ChatGPT Prompt Engineering Mastermind: we worked on Zoom to improve each other's prompts! April 6

1:09

Zishan, let me unmute you and make you a co-host. Alright, thank you. Okay. You should be able to share your screen with the ChatGPT interface up and your prompt up. So I actually didn't prepare that. I just had a prompt in mind that I was hoping you could help guide through how to actually like, set it up. That is okay. I can pull it up. Can you just tell me what the prompt is and I will share my screen? Yeah, so the prompt was, lemme find it. Basically, I want to be able to build a website using web WordPress, but I don't know how, and I want ChatGPT to take me through all the steps necessary, including things like, purchasing, new domain, hosting, whatever is relevant. And just like steps on exactly what needs to be done. Awesome. All right. I am sharing my screen and while I am doing that, it looks like Ron, you are the next one in line who asked to present. So go ahead and get your prompt and ChatGPT up and in five minutes we will switch over to you. Zhan, does this approximate what you had in mind? Let's see. Yeah. Yeah. Great. Let's see what it says and then we will probably want to rerun it from scratch. But for the people who are for everyone except Ravi and Zhan put into the chat what you would suggest would help make this better. And I see one is already high level. I would start with a persona project component. Awesome. Yes, that is definitely where I was thinking, but I wanted to let it run on its own first so we could see how interesting it might be. All right. From the chat, we're also getting the suggestion of will expand each component. Yes. Mo tried a slightly different prompt getting very similar results and are some asked, does making a sorry, designing persona actually make the big of a difference? That's a great question. I am gonna just restart this with just, the only change I'm going to make is give it a role play prompt. So as a, oops, experienced software can't spell today, developer with 10 years of experience. So let's just. How much of a difference. So it was saying gimme a domain, purchase it, hosting provider. Some of these hosting suggestions are interesting, and particularly having to set up d n s not necessarily where I would've suggested at start, but, okay. Now let's see. One, one thing I'd like to have it focus on is more like the actual so I think it was step four or five where it's install WordPress and pick a theme, and then it just goes to the next step. And I feel like there's a lot there that very much yeah. Cool. So interestingly in this case, it's actually not making much of a difference. This output is pretty similar to what it had before. So let's follow the Yes. What Robert was just saying. Please tell me in short and concise steps. From acting as an experienced website developer. Let's see if that helps make this more nuanced, these steps of setting up WordPress. I'm just gonna get rid of that and yep. More people to admit. Man, Ravi, this is surreal. We're at 47 for context people. We had been expecting five, I think was the original count that I had. And then, yeah, boom. This is definitely overwhelming for us, for sure. Cool. Okay. We've got a couple different nuances to try. So act as an expert in WordPress and web development or act as my consultant. That would be a good one. I'm gonna throw that in and run this again in a second because Yep. It's still really focusing more on the, give me a domain and, sorry. Help me buy domain oops, that's not the one I wanted. Act as an expert. Tell me. And I think we're also this is the last one I'm gonna do because the next one I'm actually just gonna make a new chat because it's clearly, this is one of the things that you run into with ChatGPT. It's fixated on the steps that I told it originally. And this is a good thing and a bad thing. It's a double-edged sword because early on I asked it to tell me about the very technical pieces of buying a domain. That was literally one of the pieces of my top prompt was include steps such as buying a domain. So it's still stuck on that. This is actually something that just came up in an interview I did for the podcast with QuestGPT, and they ran into the same issue. Sometimes it's very easy for GPT to get very stuck on something it had discussed before. Okay. We're gonna run. This one more time as a new chat, if my browser will let me. Is there like something you can say to it forget anything I just said And so yes. In practice I tend to just make a new chat. And to be clear, acting as a developer, you are essentially, you have a new chat every time, unless you include the previous messages, but Okay. Do tell me in shorten complete steps, the steps of setting up WordPress. So this is also on 3.5, but yeah. See on a completely new one, domain name stuff is option number is step. So Sean, you can see, there's some nuances here that you would need to play with, but that is our five minutes. So Ron, are you ready? Thank you. Find you. You're welcome. Ron? Ron? Ron, where did you go? There you are. All right. Ron, go ahead. I think you're unmuted, Ron. I shouldn't be. Yeah, I can hear you. Awesome. Yeah. All right. Awesome. Cool. I just had a general question. So what I wanna achieve is to create personas I'm working on a GPT app that has different personas. Some of the personas will give you right answers to the questions that you have and some of personas should ask or should engage in a conversation or lead a conversation, meaning that the persona will ask you I don't know how do you feel today, for example, and you respond with that and then the AI should respond. That's awesome. Now talk about X or Y or something like that. How would you go about doing that so that the response in of G B T will include the next question as well. Does that make sense? Not quite, but, okay. Let me take a step back here. Yeah. Do you have a prompt in mind in terms of written out or just the concept? Just the concept. Just the concept. Okay. So let me make a new chat. And I'm gonna keep this in 3.5 because I realized if I use four, we're gonna run out of prompts very quickly cuz they're still limited. So tell it to me again. You're trying to create personas and, sorry, I'll start the five minute timer. Should we have a a persona that is like a A therapist, for example. Okay. Not a real therapist but somebody who has a best friend to to talk to. Therapist will ask you how your day went. And it will follow up with questions after you answer how your day went, depending on the answers. So it's context sensitive if that makes sense. Okay. But yeah, it should kinda lead the the conversation, if that makes sense. Yeah. So that was gonna be my question is where do you want the AI to lead the person to? Because just ask me about your days. Probably gonna go in a little bit of a. Yeah. It doesn't really matter in, in that sense, I think it's, I think it's more so this will be an example for somebody who wants to just talk to someone just talk to, like a regular phone conversation doesn't really matter. Like who they're talking to. Exactly. Yeah. That will be it. That will be it. Okay. How my day is going. And feel free, what do you think, Ravi? Feel free to move on to, I think we need to set it up. We did, we need to prime it to say, it's a conversation between you and me. I'm gonna ask a question and based on that we are gonna have a conversations, something on those lines. Okay. It's going. Feel free to feel free to take What's the word I'm looking for? Take subjects from what I mentioned and turn it into a positive point to help me feel better. Yeah. Not the best grammar, but at least something like that. Hang on, let me just scroll on the chat for a second. Actually, one thing I learned, is I can add in the beginning, can you rewrite this prompt in the best way possible? And then take that and give it. That way you get really it's like creating a prompt, asking you to pro create a prompt for you. Yes. Make sense? The prompt generation ones are amazing. Let me run this and then I wanna run that cause I completely agree. Yep. So what do you mean by pro? Pro? So that's interesting. So I hadn't had that word. I haven't heard that word before. Brian Otto looks like Yeah, just pasted a prompt creator in. Alright, first Ron, what do you wanna say? How's your day been so far? Has it gone amazing? It's going amazing. I am currently sharing you with a community of, what are we up to? 49 people excited to learn about ChatGPT, and it says, that's great to hear. It sounds like you're doing something productive and engaging with others. How does it feel to be sharing your knowledge with others and being a part of this community? Ok. So there you go. Kinda nudging you in a positive direction. That's awesome. Can screenshot of this? Yeah. Oh yeah. Oh, sorry, Ron go ahead and take a screenshot at all. I got it. I got it just in time. Okay. All right. Is there anything I need to change? We're gonna try out the prompt creation and No, we're good. So we're running the prompt creation prompt. This is very meta, but I've used them too. They're gonna be very powerful. Okay. So it responded. I'd be happy to assist creating the best possible prompt. So now I will paste in our original prompt and it says, here is a revised prompt you're feeling lonely and would like to have a conversation with a therapist. As your therapist, I'll ask you questions about your day and help you find positive points to improve your mood. And then it asks some questions. I thought this prompt builder had two sections. Oh, these are, I don't think it quite did what we had in mind. As part of the prompt builder, it says, ask me questions to make the prompt better. Ah, yes. However, that's, yeah, that's where you got. Yeah. The questions that it's asking are not making the prompt better, they simply are part of this conversation. Interesting. Okay, hang on. That's the five minute timer. Quick poll in the chat. I kind of wanna run a little bit longer on this, and five minutes is feeling a little short. Can I get just a thumbs up, thumbs down emoji, or a reaction? You can do any of those if your video's on thumbs up if you'd rather take another five minutes. Thumbs down if you would like to move on to the next person. All right. I'm only seeing thumbs up, so I'm inclined to, yeah. All right. I only see thumbs up. So we're gonna go for let's, I think another five minutes. What do you think, Ravi? Let's sure. Let's do this current paste that prompt in there. Yep. And then at the beginning, say help me rewrite this prompt so that it's clear and concise. Help me rewrite this prompt. Yeah. And then that was the one. See what chat. Just said something. Oh. Robert, the reason I'm working in 3.5 instead of four is if I use four, we're gonna run out of queries. Yeah. In probably about 10 minutes, because there's a limit of 25 every three hours. Okay. Looks like Jack says they have a prompt for improving. So Jack, if you wanna paste that in, we can definitely give that a shot. But for now I will run this. Okay. That did not help. The only thing that it added is tell me about positive experiences or hobbies. I am curious though, so I'm gonna open another and run this in four. I won't keep running it in four cause like I said, we're gonna end up running out of queries, but I'm pretty sure four is gonna give a much better response than this because four usually does a whole lot better. And Ron, I gotta say it's such a vague prompt that it's having a hard time really coming up with something useful. Yeah. Okay. This is a little bit better, but not a whole lot better. And it's solving the objective though, right? So it definitely is, and it's definitely trying to actually get you to the point of, make me feel better. What if you added a persona to the question using persona of someone that is well known in the field? That is a good idea. Although, who would that be? I can't actually think of a person. Yeah. Suggestions. Dr. Oz or somebody? Oh, Esther per yes. Esther Perel is a phenomenal example. Yeah. So please act as Esther. I think. Is it two Rs or one R whatever? A therapist. A, let's even give it a little bit of a cue. Famous therapist. And I'm gonna once again make a new chat for this. Nice. So that's working a whole lot better. Ron, you noticed not only is it giving you a little bit more suggestions of directions to go, like what's weighing on your mind? Why are you feeling lonely? It also then adds a little bit of emotional support of sometimes just talking about these things can help to ease some of the pressure that we feel. Sorry, I also do voice stuff, so I occasionally I'll start acting instead of just reading. Alright. That's good. That's, I think we've got time for one more tweak and then I wanna move on to gonna mess up your name. Ars aam. Don't know. But yeah, what what's one more tweak? Okay, cool. Alright, awesome. Go ahead and get your ChatGPT window ready with your prompt in it, and then we can all work together to improve this for you. One piece of feedback in the chat is when revising a prompt, you should describe as much as possible about your intentions, your objectives, how it should work, and then ask it to revise and improve your prompt. In other words, feed it with enough information. Okay. Somebody just suggested that we should have had Freud be our therapist, and I am definitely not going to be doing that because that is going to get interesting way too quick, but I like the idea. Yeah. Yeah. That was a good suggestion. All right, so that's our time. So Arsam, you should be unmuted. Yes. Hello? Can you hear me? Hello? We can. Hi. Hey everyone. So let me stop sharing. Oh, sorry. Wait, do you have it set up? Do you have a screen to share? I do have it set up. I think I need to share my screen. Yes. Okay. You should be able to share it. Let me know if you can. I do need some guidance. So down at the bottom there's a green share screen button. If you click that, saw it. Yeah, then you can click on window. All right. Got it. There we go. All right, price start. Greg, I wanna thank you for hosting this event. It's super cool and I'm learning so much. I have, I wanna share something pretty cool, and I also wanna ask a question. Let's get into it. I'm a social media content specialist and I write a lot of content carousel content. So naturally I wanna use ChatGPT to explore carousel content and see if I could prompt it in a way that could write me carousel content. Now, to do that, I've designed engineers, I guess you could say a prompt in three sections. At the start, I'm gonna tell it to analyze the carousel that I'm going to send you. Then I'm going to send it to Carousel, that's number two. And after that, I'm going to tell it based on your analyzation of my content, I want you to write me a c carousel content with this topic and this main point. So that's basically a walkthrough of the prompt. Now Basically, this is what happened. I went through the first step. First step. Oh, interesting. Then I sent him the carer. Yeah. And after I sent him the carousel, and this is something I wrote, and this is something that really resonated with me. I really enjoyed it myself. And it went on and it broke it all down. And it told me to, okay, this is your writings. This is your format, this is your voice of tone. And it did a pretty decent job. I would say after that I told it to, okay write me a carousel post on the topic of education matters, as an example. And with the main point being, humans have a need for exploring and education helps fulfill that need. So this was the basic idea. It did give me an answer, but it wasn't flowing that well. And so I went on and I said, okay, I want you to make it flow better. Using things like, because, and so furthermore, stuff like that, and it did give me a decent answer, but I guess my main problem and my question here is how can we make this feel more genuine and more humane and something that when you read you're actually feeling that connection, if you know what I'm saying? Yeah. I do wanna pause for one second. I saw a question in the chat of what is carousel content? I have an answer for that, but I would actually rather let the expert who is asking us about it. Okay. Could you just give like a two sentence, what is carousel content? Okay. So if you've been on Instagram, you've probably seen those posts where you could swipe to maximum of 10 slides. Basically, in a nutshell, carousel content is. Slide content that you could swipe and see the next slide. You have it on Instagram, you have it on LinkedIn. It's something that a lot of educators use to express their ideas, thoughts, and knowledge and connect with their audience basically. Yeah, so Jack actually has the exact thing that I was gonna say, which is, have you thought about first developing the content as a story and then breaking it down as a slide. However, what I would suggest is we could start with that, and I think we probably should, but I'm gonna do something a little crazier anyway, which is, I think what we should do is ask it to step by step, which is, again, this is a specific phrase, step-by-step, logic and step-by-step thinking forces it to do meta thinking, metacognition. Okay. Develop the content a and then step by step, split that content into, I don't remember how many slides you said, but, 10 slides or 20 slides, whatever the number was. So go ahead and I would say, do you want me to write something here? Yeah. Down at the bottom. Yeah. Go ahead and there you go. Oh, sorry. Someone else is coming in. Yes, I'll let you, yep. I got it. Thanks. Cool. Okay the topic that you wanted to do was, what was it? Education, I think education matters, I guess you could say. Okay. So given, take the original prompt that you had and paste that in, just so we can work on that. Should I go through the three steps again? Yep. Okay. Number one, okay, so it's analyzing the carousel post. Great. It is totally missing. Oh, no. Okay. Got it. A little bit. So it the flow number five where each slide builds upon the previous one, creating a cohesive narrative that supports your main message about the importance of using fewer words for greater impact. I'm not sure where it got the, that is the main message, but that was the nuance that I was gonna say we need to include. Okay. It got that. So in your next prompt where you say, give me carousel material about whatever it was. Okay. Yeah. So paste that and don't hit submit yet. Yeah. Change the topic. Do you have any suggestions for the topic? ChatGPT matters. That's what I was gonna say. That's one matters. Two ts. Alright, there you go. Okay. And so what's our main point Gonna be? Everybody. How about for a main point? Oh, I, that's even better than I was about to say. Why it will not take our jobs. Okay. That's nice one's. Shaun. I was gonna go a different direction, not take our jobs. Cool. Okay, so then in front of use words, say follow number five, colon flow from your analysis. Should I delete this part? No, go ahead and leave that. We're gonna tweak that in a second. Okay. But in front of it. So right here, say follow. Yep. Follow point number five. From your analysis that each slide builds upon the previous one, creating a cohesive narrative. Each slide. Oh. What happened? Were each slide, could you go on again? Oh yeah. I was just basically saying what it already said. Creating a sorry. Each slide builds upon the previous one, creating a cohesive narrative. Just cut and paste that, yeah, you can just copy and paste that. Okay. Should I stand before you do that, move this text afterwards. Okay. And then, and then put use words like, okay, so right here, put a colon. So use words like colon, cuz you want to tell it a, this is a list of words. So that's at least tentatively worth trying. Gonna go a minute over the 10 minutes, but let's see what it does. All right. All right. And while it is generating who is next please, that might have actually been the last person who had a prompt. Oh no, we got one more. Nice. I think we, we've seen a lot of improvement actually. Yeah. Yeah. Yeah. So now it's starting to do the, like sentences phrases connect between slides. Yeah. Can you scroll up? What was the first bit? AI Matters ChatGPT really good many Fear ChatGPT will take their jobs. Will take jobs, but it's designed to assist, not replace, because ChatGPT needs human input and our creativity makes it thrive. Yeah. This is a lot better. What's the end? Yeah. Embrace AI like ChatGPT to grow together. That's awesome. Okay. That's the, yeah. Very appropriate. Got a request in the chat from Stephanie. If you could copy and paste that prompt in just the last one into the Zoom chat 100%. Can we do a question and answer maybe at the last 15 minutes? Yeah, totally. Yeah. That way we can also answer some of them who doesn't have prompt, but may I have questions? Yeah, totally good with that. Good call. Okay. So who was it before? I think it was Robert. Yeah, Robert. That I had called on before. Do you have a prompt that you wanted to, do you wanna try and unmute? Okay. You do have a prompt? Are you able to unmute? Sorry. I know he has a prompt because you just posted it in the chat. Oh, you don't have a microphone. That would make unmuting a little bit of a problem. Okay. Nevermind that idea. Let's do a q and a. So I might as well use Zoom as intended. If you have a question you'd like feedback on, does not mean you need to have a prompt raise your hand, which is the raise hand button. And I can unmute people who have questions. I'll break the ice. How about that? Yeah, go for it. Alright, so I don't know how many of you feel that, the te the history bars that keep on going forever, right? If you're working on certain thing I wanna go back to that, but I can, it's really hard to scroll through everything. Is that an easier way? I'm not seeing any search button there, but have you guys figured out anything easier way to. Sorry, let me make sure I'm understanding you're talking about the new chat, the bar on the left Correct. Where it shows your previous conversations. Is that right? Correct. Okay. Yeah. Cool. No, there is no way, there are a couple of extensions that will let you do that. I honestly would have to look them up cuz I don't remember, but they're like, better ChatGPT or something like that. And they do allow searching and even organizing the prompt conversations into folders, which is pretty cool. Okay. Okay. Anything specific that you liked? The extensions that worked? Honestly, I don't use them. Yeah. Meaning neith, it's not what I've needed. Yeah. Okay. I swear I just saw somebody in the chat who said something. They were a fan of one of them. Yeah. A power ChatGPT Mo says and A I P R M. If you could put links into those, that would be helpful. Also for everyone I have just put a link into the chat. This is indeed the launch of my podcast today. That happened about three hours ago, so if you could take a minute and subscribe to it on Apple Podcasts and YouTube and Spotify and rate it five stars and like the first video, cuz so far that's all I have up cuz I'm doing this instead of finishing editing the first two episodes. That would be awesome and very appreciated. Then a feedback form for today's Mastermind. So again if you're getting something out of today, do me a really big favor and subscribe to the podcast. And this will be published there as well, eventually. uh, Somebody's got a hand up. Oh, Zishaun, you've got a hand up. Great. I think you can still unmute. If not, let me know. Yeah, I can. Thank you. Cool. Yeah, so actually I guess we just started talking about it naturally, but I was wondering what you, and maybe even just I guess everyone in the chat can throw it out there as well, but what extensions you found to be really valuable and helpful for ChatGPT. I have not found any personally, does not mean that there aren't a bunch of helpful ones. Not gonna say that at all. Just hasn't been helpful for me. Also I'm building a tool because there's some very specific kind of testing that I've been doing that nothing really works for. I can share about that if people want, but is anybody else seeing things in, okay, Jack says he is looking for one that can export text. Jack actually look at the I think it was the a i p r M one cause I thought that one could do it. I know one of them can do that cuz I've seen a specific listing about export your ChatGPT output as text or P D F or image. And I know that exists. Let's see. Art, thank you. Who else is in here? Oh, that, that was actually a good point. Do, yeah, Jack just said searching through the old conversations, at least searching through the titles, you can just use the normal command or com control f to just search the text. That does actually work for the titles, obviously not for the content. I thought I saw another hand go up. Ah, Stephanie, let me unmute you. Hello? I'm speaking. Yeah, there we go. Now we can hear you. Yes. Okay, great. So yeah, so I've been experimenting a lot with prompts to get ChatGPT to generate the perfect prompt. Yeah, I was just curious to see if you've done any of those, how you feel about it. I've gotten mixed response, with that. Like sometimes it, it does generate the perfect prompt. Sometimes it just gets a little too confused. So yeah, just curious if you could talk about that. Ravi, it sounded like you had something you were about to say on that one, so go ahead. Yes. If not, I can respond. Sure. I, what I realized is it's like a trial and error method. Nothing, every single time you're gonna get a short shot at it. That's what is my experience so far. So you keep trying it until you get what you're looking for kind of a thing. I think, I wish I can give you a better answer, but that's my experience. Yeah, the the one nuance I would add to that because that's a pretty good summary. To answer the original question, yes, there are ways, no, they're not reliable. There are, I'd have to look it up, but there are a couple of prompt building prompts and a couple of prompt analysis prompts. I've heard from someone that they actually tag team between the two of them, where they'll do, build me a prompt, put it in, get the prompt, analyze the prompt, do that, and then use that again to build it again. I have not actually had any luck with that, so I'm planning on trying it myself. Cause I'm curious. The other thing though that I would say is how do I say this? Doing it iteratively is what usually works the best for me. With very careful consideration of now I'm gonna create a new conversation. So like thinking about, okay I've got like a version two prompt, still not amazing. Okay. Let's completely start a new conversation and go from there. Regarding the prompt building prompts I can throw a couple of them into the LinkedIn. Let me just make a note of that. Which I guess I should clarify, the LinkedIn group is in the document that I pasted. I'll paste it again just so that people have it. Trying some different ones is actually what I've seen works the best. I haven't, like this one always works. Yeah. Looks like just pasted a prompt builder. So Stephanie, you can check that out in the chat and Tomer would like to ask a question. Tomer, you should be unmuted. Yes. Yeah. Hi everyone. Sweet. Hey, so on my side, since Stephanie brought up the discussion on the prompt creator, I just wanted to ask, cuz I'm like in this cycle where it's asking the questions and I'm trying to respond. I'm just wondering does that end or is it, we've got enough to the wrong foot and I should start a new chat. What's your opinion on this? Sorry, making sure I'm understanding the question you asked, does it end? It's only gonna keep going as many times as you say, give me another round, make it better. It's not like it will take over and start just messaging you like message message message.. Like ChatGPT doesn't really do that. It's keep going on you keep asking it, right? So obviously you need to refine your question and start asking it. It's just a trial and error. I was just mentioning it to Stephanie the other time. Until you get it and then you, once you start and then you will you will get a hang of it, and then you know what to ask next. I see what I can give you. I can give you an example. I'm a blog writer. I write blogs, right? So when I write the blog, I created a prompt for myself saying, okay, I wanna rate can you rate my prompt my blog based upon the readability, the timing search keyboards value like seven parameters, I decided, right? It gives me a value for, on a scale of nine one to 10, every single time. Different number, but the same block. So not surprised to hear that. Yeah. Yeah, I think I'm covered. I think I need Excellent. Okay, cool. Tomer, just the last thing to make sure of is you wanna run one conversation prompt, upgrading, and the other conversation testing the prompt. You don't want to do it in the same conversation. Cause then it will get very confused. I think that's what I've been doing wrong. Yeah. Okay. Yeah. That's what I was thinking. If you're not, if you're doing it in one conversation, the prompt optimizer will just fail after one round. That's a good tip. Yeah, that's a good tip to Greg. I like that. Actually. I didn't realize I want to. Cool. All right. Let's see. We've got five minutes left. You're welcome. So there was somebody talking about meta prompt. Yes. Who was that? Would you mind whoever that, I see the message. Let me see if I can unmute you. I, Hey. Awesome. Please share about meta prompting. I have a definition, but I would like to hear yours and Yeah. What you found useful. So many things. Meta prompting is anything where you use chain of thought but you adapt it out to higher level things So First, before I do anything, go subscribe to this man pro this dude is awesome for being able to host this kind of thing and getting us together on LinkedIn. So please anybody, cuz I can see how many subs are over there and I can see how many people are in this thing. So y'all not doing your job. Go over there sub to his channel. Outside of that let's go ahead and get started on this stuff. Meta prompting is going to be anything where you take a higher level overview at the approach. So instead of approaching ChatGPT at a single point where you're gonna go, Hey, I want you to build out this carousel thing. I want you to do a SEO blog post. It's okay to do that. Then you have one higher level where you can send tax it. Right now you're gonna go, I want the blog post to look like this. Or maybe you wanna do like a level one role play. These are all beautiful things because they're really attributes and characteristics of how ChatGPT will relate with you and since actually respond. That's great. But what if we take all of these traits, put it into one persona model, shove it at the top, make that a master model, and then once we have this level of master model, what we're gonna end up doing is that once we've generated that, we're gonna load it with a persona profile So for example, when you were talking about the carousel content, right? The Instagram sell carousel host this is what I built out for that exactly. So I loaded it with a simple master model. This is a very simple one mind you. Eva and I have other things that are like six post deep. Now that we have the best educator in the world that we're interacting with, ChatGPT has this construct of who it should be, how it should be, how it should talk. So why does this matter? Your time is the most valuable thing in the world, right? So what if I told you could spend less time on ChatGPT getting more out of it. That's what this is. If you take the time to build a master model with your specialty and experiences, because I'm not you. You know what your special things is? Maybe you're a coder, maybe you're a marketer, you know how you want to define the model to respond to you or to do things, but you don't have to think about it from such a how do I want the carousel post? No, ignore that. You're defining a person. If you were to hire a person to do that job for you, how do you want that person to be? That's what you build first. That's your persona model. Then you secondarily move into what you want it to be. So you give it a job. You are named builder. You're gonna create a project. This project's gonna be this thing. So now you have all of these aliases or variables you could say to reference back to the things you want. If you want to call back the project, you just say, I'm doing this project, and Tai will know exactly what you're talking about. So now instead of having to redefine the whole damn thing every post or do this huge syntax, programmatic language, you can get lazier and lazier while ChatGPT reinforces itself and get smarter and smarter because you preemptively told it. That's what it should do. In fact, there was a research paper that was released on this called Chat Gcpt plus Reflection, which shows the accuracy of GPT four goes from something like, what is it, 77 to I, I don't wanna misquote it, but it's something like 10 to 20% increase in accuracy. It's insane levels and if that's what's is amazing. Yeah. And just realized we have actually, we just hit the hour. Real quick before everybody hops off, I'm gonna share a quick poll How often do you want to do these? You wanna do them every week? Do you wanna do them every other week? So if you could answer that really quick and Wow. Very strong reaction for weekly awesome. Okay. Thank you all so much for attending. This was a ton of fun for me. I hope it was a fun I hope it was a lot of fun for you. This recording will be shared on the YouTube channel aside from me wanting you to support the podcast, also, if you want the recording and you don't wanna subscribe, the link is in that document that I put which sure I can put that again. This one. And if this has been helpful for you please do me a solid and go subscribe to the podcast in wherever you do it. Rate it, five stars. I'm gonna be posting a whole bunch more episodes of people coming in and having conversations with them about like, How do you do prompt engineering? What have you learned, all that kind of stuff. Two other things. If you are a person who writes prompts and would like to be on the podcasts honestly, just send me an email, email redacted but also you can comment in the LinkedIn or reply to any of the dozen places that I think I posted this. Oh one last thing. The paper about reflection just got posted in the comments, so make sure that you grab that. It is a very cool technique and I'm hopefully going to be talking about that on an upcoming episode. And if not, I might just do an episode myself on it cuz it's pretty cool. Awesome. Thank you all so much and talk to you soon.

Greg Schwartz: 39:26

Thanks for coming to the Prompt Engineering podcast, the podcast dedicated to helping you learn how to be a better prompt engineer, how to sell your prompts if that's something you're into, or just use them in your day job. See you soon.