:18:12] And visual representation. As this decision unfolds, we see a series of compelling images, the construction of massive new rockets, scientists pouring over blueprints, and perhaps a cameo of a Nicholas Cage-like video embodying the adventurous spirit of this era, narrating the thrilling progress and progress on a broadcast of what's next. With this bold direction, you've set a course for the stars, but remember, every choice has its rival effects. How will this impact the economy? The next step in your journey as President Kennedy is to monitor these developments and be ready to respond to any challenges and opportunities. [1:18:42] I think this is pretty good. It's not... [1:18:45] I think what it needs to do is like, [1:18:47] it needs to mess with us again. It needs to be like, well, this went wrong. Um, and it's not quite doing that. What do you think? [1:18:54] Yeah, I agree. It also seems like it needs like a little bit more of like a story narrative versus like it like telling us all of these like very nitty gritty details. Like, I wonder if there's like some way that we can have it just like give us like a very concise, like, you know, GDP plus one percent, you know, overall happiness of population minus three percent technological innovation, like plus five percent, like distill it down to like the very concise metrics.

[1:19:24] we also need to tell it that to generate images of the visual representations. I have no idea why it's make, it's just like writing texts for the visual representation. [1:19:35] Okay. Okay. So we have a bunch of notes. So I guess, [1:19:40] My question is, what's next? I feel like we've gone through one turn of the game. It probably is time to maybe head back into instructions and, like, [1:19:51] try to refine it a bit? Or what would you do? [1:19:55] Yeah, I think we go back to the instructions for this GPT, literally copy exactly what we have, stick it into GPT-4, and then take all those notes and say, here's our notes based on this, modify it, and see how much of the heavy lifting we can get a GPT to do for us in this case. Okay, cool. Got it. So we have it. So I'll say we've— I think it's missing. We need to put in the actual instructions because I think there's some of that weirdness is coming from those. You're right. I think you're right. [1:20:25] Yeah. [1:20:27] Okay, so I'm going to take all of our instructions. I'm going to say here [1:20:33] are the instructions currently. [1:20:36] Let's also make a new chat. I wonder if that won't be helpful to us. Cool. [1:20:41] I'm saying I'm making a GPT. [1:20:45] That's a game. Here are the instructions, the current instructions for the GVT. And then... [1:20:54] Uh...

[1:20:56] Okay. [1:20:57] And I'm pasting in the instructions. That's not the instructions. Oh, it is, yeah. This is a good start, but there are some problems. Here are my notes. [1:21:09] on what went wrong. Can you please, um, should we have it just like first summarize what it thinks the problems are and then, and on the next turn, have it modified you should we do modify in one and one stop and one step. [1:21:24] I'm curious how well it will do if we do a single shot. Um, [1:21:28] and just include it. Okay. Can you please modify according to these... [1:21:33] these notes. [1:21:34] *sigh* [1:21:36] All right. [1:21:38] Thank you. [1:21:39] Thank you. [1:21:41] I'm excited. [1:21:42] I said, I noticed that in my input, I said, give us a very concise readout of metrics, GBT plus five instead of GDP. I've got GBT on the brain. Okay, so let's see what happens. We're one-shotting it. And we said, based on your feedback, here are the revised instructions for the allocator GBT, incorporating your notes for improvements. [1:22:12] Um, [1:22:13] Yeah, I think this is... [1:22:17] I think this is good. [1:22:20] You know, it's basically... [1:22:22] Go for it. Yeah, we might need to nuke this available commands because it seems like it's like starting to, I guess we could do this, like such as viewing the budget and stuff like that, but it seems like it's not super fleshed out.

[1:22:34] which just might lead to confusion if we tell it there's these commands, but we haven't actually, like, I think we need to actually, like, enumerate what those commands are. [1:22:43] Okay. So how would you, what would you, what do you want me to say? [1:22:47] I actually think it's fixed a lot of these things, like the unpredictability and story narrative piece, visual integration throughout the game. It seems like it's fixed a lot of these different things. I wonder, though, it actually seems like it's... I'm curious, just by gut instinct reading this, is it seems to have moved away from, if you go back to the original instructions of what we were talking about. I'm curious, like... [1:23:17] I wonder if it even has any of this Nicholas Cage stuff anymore. Maybe it does. Yeah. [1:23:22] Thank you. [1:23:24] That's interesting. I think it's really only doing the instructions, not the top level thing. [1:23:32] Yeah. [1:23:35] I think we might want to try to have it redo or optimize those initial instructions as well. We can paste them back in and see. Maybe first let's get it to do what it just did in Markdown, because I think it fixed some of those core instruction problems, and we can bring that back in and see what happens. And we've got to make sure it's not for the visual integration. It's not... [1:23:57] it's not using Dolly. So we got to just, we got to just manually tweak it to say we wanted to use Dolly to do that.

[1:24:07] as Markdown. Please read out with this as Markdown in a code block. And for the visual integration... [1:24:14] Um, [1:24:15] It should be... [1:24:18] In the instructions... [1:24:21] Thank you. [1:24:22] to use Dolly to visualize each step of the game. [1:24:29] see if that helps and then I can manually modify it if I have to. [1:24:36] All right, so it gave us some revised instructions. Let's just check the... [1:24:41] The Dolly one. [1:24:43] Accompany each step of the game with visuals generated by Dolly, ensuring they are directly tied to the narrative and decisions being made. Use Dolly to generate. I think the example command thing is a little bit weird. [1:24:53] I do agree. I'm not really sure why it's giving this example command. [1:25:00] prompt. And maybe that's somehow helping the model to come up with these things, but that seems a little bit odd. I've never seen that before. I think what it's actually... [1:25:09] It's an example command from the user. [1:25:12] Mm-hmm. Right? I don't know. Yeah, I think what it's actually missing is, like, a single-shot, like, turn, step-by-step, like, here is the flow of the game. Like, the user picks the thing, then they go in, choose the budget, and then they, like, some, like, very tactical... [1:25:31] like step-by-step guide of like how the game is actually going to play out. And I think the, the thing that we maybe need to decide is like after you do the budget, um, the, probably the next step is like, um,

[1:25:44] Things start happening. The GPT generates scenarios of this is the day you made this decision. Now you have to deal with the consequences of this. Here's the scenario that's happened since you've made that decision. Yeah. [1:25:58] Thank you. [1:25:59] Thank you. [1:26:00] One note, after you do the budget, things are happening. A scenario is [1:26:06] pops up with problems that you have to solve, um, with further budget reallocation. So I'm sort of asking it to like create a sort of single shot, step-by-step outline for the flow of the game and telling it to make sure to create problems when you, uh, [1:26:24] When you allocate the budget. [1:26:27] Yeah, I wonder if we need to say further, like, I'm wondering, like, can they actually reallocate the budget in real time? Like, could, like, is that something that we want people to do? I think we can, like, it's our game. But I think the question is, do we, like, is that the core gameplay mechanic that we want people to be changing? Like, or is there other things that they could make decisions about? [1:26:47] I think so. I think just to keep it simple, it's all about budget allocation. [1:26:50] Cool. Let's do it then. [1:26:52] I agree. [1:26:54] Okay, certainly. Here's a single shot, step-by-step outline for the flow of the allocator game, incorporating your note about scenarios with problems. [1:27:02] Um, requiring further budget allocation. Um, okay. Allocator game flow outline. Um, and it's saying welcome introduction player receives a welcoming introduction, setting the tone of the game, brief explanation of mechanics. Um, um,

[1:27:14] and objectives, presidential selection. This is great. This is exactly, I think, what we wanted. [1:27:20] uh, [1:27:23] We should... [1:27:27] We might want to add in, it's saying initial budget allocation, we might want to add in doing it with the web browser or whatever. But I think... [1:27:34] I think this looks good. What do you think? [1:27:37] Yeah, I like this. This is... [1:27:40] Yeah, this adds so much more depth now because you can see some of these examples that is adding like multiplayer collaboration. If multiplayer mode players collaborate on decision strategy. Yeah, yeah. Not that it's actually fleshed out any of these ideas, but it seems like it's working. This is great. So I'm just going to I'm going to keep our top level thing and I'm going to delete this and I'm going to add it back in. I'm going to. [1:28:06] Yeah. [1:28:06] I'm going to make sure that we make the actual budget from... [1:28:17] the web, use web browsing. [1:28:21] to find. And, uh, great. And I think that's, [1:28:26] Okay, it seems I've gotten rid of our Nicolas Cage cameos, which feels like an important part of our gameplay. [1:28:34] Is it in the top? Was it in the initial instructions? I don't remember. It is in the top as the narrator's tone, but I don't think it has any cameos. So let me just...

[1:28:48] Maybe there's some... Okay. [1:28:54] Uh... [1:28:57] hide small cage theme icons or references in the gameplay. I'm just going to put this, um, hide, um, [1:29:04] Hide some... I'm putting into the instructions, hide some Nicholas... [1:29:09] Cage inspired references to [1:29:13] into the gameplay where appropriate. Okay. And just see if that [1:29:18] what that does. [1:29:20] but yes very very important alright any edits or thoughts before we update this? I think the actual structure of the game is going to make this work really well I wonder if we're going to need to do some prompting back to your comment before about it getting stuck in certain steps I wonder if we're going to need to add continue to step two but I think let's try and see if it's [1:29:48] Okay. And just, just to, just to give people like a sense structurally, like what we did is we just made a really rough thing. We played through the rough thing. We made it some notes and now we're modifying it and we're just, we're iterating that way. Right. Rather than trying to make something like really perfect from the beginning, we just got something done. We made some notes and now we're doing it again, which is, you know, how this stuff works. [1:30:09] So here we are. We're playing the allocator. We still don't have a welcome thing that we like, but I'm just going to say we're ready to play. [1:30:18] Thank you.

[1:30:20] Welcome, intrepid budgeteers, to the grand and intricate world of the alligator. Imagine the halls of power echoing with the footsteps of history's greatest leaders as you step into their shoes. The fate of a nation may nay the course of history awaits your strategic mastery. It does a great job of of Nicolas Cage voice. Yeah. So what do we want to do? Which president do you want to be? George Washington, Abraham Lincoln, FDR or JFK? [1:30:48] Uh, let's do FDR this time. Okay, cool. FDR. Um, yeah. [1:30:52] So I just said FDR, FDR. [1:30:55] Ah, Franklin Delano Roosevelt, a leader who navigated through turbulent waters of unprecedented challenges. As FDR, you inherit a nation gripped by the Great Depression. [1:31:06] With the ominous clouds of World War II on the horizon, your task is not just to revive a struggling economy, but to uplift the spirits of a nation. Inauguration. The year is 1933. The United States is in the depths of the Great Depression. Banks are failing. Unemployment is soaring. And despair is widespread. Your inaugural address pledges a new deal for the American people promising reform, relief, and recovery. The weight of hope and expectation rests on your shoulders. Initial budget allocation. [1:31:36] spending. Here's the historical snapshot. Relief in social programs, 15%, military and defense, 10%. So it's actually doing a pretty good job of giving us the budget. Now it's your turn to reallocate. Will you pour more into public works to create more jobs, bolster military spending in anticipation of global conflict, or focus on social programs? Make your choice and shape the destiny of a nation. Once you've made your allocation, let's visualize the potential impact of your budgeting decision with the help of Dolly. Okay. So what would you like to do? Will you pour more

[1:32:06] programs. [1:32:07] I think I'm curious to push on the edges of this and to see what we've learned about what additional guardrails we need to put in. But let's say to put 50 percent into public works and infrastructure and the last 50 percent into relief and social programs. [1:32:24] Okay, cool. [1:32:27] Thank you. [1:32:30] I'm curious how crazy things get. [1:32:34] So we put 50 into public works and 50 into relief and social programs. And the allocator is now creating an image with the progress that we have wrought. Whether that progress is good or bad, we have yet to find out. [1:32:48] um, [1:32:51] We probably need to add some guardrails. I feel like it is going to intrinsically be over-optimistic about what the outcome of the... It's going to be like, perfect, the world is now peaceful and everything works well because you chose to do 50% towards infrastructure. Yeah, it's FDR with half public works, half infrastructure misspelled. It's a compelling image, though. I like this. It's actually a pretty cool, interesting image, honestly. Yeah, I like it a lot. [1:33:21] Uh, it's got kind of like an art art deco vibe or yeah, it's, it's, it's really cool. Um, it says as you gaze upon this image, remember your choices are not just about numbers and percentages. They're about lives, touch destinies, altered and a nation's course redirected. Let's see how these choices unfold in the first scenario of your journey. Stay tuned for the story is just beginning. Okay, let's go next step.

[1:33:42] Thank you. [1:33:44] First scenario unfolds, the Dust Bowl crisis. No. Not the Dust Bowl. As President Roosevelt, you now face a dire environmental and agricultural crisis. The Dust Bowl, vast dust storms ravage the Great Plains, displacing hundreds of thousands of devastating agricultural communities. It's a disaster of biblical proportions reminiscent of a challenge Nicolas Cage might face in a high-stakes adventure. So true. So true, Allocator. [1:34:12] Scenario challenge. [1:34:14] agricultural disaster farms are falling and families are fleeing the dust ridden planes environmental catastrophe the land is eroding and dust storms threaten public health economic strain the crisis exacerbates the great depression straining your relief efforts decision point how will you address i actually like that a lot decision point is a really cool one that's uh that's um president bush's memoir is called decision point so uh yeah that's really interesting um [1:34:37] So increase funding for agricultural support, implement soil conservation programs and support farmers, invest in environmental rehabilitation, focus on long term environmental solutions, boost relief efforts, provide direct aid to displaced families. Each choice has potential impacts and tradeoffs. Consider carefully. Which one would you do? [1:34:55] Thank you. [1:34:55] 10, you're president. You got to choose. I got to choose. Well, what's interesting is like, I wanted it to be like, okay, you're not spending it all in the military. So like Canada invaded, you know? [1:35:05] Yeah, I think we need to force it to be more crazy with what the scenarios are that it's doing. I think it's a little bit too on the rails right now where it's going to be very lukewarm with some of these scenarios that it generates. I think you're right. But I'm going to keep playing along.

[1:35:24] Uh... [1:35:29] Well, I, like, I would, I would think that, um, [1:35:33] Thank you. [1:35:34] I don't know what car ride of the Dust Bowl, but maybe soil conservation would help like [1:35:40] help it in a big way, or help solve the problem long-term, and then release efforts would be short-term. So I'm going to [1:35:47] Do I choose 90%? [1:35:53] Thank you. [1:35:54] 90% option one and 10%. [1:35:57] Option three, which is boost release, boost review. [1:36:01] Relieve efforts and we'll see what it does. [1:36:05] It's going to create an image. [1:36:08] I like the image as like the first thing that happens after you just to like conceptualize. I wonder if we need to give some additional instructions depending on what this image looks like to make it more like... [1:36:18] um, a picture of the world or if it's going to be like, uh, [1:36:23] Another picture of FDR. I'm curious. It's going to be his face with corn on one side and dirt on the other. I don't know. Interesting. That is... [1:36:33] Thank you. [1:36:35] That's pretty cool. [1:36:36] It looks a little bit more utopian than I had imagined, given that it's the Dust Bowl. But it's saying you made the right allocation. Yeah, it's like no utopia. [1:36:51] Your decisive action as President Roosevelt in the face of the Dust Bowl crisis is now visually represented. The larger part of your budget is dedicated to rejuvenating the American heartland. Vast fields transform under innovative soil conservation methods, symbolizing a rebirth of agricultural might.

[1:37:06] yet equally poignant segment of this image. Your commitment to relief efforts shine. We see the humane touch of your administration, food being distributed, temporary shelters, providing respite and medical aid being administered. So, um... [1:37:18] What I... [1:37:19] What I'm learning from this is like, I would be a great president. Yeah. As long as, as long as you have Nicholas Cage and Chattapiti to help you, you'd be fine. A hundred percent. Um, so I think we could like, we could keep going with this pretty much endlessly. There's obviously like so much room for, um, for improvement, but, um, I think it's, it's, it's, it is super obvious that, um, [1:37:44] What we have right now is a game. It's working. We've got a gameplay mechanic. We've got complications that arise. We've got images. It's like the writing is kind of good. It's making Nicklaus Cage references. Like we've been doing this for, I don't know, maybe an hour and we just sort of like we're just messing around like that's so cool. That's amazing. [1:38:07] Yeah, and I think this is like scratching the surface. I think what would somebody needs to build a GPT game builder to like take the best practices of like what make a really great game and like add all those guardrails and nuance like so that every person maybe this will be our another video we do some time about helping people do this or hopefully someone in the audience will go and do this for us because there's just so many nuances about games and the model. [1:38:32] really needs to be sort of like driven in a certain direction. I think this goes back to like it being lukewarm and like always going to be like positive about the things that you do. Like you really need to be intentional about like,

[1:38:43] Bad things can happen. Like there needs to be some variance. There needs to be randomness. And I wonder if that's where we didn't get code interpreter was not enabled for this. But I wonder if like a dice roll or something like that or like a random number generator could be a really interesting twist of like the probability. You could have like a probability distribution every time of how horrible or how positive things turn out. I think that that's like a big missing piece of this. [1:39:10] That's a really great next step, which actually wouldn't be too hard to do. I'm like tempted to do it right now. But I think this episode is getting a little long. And and and I what I think what I want, what I think we should do. [1:39:23] We'll do this. We'll release this one. [1:39:25] It'll be part of the episode. We'll get people playing. We'll get some feedback from beta people. And then we'll have you come back and we'll tweak the allocator game with the dice roll and any feedback that we receive. And release a part two and a version 2.0 of the allocator in the next couple months. [1:39:48] Dan, when you woke up this morning, you did not think that Every was about to become a AAA game studio. So I'm happy that the diversification because of AI continues to happen. You now have another branch, which is Every Game Studios. So I'm happy for you. I think people are going to like this.

[1:40:18] But no, this is great. I feel, I don't know. I just, when I was a kid, I just, one of my big dreams was to like make games. And I spent so, that's one of the reasons I learned to code. And I spent so long like, you know, reading these gigantic books about like graphics programming and like all this stuff and stuff. [1:40:39] And I stopped doing that and I started doing like SaaS stuff in high school and Blackberry apps and iPhone apps that like were for work purposes because... [1:40:49] That was the only thing that you could do as a solo developer at that point is like, you know, sort of crud apps where, you know, it's just like forms you're filling out or whatever. Like I had this I had one of my big apps in high school was this thing called Find It, where this is before the iPhone came out. It would make your BlackBerry ring when it was on silent. And it was basically was Find My iPhone before Find My iPhone came out. [1:41:11] That's how I paid for gas and food in high school. But the reason I started doing that is... [1:41:17] is because I couldn't make a game because, you know, there's so much that goes into making games. There's really intense programming and math and all this kind of stuff. There's art, there's music. And as a kid, like, yeah, you can sort of do some of that. And I learned to do 3D modeling and I learned to do programming or whatever. But putting it all together into an amazing game was basically impossible back then unless you're an absolute genius. [1:41:45] And I really think that games and movies, like all that stuff is like, it's so possible now for individual people to do that in basic ways, even if you don't have any familiarity with like programming or anything like that. And it's going to be even easier in the next couple of years. And so I like there's this little child in me that's like, oh, my God, I finally get to do all this stuff. And so this was this really like reawakened my my game loving nature. So I appreciate you taking the time to show this to me.

[1:42:14] Yeah, I love that. And I think I have a similar story and we'll talk about it some other time. But I think this is really like these models are going to continue to unlock this like democratize access to like people's creativity. And I think it's going to be so much fun to put the tools in the hands of everyone in the world. And like you now aren't stuck, you know, going to have to raise millions of dollars if you want to build a really cool game. [1:42:44] which I think is just so cool and empowering. I'm with you. I love it. I love it. Any final thoughts? Anything you want to leave us with? Any OpenAI gossip or dirt you want to spill or release for the world on this show? Yeah, what should we be thinking about? [1:43:04] Yeah, keep building GPTs. I think at the end of the day... [1:43:08] this is such a moment to be able to create these things. And monetization for GPTs is right around the corner. So if you start building now, you get a bunch of people on board. There's going to be an opportunity to actually make money from this stuff, which I think is, again, really, really exciting. At the end of the day, people want to make money for the really cool things. And we're going to build a way for them to do that. So I think that is, from an excitement perspective, I think once that is released, that's going to... [1:43:35] 10x the amount of hype around gpt's and like people are just going to be building such cool stuff and being rewarded for the cool thing so um now's the time to get started build something cool and yeah i'm excited to see what it is amazing i'm psyched um i'll i'll put the profits with you 50 50 on the allocator you can have you can have allocators profits are you sure because like i mean in a couple years i could be like george lucas like you know there's merch there's like there's all this stuff like there's gonna be nicholas cage things going on like there's there's

[1:44:05] a lot of profit, but I'll take it. I'll take it. [1:44:08] You got to reach out to Nicolas Cage and see if we can land the official partnership with him for Alligator to have him be the true narrator. We'll get his voice in there and everything. [1:44:19] Before next episode, I'll see if I can get in touch with his people. I'll let you know. [1:44:25] Well, thank you again. This is like super fun. I had an amazing time. It was awesome to finally get to hang out with you. And yeah, I really appreciate your time. [1:44:34] Yeah, Dan, this was awesome. I think, honestly, my takeaway has been like more people should do the co-creation process like with AI and another human. Like I feel like I like I'm always doing this stuff by myself because it's just like what I'm working on it. But I think it's like a ton of fun to like have another human's mind in addition to the to the what AI is capable of. It's just that it makes it a little bit more fun. So thanks for thanks for going through it with me. [1:44:56] Amazing. Amazing. Cool. Well, [1:44:58] See you next time. [1:45:00] Thank you.