Everyday AI Podcast – An AI and ChatGPT Podcast - EP 228: OpenAI Ambassador Gives Prompting Secrets

Episode Date: March 14, 2024

Awesome Stuff From Our Partner, NVIDIA -Register for the FREE virtual NVIDIA GTC Conference or buy tickets to the in-person event and fill out this form here: https://www.youreverydayai.com/nvidia-giveaway/There's one secret skill for more effective prompting! It's a skill set that we all have but not recognized as something you can use toward prompts. Even better, we have an OpenAI Ambassador here to help talk about prompting and how to do it effectively. Abran Maldonado joins us to discuss what that secret skill is and how you can use it for better results. Newsletter: Sign up for our free daily newsletterMore on this Episode: Episode PageJoin the discussion: Ask Jordan and Abran questions on promptingRelated Episodes:Ep 217: 7 Steps on How To ACTUALLY Use ChatGPT in 2024Ep 194: 5 ChatGPT Facts You Might Not KnowUpcoming Episodes: Check out the upcoming Everyday AI Livestream lineupWebsite: YourEverydayAI.comEmail The Show: [e-mail] with Jordan on LinkedInTimestamps:01:55 Daily AI news04:35 About Abran and being an OpenAI Ambassador08:01 Access to future models, testing, providing use cases.11:10 Engineers from diverse locations think quickly.16:31 Proficiency with AI tools and Excel important20:46 Elon Musk invented Neuralink for brain communication.26:26 Imposter syndrome, calm down, noncoder perspective.30:04 Excited for early access to custom GPTs.30:51 Limiting Internet searching could impact ad revenue.35:35 New technology levels the playing field.Topics Covered in This Episode:1. Abran's role and involvement with OpenAI2. Secret Skill for Effective Prompting3. AI and Communication SkillsKeywords:Custom GPTs, Generative Pre-trained Transformers, personalized learning, department-specific GPTs, AI technology, practical advice, careers, AI news, Siri, Google Bard, OpenAI, AI ambassador, Create Labs Ventures, pandemic, prompt engineering, communication skills, prompt guidance, feedback, AI art, prompt engineering, GPT store, user feedback, Chat GPT, job seekers, AI-related skills, intent understanding, communication assistance, communication challenges, communication sSend Everyday AI and Jordan a text message. (We can't reply back unless you leave contact info) Start Here ▶️Not sure where to start when it comes to AI? Start with our Start Here Series. You can listen to the first drop -- Episode 691 -- or get free access to our Inner Cricle community and all episodes: StartHereSeries.com Also, here's a link to the entire series on a Spotify playlist. 

This is the Everyday AI Show, the everyday podcast where we simplify AI and bring its power to your fingertips. Listen daily for practical advice to boost your career, business, and everyday life. Meet Firefly AI Assistant, now live and Adobe Firefly, the all-in-one creative AI studio. Just describe what you want to create and the assistant handles the rest, orchestrating multi-step workflows across Photoshop, Premiere Express, and more in one conversational interface. You direct the outcome. The assistant accelerates execution. There is one secret skill for more effective prompting.

And it's not what you think. It's not finding someone else's prompt and copying and pacing it into your chat GPT for the best outputs. That's not what it is. It's a skill set that we all have, but I think so few of us actually know that it applies to better prompting and getting better results out of chat gpt. all large language models. So we're going to be talking about that today and more on Everyday AI. Welcome. My name is Jordan Wilson. I am your host of Everyday AI. And this is your daily live stream, podcast, and free daily newsletter, helping everyday people learn and leverage

generative AI to grow their companies and grow their careers. So if you're new here, thank you for joining us. If you're listening on the podcast, make sure to check your show notes. There's related episodes, a lot of other resources as always, as well as a link. to come back and watch this, watch the live, ask questions too. So today is one of those days. I'm going to tell our live audience multiple times, you're going to want to get your questions in because we are talking with an open AI ambassador

about more effective prompting. I mean, how else can you get access like this? Like, you can't. All right, Abron Maldonado is an open AI ambassador and the co-founder of Create Labs Ventures. Abron, thank you so much for joining us. Thanks, Jordan. I really appreciate it.

It's morning over here, It's good to get a start like this to get excited and carry that through the day. I'll say this. I talk about generative AI every single day. And it's still on the top of my list on things that I want to improve on. So I think today's episode is going to be a great one, especially if you're a newbie. So before we get into that secret skill, Abron, can you tell everyone a little bit about what it is that you do? Like what is an open AI ambassador?

Sure. So just as such a stage of history, you know, it's all about timing. There was no specific skill set that we needed. Maybe there was. I don't know. So back in 2020, you remember what 2020 was, right? It was the pandemic for everybody. We were all just home trying to figure out our next move.

And at the time, I was doing a lot of social impact work in the city, across the country, in inner cities with underserved communities, trying to give them access to cutting-edge technologies. So I was doing events, bringing ARV, V, VR, drones, robotics, AI, to underserved communities that never saw any of this technology in person or touched it live in person. They only saw it on TV. And it was very gratifying. But the pandemic hit shut down all of those events, right?

So I'm back in my garage, trying to figure out what the next move is, but still trying to do some R&D to figure out what are the technologies that are out there that being developed. And I came across the papers for GPT, too, when they deemed that it was too unsafe for the public. I was like, oh, okay, this is interesting. Let me see where this leads. And then I learned about the private beta of GPT3. Now, this is three years before Chad GPT. So this is dating back when no one cared about it.

And not many people had access. Less than 1,000 people across the world had access to the original private beta. And, you know, it was something that I felt excited about and wanted to be a part of. just from the always thinking of like the social impact use case and then I saw a DM in my on my Twitter inbox and it was from Greg it was from Greg Brockman and said you know shoot me your email I want to give you access to to this private beta and so I didn't know what that meant but now we know right you know fast forward to what that meant meant for me but once they started to see what I was doing with the technology, they tapped me on the shoulder and they're like, hey, look, we want you to be an ambassador.

You know, we'll bring you in in the inner circle and give you access to these tools, to the future models that aren't out yet that we're going to release. We would love for you to test them out and demo and give us some business use cases, give us some social impact use cases. That's your lane. Let us know what you think about this and your unique perspective around this model, right, before we give it to the rest of the world. And that also requires, like, office hours. So you could find me on the open-eye website and you go to, like, forward slash ambassadors,

and you can put time with me and the other ambassadors to just learn more about these models, how to use them. So I've spoken to hundreds of thousands of people around the world on their first experience with opening eye tools where they come to me and say, how do I use this, right? And scientists, expert engineers, professors, senior citizens, people as old as in the 80s, like, how do I use this? How do I, you know, spend time with this to show other seniors who are lonely, how to use

these tools. Just had a conversation yesterday. Shout out to Maria. Like there's so many interesting use cases. And that's kind of molded how I perceive this technology for myself. And just hearing, you know, this scope from the world of like all the different ways that you can use this makes me think a bit more diverse and more collective about, you know, this technology.

So many things I want to unpack there, right? Like, Abron, I love that you are from the beginning looking to use AI for good. I think so many people, especially when they don't know or understand AI, they just think it's a bad thing. So I love that background, helping seniors, all of those things really amazing. But I actually want to get to the heart of the show. And today we're just going to skip to the end. I'm not going to keep dragging you on any longer.

But, Abron, what is that one secret skill? for more effective prompting. And spoiler alert, it's not using someone else's prompts. But what is that one skill? It's 100% communication. Communication skills, knowing how to talk to people is exactly how you talk to a machine. And, you know, they're not, you know, can't believe it. Like communication skills are something that we struggle with, you know, as humans.

And not everyone born with that skill set is a skill set that needs to be refined. but for those that have that skill set, that felt like, oh, I'm on the outside looking in because I pursued a different career other than technology. Now was your moment. Now was your opportunity to jump in. And I think that that's one of the most misunderstood things about large language models, but especially chat GPT. That's what I've used the longest.

You know, our team's been using it, not since GPT2, but, you know, GPT3. But it seems like people think like, oh, I'm not a technical. person. I'm not a developer. So, you know, this whole, they think of a large language model or open AI, chat EBT, like coding, but it's not like that. It's talking like a human. You know, abroad, with all the talks that that you've done to people and teaching people, what is the most misunderstood thing when it comes to prompting? So in these early ambassador calls, I would meet with an engineer from, you know, India or even Israel somewhere not. in New Jersey where I'm at and they would they think fast like engineers think they're they're

brilliant thinkers but their their minds are moving so fast and they think in code and they think in commands and like you know branches so they're like what what's what's the command what's the key stroke to to get this output right and I'm like well show me what you put and they're like you know give me this right or like enter that right just one word word or two words. And I'm like, where's, where's your prompt? And they're like, that's it. That's the prompts. And I'm like, no, no, no, no, no. Just back up. You have to talk to the machine. Right. What do you mean? Tell me what you want to do. Well, you know, I have this business and I wanted to generate this. And, you know, when people enter this, this needs to be the output. I'm like,

that's exactly what you tell the machine. I'm like, turn around and just explain your problem. and explain your use case and explain your ideal scenario for the output to the machine. And it's a people pleaser. It's going to learn your pattern. It's going to learn your tendencies. And it's going to want to match what you expect of it, your desire. And if it gets it wrong, you just reinforce with a little bit more feedback. And you say, okay, well, you're close.

I love having this conversation with teachers. When I go to education conferences, I just did one on Monday, Tuesday. and they're experts at prompt engineering already because they're educating young people and reinforcing them with feedback and they don't realize that that's the same skill set that you use for prompt engineering. This is what we're going to learn today. When I give you this, you give me this in return. Let's do it together, right?

So it's like a shared, guided, independent model. Let's do it together. I'm going to show you how to do it. let's let you try it a little bit while I give you some feedback and reinforcement. And then at some point, you're going to do it on your own. That is in a nutshell, prompt engineering. Oh, so you're saying I shouldn't just be buying, you know, someone's prompt book for $100 with $10,000 best prompts.

So that's not the way to get it done is what you're saying? I mean, you could because sometimes when I look at those prompts, you know, I'm like, okay, well, what can I take from this, but then flip it to my use case. Right. Like what are the elements in here that maybe I didn't think of? So I do that a lot with AI art prompts. So I'm an AI artist and, you know, I've done magazine covers. We actually did the first AI art magazine cover for Entrepreneur Magazine. Oh, I saw that one. That was amazing. No, that was a lot of fun. Shout out to Matt Sinclair on my team who led the creative direction. But sometimes when I look at other prompts from a from a art perspective, I'm like, oh, they mentioned like a lot. lighting. I didn't mention the lightning in my prompt. I'm like, let me add that. Or like they mentioned like shutter speed or, you know, a certain camera. Like they'll mention like a LACA camera. I'm like, oh, I didn't even think. Like this thing knows camera models. Like, let me throw that in, you know, because that'll be that one nugget that just gives it a little different feel. Or the last one was just like hyperreal,

like just like a straight up photo, but they put style raw. I'm like, ah, okay, if you don't want the AI filter, just tell it, just give me the raw unfiltered, you know, version. So that you can always learn from other people's prompts and we all look at each other's prompts, but sometimes your prompts are, that's, that's yours. You know what I mean? Like sometimes you don't want to share your prompt that I'm, I'm in that camp. Yeah, same. For me, if I'm being honest, early on, I tried other people's prompts and I found that prompting, at least in my opinion, is not a shortcut. It's an essential skill that you have to build. So my hot take is, man, if you're just using someone else's prompts, all you're doing is you are robbing yourself of

the opportunity to properly learn the most important skill set moving forward because, hey, whether you are using chat GPT or not, it's like think of Microsoft 365 co-pilot. Prompting is coming to your operating system. So you have to become better at it. Like what's, What's your thoughts on that, Abron, just like prompting as an essential skill and even just, again, the heightens of communication in that? At least at the basic level. Not everyone has to be an expert prompter. But I think the same way, something that I explain to a lot of folks is that your resume, right, before you get replaced by AI, you're going to be replaced by those who are augmenting their productivity with AI. And remember in that section on your resume, that little section where you said, oh, I know Microsoft Office and I know PowerPoint and I know Excel.

I know Photoshop. Like that section is going to be replaced with I know ChatsbyT. I know Mid Journey. I know Adobe Firefly. I know Tomey how to make an AI presentation. I use Canva. Like all that, they're going to want to know what AI tools you're comfortable with and you're fluent in. And how could you use those skills?

here to be more productive at our company. And yeah, well, there's, I mean, we all use Excel, but we're not the Excel experts that every company has. Like, there's going to be different levels and there's going to be a spectrum of proficiency with mid-journey, proficiency with prompt engineering and with chatty, you know, but they're going to want to know, do you at least have a baseline understanding of this tool? So that way, if I give you a project that's likely going to require you creating, you know, spreadsheets at a high level of output with Chad GBT or with one of these tools, you got to be ready for it. You know, and that's a thing. For those of you who are still holding off, I'm like, at some point, it's going to become a baseline

skill set. Yeah. I'd argue, hey, and maybe this is abroad just because I'm talking about it every day, I argue it's already like a required skill set, right? Like this is, if you look at, you know, studies on job postings and the economy and in the market and everything like that, this is the most in demand skill that there is right now in terms of supply versus demand. More and more companies are needing people, you know, whether you are in with the term prompt engineering or not. But it is a high in demand skill right now.

What's the one thing, Abron, that you think, because not everyone's a great communicator, right? Like, I'd like to think I am. I have a master's degree in journalism. So I'd like to think I'm an okay communicator, but sometimes I'm not. But maybe what are some tips that you have for people, specifically when it comes to using communication as that secret prompting skill? What's some tips that you have for people that maybe aren't the best communicators? Adobe just introduced an entirely new way to create, bringing the power and precision of its

creative suite into one conversational experience. Meet Firefly AI assistant, now live in the Adobe Firefly app, the all-in-one creative AI studio. Powered by Adobe's creative agent, Firefly AI assistant lets you start with your vision, just describe what you want, and shape the outcome as it takes form with the assistant. The assistant orchestrates multi-step workflows, drawing on 60-plus pro-grade tools across Adobe Creative Cloud apps, including Photoshop, Illustrator, Premier, Lightroom Express, and more to help bring your ideas to life. You can also get started with creative skills, a growing library of pre-built workflows for common creative tasks like batch editing photos, creating mood boards,

portrait retouching, and creating social variations. Every step the assistant takes is visible so you can refine, redirect, or take over at any time. You stay in the driver's seat as the creative director. Adobe Firefly AI assistant now in public beta. See it today at firefly.adobie.com. I think we don't realize the, I don't want to use the word expert, just like the communication skills that we do have, right? And, you know, my children struggle with it.

I see young people struggle with it where sometimes the way you communicate verbally is not how you communicate with a pencil or even in typing, right? Like there's something that gets lost in that processing, right? That language processing that goes down to your family. fingers. And I think this technology, you know, solves for that when it allows for, you know, speech recognition, transcribing, right? Sometimes you just need to talk to, you know, a voice model and say, all right, well, here's what I want. And you just describe it in your own style. The best thing for me, with my own struggle with communication skills, is chatDBT understands my intent. So I don't have to be

You don't have to say something verbatim and trigger or a wake word like with Siri. Or like, oh, I said that wrong. I got to say it again. Or I said this wrong to Alexa. I got to say it again. I could spell things incorrectly. I could just just say things in a short form. And chat Chiquotis is like, I get it.

Like it puts his hand up. It's like, I get what you're trying to say. Like this is kind of messy, but I can see through this mess what you really want. of this. And if it's easy, you just talk to it. You know, you set the voice function on and you just have a conversation with it. There's this clip. I wish I had it here. There was this woman laying in bed and she was trying to understand currency, right? U.S. currency and like global currency. And the way she asked Chad GBTBT, you were like, it was like four-year-olds trying to understand currency. And, and Chachapit figured it out. They were like, I know what you

want. You're trying to understand how a currency of like a million pesos translates to one dollar in the U.S. Here's how that works. But the way she asked her question would have broke your brain. And I think we all need to be comfortable with so many neurodivergent learners, with so many people with different skill sets and different abilities from an accessibility standpoint, verbal language, you know, and typing. To be honest, as crazy as this guy is, and I'm not, biggest fan with Elon Musk I saw on one of his podcast I think was the Rogan one the reason he invented NeuroLink the BCI the brain chip interface is because and if you ever see him in an interview when he gets asked a question he pauses for like 10 seconds to process and then he responds

right and then he said the reason he invented this chip is that how he thinks about in output, the loss between that going to his thumbs to text something, or to his fingers to type something, something gets lost in the communication and the translation from how his brain is thinking about it to how his fingers is processing it, right? The dexterity to try and keep up with his brain. So he just wanted something where you can communicate right from the source. That's why he came up with the brain chip, right?

That happens in different spectrum, different variations to a lot of people. where like you know what you want to say and it's up here, but you can't just get it out, right? Maybe you can get it out speaking, but you can't get it out writing. Maybe you can get out writing, but you can't get it out speaking, right? And this is just an assistant. Like, just think of as an assistant. Like, wherever you're lacking, it can pick up the slack and supplement where you feel like you need the most help. And I don't know how they programmed it into GPT4, but it understands your intent.

Right. And then the intent is there. And it's like, okay, now that I know, is it. this what you meant? And you say, yes, that's exactly what I meant. Okay. So we're going to go with this prompts based on what you, what I felt you meant that you're verifying. And let's take it from there. Sorry for the long winded answer. No, that needed to be said. I mean, like Brian is saying here, such great insights. Ben saying already one of the best everyday AI shows ever, which I agree, FYI. So I always tell people because, yeah, we, we teach thousands of people prompting. I say talk to

with like a human, people are confused. They're like, no, you have to speak to it in code. And it's like, no, you don't. You're right. But I like to tell people, and if, if, if you're like me even still, hearing things from a brown right now and being like, oh, wow, that's, that's, I never thought of, you know, prompting like that. I like to say that when you start a new chat inside of chat GPT, it has the capacity of like the floor in the ceiling. And it's your communication skills that are going to dictate where your outputs are going to go. So, Abron, you said something there that I've never thought of, like teachers being great prompters because they're constantly having to explain something to young students that are

still developing their communication skills. What other maybe, you know, types of jobs or what other, you know, kind of skills related to communication can ultimately really help like that in the long run, getting better results? So I say this a lot on stage. But I just saw it echoed yesterday in a tweet by Blake Lemoyne. And for those of you who don't know who that is, he's the one that was kind of like the whistleblower at Google around like is AI sentient. Right. So he's kind of a quirky guy on Twitter.

Not always a fan of his tweets, but the one thing he did get that was on target with, you know, something that I say on stage was English is the new programming language. And, you know, those who were worried that they didn't know or in coding language, and we're on the outside looking in, now is your moment. And for those of you who were middle career, maybe already a professional in the humanities, or you're a social worker, or you're an English major, shout out to all the English majors.

There we go. They're like, I don't want to learn Python. I don't want to learn JavaScript because I don't, just to get that bag in the tech industry. Like, I did so much with my English career, with my English major, doing work in humanities or doing work in communication, I don't really want to reskill all that and give up all that to join this tech boom. You don't have to.

Like those who studied the humanities that studied in communication skills that were English majors, now is your moment because you are that missing piece in the future of prompt engineering. So educators are a great example of that because they're constantly, like you said, they're constantly having to teach a concept and reinforce a concept and give feedback to a particular concept to a young learner. Every language model is a young learner because they're learning your concept from scratch, your intent, the instructions that you're providing it. And it has great potential, just like all those students, right, has great potential to deliver at an expert level, but it's not going to get there until you give it, you know, the initial instructions.

So authors, you know, the lead prompt engineer on my team was a TV writer. The ambassadors, the other ambassadors, and I call it the AI Avengers because they look around. I'm like, you're all are such a quirky bunch. They're painters, their producers, their poets. I kid you not. Shout out to Mersmensch, you know, Vlad, he's Mersmensch on Twitter and on Medium. He's an amazing writer, but he's a poet. And every time a new model comes out with opening eye, the first he tests, is how good is it at writing poetry?

And he's an artist as well. And these are all the other expert prompt engineers that I came up with in the face. And I'm like, y'all aren't the same Silicon Valley nerds that I was expecting in this room. So you're making my imposter syndrome kind of like calm down because I live in this hipops syndrome space because at this point, and now it's like an inside joke, it's like I refuse to code just to see how long it's going to take for this technology to reach me as a non-coder before I have to give in and finally take that Coursera course on JavaScript. You know, like everyone's like, hey, you should at least learn something.

I'm like, nope. I'm over here hanging out as a non-coder and seeing how, you know, how interesting, you know, how creative I can get with this technology as a no-coder. And so far, so good. Oh, man, it's so good. I love people are already taking, taking your taglines here, you know, loving the AI Avengers. Every language model is a young learner. Abron's just spitting out like chat GPT quotes that you should put on your wall if you want to get better, right? So I would be kicking myself, Abron, if I didn't ask you quickly about the GPT store, right? So, so yes, you just got all, if like if you're listening to this, you just got like an advanced level education on effective prompting with communication. But with these new GPTs, you know,

which have been out for now about two months and the GPT store, how was this going to change how the everyday person does business? You all heard my hot take. I said, I think eventually this is going to be bigger than the iOS Apple App Store. What's your thoughts on how this is going to change how work gets done? A lot of ways. And I don't know how far out I want to make these kind of predictions. Oh, bring them, bring them.

We're here for it. Yeah, no. So I was there. You see the shirt, right? I was at Dev Day with Sammy, the announcement of the store and, you know, the GPTs. and some things he said on stage were kind of like reeled back. But we're like, right, well, we announced it. And that's, that's something that I don't like across the entire tech ecosystem

that I appreciated more with opening eye. They're like, as a starter founder, someone told me, like, don't wait for 100% for something that you could put out 80% today. Right. And that's so true for the perfectionist. and all of us to like not put out something that we just keep refining and refining because we feel like, it's not ready. It's not ready yet.

Who cares? If it's a concept that you think that people will respond to, half baked and all, just put it out there. Right. And because you're going to get a lot of feedback from users on how to further refine that, right? You're not the only one to contain. Open AI did that with every model.

They're just like, look, we're making this thing. It's not all the way there. But here you go. Try it out. Right? And then we hear a tweet, oh, you know, is it the end for chat TBT because this new thing came out, right? Like Elon Musk came out with something or Apple's going to come out with something. And I'm like, where is it?

Let us try it. You keep putting out these press releases of announcements of its coming, but let us determine. And like, you're not the one to determine, is it better than chat TV? Let us determine. Give it to us. Put it in our hands. Right. So I have friends that send me all these robots.

I'm like, I don't care about these robots. Until I can get a robot in beta form that I can test out in my house, it's all still science fiction. Right? Until we can all test out these robots in our house, it's all still science fiction. It's just an announcement. So when I saw the announcement of the store, I'm like, awesome, when can we get access? And they're like, oh, they gave us access to the custom GPs before the store came out so we can test what it was like. I'm like, okay, that's cool.

Then let's try to see what the potential of this is. what you're going to see happen in, I don't know, five years time probably is the, you're not going to need websites or apps anymore. Like at some point, the concept of an app, the concept of a website is just going to go away. You're going to speak to a GPT for everything that you would need an app for there, for everything that you would need the website for. You can, you'll have multiple GPs, and at some point you're just going to have one GPT that knows all those, all those sites. You're going to have one communication point with the internet rather than searching the internet, right? Which is, it's going to cause trouble for Google because their number one moneymaker is selling ads against search results, pages and pages and pages of search results. What happens when you need just one search result?

What do you sell ads against? Where's the real estate to sell ads against when you just get one result back, right, from an AI? Yeah. And so these stores, what I tell teachers when I, and I keep referring to the teaching because I just did this keynote on Tuesday, what teachers do, they play the passive role where like an AI technology comes out, any new technology comes out. They sit and wait. They're like, all right, I'm waiting for someone to come out with one for the classroom. Right. And I'm like, why wait?

You don't need to wait. If you, you don't even need to buy anyone else's software, just go make one for your students with a GPT. right so instead of them trying to bake in a preset prompts to assume what they think your students need they don't know your actual students so there's no way for them to truly personalize this app to your students because they've never met your students you know your students so go make a gpt specifically for your class of 25 students and related to the iEPs the differentiated line their neurodivergent learning you know sally needs this you know johnny needs that so make a gpti julyt just us for your crew and then for your other class that comes in with the other 25 make a GPT for

them that's specific to their needs right so instead of having a big company like a Nike like oh all these companies are struggling they still haven't adopted GPT a lot of them have bandit what are you doing to your employees you're setting them back so far right just from a skill standpoint right you don't need one GPT that knows everything at Nike. You develop one GPT for the marketing department. You develop another one for the product design department. You develop another one for the sports ambassador department that works with the athletes. Right. Like every department is going to have its own custom GPT to better understand. So it's unlimited. It's unlimited the things that you can do with a GPT. Right. You take this GPT for technology

and apply it to all things. Now you have to look at the world through GPT lenses and say, okay, what can I do it by GPT that? What could I do if I GPT that? And it's unlimited. So the volume of the potential of of valuable apps, meaningful apps, meaningful GPs is going to eclipse what's in the iOS app store. Because to be honest, when you search for a freaking app in the app store, the first two or three are relevant. The rest is just spent. The rest is just like ad fodder from like some Russian bot. You know, yeah, it's, it's just, that's a good point. There's so much garbage out there.

There's so much garbage out there, right? And I love Abram, what you said about make a GPT for this and this and this, right? Like I tell people for every single specific skill set that you do before GPs came out, I said, have a chat dedicated to that. Build that chat up, take it from student to expert for every single skill set. So I love that you just said, do the same for GPTs. So we've covered so much here. Abron, I wish we could talk for hours because I think the audience here would appreciate that.

But as we wrap, what is that one most important thing? So we talked about the secret skill sets for more effective prompting is communication. What is the one specific piece of advice when it comes to communication leading to more effective and more impactful outputs? What is that one piece of advice you have? Bravery, man. like this this space now is is intended to cater to folks that are just willing to just try it out and so many people have created now courses you know training track certifications

you know cheat sheets from a prompt engineering standpoint and how to use gpte we did not have that luxury as as the early folks and the ambassadors and the original prompt engineers and and I'm probably one of first prompt engineers is probably the first prompt engineer of color um out in the space and in the beginning you know what we did we stayed up to four in the morning with trial and error trying this trying that and if that worked you know not knowing what we're going to get back and then you have like a light bulb moment when you get a certain output back and you're like Oh, that's that's it. That's what I need to do with this. And guess what? When a new technology, every three months a new technology comes out. And everyone in the industry, Sam Altman, Satya, Elon and me and you are all starting at the same point with this new technology. Right. And it's let's all figure it out together. So they have when a new technology comes out, they have no other advantage over you in how to figure out this technology. And. And it's it's let's all figure it out together. And And if you're too scared to try it out, then you're already behind.

But like if you're out there just trying it, trying to break something and demoing stuff, I can't tell you how many people have gotten jobs from just their demos, just trying something out, posting their demo online. Someone sees their demo and they're like, hey, I love what you did with this. Can you make this for me? And I'll pay you either for the job to build this thing at scale for myself. Or I love the skill set that you've demonstrated by this demo. come over and work at Google.

Come over and work at Metal. So just go out there and try it out and post their demos and share it with the community. And then you'll have some amazing feedback from the community. And then you'll find your tribe. You'll find other people. You'll find your ambassador group that's like, oh, I'm trying to tackle the same thing. Let's do that together. And soon enough, one of you going to get a call from like a big brand.

It's like, hey, I saw your demo on Twitter on LinkedIn. Can you build that for me? and you're like, yes, absolutely. So you always say yes. You say yes. And then you figure it out after. You say yes. And then you call the people in your tribe and you're like,

yo, I got this big gig. You want to go in with me and let's go build this thing together. It's not about resumes. No one's going to ask like where you're five to 10 years of prompt engineering. There's no bachelor degrees of prompt engineering. It's still just like in real time. So don't worry about credentials. Don't worry about experience.

Just go try something out and go have fun with it. Y'all, if that doesn't inspire you, come on, be brave, say yes, communicate like a human. That's how you dominate in 2024 with chat GBT. Abron, thank you so much for joining the show. This was an instant bangor, instant replay. Can't thank you enough for stopping by. So, appreciate you. Have a good thing.

Have a good weekend. All right. And hey, as a reminder, there was a lot there to unpack. Go to Your EverydayAI.com. Every single day, we recap the podcast. put in other great resources and insights. Maybe we didn't have time to get to. So make sure you do that and make sure you join us again next week and every day for more

everyday AI. Thanks y'all. Meet Firefly AI Assistant. Now live in Adobe Firefly, the Allman One Creative AI Studio. Just describe what you want to create in your own words and the assistant handles the rest, orchestrating multi-step workflows across Adobe Creative Cloud apps, including Photoshop, Premiere Express, and more in one conversational interface. You direct the outcome while the assistant accelerates execution.

Stay in control with the ability to step in and refine at any time. See it today at firefly.adobie.com. And that's a wrap for today's edition of Everyday AI. Thanks for joining us. If you enjoyed this episode, please subscribe and leave us a rating. It helps keep us going. For a little more AI magic, visit Your EverydayAI.com and sign up to our daily newsletter so you don't get left behind.

Go break some barriers and we'll see you next time.