Alastair McDermott 0:00
I have a special episode of the podcast for you today. This is the first episode of my new podcast called The AI powered thought leader. And I’m going to run it here for you today on The Recognized Authority podcast, the concept of AI and thought leadership, there’s an inherent conflict in that. And I’m really interested in exploring that. I’m also really interested in using AI. As an aspiring thought leader, as somebody who wants to build authority through content, I think it’s super important for me to understand the nuances around this topic. And no better way than to speak with the top leaders in the field. But people who are creating AI, people who are using AI, I want to speak to them, and find out how they think about this issue.
So I don’t want to make The Recognized Authority podcast all about AI, which is why I’ve created a separate podcast just for this topic. I’m planning to run it for about eight to 12 episodes for season one of the AI powered thought leader, and I’d love to get your feedback on it, it will be totally driven by feedback as to whether I can initiate more of those episodes. But rest assured, if you’re a fan of The Recognized Authority, and you’re not at all interested in AI, I won’t be I will be copying every podcast episode over that’s not my plan. What I might do is if there’s something particularly interesting, I might run it on The Recognized Authority feed, but for the most part, I’m going to run the two of them separately. So without further ado, here is the first episode of the AI powered thought leader.
Alastair McDermott
Can thought leaders use AI in an authentic way? Or is that a contradiction in terms? How can we use AI without compromising ourselves as thinkers and pioneers and thought? How do we resolve the tension that occurs between these conflicting concepts? I’m going to speak with experts in thought leadership and AI. I’m going to demonstrate some of the tools and processes that I use myself that use AI. I’m going to talk to others about the tools that they’re using. And I’m going to explore some of the cutting edge of technology that’s coming online. Now, this show is going to cover practical issues, as well as some of the more difficult questions about ethics, intellectual property and thought leadership, how we bridge that gap of, can we use AI in an authentic way for thought leadership? That’s what we’re going to talk about unexplored in the AI powered thought leader.
Alastair McDermott 0:53
I think that the reality is that just like in every other field, the integration of AI and thought leadership is inevitable. It’s more a question of how it happens, rather than if it happens. And you might not be concerned about AI making your ideas obsolete. But you might be concerned about the fact that AI can generate really high quality content in seconds. And if you think that it can’t, then you maybe you need to take another look at some of the tools. And we’re going to do that on this podcast. And what then becomes of the human journey on the intellectual labor, creating and cultivating these insights, is our role to be reduced to curator or editor of machine generated content on machine generated thinking. If AI can help with distribution, and idea generation and content generation, where does authenticity and originality fit in? Does AI undermine our value and commoditize our work? Does it marginalize our human effort? Will it be impossible to tell? What is authentically human versus artificially created? And does that even matter? But first, I’d like to define what is thought leadership? And I’m going to ask a friend of mine, and please just bear with her. We’re on a little bit of a slow connection. So it’s gonna take her a second to answer, but she’s pretty smart. And I just want to get her perspective on this. Hey, I’d like to have a quick conversation with you about AI and thought leadership for my podcast. Is that okay?
ChatGPT 2:23
Absolutely. That sounds great. What specific aspects of AI and thought leadership would you like to discuss?
Alastair McDermott 2:30
Well, first off, can you define thought leadership for me, I’m really interested in a definition of thought leader and thought leadership.
ChatGPT 2:44
A thought leader is recognized for their expertise and perspective that contribute to the advancement of their field, often influencing trends, innovations and best practices. They share their knowledge through various channels, like articles, speeches, and social media, aiming to educate and inspire others. Does this help clarify the concept for you?
Alastair McDermott 3:07
Yeah, it does. I’m interested and maybe concerned about the tension between the concept of being a thought leader, and the credibility and authenticity that comes with that. And then the concept of using AI assistance in creating content and specifically and creating thought leadership content, because it seems like those two things are at odds. Can you tell me a little bit more about how you think about that?
ChatGPT 3:38
That’s a really interesting point. The tension between thought leadership and using AI for content creation is indeed a nuanced issue. On one hand, thought leadership is deeply tied to personal expertise, experience and authentic insights. It’s about bringing something new and valuable to the conversation, which is inherently human. On the other hand, AI can assist in various ways, like enhancing the efficiency of content production, offering data driven insights, and even suggesting novel ideas based on vast amounts of information it can process.
Alastair McDermott 4:14
Okay, so can you tell me what is the most important thing for me as an aspiring thought leader in my use of AI and how I approach it?
ChatGPT 4:30
The most important thing as an aspiring thought leader using AI is to ensure that your unique voice, expertise and authentic insights remain at the forefront of your content. Think of AI as a tool to augment your abilities, not overshadow them. Here are a few tips. One, use AI to handle research and data analysis, giving you more time to focus on interpreting the findings and adding your personal insights to leverage AI for content suggestions, but always infuse the final output With your experiences perspective and voice to maintain authenticity, three, stay informed about the capabilities and limitations of AI in your field to ensure accurate and credible content. In essence, it’s about striking a balance, where AI enhances your work, but doesn’t dilute your personal touch and the value you bring as a human expert.
Alastair McDermott 5:21
Okay, so that was dual purpose, I wanted to get a definition of thought leadership at the start of this podcast so that we have something to refer back to and but I also wanted to demonstrate to you where the cutting edge is right now of AI in terms of interaction, and that sequence was recorded. It’s not edited in any way, I know, there’s a gap between me speaking and then the response that it waits half a second or so for me to stop speaking. And then it goes off, it uploads my voice up onto the servers, a transcribes it. And then it goes through what I just said, and then figures out how to answer it. And then it translates that back into sound. So that was all done live. That wasn’t like the voiceover intro. What you heard at the start of this episode, is something where I took a script, and I put that into a tool. And I said, Hey, I want you to read this out and give me the sound file for it. That wasn’t what I just did now with this conversation about thought leadership that was completely recorded live, and in one straight through uncut session. So that’s where the cutting edge of these tools are right now. And that’s what I find really fascinating is that we are now at the point where we can have this conversation back and forth, and get really solid, good answers to a conversation that we’re having. And I use this tool all the time now, particularly when I’m driving, or sometimes when I’m cooking in the kitchen. And I get it to help me with recipes and suggestions and things like that. So those are, you know, like that’s the, by the way, just so in case you’re interested in testing this out. That’s using the ChatGPT app from OpenAI on my iPhone. And so that’s the latest version that I’m recording this in March of 2024. So that’s where it’s at. Now, in early days of, of AI, really, I think this is going to get much better and better, which is very exciting, and also very scary. And that’s why I think it’s really important that we learn more about these tools, but how they work, we think about how we integrate them, we think about how we use them how we acknowledge our use of them. You know, that was something that that ChatGPT suggested there is talking about authenticity, and that’s one of the things that I really like about doing this particular podcast is I can be very transparent and honest and straight straight up about telling you, you know, all of the things, not that I wouldn’t want to do that otherwise, but you know, it is a consideration where, you know, we use a tool, for example, if we use an AI now, do we need to think about okay, do we acknowledge that we used it? So for example, if I use Microsoft Word with spellcheck, you know, in 2007, I didn’t acknowledge Microsoft Word spellcheck in my writing do I need to do if I ask ChatGPT to do a spelling and grammar check? If I ask it to reword something, do I need to acknowledge it? So you know, there’s these kind of nuanced things that we need to figure out that are not so straightforward. I had a great conversation with my friend, Joe Cassia, bona. And I’m going to run that podcast episode on this podcast at some point, because it really helped to develop my thinking about this. And I think that, you know, there’s a lot of nuance to this discussion that I think needs to be aired. So I’m going to be talking to a lot of people who are experts in AI, people who are just using AI a lot people who are thought leaders, and I’m going to be talking to them about how they think about all of these things, because I think it’s something that we really need to think a lot more about, discuss and figure out. You know, there’s a lot of other issues that need to be figured out with AI. But at least we can approach on this podcast, we can approach how we can think about using it for thought leadership. Okay, final thing before I wrap this up, I want to give you a quick rundown of the tools that I actually used in making this episode. And it’s important to note that this is also available as a video. So wherever you got this, if you’re accessing the audio only version of the podcast, there is a link in the show notes somewhere to access this on YouTube. And you’ll be able to see what I’m talking about. So I want to give you a rundown of all of the tools that I used. And if I go back to the very start of the planning and ideation, I started planning this while I was on a drive last week cross country and I was brainstorming and using the paid version of ChatGPT as an app on my phone, I had my headset in. And I was just using the conversation feature of ChatGPT in order to have a conversation and start to plan out the podcast. And it was just a slightly longer version of what I just did with you earlier on where I had that conversation back and forth. I And so I started to do planning for the podcast in that way. Now, there was another thing that I used, which is part of ChatGPT, which is called a custom GPT. And this is where you can make your own version of ChatGPT as a chat, where you give it your own information and documents. And I made one of these with my books. So for example, in particular, I’ve read a book called 33 ways not to screw up your business podcast. And obviously, that’s about planning and creating a business podcast and mistakes that people make. And there’s also a companion workbook called your podcast launch workbook. And so I use this custom GPT. And I was having a conversation with this custom GPT, in particular, to help plan out my podcast because I have a lot of information on there about planning a podcast. And so what I was able to do was get ChatGPT using my own podcast planning and information guides to actually help me plan out everything that I needed for this podcast, and walk me through step by step through the process. And so we ended up with a table, you know, rows and columns, with all of the planning all the things I need to do on a to do list of items. And this was all done completely hands off while I was driving. So that was the basic planning done using ChatGPT. The next thing that I needed to do was I needed to create some initial images, some artwork. So I did actually ask ChatGPT, again, using the dolly version of the image generator, so there’s an image generator built into ChatGPT, called Dali. And so I use that, I also use a tool called Midjourney, which is another image generator, I think it’s a bit more advanced than Dali. But it’s also harder to use, just because of the way that we access it currently through discord. So I use that tool, I use both of those to create some images for the podcast and create some like the title images and cover art and things like that. So that got me to the stage where I had most of the planning done most of the kind of the the basic assets for the podcasts in general. Okay, so the next thing I wanted to do was, I wanted to actually start recording the voiceover intro. So what have a voiceover intro where there’s a, somebody introducing me on the podcast. And what I like to do is like to have that person be the opposite gender to whoever the host is. So because I’m male, I wanted to get a Female voiceover, if it was a female host, by the way, I’d recommend that it’s a male voiceover, just for that contrast, and just to break up the audio a bit for the listener. So I took the script of the of the voiceover intro that I had written with the assistance of ChatGPT. And I put it into a tool called 11 labs. And I tested a few different voice types. And eventually, I picked the one that I’m using here.
Voiceover AI 12:51
This is a demo of me using 11 labs to convert text to speech for the AI powered thought leader. So
Alastair McDermott 12:58
now from 11 Labs, I have an mp3 audio file of the intro script. And so now what I want to do is create some video images to go along with that, and also some background music. So just to start with the background music, I tested a few different AI music generators. And so the one that I used in the end, I think it was called Bhumi. I tested one called Splash, one called iveragh. And I wasn’t happy with many of them. But this one gave me kind of the feel that I was going for this kind of interesting, maybe slightly eerie, but kind of just kind of low key audio, a kind of a low key introduction. And so we have that voiceover background music, we’ve got the voiceover script itself. And so the next thing I wanted to do was I wanted to create some actual images, some some images representing thought leadership in particular. And so went back to brainstorm with ChatGPT. Specifically, I asked it for suggestions for iconic thought leaders from various different stages of history. And I gave it some examples. Like I said, for example, Isaac Newton, Leonardo da Vinci. But I also wanted to make sure that women were represented. So I asked him specifically for some suggestions for that. And so it suggested, for example, I Patea of Alexandria in the Great Library, and Mary Wilson craft, one of the thought leaders in women’s rights, she wrote thoughts on the education of daughters in 1787. So now I have some really great iconic thought leaders to represent in this video. And what I wanted to do next was create the actual pictures and the video. So what I did was I asked ChatGPT, to use dolly to generate some images of the thought leader created in the style of drawing a recording that they had available to them in the time. So for example, there’s a like a hand drawing of the ancient Greek agora, where Socrates and Plato might have spoken with other philosophical leaders. With the image of Einstein, for example, I asked for it to be generated in the style of a black and white film camera that might have been used at the time. So that got me now still images of each one of these thought leaders. And I could have put this together, this would have been good enough with the background music to put together a slideshow style. But I wanted to, I wanted to make it a bit more than that, I wanted to add some motion into it. And so I use a tool called runway, which is a video generation tool. And you can actually give runway a text prompt and ask it to generate video for you from that. But it wasn’t crazy about the quality of video that it created from that. So what I did was I gave it the images as input. And so if you give an input image to runway, it can add some motion and movement into the image that you give it. And so I tested that with a few different things. And it worked very well. It gave me a short, maybe four or five second video clip for each of the images that I generated. And then I manually stitch those together, one by one in order, actually an order of the real world timeline. So starting with the Greeks, and then Alexandria and then DaVinci, and then Newton, Einstein, and so on. And then I actually just for fun, I added a futuristic robot and the human having a discussion, kind of like that’s the future of AI and thought leadership. So I put all that together, I run the the voiceover intro with the background music. Welcome
Voiceover AI 16:26
to the AI powered thought leader. This is the show that helps thought leaders and aspiring thought leaders to explore the challenges and contradictions that occur at the intersection of AI and authentic thought leadership. Here is your host, Alastair McDermott.
Alastair McDermott 16:42
So if you’re watching the video, you’ll see that this video is far from perfect. In fact, there’s some glitches that you can see, like, for example, Einsteins face is definitely not perfect. But it’s still pretty good. But here’s the really key part. So in the context of everything that I just described to you start to finish in terms of making the video, I did all of that in under two hours. And that’s not because I’m amazingly skilled or anything like that, it’s simply because the tools are available to do these things quickly. And if you know how to put together these basic tools, you can do stuff like this very quickly. And so for me, it’s the accelerating effect of this. And that, you know, that’s the real power. So that’s a rundown of all of these tools. And that allowed me in the course of you know, a three hour drive. And then a morning, with with my computer in the office, put together pretty much everything that you see here, I’m going to give you a list of all of those tools again, and I’m going to link to all of them in the show notes. So I’d be more than happy to answer any questions about AI, any thing that we’ve covered today, and I’d love to get your feedback, I’d love to get your thoughts on this. And the amount of feedback and shares and comments and things like that, that kind of engagement that will tell me how much effort I should put into this podcast. So if you do like it, please do share it and tell people about it. So please stick around. I hope that you enjoyed this first episode. And I’m going to bring you some more great episodes with some great conversations with people who are absolutely at the forefront and cutting edge of this. So thanks for listening. Thanks for watching, and see you in the next episode.
Voiceover AI 18:20
Thank you for tuning into the AI powered thought leader. This show depends on your reviews. And we’d greatly appreciate it if you could take a moment to rate and review our show in your podcast app. Your support means we can keep bringing you more of this great content
