She’s Running a Business, Writing a Book, and Getting a PhD—with ChatGPT - Ep. 11 with Anne-Laure Le Cunff

[00:00] I'm doing a PhD, writing a book, running a business, I have a team to manage, having to recruit someone and writing the job description, admin stuff, even grant proposals. So honestly, I don't think I would be able to do everything I'm doing at the moment if ChatGPT didn't exist. It's saving me so much time. And several times a week, I'm thanking the creators of ChatGPT for making my current life possible. [00:30] . [00:33] Hey, I want to just take a quick break from this episode to tell you about a podcast you should know about. It's hosted by Nathan LeBenz, who's actually on this show and did one of the most popular episodes we've ever had about how to use AI as a co-pilot for the mind. Nathan hosts a podcast called The Cognitive Revolution, where he interviews builders at the edge of AI and discusses the profound shifts that it will unlock over the next decade. He talks to the researchers and entrepreneurs that are shaping this moment, like Logan Kilpatrick of OpenAI, who I interviewed for the show as well. Eugenia Kudia of Replica and Suhail Doshi of Playground. [01:03] To listen to the show, search for Cognitive Revolution, your podcast player. All right, now let's get back to how do you use ChatGPT. And Laura, welcome to the show. [01:11] Thanks so much for having me. [01:13] Of course. Yeah, it's so good to have you. We've been friends for a while. We've been following each other on our internet newsletter productivity journeys for a while. And it's really great to get to sit down. For people who don't know you, you are a neuroscientist, a writer, and an entrepreneur. You run an excellent newsletter and community of which I am a subscriber called Nest Labs. You're also pursuing a PhD in neuroscience.

[01:38] And you're writing a book. So you are officially like, I think I'm busy. You're officially like the busiest person that I've ever met. And I'm always so impressed with everything you do. It's so amazing. [01:48] Thank you. Yeah, I have lots of different interests, so I am a little bit busy at the moment. [01:56] Maybe we should start there. Like, how do you get so much stuff done in a day? Honestly, I... [02:04] This is very relevant to this show. And I swear I'm not making it up just to make it relevant. But I don't think I would be able to do everything I'm doing at the moment if ChatGPT didn't exist. As you mentioned, I'm doing a PhD, writing a book, running a business. I have a team to manage, a bunch of things to do. And there are so many things that would have taken me hours before. And that now take me maybe 10 minutes. [02:34] that adds up, right? Just all of this time that I'm saving boring stuff sometimes, like having to recruit someone and writing the job description, it gets 80% of the way there by using ChatGPT. Admin stuff, even grant proposals, like sometimes I use it for that. So it's saving me so much time and [02:55] Several times a week, I'm thanking the creators of ChatGPT for making my current life possible. [03:03] That's so funny. I swear this was not discussed beforehand. I didn't pay you to say that, but it makes me excited to hear that because I...

[03:14] A, I think it's just great that it is furthering your creative life. I think that's a key thing that I feel about it that I want to bring to the people who listen to this. And so it seems like you feel that too. And then B, I'm just excited to see how you use it. Because maybe I'll pick up some things that I can use. Maybe I'll get a PhD or something. [03:37] Yeah. [03:38] So maybe we can, maybe we can dive into that. Maybe we can dive into a little bit of the, uh, some of your, your use cases for it. Um, [03:49] Do you want to start with, I know you said one of the things that you use it for is research, like talking to research papers. And where are you getting the papers from? Do you have some sort of Google alert set up or some search somewhere that feeds you the papers? Yeah, so I have an alert that feeds the papers into my inbox. So I receive it over email and I can have a quick look. [04:13] Very often, just from the title, you can know that maybe that has nothing to do with the research that you're doing. And if it's relevant, then I'll open it, download the PDF, which there are various ways to do. I have access to all of them because I have an academic email address. But if you don't, there are other ways to get access to these PDFs. And you can upload it to ChatGVT and ask your questions. [04:36] Got it. That's really cool. Okay. So basically you're getting these papers in your email, you're scanning through them, you're doing like a first little triage yourself just on the title. And then if you're interested, you're like, okay, I'm going to upload. So it looks like you have a paper here that you're going to show us. What is this paper?

[04:51] So this paper, I'm just going to demo it with one of my papers that I have published because I didn't ask for permission to another researcher to upload their papers. And people can be a little bit worried when it comes to research and rights and redistribution. So just for the sake of explaining how it works, I'm going to upload one of my papers. I am giving myself authorization to use this paper for this show. Great. I love it. And so the first thing you want to do is obviously to upload the paper. [05:21] here, I have uploaded the paper as a PDF. And then you can ask it a question, something I have found, which is a bit silly with ChatGPT. But if you don't tell them to answer the question based on the uploaded PDF, sometimes they will just ignore what you've uploaded. So when I type the question, I always say, based on the PDF attached, [05:45] please answer the following question. [05:51] we can ask something like, what are the key considerations to take into account when implementing [06:02] a neurophysiolo... Oh, this is a long word. Physiolo... [06:07] measure of cognitive load in ADHD. You don't need to necessarily like understand what the question is. I'll still explain because it's not that complicated, but when you want to measure cognitive load, which is the mental efforts that you put into doing something, there are different measures that you could use. You could use eye tracking, you could use electroencephalography, you could use fMRI. There's lots of different ways of doing it. And you have some considerations that

[06:37] Thank you. [06:37] if the participants have ADHD versus if it's just neurotypical participants. So that's a question we can ask to this paper, which was a review of all of the different measures used in ADHD. Before you ask the question, it sounds like one of the things you do first is you just review like what is in the paper? Like, is it relevant to you? Do you have like a thing that you usually say for that? [07:02] So I always read the abstract before I upload a paper here. There's no point uploading something that has nothing to do with my research. So I always have a sense that it is at least relevant to my field. [07:16] of research and then the questions I asked allow me to know if it's relevant specifically to my research. Okay, got it. Yeah, without having to read the entire paper yet. Okay, cool. [07:28] Thank you. [07:29] So I press enter and send it. [07:33] ChatGPT is reading the document. [07:36] Thank you. [07:38] Thank you. [07:40] And then we get an answer and it gives you a bullet point list of all of the different considerations to take into account. Hmm. [07:48] based on the paper. [07:50] And what do you think of these considerations? [07:53] And they're actually relevant and they are the ones that are in my paper, which I can tell you now, I wouldn't necessarily be able to tell you if it wasn't mine, but because I wrote it, I can confirm that this is exactly what's in the paper. And it's very helpful because as you can see, I get four bullet points.

[08:13] Instead of, I think this paper is 30 pages. Right. So four bullet points with this answer. And you can keep going and you can ask more questions saying... [08:26] Am I the only one who's weird? But I always say thank you. I always thank ChatGPT. So I say thank you. [08:34] And I say still based on this PDF because sometimes it forgets. [08:39] How has eye tracking been used to measure cognitive load in ADHD? [08:49] Thank you. [08:50] Thank you. [08:53] Thank you. [08:54] And so, again, [08:57] It's censoring and it's, yeah. [09:00] telling that pupil deletion, fixation patterns, saccadic movements, definitely things that are included in this paper. [09:08] So it all makes sense. So this is great. And if... [09:12] Obviously, I know the answer already, but if I didn't with this, it would be enough for me to at least know that this belongs in the to read pal and not in the I don't care pal. [09:24] Thank you. [09:27] And do you use it like once you're in the middle of reading something, do you use it to look things up or sort of do a deeper dive or do you find that you don't need it for that? [09:37] Oh, no, that happens all the time when I'm in the middle of reading a paper and sometimes I...

[09:46] I generally don't understand what the author is talking about. It's especially true if it's from an adjacent field of research where we're kind of talking about the same things, but they don't necessarily use the same words that I do when in cognitive neuroscience. And so I know we're talking about the same thing, but I don't understand what they're saying. And so what I can do, same is upload it here and ask questions. You know, you can... [10:11] I really like explain me like I'm five, where it is like, explain me like I'm five. What is this author saying? Or tell me what were the findings? What were the limitations? And I can even use it as a translator asking, can you translate this in a language that I can understand from my field in cognitive neuroscience? So it can really be used as a kind of translator for research papers as well. [10:37] You're so right. This is you're hitting on so many points that I've been I've been talking a lot about on this podcast and writing about a lot. And it's so great to see that that you're you feel it, too, because like the like the key underlying thing that I think is going on here that people might miss is. [10:54] I think ChatGPT is an incredible tool for human coordination, allowing humans to work with each other. [11:01] Um, [11:02] Because we have, basically we have all this knowledge that's all out there. And there's so much knowledge that like, [11:10] A single human cannot even know what it is, like know even a small percentage of it, let's say. [11:15] And what ChatGPT is able to do is find the right

[11:21] little bit of knowledge [11:23] compress it and reformat it and translate it so that you can understand it and use it in your context. And one of the like really, and you know, I think thinking of ChatGPT as a summarizer is something that we're maybe a little bit familiar with, but one of the really interesting things about what you said that is a nice twist too, is that it translates for you, but the thing that people miss is that it translates from English to English. And what I think ChatGPT lets us see [11:53] of English that are spoken by many different sub-communities who all have their own ways of talking about things. And the fact that we have different versions of English makes it harder for us all to work together. And ChatGPT, as this universal translator, [12:10] is able to allow someone like you who's working in cognitive neuroscience to like understand the words and conventions of a different community. And that's like, that's just going to be net beneficial to progress for humans. [12:23] Absolutely. And I love that kind of lateral translation from one field to another. But also you can use it in a more vertical manner where, for example, you know, when you're like a second year PhD student and you're reading a paper that has been written by a professor in neuroscience that has been in the field for 15 years, they are, without even realizing it, maybe going to use more jargon and it's going to be a little bit more difficult for you to understand.

[12:53] or maybe they're even going to use concepts that you haven't even studied yet at school. And so, again, you can have a little bit like the explain me like I'm five, but you can go like, explain me like I'm an undergraduate psychology student or explain me like I'm a product manager at a tech startup or explain me like I'm insert whatever you are, what your role is and what your current knowledge is. And so that can also be this vertical translation that's filling the gap between the two. [13:21] with the knowledge that you have today and that additional knowledge that is in this paper, this article, etc. But that's a little bit out of reach at the moment. Right. [13:32] That makes perfect sense. I think it's so valuable because previously... [13:40] you might read something and not understand the terms and then end up having to spend like, [13:47] a day like looking up each individual term or like trying to find something that that could fill in the gaps because there's probably something that does fill in the gaps, but it's really hard to find. And chat GPT just like does that without really even blinking. And yeah, I think that's amazing. [14:00] Yes. Yeah, I have another example of this where when I submitted a paper for peer review, one of the peer reviewers came back and said, [14:09] the comment was... [14:11] But when, [14:12] what does it mean based on this theory of dyslexia, basically? And I had never heard of that theory. And if you don't know the theory, that comment... [14:21] Makes no sense. [14:22] Because you're like, what do you mean? What do I mean in regard to that theory? What part of the theory and what?

[14:28] And I actually copy pasted that comment from the reviewer in ChatGBT and ChatGBT was like, oh, the reviewer probably means this because that's the part that a lot of researchers are still debating and you're making a claim here. [14:42] And maybe you should not sound so sure what you're saying, because this is something that is still a topic of debate. [14:50] And see, this is an example where what... [14:53] I don't even know what I would have typed in Google to get an answer to this. [15:00] That makes total sense. Yeah, there are so many of these like un-Google-able Google blind spot things that it sort of fills in. I love that. Did you just, did you copy paste any of its responses back to the reviewer? Did you spend some time thinking about it? No, because first, ChatGPT does sound like ChatGPT. So I think anyone would know that even though it is getting a little bit better. [15:23] and I didn't upload the entire paper at the time, so it was lacking context, but at least [15:30] I understood the question. [15:32] And so I could address the feedback, whereas before that, I was literally staring at that question from the reviewer. [15:39] and had no idea where to start. [15:41] That's great. That's great. I love this use case. I know you have some more stuff to show us. So if you're cool with it, I see one of the things you said that you use it for is deep research on online ghosts. And I'm very curious to learn what that means. Yes, it is actually a little bit adjacent to what we just talked about, where sometimes you don't even know what to Google.

[16:11] results. [16:12] And you know that knowledge has to be somewhere on the internet. But somehow it is not part of your circle, of your map. It's a little bit like... [16:25] you know when you played like games that map-based games like Age of Empires or games like these and you can only see the places that you have explored already so you have no idea what beyond this so it's a bit like that and so those online ghosts they are traces of their existence you know somewhere this information is available but you keep on googling and you find links but they go [16:55] but they didn't link back to the source where they found it. And so you can't find the answer to your question. [17:01] And the example that I want to share has nothing to do with neuroscience. [17:09] I'm French Algerian, and I've been trying to reconnect a little bit with the Algerian side of my culture. [17:18] And one of the ways of doing this for me is to learn a little bit more about Algerian cuisine. I've been eating a lot of Algerian food when I was at home as a kid, but it was always the same basic stuff. And I've discovered as an adult that Algeria actually has a very rich culinary culture with lots of different dishes that I have never heard about. And so I'm trying to learn more about them and I'm even trying to make some of them.

[17:43] And something I discovered recently is that [17:46] Algeria, [17:48] consumes a lot of cheese. They make and eat a lot of cheese, which is funny for me being half French, because I thought that was a very French thing. But apparently, Australian people also do this. And there was this specific cheese that I found. [18:01] that, [18:02] Seemed very interesting and not that complicated to make, but it was impossible to find a recipe for it. I tried in English. I tried in French. [18:11] I could not find anything. [18:13] And I'm going to show you a little bit [18:16] how [18:17] I managed to find it and then I published a recipe in English because I wanted to contribute back to the Internet, even though I don't even know if anyone is going to ever look for it. I love that. Wait, like I'm sort of curious. [18:31] How did you become informed of this cheese so as to know that you would want to find a recipe for it? I was reading an article about Algerian cuisine in general. [18:41] And there was just one paragraph saying, and Algeria is one of the biggest producers of cheese in Africa. They love cheese. They have so many different ones. And Algeria. [18:53] I had never heard of that. I was never served cheese at home as a kid. [18:58] So it was completely new and that's when I fell into a rabbit hole of figuring out the entire cheese industry in Algeria. Okay, and what is this specific cheese called? [19:10] It's called the Camarilla. Camarilla. Camarilla. Yeah. And it's made with goat milk. And it's very, very simple. You can make it in a couple of hours. And the way you serve it is with honey.

[19:24] and some pistachios and tea. [19:26] And no bread. You just eat the cheese like that. And is it like, is it sort of like a chef? Like, is it... [19:33] This is very soft. Or is it harder or what's, yeah. [19:38] It's very soft because you don't age it. So it's, yeah, it's very soft. I'm going to, yeah, I'm going to show you and we can, I can describe it because I know some people listen to the audio only. So I initially found about this cheese with a different name, Tekemarit. It has two names because you have Arabic and Berber people in Algeria. So you have two languages. And because it's a cheese that was initially made by Berber people from the north of Algeria, they call it Tekemarit. [20:08] and so as you see what's the recipe to make Tech Emeritus at home? I'm sorry but I wasn't able to find a specific recipe for Tech Emeritus. [20:18] It's very rare that you ask a question to chat GPT, [20:21] And, [20:22] Literally, it says it doesn't know. [20:25] Um, yeah. [20:27] And so then I give it a bit more information. I'm like, here's what I found on Wikipedia about the cheese, right? And so I'm like, this is the cheese. I put, it was on the French Wikipedia. There's nothing on the English Wikipedia. On the French Wikipedia explains a little bit more. And then ChatGPT goes, thank you for the information. Now that I have this, I can tell you these are the ingredients and here are the instructions. [20:51] But I'm reading the instructions and I'm like, that doesn't really make sense. And so I ask, are you sure you'd make the cheese first, then mix it with the leben, which is one of the ingredients?

[21:02] ChatGPT says, "You're correct to question that. My previous description may not accurately reflect the traditional method of making ticket rates." [21:11] So we have a little bit more back and forth. And then I realized that this cheese has another name. So I tell ChadGPT, I found another name for that cheese. Does that help with finding a recipe? Please have a look in French and in English. [21:26] And so then it looks like it's finally understanding what I'm talking about. So the recipe is starting to make a lot more sense. And it also links to the source. But then I noticed that it contradicts itself with something it said before. So... [21:46] There's one recipe where there's one ingredient that's mentioned, and then there's another recipe where that ingredient doesn't exist. So I'm asking, ChildGPT is so nice with me saying, you're absolutely right. I apologize for the confusion and updating the recipe again. At this point, I'm a bit tired, so I just check before I go further with this. [22:05] So there's no cooking involved, I ask. [22:09] And it says, yes, it says it's just heating the milk. [22:14] But there's no actual proper cooking involved. So I'm just going to spare you the entire very long conversation that I'm having. But the breakthrough moment was when I asked it to look it up in Arabic. [22:29] which didn't occur to me before because I don't speak Arabic. My mom didn't teach it to me.

[22:35] And so I just, I was sticking to the two languages that I know. Wait, can I ask you a question? Like, um, when it, like at this point, cause it had given you a recipe, it had given you a couple of different recipes before. Um. [22:49] It seemed like the recipe that I had just given you was like pretty much right. But were you still sort of suspicious? Like it wasn't quite. [22:57] It wasn't quite right. Yes, I could tell that it was hallucinating part of it. And so the ingredients sounded right, but the order, the steps... [23:08] felt a bit wrong and this is why I spare you that entire part but I asked a bunch of questions about how to make other types of cheese and that didn't match it was [23:18] It would have been a really weird cheese if you did it with these steps. Not that I know anything about cheese. Well, now I know quite a bit after this conversation, but at the time I didn't. And so I was definitely suspicious that something was wrong with it. I was getting closer, but that was not the actual recipe. [23:35] And this is when I asked it to check in Arabic and it found... [23:41] A YouTube video. [23:44] which I didn't even know ChatGVT could do this until this conversation. So it found the video and I watched it. You can see a little bit what it looks like. Sorry, this is so funny, the transition.

[24:07] So that's the video. [24:14] Bye. [24:17] Yeah. [24:17] And this is something that you just never would have found. Like, how could you, you couldn't Google for this really, you know? [24:24] No, I couldn't Google for it. It's in a language I don't even... [24:28] speak, I wouldn't even, you know, I was already struggling with the name in French and English of that cheese. So no idea how to write this in Arabic. [24:39] And again, it's a cheese where there's very little information online. So... [24:44] there's no way I would have found that video without ChatGPT. And the part where I was incredibly lucky here is that the video... [24:53] actually has no voiceover and it's all... [24:57] "Subtitles: Explaining the Steps" [25:00] So what I did is that I used the camera of Google Translate. [25:06] No way. To watch the video. [25:09] and translate the subtitles to English. Oh my God, that's amazing. That's so cool. Like, were you just taking pictures for each frame? Or were you like, did you download the video? Like, I don't know how Google Camera works, to be honest with you. [25:23] So it's live. So I was posing, translating with the camera. You don't need to take a photo. You just need to point your camera at whatever you're looking at. And I had ChatGPT open in another window and I was just typing things there in the text box, but in a very messy way, because the next step was to ask ChatGPT to clean it up and format it as a normal format.

[25:46] like recipe instructions. But yes, that's what I did with the Google Translate camera. That is the best. That is so cool. I love it. Can we see what came out? [25:58] Yes. [26:00] So you can see here, I say thank you because I still thank ChatGPT. I always do that too. I agree with that as a best practice. [26:08] You never know what's going to happen in the future. So I say thank you. Here's the transcript of the video. And as you can see, it's really just bullet points. It's very messy. I didn't change anything from the direct translation of the subtitles to what I copy pasted into ChatGPT. And then I asked it, can you clean it up by combining steps, removing unnecessary information, fix the grammar where I needed, and fix the spelling of Camarion? [26:38] throughout because I butchered it when I was typing it. [26:43] And voila, the recipe that I obtained after hours of collaborative work with ChatGPT. [26:53] I love this. This makes me so happy to see. It's such a cool process, right? Like there's this thing that you wanted and the information is out there. [27:02] And you couldn't have found it before. It found you the information and then it translated it for you and put it into a format that you can use. And then the kicker is you put it back on the Internet. [27:12] Um, like it's now on the internet and now anyone can find it. I love that. That's such a good story. Thank you. It's, uh, as I posted it on Twitter and I was saying I was supposed to write a research paper, but I felt like the internet needs this a lot more.

[27:29] Did you make it? How was it? I haven't actually bought goat cheese. It's, um, sorry. I'm, I haven't actually bought goat milk. It's in my fridge and it's my weekend project for this weekend. [27:42] uh i i have the the solution that you need to to do the fermentation process i even have the i ordered honey from algeria which arrived a few days ago i'm taking this very seriously imported algerian honey yeah i love that um well if if you do make it this weekend you should definitely send me pictures and we'll put it in the show notes we'll put links to it in the show notes so that [28:12] Yes. I think like this kind of reminds me of another like little soapbox I've been on recently. And you're just doing this so well that I feel like I need to point it out, which is [28:24] I think people... [28:27] They use ChatGPT for something like this. They realize that it's sort of like hallucinating a little bit. And then they just give up and they're like, ah, this doesn't work. And I think one thing that people who are good at this do is they act like model managers. And by model manager, I mean, you use a lot of the skills that a manager in like a company would use in order to get ChatGPT to do something. [28:53] the thing that you want or get the result that you want. And so the first thing that you do, [28:57] is you have a good sense for, um,

[29:01] when something doesn't make a lot of sense. Like you have a little bit of a sixth sense for like when the person that you asked to go do something, like it comes back and it's like not quite right. Same thing for ChatGPT. It's like not quite right, right? And then instead of throwing up your hands, what you do is you kind of like go in a couple different directions to try to like nudge it. You know, you like ask about other cheeses to like get your own knowledge up to speed in the area. And you can kind of trust that. And then you kind of like think about other things. [29:31] Thank you. [29:31] trying to find it in Arabic, it will like learn, it'll know how to do the right thing. And I think that that's such a smart... [29:38] such a smart way to think about it. It's definitely the best way to get the best out of people that you work with. And I think it's also definitely the best way to get the most out of ChatGPT. And you can see the results here. It might seem like a simple thing, but this is actually really cool. And I'm really glad you shared it with us. Thank you. Yes. And it definitely feels like [29:59] managing someone. And it's true when you manage someone, it's actually always a little dense collaboration. You have to listen. You have to also help be supportive. [30:12] Um, so it's, uh, yeah, I never thought about it this way, but it's definitely the way it feels working with chat GPT. Yeah. Yeah. You also have to say thank you. And you do that a lot too. So, um, you gotta be nice to your chat GPT, you know? Um, cool. Uh, well, that was great. Um, I love that, that, that was a good online ghost. Um, I, yeah, I want to, let's, let's keep going. So

[30:38] Another thing it seems like you use this for is you say to delegate tasks. Delegate is to [30:45] is to delegate tasks that are sort of outside of your circle of competence. So like, tell me about circle of competence in case people aren't familiar with that phrase. And then tell me like what kinds of tasks you tend to delegate. Yeah. So the circle of competence was a concept that was developed by Warren Buffett and Charlie Munger. And they used it initially to... [31:06] in relation to investments, knowing when making an investment fell [31:12] inside or outside of the circle of competence, which is very helpful for you to know what kind of risk you're taking here, being aware of where you're stepping outside of that circle and taking a bit of a bigger risk. [31:24] And maybe you need to bring some outside opinions to help you make that decision. Or when you're right... [31:30] in the bull's eye of your circle of competence and you have higher chances of knowing what you're doing when it comes to investments. And I find it really helpful in general for work and collaborating with other people, just knowing what is my circle of competence, what is outside of my circle of competence. And it doesn't mean you need to stay in your circle of competence, but just being aware of it again. And I find that there are lots of tasks that are outside of my circle of competence where [31:57] I don't feel the need to expand myself. [32:00] my circle to include those skills. I don't feel like that's where I want to spend my time, my energy, and my creativity. And if it's something that's going to be very long term, I'm probably going to hire an actual human being to work with me on this project. But if it's for a very quick thing that I just want to do right now, ChatGPT is amazing for this.

[32:23] And one example that I wanted to share with you is very recently, I attended a workshop with Nate Cadillac and Johnny Miller that was all about YouTube thumbnails. And I think that's a great thing. [32:35] My YouTube thumbnails were so bad, so, so bad, because I made the mistake that a lot of people are making, but I would spend so much time researching, scripting, shooting the video, editing it. [32:46] And then five minutes before uploading it to YouTube, I would think, oh, no, I forgot about the thumbnail. I would put something together very quickly. So during that workshop, I wanted to experiment and just do one round of redesigns very quickly. And I'll probably in the future work with someone longer term to really create something much better. But to me, it was a way of understanding the process and fix it in the short term. I love that. Yeah. [33:14] go for it. And I was going to ask, should I share my chat GPT or do you want to say something? No, no, no. Like, I love that. I mean, I'm, I'm really, if you can tell I'm like leaning, I'm like a little closer to the mic right now because like, I need to know this. So like, I want to know how to make my YouTube thumbnails better. So, uh, this is, I'm right there. I'm glued to this. So let's, um, let's, let's move into the, like, into how you did it. Like, um, you know, it sounds like, it sounds like you had a chat with chat GPT about improving your [33:44] how that went. [33:46] Yes. So the first thing I did was to give a very, very detailed brief to ChatGPT. And I asked it to be a YouTube thumbnail strategist. I literally said, you are a YouTube thumbnail strategist. I love it. And your role is to help me come up with a short design brief for a YouTube video thumbnail based on the transcript I will provide.

[34:06] please make sure that you follow these two pillars. And as I mentioned, [34:10] I am not good at making thumbnails. So for these pillars, I didn't make them up myself. I follow this amazing YouTube creator. She's called Apriline Alter. And recently she published... [34:23] a YouTube video and an infographic that explains how to design great YouTube thumbnails. And she spent [34:30] Hours, hours and hours, like hundreds of hours. I can't remember how many hours, but it was a very long time. She said, watching a lot of different videos, the corresponding thumbnails from successful creators, seeing what works and what doesn't. And she distilled it in that content that she shared with everyone for free. So I printed, if you're listening to this, thank you so much. What I did is that I took those pillars that she shared and I used them as the basis to craft the brief. [34:57] for chat GPT. And the two main ones were first to create a curiosity gap [35:04] So that's showing the gap between what we currently know and what we want to know. And the second one is using scroll stoppers. And so those are like bright colors, large numbers, danger, movement, money, emotion, faces, etc. And I printed it to be careful and to not use too many of them because that can delete your brand. [35:26] And so... [35:27] After I provided this, I said, after reading the transcript, please provide me with the following. First, content. What's in there? What's the main focal point, etc. Second, composition.

[35:39] What are the elements placed? How will the terminal direct attention and to what? And third, contrast. How will the terminal pop? And this can be luminosity contrast, saturation contrast, or hue contrast. [35:52] And I, [35:53] In addition, I said, please do not suggest using people and characters in the thumbnails. And please do not be verbose because... [36:01] I tried it a little bit before and it was giving me very long answers. It was really hard to know [36:06] what to design exactly. So I wanted to really be to the point and tell me, here's what you need to design. And why do you not want to use people? So I didn't want to have to spend a lot of time taking photos of myself and, [36:22] To then design the thumbnail, I'm going to go with something very simple and scalable. [36:28] And I noticed that other channels were doing really well without showing the face of the person actually doing. [36:36] recording the videos. [36:38] And once I noticed that, I was like, oh, that's great. And that also means that I don't have to take a terrible photo of myself five minutes before uploading a YouTube video. And it always looks like crap. Instead, I can design something nice that looks consistent. And it's just a lot easier, I feel like, to... [36:57] hire a designer in the future and tell them here are the brand guidelines you don't need me you don't need to take 10 different photos that's that was why cool i love it and uh okay so it sounds like chatty bt wrote you back and and asked for the brief exactly so it said absolutely i'm ready to help you create a design a design brief based on your transcript and so what i did after

[37:27] free-floating anxiety, which is when you're feeling anxious for no particular reason. You don't know where it's coming from. And so I just copy-pasted the script. [37:38] which I'm scrolling through now so we don't have to read it. And then ChatGPT replies, and that's what's amazing is that it's really following my instructions. It's giving me the brief using those three different sections: A, the content, B, the composition, C, the contrast. [37:56] And it's giving me the main focal point, the supporting elements, and it's telling me to use different types of contrasts. [38:04] And it's explaining how this design should create a curiosity gap for the viewer. [38:12] This is amazing. Like the fact that I could get this... [38:16] Brief. [38:17] based on just pasting the transcript, I was absolutely amazed. I love that. That's so cool. I feel like I need this. You should make this into a custom GPT. [38:26] Oh, yes, actually. I mean, I would... [38:29] I would ask Aprilin to do it or ask her for her permission because a lot of the reason why this is working so well is because there was a lot of research done into what is important to include in the brief. It was fast for me to create things. [38:43] this prompt because I leveraged her research. But I think it does point to the fact that when you want to save a lot of time like this for something you're going to do a lot of times, a repetitive task, it is worth it investing in crafting a really good prompt at the beginning. And in this case, I wouldn't have been able to do it if I didn't have existing material to leverage.

[39:07] That makes a lot of sense. Yeah. I mean, definitely the specificity of your prompt is going to make all the difference. You sort of like, you get out what you put in, which had GPT. If you put in something smart, you're going to get something smart back. If you put in something dumb, dumb. [39:19] It's not going to be that smart usually. Or it'll at least be generic. I'll say that. [39:24] Um, and, um, and I'm curious, so in this chat, like it was, that is the output there. Was that enough for you to keep going? Or like, was that enough for you to go build a thumbnail or did you keep going in the chat? [39:34] That was enough. I just used that. And then I used Canva and I used it. As you can see, the next one, I say, thank you. This is great. Now please write a brief for this transcript. And I just moved on to the next one. And I did that for all of my thumbnails. That's awesome. And really, every time it was enough, I didn't. [39:53] follow to the letter exactly what it said there were times where i was like actually i don't think we need those two different elements so i'm just going to have one but it was really enough every time to give me inspiration and for me to design this um [40:09] I'm going to show you very quickly so you can also have it on the... [40:12] screen but just showing the results i want to see yeah show us show us your channel yeah [40:17] I have not subscribed to you. I need to subscribe right now. I don't post very often. Okay. I should post more often, but I'm just going to post this because this is auto start. And so it's going to be noisy. You don't need to hear me. [40:30] Sing. I started this video by singing. You didn't think you did it. That's brave. I just subscribed. Especially with my voice.

[40:40] So yeah, you can see the results here. And I don't think I would have been able to come up with those original ideas for each thumbnail. [40:49] And 90 minutes, because all of this only took me 90 minutes to create all of those different thumbnails. [40:56] And I really like them for something that I created so quickly. I think they're really good. And I think it it sort of goes to show. [41:07] When you have a smart prompt for ChatGPT for creative work, it can get you this starting point where, yeah, you're not taking the idea like totally wholesale, but you have a starting point. And so you can like tweak it in your own little, you can editorialize it like a manager would. You can be the editor and say, I don't really want this, but like this general concept is enough. And sometimes they're like, [41:28] The general concept, finding that is the thing that takes the most time. And then once you have it, it's really just like sort of tweaking and doing the actual work. And I think that's, you know, when you when you talk about chat to be saving a lot of time, this seems like a really prime example. If this only took you 90 minutes, how long would it have taken you to come up with that that general concept? It's like that's a real work block where you're like, I have to sit down. No one can bother me. I have to like think all of this through. And it's really nice that you don't have to do that. [41:56] Exactly. And it's being a YouTube person, [42:00] thumbnail designer is a full-time job and I know that an actual human being at this stage would be able to do a better job than what I did but I talked to several YouTube thumbnail designers to understand how they work

[42:14] And 90 minutes would probably be the time that they use just to brainstorm a few ideas for one thumbnail. Right. Right. Yeah. So that's another I think that's I think you're making a good point. Like. [42:27] Thank you. [42:28] The AI stuff right now, [42:31] is good, but it's not like generally going to be like elite. [42:36] at some of this stuff, but it will be good enough where, especially for people, like if you don't have a lot of time or you're sort of at the beginning, like... [42:47] you're at the beginning of doing a particular skill, it can like uplevel you. Like if you're becoming a developer and you're not a good developer, it can like let you code when you wouldn't be able to code ordinarily. Or if you're, you haven't really designed thumbnails before, it can like help you get to like a pretty good level of thumbnail design pretty quickly. But yeah, to be like an expert, that's a totally different level of investment that I think most of these tools aren't, [43:09] they're not just going to get you there automatically. You still need to be like a skilled human to do that. Absolutely. But still, like to your point, there are so many people who are running businesses where they don't necessarily also... [43:22] have the ability to hire people for everything that needs to be done in the business. And so not everyone is going to hire a YouTube thumbnail designer if they're starting a YouTube channel. And similarly, not everyone is going to be able to hire a developer to do little fixes on their website as a small business. [43:40] And for this chat, GBD is amazing. [43:43] That's great. I love it. So I know before we, we're going to do a little exploration together, but I know before we do that, we had one more ChatGPT demo to show me. I think specifically...

[43:59] Use it to write. And I think that that's going to be a thing that a lot of people watching this are going to want to know because you're such an excellent writer and you're also so prolific. Like, talk to us about how you use ChatGPT for writing. And so talk to us about how you use ChatGPT for writing. And yeah, show us how you use it in your process. Yeah. I don't know if you're familiar with the quote from GRR Martin that says that most [44:27] Writers are either architects or gardeners. Yes. [44:31] okay so but but tell us in case in case some people who are listening don't know so some writers are architects which means that they need an outline they need a plan they need to have a good idea of where they're going with the story before they start writing whereas some other writers are gardeners where the story is unfolding and emerging as they go as they write they have no idea they're almost following the characters and discovering the story as it happens [45:01] And I'm definitely more of a gardener, but ChatGPT helps me turn into an architect in the last phases of writing to really structure it in a way that can be shared with other people. [45:16] So I'm going to walk you through very quickly [45:20] It's an article I actually wrote today, and that's going to be in the newsletter tomorrow. Wow. [45:26] So, yes, it's on the website. People don't necessarily know it, but I tend to publish the article a little bit before the newsletter comes out, but nobody checks. So they wait for the article to come in their inbox. So what happens usually when I start being interested in something is that I start collecting a lot of little breadcrumbs that I add into my note-taking system in Rome.

[45:56] is the concept that [45:58] It's a phrase I created that didn't exist before, but curiosity attractors. So those ideas, those creative projects, those questions that are always on the back of your mind and you keep on coming back to, and you know, it's not the most urgent thing. You know, it's not necessarily the most aligned thing when it comes to your current work, but you know. [46:20] You know that at some point in your life, you will have to tackle this thing. You will have to work on this thing. You will have to find an answer to that question. And you keep on circling. [46:30] looping around those ideas and those concepts and those questions and they're always there they're always there. [46:39] I love that. I am. You're describing my whole life, basically. It's just me circling around a particular curiosity attractor and then being like, OK, I've sucked everything I can out of that. Like now I'm going to go on to another one or or or debating like, oh, I really want to like write or think about this thing, but I should be thinking about this thing. Like, what should I what should I do? [47:09] just to see if other people are interested in it but also if people have things to recommend maybe maybe actually this is something that someone else has already written about and I didn't know about it so I like to do a quick little sanity check on Twitter so I did that for this and I posted I want to write an article about what I think and be best described as curiosity attractors ideas we try to shake but keep coming back to diffuse obsessions creative projects we know

[47:39] you one day. And I added a little image which was actually created with chat GPT. [47:44] of how I visualize a curiosity attractor. And so it's like this bunch of spirals that keep on coming back and keep folding onto each other and all attracted to one center. [47:56] And the answers showed that first people were really interested in the topic and nobody apparently had written about it before. So it was something that was worth exploring for me. [48:08] That's great. This is, um, I, I love this and it's, um, [48:13] It's sort of a little content creator hack is rather than like stay in your lab and like spend a year working on an idea, you can just like push out like little little things here and there to like see what the reactions are, what you might be missing or whatever. Like you can really engage in the world in this like in this really nice way. And even if you don't get a react, if you don't get a reaction, like that's totally fine. You can still work on it if you like it. Maybe there's a different way to position it or phrase it or whatever. But I think people tend to be quite precious. [48:43] Like, oh, I came up with this amazing term, curiosity attractors. Like I have to like go write my magnum opus. And I really think I like I love your your move to just be like, cool, I'm just going to throw it out there. We'll see what happens, you know. And then the response is great. And now you can go write that with a lot of confidence that people are going to be into it. [49:00] Yeah, exactly. And even the questions that people ask me on that tweet very often help feed my creativity for writing the article itself. So it's a virtuous cycle, really. I ask a question, I get answers, it gives me more questions, and this becomes a source of inspiration for writing the article itself.

[49:29] How are you organizing? Like if you have an idea like this, how are you organizing all of the different like little threads that go into this idea? What is the screen I'm seeing? So as I mentioned, I'm a gardener, so organizing, not my forte. So there's really no organization. It's just that whenever I stumble upon something that I feel like is relevant, this idea, I will add it to Roam and I will just tag it with the corresponding name. In this case, Curious E.T. Attractors. [49:59] is that this then creates a page called Curious Eat Your Attractors, where all of those breadcrumbs that I have collected over the days, you can see here, this is over the course of several days, they're all created. [50:12] collected together on that one page. [50:15] So I don't need to be organized. Rome is organized for me, basically. Got it. That's awesome. Yeah. Okay. So that's what we're looking at. We're looking at all the things you've tagged with CuriosityTractors. Okay, cool. And so... Exactly. So these are all the little notes that I took over the course of a few days. Okay. And then what I do is that on the same page... [50:35] I will take all of these little notes and I will try to put together an outline. [50:42] What you're seeing here is the exact same content that you saw at the bottom. Those are the same breadcrumbs. I just moved them around. [50:50] under three sections. [50:52] introduction, buddy, [50:53] In conclusion, [50:55] That's it. At this stage, I'm really just trying to organize those ideas to see if there's any coherent manner.

[51:04] of presenting them. [51:05] Once I have this, what I do is that I export. [51:11] this outline [51:14] and I upload it into ChatGPT. [51:17] And I, [51:18] I ask it. I'm saying, I'm writing an article about what I'm calling Curious Ethiotractors. I explain what it is. [51:25] And then I say, I have attached a rough outline. Please wear your editor's hat. What aspects do you think I'm missing? Please be detailed and refer to research from theoretical concepts and or empirical evidence in psychology. [51:40] Psychology twice. I don't know why I wrote it twice. Just emphasizing psychology. Yes, exactly. Very important. And cognitive neuroscience when relevant. So here somehow it had a little problem reading the document. I re-uploaded it. [51:56] So here's what I get back from ChatGPT. So ChatGPT comes back. And I also like how it's very often complimenting me, even though I didn't ask for it. So before giving me the feedback, it always tells me that this is a solid foundation and this is great. [52:12] really good ideas in there, but you're missing those things. [52:16] And here we have eight different [52:18] different aspects of curiosity that ChatGPT is mentioning that I should maybe include in my article. What's interesting for me here, and this is why you will notice that the prompt here is a lot shorter than the one I had for the thumbnail brief, is that,

[52:36] Um... [52:37] aiming for a broad answer. I'm just trying to see if I didn't miss anything. So I don't want to be too specific. And this is why we have a very long list here. And to me, there are actually quite a few things that are not relevant, because I'm not writing an article about curiosity in general. [52:52] I'm writing an article about curiosity attractors. So here, the neuroscientific basis of curiosity, for example, I don't think is relevant for this article. I have actually written about this in the past, and I don't think this belongs in this one. [53:07] Psychological safety, also not quite sure. The two ones that really caught my eye here are curiosity and creativity and the practical implications for education and lifelong learning. [53:22] in my outline that I think are actually quite important and relevant. [53:27] So what I do is that [53:30] At this stage, I start working from Google Doc because I'm going to start writing and [53:36] I add... [53:38] the suggestions that ChatGPT has given me in my outline. That's really cool. I love that. So you're kind of using it as a little bit of a developmental editor in the... [53:50] Um, [53:51] in the sort of outlining stage of your draft to make sure, to help you look around corners and make sure you're not missing something, make sure you don't have any blind spots or arguments that you're missing. I think that's really great. I've never, I don't think I've really seen that before. I think that, yeah, I love it. [54:05] Yeah, and that's also why I insist in the prompt to only give me advice based on psychology.

[54:12] twice again in cognitive neuroscience, because I actually don't use chat GPT to find papers, because it's still at the stage where it, [54:22] also hallucinates papers a lot. They usually don't exist when it recommends a research paper, but it's very good at research fields and areas and theories in general. And then I can go and read the research myself. [54:35] But it can point at different angles and perspectives and type of research that, again, is outside of my field and I would have not necessarily thought about. So, again, like you can see the social aspect, for example. [54:49] would be more from sociologies. I wouldn't really know about this because I'm really focused on psychology and neuroscience on my side. So it's very helpful to have someone look at the gaps and just list them. That makes perfect sense. Do you, once you're like into the actual writing process, do you use it at that point at all? Or is it really only for outlining? [55:09] I use it sometimes to, again, if I read a paper, I don't really understand what it's saying. I'll still have those conversations with ChatGPT. [55:18] I also sometimes have just silly translation conversations. [55:23] Questions. You know, English is not my first language. So sometimes I still struggle with words. So I'm just... [55:30] I'm going to show you one from... [55:32] Today, I'm asking, well, I'm talking to it in French, but comment traduierais-tu to chase the brass ring en français?

[55:43] And what does that mean in English? So in English, it's to... [55:49] Chase an objective that you care a lot about. [55:54] To the point of maybe forgetting about other priorities in your life. Right. And so you're asking it. [55:59] in French to translate a English idiom for you so that you can understand how to use it in English. But you just asked it. You happened to ask it in French. Because I tried in English on Google first. [56:11] I typed, what does to chase the brass ring mean? And all of the explanation in English didn't make sense to me either. Like, what? Chase, what? And the explanation I just gave you, I think is pretty clear, but that wasn't what I was reading on Google. And so I reverted back to my native tongue to listen to where it is. And it's interesting because it's saying in French here that there's no exact equivalent. [56:35] for this expression in French. So it just gave me similar ones, but it was enough for me to understand what it meant. [56:41] Got it. That makes a lot of sense. This actually reminds me, I asked people on Twitter, what did they want to know? And I think there's a couple relevant Twitter questions for you, if we can just answer them in a sort of rapid fire way. Yeah, let's do it. So the first one is... [56:58] So Alex Exum, I think his name is Alex Exum, asked, how do you know when to use ChatGBT versus another AI writing tool? And I think the underlying premise of the question is that there's a lot of different tools out there for writing with AI. Like we at EveryWear actually incubated a tool called Lex, but there's a bunch of them. And I think Alex is curious, and I am too. Do you just use ChatGBT? Do you use others? And how do you think about how they fit into your workflow?

[57:28] GPT is... [57:29] struggling to give me good answers and I don't know why is that because I [57:36] It varies throughout a week sometimes. [57:39] On Monday, it can give me really good answers. And then on Tuesday, for very similar work, it's not doing great. I have actually no idea what's going on with that. And so when it's in a bad mood like this, I... [57:52] I switched to Cloud AI. [57:55] which is also great. And I really like using as well. I pay for both. So I have the pro version for both. And Claude... [58:04] AI actually tends to hallucinate research a little bit less than chat GPT. So if it's really research focused, I will sometimes double check with Cloud AI. And it happens also that I use the same prompts in both. [58:21] And I'll just use the answer that makes the most sense. But somehow for more casual conversations when I'm trying to understand something, or if I don't find the answer I need on Google, my first instinct will always be to open ChatGPT. That makes sense. Yeah. I also use ChatGPT as my first line of defense, but I also use Cloud for writing. And I also find it's good for reflecting on text. Like if you give it to some text and you're like, what do you think? Like, what are the patterns in here? All that kind of stuff. It's really good for that. [58:50] Yes, I really like it. And it's, the tone, sometimes it's a bit better. It sounds a little bit less like AI, I feel like. So yeah, I like both of them. And I alternate. I don't have a very rigid role when it comes to this. Okay, that makes sense. And then last writing-related Twitter question. Circe asks, and this is a good one, you'll be happy about this. How are you always

[59:20] Thank you for the first part, I guess. I read a lot and I just write about what I read. So I think that's probably why I share about lots of different topics. And in terms of AI... [59:36] Yes, definitely. My entire creative process has changed. I just showed you how it was helping me explore [59:44] different aspects see the gaps that I may be missing even at the outlining stage but I [59:52] There are even questions sometimes where I think in the past... [59:56] just thinking about how I would get the answer [1:00:01] felt like such an impossible mountain to climb that I would just park those questions and [1:00:09] to the... [1:00:10] Maybe one day. [1:00:11] I'll figure out this thing. And now I can just type it in ChatGPT, and it doesn't mean I'll have the full complete answer, but I can have a little bit of an answer very quickly. [1:00:24] And so I feel like for someone like me who's very curious about lots of different things, [1:00:30] It's been really magical to have access to this and to be able to get all of these answers so quickly. I feel you. I've been reflecting on that a lot for myself because I'm the same way. Like, I'm super curious. I always have questions about things. I always want to ask stuff. And then I'm also just reflecting on it for like my nephew, for example, he's like one and a half and he's not old enough to ask questions. I mean, at least verbally, like he can ask questions in other ways,

[1:01:00] And a lot of them are like really unanswerable. And I'm just, I've been thinking about him because I'm like, what will it be like to grow up in a world where every question is answerable? [1:01:11] Um, [1:01:12] And I think the internet and Google, it got a lot of questions, but there's still a lot that's not really answerable. But ChatGPT is just a totally new level. And I'm just so curious what that does to our minds when it's like, yeah, everything is like, we can find the answer pretty much. As long as one human knows it, we can pretty much get a good answer. That would be really interesting to see what that generation does. Yeah, absolutely. I'm very curious too. [1:01:42] the case and we've seen this evolution already in the past few decades but I think it's a really good thing also that we're going to keep on relying less and less and less on rote memory [1:01:53] And we're going to use our brain power for creativity instead. And that's going to be a really good... [1:01:58] impact, I think. Totally, totally. So this is great. I want to make sure we get to our little, our explore section. So the next step is for me to write it. And I'm obviously not going to do this live on the show, but I write in Google Docs. [1:02:14] So you can see the final article here in Google Doc. And I use my normal process where I will write and I will look up research papers, and I will talk to ChatGPT to have conversations with these papers so I can supplement. [1:02:29] My thinking here, this is very close to the outline that I co-created with ChatGPT. There's not much that has changed here. The last step...

[1:02:39] before I consider this draft. [1:02:42] finished is that I uploaded back into ChatGPT. [1:02:47] And then I ask it again if I'm missing anything, and if there's anything that I can do to improve the clarity, the flow, or the accessibility of the argument. And I ask it very explicitly to include a bullet point list of suggestions for improvements. [1:03:03] keeping it very specific to this draft. [1:03:06] rather than general things that are helpful when writing an article. That's really great. I love that. I think it's really... [1:03:16] I guess like for me, so at every like I have an editor who looks at my stuff. Do you have do you have a human editor or are you are you just kind of going back and forth with chat GPT on this stuff? [1:03:26] No, I have a human, I love that. Sorry. I have a human editor for my book, but I don't have one for anything that I publish on Nest Labs or on the newsletter. Yeah, no, that makes a lot of sense. And like, it's really nice if you're not, if you don't have that resource, like just having an extra pair of eyes, even if it's ChatGVT, it seems like it makes a huge difference just in comfort level. You're like, I don't want, I want to make sure that there's everything I can do to make this good is, is done, you know? [1:03:51] Exactly. Absolutely. So I go through the feedback that Chagibiti is giving me. And then I go back to the draft and I will sometimes make a few changes. And then voila, this is on the NetSav's website. And this is the live article. That's it. That is so cool. I love that process. I mean, I'm a fellow gardener.

[1:04:20] Um, like I can't, it's really hard for me to outline something. [1:04:24] I have to just like go write it. [1:04:25] And I found something similar where ChatGPT, like I can take a bunch of notes and like throw it in and then it writes a little bit of an outline and I can kind of see the piece. And I think... [1:04:34] Having that as a resource to become a little bit more like an architect is nice because I actually think architects. [1:04:41] are a little can be a little bit more productive because you spend less time like meandering around through like corners that don't really work in your writing. [1:04:49] And they also tend to be, the writing tends to be tighter. So even like for like fiction, for example, I think like JK Rowling, her, her plots, her structure is like super tight. Cause she's such a, she's such a, um, an architect. Whereas like, uh, George RR Martin, like his are so all over the place and meandering that he can't even finish them because he's a, he's a gardener like us. Um, and so he, maybe he needs to put his latest novel into chat GBT and see if, uh, see if it can help him get an outline. [1:05:19] adding yeah adding that is like a little skill. [1:05:22] if you're the kind of person whose brain is, is a little bit more organic and, and, and, um, spontaneous, like ours is to like, uh, to put a little bit more structure around it can like help you get the best of both worlds. Cause there's a lot of good stuff about being a gardener. Um, so I, yeah, I think it's really smart. You're using it in that way. [1:05:39] Exactly. And again, I really like truly believe that it's not fixed, that you don't have to be a gardener all the time or to be an architect all the time. And if you tend to be one, it's always nice to see what you can learn and use and leverage from the other mode of creating.

[1:05:55] Totally. Cool. Well, thank you so much for showing us that. That's very special. I think people are going to love that. So we are about to enter the exploration section of this show. And what I like to do in this part of the show is just go on a little journey together to see what we can use ChatGPT for to find stuff out about ourselves, about the world, and maybe about how ChatGPT works that we might not have expected. So yeah. [1:06:23] As part of this segment, you shared with us a meditation log you've been keeping recently, and we're going to see what we can get out of that log. So as just a starting point, tell us about this log, why you kept it, and what's in it. Yeah, so I have been for the past few years conducting little experiments. Whenever I'm curious about something, I will just give it a try and see if it works for me or not. [1:06:53] 100 articles in 100 weekdays. That's how I started my YouTube channel where I said I was going to publish one video every week for six months. And this latest experiment was to meditate for 15 minutes every day for 15 days. And it started because I heard myself saying on the call to someone that I really sucked at meditation, that I was really bad at it, that it was not for me, [1:07:23] and trying [1:07:24] And this was such a...

[1:07:26] a blatant massive demonstration of fixed mindset that i was like oh wait [1:07:33] I have to do something about this. Is this true? Is this true that I can't learn how to meditate? So I made this little pact. [1:07:42] to do this 15 for 15. And something that I've always found very helpful is to learn in public. So I created this Google Doc and every day I wrote my notes about my experiences of that day, [1:07:56] what it felt like, my questions, et cetera. And I posted it in my newsletter. And as you can see here, lots of people added comments, shared ideas, and really guided me through this journey for 15 days. So I could learn about how to meditate, what worked, what didn't for me, and also just reassuring me when I felt like I was really bad at it and telling me, no, that's normal. [1:08:26] I love that. This is sort of the same theme as putting out the curiosity tractors on Twitter. You're just so good at being like, I'm going to do this in public. I'm going to be experimental. I'm going to let the world bounce off me and that will help me be better. And I can even see Johnny Miller, who's a huge expert on some of this stuff, is popping into this doc being like, you should do some breath work. Of course, Johnny Miller would say you should do some breath work, [1:08:56] And I'm curious, like your own reflections, having done this 15 minutes per day for 15 minutes, like what did you get out of it? Where did you end up? So I finished this particular experiment about a week ago, and I'm still meditating every morning. And I think...

[1:09:12] This will be part of my routine moving forward, which I really... [1:09:17] was skeptical about before I started. But after 15 days, I have seen how it's been impacting my life in a very positive way. It doesn't take a lot of time. It's very easy. And I still feel like I have a lot to learn, but I don't need the accountability of the public document anymore to keep going. And I'm also very grateful for all of the feedback that I received, because there are [1:09:47] One thing that ChatGPT is great at is answering questions, but I didn't even know what questions to ask here. And so just... [1:09:56] typing up my notes and having people adding comments was really, I feel like a great way to dip my toes and to explore meditation without any pressure of having a specific outcome. That's really interesting. Yeah, that makes a lot of sense. And in terms of like positive effects, what would you pick as being a couple of the main positive effects you've been seeing? [1:10:18] One of the main ones has nothing to do with work. But after the Christmas holiday, I was having really bad sugar cravings. Really, really bad. I think it's because of all of the sugar that I ate during the holidays. But it was really hard to resist. And since I started meditating, my sugar cravings are gone. [1:10:39] They're just gone. And I know it must be that because that's the only thing I changed in my life. And I can sometimes think about, oh, maybe I want something sugary, but it's almost as if I can observe the thought that I want something sugary instead of being that thought and just creating that distance between me and the thought has been really helpful. And it's just a thought now. It's not a craving. It's very different. The feeling is very different. So that's one thing. And then another one is in terms of creativity.

[1:11:09] Okay. [1:11:09] just having that space to not think about anything and, [1:11:14] Well, I mean, not really, because I do think about a lot of things when I meditate and I try to bring my attention back to this like expanded awareness. But some of the meditation sessions, to be honest, felt more like a mini brainstorming session because I came out of it with like three different ideas for NET Labs. [1:11:44] weeks. And it was just this aha moment while meditating. And I know that's not what meditation is for. Yeah, exactly. It's great. I'm not complaining at all. And I really great. [1:11:55] That's awesome. I love that. So I want to see like what we can find with this. Like, let's see what's hidden in here. We have some we have some of your reflections. We'll see if it can it can give out like some of the reflections that you've already taken away. And maybe there are some other things that are hidden in here that that we don't know about. So what I'm going to do is I'm [1:12:14] fine, but I think this is short enough that it'll fit in the context window for Chat2UT. I just did an experiment where I meditated once a day for 15 minutes. [1:12:27] for 15 days and I kept a log the log is below [1:12:34] I want to bring in a few experts to help me find interesting patterns and learnings about myself from the log. Can you read the log and then recommend it?

[1:12:50] some experts that would have interesting insights for me about, uh, [1:12:58] about what's contained in it. [1:13:01] So, and then I'll say log, and then I'm just going to [1:13:06] Paste and go. [1:13:08] let's see what it does. So pasted the log and it's saying, based on the detailed log you provided, several types of people could offer valuable insights and share meditation practice. One, a meditation teacher or mindfulness coach, a professional in this field could help you refine your technique, explore different meditation styles and understand the nuances of your experience. Two, cognitive neuroscientists or psychologists specializing in mindfulness, given your numerous [1:13:38] psychologists could provide insights into how meditation is affecting your brain function. Three, physiologist or physical therapist. Considering your physical reactions during meditation, such as fidgeting, itches, and numbness you experienced, a physiologist or physical therapist could offer advice on posture, ergonomics, and techniques to minimize discomfort. It keeps going. A behavioral psychologist or habit formation expert, a spiritual advisor, a teacher from a specific meditation tradition, or a therapist with a focus on emotional processing. [1:14:08] particular kind of person that you'd like to analyze your log? [1:14:16] The one that was so surprising to me was the physiologist. That is so interesting because all of the other ones have to do with the mind, the behavioral psychologist, the cognitive neuroscientist, the mindfulness teacher. But this one is about the body. And I find this fascinating how...

[1:14:33] I haven't really thought about this, but I imagine that your posture has a big impact on how you experience your meditation sessions. And this is something I haven't been paying too much attention to, but I definitely felt a lot of physical discomfort sometimes where I just was like, you know, my leg going numb and just feeling like fidgeting and being itchy, etc. So that was that surprising. I would have not thought about this one. [1:15:01] Okay, so you want to talk to a physiologist? I think I'm going to try and figure out if, is there any physiologist that wouldn't think that this is a really weird request? No, ChatGPT, ChatGPT will do it. Let's do it. So you are an expert physiologist. [1:15:21] Um... [1:15:22] specializing, I don't think I spelled that right, specializing in mindfulness or with a, let's say with a particular interest in mindfulness, with a particular interest in [1:15:35] Um, [1:15:36] Thank you. [1:15:37] interest in and experience with mindfulness and all sorts of meditation practice practices [1:15:47] Um, I am a meditator, uh, who just did an experiment where I, um, I [1:15:57] Uh, sat, uh, every day for 15 minutes for 15 days. And I kept a log, um,

[1:16:05] as [1:16:06] An expert. [1:16:08] physiologist. [1:16:10] you to read my log and give me a detailed summary of everything you notice. [1:16:20] of everything you noticed. Be specific, detailed, detailed, [1:16:25] organized and don't leave anything out. Be direct. Okay, here's my log. [1:16:36] And we're just going to say send and we'll see what happens. [1:16:40] Thank you. [1:16:41] Okay. Your meditation log presents a detailed introspective journey through 15 consecutive days of meditation, demonstrating a progression in your practice, self-awareness, introspection. Here's a structured summary of your observations. [1:16:58] Thank you. [1:16:59] Okay, interesting. So it's giving me... [1:17:02] it's giving me a summary of your own experience rather than its experience as a, um, [1:17:09] as a meta as a physiologist and so i think it's possible that because the log is so long it sort of forgot who who who it's pretending to be um and so uh i am going to redo this um and we'll see if we can make it better see if it works [1:17:30] Thank you. [1:17:30] All right. [1:17:32] Several key observations about the physiological and cognitive responses to your meditation practice emerge. These observations are categorized under several themes for clarity and directness. Physical sensations. Okay, so it's saying things that we know. Initially, discomfort and itchiness. Initially, you experience physical discomfort and itchiness common for beginners as they become more aware of their bodily sensations during meditation.

[1:17:55] Over time, you learn to either give into these sensations, like scratching an itch, or focus on them until they dissipated, indicating an increasing ability to manage discomfort through attention redirection. Body awareness. You notice various sensations of heaviness, groundedness, and sometimes discomfort in specific areas, e.g. back pain. These observations suggest an enhanced body awareness, allowing you to feel more in tune with your physical sensations, which is a key aspect of mindfulness practice. Movement and posture. Your adjustments in posture, hand positions, and even slight movements indicate a search for comfort and stability during meditation. [1:18:25] Adaptive behavior is crucial as it shows an understanding that physical comfort can support deeper meditation states. Then it goes into some stuff about cognitive and emotional processing, environmental awareness, noise sensitivity. Your initial heightened awareness of background noise is followed by the ability to incorporate or disregard these as part of the meditation experience. It illustrates an adaptive response to the environment. [1:18:44] adaptability and experimentation. So it's, it's noticing a bunch of, a bunch of stuff around there. Um, [1:18:51] it notes your back pain and your numb leg during these sessions. And so I think it's giving, it seems like it's giving actually a pretty good summary of your journey. I'm curious, how does that strike you? Do you think it's getting it right? And then do you have any questions for it about anything related to your body or your body awareness during this practice? [1:19:19] This is super interesting to me because it's really talking about all of these different bodily sensations that I had as something positive. It's really framing it as some good me becoming more aware of my body when I'm.

[1:19:32] I was really annoyed with this and I wanted to get rid of them. So just that reframing already is very helpful. That's interesting. That being said, I would like to feel more comfortable. So... [1:19:45] It would be great to ask if there are any ways for me to feel more comfortable in my body while I'm at the day. Okay, cool. I would like to feel more comfortable in my sessions. Oh, I got to say, thank you. Got to be nice to your chat to BT. [1:20:00] I would like to feel more comfortable during my sessions as an expert. [1:20:04] physiologist. [1:20:07] Do you have any suggestions based on my log for how I could adjust my posture or otherwise? [1:20:18] or environment, let's say, or otherwise in order to be more comfortable. [1:20:26] See what it says. [1:20:29] Thank you. [1:20:29] Thank you. [1:20:31] Given the insights from your meditation log, there are several tailored suggestions that it could enhance your comfort during meditation sessions. These recommendations focus on adjusting your physical environment posture and approach to ensure a more conducive setting for your practice. Okay, so it's saying things like adjusting your physical environment, so noise management. Consider using soft background sounds or white noise to mask external disruptions. Alternatively, earplugs. [1:20:58] Two is your seating arrangements. [1:21:01] experiment with different seating positions. If sitting on the carpet causes discomfort, you might try a meditation cushion or Zafu to elevate your hips and allow your legs to rest comfortably. A meditation bench or chair can also be alternatives, especially to alleviate back pain or discomfort. Temperature control, ensure the room is at a comfortable temperature, feeling too warm or too cold can distract from your meditation.

[1:21:23] The next section is enhancing your posture. Aim for a posture that allows your spine to be straight yet relaxed. This alignment supports alertness while minimizing strain. If you're sitting on the floor, a slight forward tilt of the pelvis achieved by sitting on the forward edge of a cushion can help maintain this natural curvature. If on a chair, your feet should be flat on the ground with your back supported. [1:21:45] Hand position. You also mentioned experimenting with hand positions, snail hands and prayer hands. Continue to use whichever hand position feels most natural and comfortable. Hands resting gently on your lap or knees can also reduce strain on your shoulders and neck. [1:21:58] Head and neck. Keep your head balanced comfortably so your neck isn't straining. A slight chin tuck can help achieve a natural alignment of the head over the spine. [1:22:07] Um, [1:22:08] And then it says adjusting your approach, movement acceptance, allowing yourself to adjust your posture or scratch an itch without judgment can increase comfort. Time of day. You also noted that difference in your meditation experience based on the time of day, you might find it beneficial to meditate when you're naturally more relaxed or alert. Duration and frequency. [1:22:28] Pre-meditation routine. Engaging in a brief routine before sitting can signal to your body it's time to meditate and help ease into the session. And then exploration of styles. [1:22:38] meditation styles. I'm curious what you make of these. Are they good? Yeah, this is really good. It's funny because I actually hadn't looked at all into getting a cushion because I thought it was more... [1:22:51] decorative I guess I didn't even question it I didn't even yeah it's which sounds very silly now but now that I'm listening to this I'm like oh there's actually a real reason why people use those cushions and the tilted forward position of the pelvis that it's describing and

[1:23:10] actually does sound helpful. So I think first I'm going to get a cushion to experiment with this. And there were a few things that were interesting as well with the noise because my flat is very noisy. I live in London. I don't have double glazed windows. So I will try the earplugs as well to see if that helps. But lots of great suggestions actually. And it all makes sense based on my log and even mentioned the two hand positions that I mentioned because I call them [1:23:40] real term is just me explaining what they look like and the prior hands. And so the fact that we referred back to this, it's so nice to have feedback based on my actual experiences rather than just random tips that you would find on Google. Isn't it, isn't it sort of wonderful? Like, cause it's, [1:23:57] I think there's two interesting things to me here. One is I love the like, which expert should I ask question? Because sometimes you don't know like what you don't know. And you may not have realized that you wanted to ask a physiologist or you had these kinds of questions. And so it found the expert for you. And then the tips that it's giving you, they're not necessarily like super groundbreaking. [1:24:22] They are basic meditation tips in a certain way, but they're so... [1:24:27] They're very tailored for you. [1:24:30] And I think sometimes, you know, I've talked about this before on this podcast, like sometimes the answers that you need or the tips that you need. [1:24:40] they're, they're simple, but they're like hard to remember, or they're hard to know that that's what you need. And just having that, that resource that that can proactively be like, here's what you should do. It just like clicks in your head. And you're like, of course, I should have, I should use a cushion, or of course, I should use earplugs, but like, for whatever reason, that wouldn't occur to you in your day to day life. And it's like, so valuable just to have this little engine to like, give you those simple tips that you didn't know you needed. I just love seeing stuff like this.

[1:25:06] And also, in addition to this, even though the advice is simple, I think this is such a perfect illustration and a perfect use case because... [1:25:17] When it comes to meditation, so I'm a complete beginner. I started three weeks ago, right? And there is a lot of simple advice out there, but there is a lot of it. [1:25:26] And it's very hard, actually, for someone who's just getting started to know what is important, what is optional, what is actually going to make a difference. And as you said, it's because all of these are very simple things, but it's a thousand of them. [1:25:43] I can't implement everything. There are lots of different schools of thought when it comes to meditation as well that recommend completely different things. Say a mantra, don't say a mantra, sit on a chair, sit on the ground, do this, do that. And so what he's doing here is, yes, it's simple, but it's for me and it's answering my needs and not just giving me a general answer, which makes it very powerful. Totally. And I think it's also worth noting, [1:26:13] gather the data for it. [1:26:15] And I think people that have these like journaling or note taking practices have a real leg up here because ChatGPT gets so much better if you have more information to give it to like to work off of. And so like you wouldn't be in a position to get this kind of advice if you hadn't taken the time to, as you're going through this, record things you're thinking and feeling. I think people that I think people underrate how important and how useful it is to like have that data to feed into into something like this.

[1:26:45] I journal every day. I take a lot of notes. And I think for a lot of people who already do this, it's unlocking so many possibilities based on data that they have already collected throughout the years. And I hope that for people who don't already have either a journaling or a note-taking practice, that it's going to be an encouragement to get started with it and just start taking [1:27:15] you can implement in your work and in your life. Totally. Totally. I love it. This was a wonderful, wonderful episode. I really appreciate you coming on and showing us all the ways that you use ChatGPT, doing this exploration with me. I'm leaving feeling just excited and inspired. And I cannot wait for your book to come out. And I really appreciate you spending the time to chat with me [1:27:45] Thank you. [1:27:51] Bye. [1:27:52] Oh my gosh, folks. You absolutely, positively have to smash that like button and subscribe to How Do You Use ChatGPT. [1:28:00] Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard, but instead of gold, it's filled with pure, unadulterated knowledge bombs about chat GPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat.

[1:28:17] craving for more. It's not just a show. It's a journey into the future with Dan Shipper as the captain of the spaceship. [1:28:25] So do yourself a favor, hit like, smash subscribe, and strap in for the ride of your life. [1:28:31] And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.