Exclusive Analysis of ‘How Do You Use ChatGPT?’ With Anne-Laure Le Cunff

My take on the latest episode of How Do You Use ChatGPT? with Anne-Laure Le Cunff and the episode transcript is below for paying subscribers.

I’ll admit I was a bit surprised that Anne-Laure told me that she could only accomplish so much with ChatGPT. It seemed too good to be true, but I swear I didn’t pay her to say so—she just came right out with it. 

We covered so much good stuff in this interview, but my favorite part of it was the end. Anne-Laure has been establishing a new meditation practice, and we used ChatGPT to coach her through how to improve it. We fed it a detailed log of her practice and how she’s been feeling that she’s been keeping. Then we did a trick I’ve been meaning to do on the show for a while: We asked it what kind of expert could help her improve the most. 

It’s commonly known that ChatGPT gets better when you tell it to simulate being a particular kind of expert when it responds to you. But what people don’t tend to know is that you can ask ChatGPT which expert it thinks would be best—and then use the expert it suggests.

In this case, ChatGPT suggested that Anne-Laure chat with a physiologist (a healthcare professional focused on the functioning of the human body) to help her improve her practice. As a physiologist, it noted several ways she could make herself more physically comfortable as she meditates, like using a cushion and getting a white noise machine—things she wouldn’t have explored on her own.

The advice it gave her was fairly simple, but straightforward advice from a perspective we might not have considered is often the most valuable kind. If you’re interested in improving your use of ChatGPT, try asking it what kind of expert could solve your problem. It’ll make it significantly more helpful.

Timestamps:

1. Introduction 01:10
2. How to use ChatGPT to save time 02:11
3. Tips to breakdown research papers with ChatGPT 05:17
4. How to use ChatGPT to generate explanations tailored for you 09:38
5. Leveraging ChatGPT to find hidden gems on the internet (like recipes for obscure cheese) 19:51
6. How to create awesome YouTube thumbnails with ChatGPT 33:47
7. Incorporating ChatGPT into your writing process 51:13
8. Rapid-fire questions from X 56:52
9. Surfacing useful insights from Anne-Laure’s meditation journal 1:13:01
10. The case for journaling in the age of AI 1:29:04

Transcript

Anne-Laure Le Cunff (00:00:00)

I’m doing a Ph.D., 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. 

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.

Dan Shipper (00:00:35)

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 Labenz, who was actually on this show and did one of the most popular episodes we’ve ever had about how to use AI as a copilot 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 who are shaping this moment, like Logan Kilpatrick of OpenAI, who I interviewed for this show as well, Eugenia Kuyda of Replika, and Suhail Doshi of Playground.

To listen to the show, search Cognitive Revolution in your podcast player. Alright, now let’s get back to How Do You Use ChatGPT?

Dan Shipper (00:01:10)

Anne-Laure, welcome to the show.

Anne-Laure Le Cunff (00:01:12)

Thanks so much for having me.

Dan Shipper (00:01:14)

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 Ness Labs. You're also pursuing a Ph.D. in neuroscience. And you're writing a book, so you are officially—I think I'm busy. You're officially the busiest person that I've ever met, and I'm always so impressed with everything you do. It's so amazing.

Anne-Laure Le Cunff (00:01:50)

Thank you. Yeah. I have lots of different interests, so I am a little bit busy at the moment.

Dan Shipper (00:01:56)

Maybe we should start there. How do you get so much stuff done in a day?

Anne-Laure Le Cunff (00:02:02)

Honestly, 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 know, you mentioned I'm doing a Ph.D., 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. 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 percent of the way there by using ChatGPT, admin stuff, even grant proposals. Sometimes I use it for that. So 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.

Dan Shipper (00:03:03)

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. I think it's just great that it is furthering your creative life. Cause A, 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 Ph.D. or something, you know? 

Anne-Laure Le Cunff (00:03:42)

Why not?

Dan Shipper (00:03:43)

So maybe we can dive into that. Maybe we can dive into a little bit of some of your use cases for it. 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 alerts set up or some search somewhere that feeds you the papers?

Anne-Laure Le Cunff (00:04:06)

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 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 ChatGPT and ask your questions.

Dan Shipper (00:04:36)

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?

Anne-Laure Le Cunff (00:04:51)

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 from 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. 

And so the first thing you want to do is obviously to upload the paper. So 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, please answer the following question.” And in this case, we can ask something like, “What are the key considerations to take into account when implementing a”—this is a long word—”neurophysiological measure of cognitive load in ADHD.” You don't need to necessarily understand the question—I'll still explain because it's not that complicated. But when you want to measure cognitive load, which is the mental effort 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 you need to take into account. 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. So—

Dan Shipper (00:06:50)

Before you ask the question, it sounds like one of the things you do first is you just review what is in the paper? Like, is it relevant to you? Do you have a thing that you usually say for that? 

Anne-Laure Le Cunff (00:07:06)

So, I always read the abstract before I upload a paper here. There's no point in 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 of research. And then the questions I asked allow me to know if it's relevant specifically to my research without having to read the entire paper yet.

So I press enter and send it. ChatGPT is reading the document and then we get an answer. And it gives you a bullet point list of all of the different considerations to take into account based on the paper.

Dan Shipper (00:07:53)

And what do you think of these considerations?

Anne-Laure Le Cunff (00:05:4)

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 instead of, I think, this paper is 30 pages. So four bullet points with this answer. And, you can keep going and you can ask more questions saying—am I the only one who's weird, but I would say, “thank you.” I always thank ChatGPT.

So I say, “Thank you.” And I say, “Still based on this PDF,” because sometimes it forgets. “How has eye tracking been used to measure cognitive load in ADHD?” And so, again, it's telling that pupil dilation, fixation patterns, psychedelic movements, definitely things that are included in this paper. So it all makes sense. So this is great and if—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 pile and not in the I don't care pile.

Dan Shipper (00:09:32)

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?

Anne-Laure Le Cunff (00:09:38)

Oh, no, that happens all the time when I'm in the middle of reading a paper. And sometimes 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 it comes to 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.

I really like explain me like I'm five, where it’s like, explain me like I'm five. What does this author say? 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.

Dan Shipper (00:10:37)

You're so right. You're hitting on so many points that I've been talking a lot about on this podcast and writing about a lot. And it's so great to see that you feel it too. ‘Cause the key underlying thing that I think is going on here that people might miss is I think ChatGPT is an incredible tool for human coordination, allowing humans to work with each other because we have basically we have all this knowledge that's all out there and there's so much knowledge that like a single human cannot even know even a small percentage of it, let's say. And what ChatGPT is able to do is find the right little bit of knowledge, compress it, and reformat it, and translate it so that you can understand it and use it in your context.

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 is that there are many different versions of English that are spoken by many different subcommunities 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 is able to allow someone like you who's working in cognitive neuroscience to understand the words and conventions of a different community. And that's just going to be net beneficial to progress for humans.

Anne-Laure Le Cunff (00:12:24)

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 Ph.D. 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, 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 knowledge that you have today and that additional knowledge that is in this paper, this article, et cetera, but that's a little bit out of reach at the moment, right?

Dan Shipper (00:13:30)

Right. That makes perfect sense. I think it's so valuable because previously. You might read something and not understand the terms and then end up having to spend a day looking up each individual term or trying to find something 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 ChatGPT just does that without really even blinking. And, yeah, I think that's amazing.

Anne-Laure Le Cunff (00:14:02)

Yeah. I have another example of this where when I submitted a paper for peer review, one of the peer reviewers came back and the comment was, but 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 makes no sense, because you're like, what do you mean? What do I mean in regard to that theory? What part of the theory? And I actually copy-pasted that comment from the reviewer in ChatGPT and ChatGPT 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. And maybe you should not sound so sure what you're saying, because this is something that is still a topic of debate. And see, this is an example where I don't even know what I would have typed in Google to get an answer to this.

Dan Shipper (00:15:02)

That makes total sense. Yeah. There are so many of these like ungooglable Google blind spot things that it sort of fills in. I love that. Did you just copy paste any of its responses back to the reviewer? Did you spend some time thinking about it?

Anne-Laure Le Cunff (00:15:14)

No, because, first, ChatGPT does sound like ChatGPT. So I think anyone would know that, even though it is getting a little bit better. And second, I didn't upload the entire paper at the time. So it was lacking context, but at least I understood the question. And so I could address the feedback. Whereas before that, I was literally staring at that question from the reviewer. And had no idea where to start.

Dan Shipper (00:15:41)

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.

Anne-Laure Le Cunff (00:15:59)

Yes, it is actually a little bit adjacent to what we just talked about, where sometimes you don't even know what to Google. In this case, it's different. You know what to Google, but it's not returning any results. And you know that knowledge has to be somewhere on the internet. But somehow it is not part of the circle of your map. It's a little bit like—you know, when you play 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's beyond this. So it's a bit like that. And so those online ghosts, they are traces of their existence, you know that somewhere this information is available, but you keep on googling and you find links, but they go nowhere or someone mentions some sort of information that they read somewhere, but they didn't link back to the source where they found it. And so you can't find the answer to your question and the example that I want to share has nothing to do with neuroscience. I'm French-Algerian, and I've been trying to reconnect a little bit with the Algerian side of my culture. 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. And something I discovered recently is that Algeria 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, Algerian people also do this. And there was this specific cheese that I found that seemed very interesting and not that complicated to make, but it was impossible to find a recipe for it. I tried it in English. I tried it in French. I could not find anything. And I'm going to show you a little bit about how I managed to find it and then I published a recipe in English because I need to contribute back to the internet, even though I don't even know if anyone is going to ever look for it.

Dan Shipper (00:18:27)

I love that. Wait, I'm sort of curious. How did you become informed of this cheese so as to know that you would want to find a recipe for it?

Anne-Laure Le Cunff (00:18:41)

I was reading an article about Algerian cuisine in general. 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 I had never heard of that. I was never served cheese at home as a kid. So it was completely new. And that's when I fell into a rabbit hole of figuring out the entire cheese industry in Algeria.

Dan Shipper (00:19:08)

Okay. And what is this specific cheese called? 

Anne-Laure Le Cunff (00:19:10)

It's called kemariya. 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 and some pistachios and tea and no bread. You just eat the cheese like that. 

Dan Shipper (00:19:30)

And is it sort of like a chèvre? Is it very soft or is it harder or what's—?

Anne-Laure Le Cunff (00:19:39)

It's very soft because you don't age it, so yeah, it's very soft. I'm going to show you and I can describe it because I know some people listen to the audio only. So I initially found this cheese with a different name: Takemmarit. It has two names because you have Arabic and Berber people in Algeria. So you have two languages. And ‘cause it's a cheese that was initially made by Berber people from the north of Algeria and they call it takemmarit.

And so, as you see, “What's the recipe to make takemmarit at home?” “I'm sorry, but I wasn't able to find a specific recipe for takemmarit.” It's very rare that you ask a question to ChatGPT and literally it says it doesn't know. 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.” It was on the French Wikipedia—there's nothing on the English Wikipedia. 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.” But I'm reading the instructions and I'm like, that doesn't really make sense. And so I asked, “Are you sure you'd make the cheese first, then mix it with the leben, which is one of the ingredients. ChatGPT says, “You're correct to question that. My previous description may not accurately reflect the traditional method of making takemmarit.” 

So we have a little bit more back and forth. And then I realized that this cheese has another name. So I tell ChatGPT, “I found another name for that cheese: kamariya. Does that help with finding a recipe? Please have a look in French and in English.” 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 there's one recipe where it is 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 update the recipe again.” At this point, I'm a bit tired, so I just check before I go further with this. “So there's no cooking involved,” I ask, and it says, yes, it says, “It's just heating the milk 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, which didn't occur to me before, because I don't speak Arabic. My mom didn't teach it to me. And so I was sticking to the two languages that I know.

Dan Shipper (00:22:39)

Wait, can I ask you a question? At this point—’cause it had given you a recipe, it had given you a couple of different recipes before. It seemed like the recipe that it had just given you was pretty much right, but were were you still sort of suspicious that it wasn't quite right?

Anne-Laure Le Cunff (00:23:01)

Yeah, I could tell that it was hallucinating part of it. And so the ingredients sounded right, but the order, the steps 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 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. And this is when I asked it to check in Arabic and it found a YouTube video, which I didn't even know ChatGPT could do this until this conversation. So, it found the video and I watched it. You can see a little bit of what it looks like. Sorry, this is so funny. The transitions. So that's the video.

Dan Shipper (00:24:19)

And this is something that you just never would have found. You couldn’t Google for this really, you know?

Anne-Laure Le Cunff (00:24:25)

No, I couldn't Google for it. That's in the language I don't even speak. I was already struggling with the name in French and English of that cheese. So, no idea how to write this in Arabic. And again, it's a cheese where there's very little information online. So 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 actually has no voiceover and it's all subtitles explaining the steps. So what I did is that I used the camera of Google translate to watch the video. And translate the subtitles to English.

Dan Shipper (00:25:13)

Oh my God. That's amazing. That's so cool. Were you just taking pictures each time for each frame? Or did you download the video? I don't know how Google camera works to be honest with you.

Anne-Laure Le Cunff (00:25:25)

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 normal recipe instructions. But yes, that's what I did with the Google translate camera.

Dan Shipper (00:25:54)

That is the best. That is so cool. I love it. Can we see what came out? 

Anne-Laure Le Cunff (00:25:59)

Yes. So you can see here, I say, “Thank you, because I still thank ChatGPT—”

Dan Shipper (00:26:04)

I always do that too. I agree with that as a best practice. 

Anne-Laure Le Cunff (00:26:10)

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 needed, and fix the spelling of kemariya throughout because I butchered it when I was typing it. And voilà, the recipe that I obtained after hours of collaborative work with ChatGPT. 

Dan Shipper (00:26:55)

I love this. This makes me so happy to see it's such a cool process, right? There's this thing that you wanted and the information was out there 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. It's now on the internet and now anyone can find it. I love that. That's such a good story. 

Anne-Laure Le Cunff (00:27:20)

Thank you. 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.

Dan Shipper (00:27:31)

Did you make it? How was it?

Anne-Laure Le Cunff (00:27:32)

I haven't actually bought goat cheese—Sorry, I haven't actually bought goat milk. It's in my fridge and it's my weekend project for this weekend. And I ordered everything. I have the solution that you need to do the fermentation process. I even ordered honey from Algeria, which arrived a few days ago. I'm taking this very seriously.

Dan Shipper (00:27:57)

Oh, man. Imported Algerian honey. I love that. Well 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 people who are watching this in a couple weeks can see it. That'd be great. 

I think this kind of reminds me of another 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, I think people 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 what 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 a company would use in order to get ChatGPT to do the thing that you want or get the result that you want. And so the first thing that you do is you have a good sense for when something doesn't make a lot of sense. You have a little bit of a sixth sense for when the person that you asked to go do something, it comes back and it's like, not quite right. Same thing for ChatGPT. It's 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 nudge it, you know. You ask about other cheeses to get your own knowledge up to speed in the area. And you can kind of trust that. And then you kind of think about other things like, oh, maybe if I ask it about trying to find it in Arabic, it will know how to do the right thing. And I think that's 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. 

Anne-Laure Le Cunff (00:29:58)

Thank you. Yes. And it definitely feels like managing someone. And it's true when you manage someone, it's actually always a little dance—collaboration. You have to listen, you have to also help be supportive. So yeah, I never thought about it this way, but it's definitely the way it feels working with ChatGPT.

Dan Shipper (00:30:20)

Yeah, you also have to say thank you, and you do that a lot too. So you gotta be nice to your ChatGPT, you know? 

Cool. Well, that was great. I love that. That was a good online ghost. Let's keep going. So, another thing it seems like you use this for is you say to delegate tasks that are sort of outside of your circle of competence. So tell me about the circle of competence in case people aren't familiar with that phrase. And then tell me what kinds of tasks you tend to delegate. 

Anne-Laure Le Cunff (00:30:58)

Yeah. So the circle of competence was a concept that was developed by Warren Buffett and Charlie Munger and they used it initially in relation to investments, knowing when making an investment falls 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. And maybe you need to bring some outside opinions to help you make that decision, or when you're right in the bullseye 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 I don't feel the need to expand 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. One example that I wanted to share with you is very recently I attended a workshop with 

Nate Kadlac and Jonny Miller that was all about YouTube thumbnails and 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, and then five minutes before uploading it to YouTube, I would think, oh, no, I forgot about the thumbnail. And 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. 

Dan Shipper (00:33:14)

I love that. 

Anne-Laure Le Cunff (00:33:10)

And I was going to ask, should I share my ChatGPT here? Do you want to say something?

Dan Shipper (00:33:20)

No, no, no. I love that. If you can tell, I'm leaning a little closer to the mic right now because I need to know this. So I want to know how to make my YouTube thumbnails better. I'm right there. I'm glued to this. So let's move into how you did it. It sounds like you had a chat with ChatGPT about improving your thumbnails. Talk to us about how that went. 

Anne-Laure Le Cunff (00:33:47)

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 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. Please make sure that you follow these two pillars.” And as I mentioned, 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 Aprilynne Alter. And recently she published a YouTube video and an infographic that explains how to design great YouTube thumbnails, and she spent 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 Aprilynne, 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 for ChatGPT.

And the two main ones were first to create a curiosity gap. 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. so there's bright colors, large numbers, danger, movement, money, emotion, faces, et cetera. And I pretty much said to be careful and to not use too many of them because that can dilute your brand. And so 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, et cetera? Second composition, what are the elements placed? How will the thumbnail direct attention and to what? And third contrast: How will the thumbnail pop? And this can be luminosity contrast, saturation contrast, hue contrast.” And in addition, I said, “Please do not suggest using people and characters in the thumbnails. And please do not be verbose” because I tried it a little bit before and it was giving me very long answers. It was really hard to know what to design exactly. So I wanted it to really be to the point and tell me, here's what you need to design. 

Dan Shipper (00:36:15)

And why do you not want it use people?

Anne-Laure Le Cunff (00:36:17)

So I didn't want to have to spend a lot of time taking photos of myself to then design the thumbnail. I wanted to go with something very simple and scalable. And I noticed that other channels were doing really well without showing the face of the person actually recording the videos. 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 to 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 hire a designer in the future and tell them, here are the brand guidelines. You don't need me. You don't need me to take 10 different photos. So that's why.

Dan Shipper (00:37:07)

Cool. I love it. And okay. So it sounds like ChatGPT wrote you back and asked for the brief. 

Anne-Laure Le Cunff (00:37:14)

Exactly. So it said, “Absolutely. I'm ready to help you create a design brief based on your transcript.” And so what I did after that is simply copy-paste the script. So this one was a YouTube video I recorded about 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, 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. And it's giving me the main focal point, the supporting elements, and it's telling me to use different types of contrasts and it's explaining how this design should create a curiosity gap for the viewer. 

This is amazing. The fact that I could get this brief based on just pasting the transcript, I was absolutely amazed.

Dan Shipper (00:38:22)

I love that.That's so cool. I feel like I need this. You should make this into a custom GPT.

Anne-Laure Le Cunff (00:38:28)

Oh, yes, actually. I mean, I would ask Aprilynne 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 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 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. 

Dan Shipper (00:39:07)

That makes a lot of sense. Yeah. I mean, definitely the specificity of your prompt is going to make all the difference. You get out what you put in with ChatGPT. If you put in something smart, you're going to get something smart back. If you put in something dumb, it's not going to be that smart usually. Or it'll at least be generic. I'll say that. And I'm curious, so in this chat, that is the output there. Was that enough for you to keep going? Or was that enough for you to go build a thumbnail? Or did you keep going in the chat?

Anne-Laure Le Cunff (00:39:35)

That was enough. I just used that and then I used Canva and I used it as you can see in the next one. I said, “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. Really, every time it was enough. I didn't 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. 

I'm going to show you very quickly so you can also have it on the screen, but just showing the results—

Dan Shipper (00:40:18)

I want to see—yeah. Show us your channel. I have not subscribed to you. I need to subscribe right now.

Anne-Laure Le Cunff (00:40:21)

I don't post very often. 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 sing. I started this video by singing. You don't need to hear that—especially with my voice.

Dan Shipper (00:40:36)

That's brave. I just subscribed. 

Anne-Laure Le Cunff (00:40:41)

So yeah, you can see the result here. And I don't think I would have been able to come up with those original ideas for each thumbnail in 90 minutes. Because all of this only took me 90 minutes to create all of those different thumbnails. And I really like them for something that I created so quickly.

Dan Shipper (00:41:02)

I think they're really good. And I think it sort of goes to show: When you have a smart prompt for ChatGPT for creative work, it can get you to this starting point where you're not taking the idea totally wholesale, but you have a starting point. And so you can tweak it in your own little way— you can editorialize it, like a manager would. You can be the editor and say, I don't really want this, but this general concept is enough and sometimes the general concept, finding that is the thing that takes the most time. And then once you have it's really just start tweaking and doing the actual work. And I think that when you talk about ChatGPT saving you 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 general concept? That's a real work block where you're like, I have to sit down, no one can bother me. I have to think all of this through. And it's really nice that you don't have to do that.

Anne-Laure Le Cunff (00:41:58)

Exactly. And being a YouTube 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. And 90 minutes would probably be the time that they use just to brainstorm a few ideas for one thumbnail. 

Dan Shipper (00:42:23)

Right, right. I think you're making a good point. The AI stuff right now is good, but it's not generally going to be like elite at some of this stuff, but it will be good enough where, especially for people if you don't have a lot of time or you're sort of at the beginning—you're at the beginning of doing a particular skill, it can up-level you. If you're becoming a developer and you're not a good developer, it can let you code when you wouldn't be able to code ordinarily, or if you haven't really designed thumbnails before it can help you get to a pretty good level of thumbnail design pretty quickly. But to be like an expert, that's a totally different level of investment that I think most of these tools aren't going to get you there automatically. You still need to be like a skilled human to do that.

Anne-Laure Le Cunff (00:43:15)

Absolutely. But still to your point, there are so many people who are running businesses where they don't necessarily also 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. And for this, ChatGPT is amazing. 

Dan Shipper (00:43:44)

That's great. I love it. So I know before we—we're gonna do a little exploration together, but I know, before we do that, you had one more ChatGPT demo to show me. I think, specifically, you use it to write. And I think 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. 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.

Anne-Laure Le Cunff (00:44:24)

Yeah. I don't know if you're familiar with the quote from G. R. R. Martin that says that most writers are either architects or gardeners.

Dan Shipper (00:44:33)

Yeah. But tell us, in case some people who are listening don't know. 

Anne-Laure Le Cunff (00:44:39)

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. 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. So I'm going to walk you through very quickly—it's an article I actually wrote today, and that's going to be in the newsletter tomorrow. 

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 into 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 Roam. So something I was recently interested in is the concept that—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, 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, looping around those ideas and those concepts and those questions and they're always there. They're always there. 

Dan Shipper (00:46:39)

I love that. You're describing my whole life basically. It's just me circling around a particular curiosity attractor and then being like, okay, I've sucked everything I can out of that. Now I'm going to go on to another one or debating like, oh, I really want to write or think about this thing, but I should be thinking about this thing. What should I do? Yeah, you're really speaking my language here.

Anne-Laure Le Cunff (00:47:04)

So, very often when I'm curious—this is a bit meta—but when I'm curious about an idea, I post about it on Twitter just to see if other people are interested in it, but also if people have things to recommend, 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 can be best described as curiosity attractors. Ideas we try to shake, but keep coming back to; diffuse obsessions, creative projects we know we'll just have to pursue one day.” And I added a little image, which was actually created with ChatGPT of how I visualize a curiosity attractor and so it's like this a bunch of spirals that keep on coming back and keep folding onto each other and all attracted to one center. 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.

Dan Shipper (00:48:13)

That's great. I love this and it's sort of a little content creator hack—rather than stay in your lab and spend a year working on an idea. You can just push out little little things here and there to see what the reactions are, what you might be missing or whatever. You can really engage in the world in this really nice way and even if you don't get a reaction, 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. They're like, oh, I came up with this amazing term, curiosity attractors. I have to like go write my magnum opus. And I really think I love 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.

Anne-Laure Le Cunff (00:49:06)

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.

Dan Shipper (00:49:27)

I love that. So tell me first how are you—so this is in Roam. How are you organizing—You have an idea like this? How are you organizing all of the different little threads that go into this idea? What is the screen I'm seeing?

Anne-Laure Le Cunff (00:49:44)

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, curiosity attractors. What it does is that this then creates a page called curiosity attractors where all of those breadcrumbs that I have collected over the days. We can see here, this is over the course of several days, they're all collected together on that one page. So I don't need to be organized. Roam is organized for me, basically.

Dan Shipper (00:50:25)

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 curiosity attractors. Okay, cool. And so—

Anne-Laure Le Cunff (00:50:32)

Exactly. So those are all the little notes that I took over the course of a few days. And then what I do is that on the same page, I will take all of these little notes and I will try to put together an outline. 

What you're seeing here is the exact same contents that you saw at the bottom. Those are the same breadcrumbs. I just move them around under three sections: introduction, body, and conclusion—that's it. At this stage, I'm really just trying to organize those ideas to see if there's any coherent manner of presenting them. Once I have this, what I do is that I export this outline and I upload it into ChatGPT. And I ask it, I'm saying, “I'm writing an article about what I'm calling curiosity attractors.” I explain what it is. 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 and psychology.” Psychology twice—I don't know why I wrote it twice.

Dan Shipper (00:51:49)

Just emphasizing psychology. 

Anne-Laure Le Cunff (00:51:50)

Yes, exactly. Very important. “—and cognitive neuroscience when relevant.” So here somehow it had a little problem reading the document. I reuploaded it. 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, really good ideas in there, but you're missing those things. And here we have eight different aspects of curiosity that ChatGPT is mentioning that I should maybe include in my articles. 

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 I'm aiming for a broad—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. 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. “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.” So these are things that I didn't have in my outline that I think are actually quite important and relevant. So what I do is that at this stage, I start working from a Google doc because I'm going to start writing and I add the suggestions that ChatGPT has given me in my outline.

Dan Shipper (00:53:48)

That's really cool. I love that. So you're kind of using it as a little bit of a developmental editor in the sort of outlining stage of your draft, 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 don't think I've really seen that before. Yeah, I love it.

Anne-Laure Le Cunff (00:54:13)

Yeah. And that's also why I insist in the prompt to only give me advice based on psychology— twice again—in cognitive neuroscience, because I actually don't use ChatGPT to find papers because it's still at the stage where it 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. 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, you can see the social aspect, for example, would be more from sociology. 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.

Dan Shipper (00:55:06)

That makes perfect sense. Once you're into the actual writing process, do you use it at that point at all? Or is it really only for outlining?

Anne-Laure Le Cunff (00:55:15)

I use it sometimes, again, if I read a paper, I don't really understand what it's saying. I'll still have those conversations with ChatGPT. Also, I sometimes have just silly translation questions. You know, English is not my first language, so sometimes I still struggle with words. So I'm just going to show you one from today. I'm talking to it in French, but, “Comment traduirais-tu ‘to chase the brass ring’ en Francais?”

Dan Shipper (00:55:50)

And what does that mean in English? 

Anne-Laure Le Cunff (00:55:51)

So, in English, it's to chase an objective that you care a lot about to the point of maybe forgetting about other priorities in your life.

Dan Shipper (00:56:04)

And so you're asking it in French to translate an English idiom for you so that you can understand how to use it in English, but you happen to ask it in French.

Anne-Laure Le Cunff (00:56:13)

Because I tried in English on Google first. I typed, “What does ‘to chase the brass ring’ mean?” And all of the explanations 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, and it's interesting because it's saying, in French here, that there's no exact equivalent for this expression in French. So it just gave me similar ones, but it was enough for me to understand what it meant.

Dan Shipper (00:56:47)

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.

Anne-Laure Le Cunff (00:57:00)

Yeah, let's do it.

Dan Shipper (00:57:01)

So the first one. Alex Exum—I think his name is Alex Exum—asked, “How do you know when to use ChatGPT 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. At Every, we actually incubated a tool called Lex, but there's a bunch of them. I think Alex is curious, and I am too, do you just use ChatGPT? Do you use others? And how do you think about how they fit into your workflow?

Anne-Laure Le Cunff (00:57:32)

Yes. Sometimes ChatGPT is struggling to give me good answers. And I don't know why is that? Because it varies throughout a week sometimes. 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,I switch to Claude AI, 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 AI actually tends to hallucinate research a little bit less than ChatGPT. So if it's really research focused, I will sometimes double-check with Claude AI and it happens also that I use the same prompt in both, 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.

Dan Shipper (00:58:41)

That makes sense. Yeah, I use ChatGPT as my first line of defense, but I also use Claude for writing and I also find it's good for reflecting on text. If you give it some text and you're like, what do you think? What are the patterns in here? All that kind of stuff. It's really good for that.

Anne-Laure Le Cunff (00:58:56)

Yes. I really like it. And the tone sometimes is a bit better. It sounds a little bit less like AI, I feel like. I like both of them and I alternate—I don't have a very rigid rule when it comes to this.

Dan Shipper (00:59:13)

Okay, that makes sense. And then, the last writing-related Twitter question. Circe asks, and this is a good one. You’ll be happy about this. “How are you always so interesting? Did you change your approach to note-taking with AI?”

Anne-Laure Le Cunff (00:59:27)

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, yes, definitely. My entire creative process has changed. I just showed you how it was helping me explore different aspects, see the gaps that I may be missing even at the outlining stage. But there are even questions sometimes where, I think, in the past, just thinking about how I would get the answer felt like such an impossible mountain to climb that I would just park those questions to the maybe one day 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. And so I feel like for someone like me, who's very curious about lots of different things, it's been really magical to have access to this and to be able to get all of these answers so quickly.

Dan Shipper (01:00:42)

I feel you. I've been reflecting on that a lot for myself because I'm the same way. 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 my nephew, for example. He's one-and-a-half. And he's not old enough to ask questions—I mean, at least verbally. He can ask questions in other ways, but he'll be old enough to ask questions soon and kids ask a lot of questions and a lot of them are really unanswerable. And 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? 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 we can find the answer—pretty much. As long as one human knows it, we can pretty much get a good answer. It'll be really interesting to see what that generation does.

Anne-Laure Le Cunff (01:01:43)

Yeah, absolutely. I'm very curious too. I think it's already 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 and we're going to use our brain power for creativity instead and that's going to be a really good impact, I think.

Dan Shipper (01:02:05)

Totally, totally. So this is great. I want to make sure we get to our little explore section. 

Anne-Laure Le Cunff (01:02:11)

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 doc. 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 to, again, supplement 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 before I consider this draft finished is that I uploaded back into ChatGPT, 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, keeping it very specific to this draft, rather than general things that are helpful when writing an article.

Dan Shipper (01:03:16)

That's really great. I love that. I think it's really, I guess— So, at Every, I have an editor who looks at my stuff. Do you have a human editor or are you just kind of going back and forth with ChatGPT on this stuff?

Anne-Laure Le Cunff (01:03:32)

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 Ness Labs or on the newsletter.

Dan Shipper (01:03:43)

Yeah, no, that makes a lot of sense. And it's really nice if you don't have that resource. Just having an extra pair of eyes, even if it's ChatGPT, seems like it makes a huge difference just in comfort level. You're like, I want to make sure that everything I can do to make this good is done, you know?

Anne-Laure Le Cunff (01:03:58)

Exactly. Absolutely. So, I go through the feedback that ChatGPT is giving me and then I go back to the draft and I will sometimes make a few changes and then, voilà, this is on the Ness Labs website. And this is the live article.

Dan Shipper (01:04:21)

That is so cool. I love that process. I mean, I'm a fellow gardener. It's really hard for me to outline something. I have to just go write it. And I found something similar where ChatGPT—I can take a bunch of notes and throw it in and then it writes a little bit of an outline and I can kind of see the piece.

And I think having that as a resource to become a little bit more like an architect is nice because I actually think architects can be a little bit more productive because you spend less time meandering around through corners that don't really work in your writing, and also the writing tends to be tighter. So even—for fiction, for example, I think J. K. Rowling, her plots, her structures are super tight because she's such an architect, whereas, like George R. R. Martin, his are so all over the place and meandering that he can't even finish them because he's a gardener like us. And so maybe he needs to put his latest novel into ChatGPT and see if it can help him get an outline. But I think adding that is a little skill if you're the kind of person whose brain is a little bit more organic and spontaneous like ours is to put a little bit more structure around it, can help you get the best of both worlds because there's a lot of good stuff about being a gardener. So yeah, I think it's really smart that you're using it in that way.

Anne-Laure Le Cunff (01:05:46)

Exactly. And, again, I really truly believe that it's not fixed. 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.

Dan Shipper (01:06:02)

Totally. Cool. Well, thank you so much for showing us that. That's very special. I think people are going to love that. I want to go into the last segment of our show where we do a little bit of mutual exploration. So I don’t want to cut this out, but I think we only have time for one. Would you rather explore what your journal entries about meditation say about you and find some lessons in those, or would you rather talk through this decision about staying in academia? What feels more interesting to you?

Anne-Laure Le Cunff (01:06:38)

The research log is more fun, I think. I don't think that we’ll arrive at a big life decision in 10 minutes whereas

Dan Shipper (01:06:50)

I don’t know! I mean, no, yeah. I think that's good. I think that's good. Okay, cool.

Anne-Laure Le Cunff (01:06:56)

I love sharing so you can share and you'll probably need to download it as a PDF to upload it.

Dan Shipper (01:07:04)

I’ll just copy-paste it. It'll be fine. 

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 to find stuff out about ourselves, about the world, and maybe about how ChatGPT works that we might not have expected. So 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 it was just a starting point tell us about this log why you kept it and what's in it. 

Anne-Laure Le Cunff (01:07:43)

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. That's how I started Ness Labs, actually, when I decided I was going to write 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. It's 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 and that it just didn't work. And there was really no point in trying. And this was such a blatant, massive demonstration of fixed mindset that I was like, oh wait, 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 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, what it felt like, my questions, et cetera, and I posted it on 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 that's normal. It's completely normal to get distracted and just keep showing up every day.

Dan Shipper (01:09:31)

I love that. This is sort of the same theme as putting out the curiosity attractors 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 Jonny Miller, who's a huge expert on some of this stuff, popping into this doc being like, you should do some breathwork. Of course, Jonny Miller would say you should do some breathwork, but I think it's really great. And I'm curious in your own reflections, having done this 15 days for 15 minutes what did you get out of it? Where did you end up?

Anne-Laure Le Cunff (01:10:09)

So, I finished this particular experiment about a week ago, and I'm still meditating every morning, and I think this will be part of my routine moving forward, which I really 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 many things that I think, again, would have taken me so long to figure out. And one thing that ChatGPT is great at is answering questions, but I didn't even know what questions to ask here. And so, just 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.

Dan Shipper (01:11:14)

That's really interesting. Yeah, that makes a lot of sense. And in terms of positive effects, what would you pick as being a couple of the main positive effects you've been seeing?

Anne-Laure Le Cunff (01:11:29)

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. 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 thoughts 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. Just having that space to not think about anything. 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 expanded awareness, but some of the meditation sessions, to be honest, felt more like a mini brainstorming session because they came out of it with like three different ideas for Ness Labs. And you know, even one of the—I wrote about it in my notes, but at some point while meditating, I found a solution for a problem that had been banging my head on in the lab for weeks. And it was just this aha moment while meditating. And I know that's not what meditation is for. It's great. I'm not complaining at all. Really great.

Dan Shipper (01:13:01)

That's awesome. I love that. So I want to see what we can find with this. Let's see what's hidden in here. We have some of your reflections. We'll see if it can give out some of the reflections that you've already taken away. And maybe there are some other things that are hidden in here that we don't know about. So what I'm going to do is I'm going to copy it and I could have exported it to PDF and I think that would have been fine, but I think this is short enough that it'll fit in the context window for ChatGPT

And I'm gonna write something like, “I just did”—actually, I gotta make sure that it doesn't know who I am, so I'm gonna turn off my custom instructions. Save. Okay, cool. So I'm gonna say, “I just did an experiment where I meditated once a day for 15 minutes for 15 days, and I kept a log. The log is below. 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 some experts that would have interesting insights for me about what's contained in it.” So, and then I'll say, “log,” and then I'm just gonna paste and go.

Let's see what it does. So I 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 aha moments and the impact of meditation on your creativity, a cognitive neuroscientist or psychologist could provide insights into how meditation is affecting your brain function. Three, physiologist or physical therapistL considering your physical reactions during meditation, such as fidgeting, itches and numbness, you could experience the physiologist or expert could 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 or teacher from a specific meditation tradition, or a therapist with a focus on emotional processing.” Do you have any thoughts on a particular kind of person that you'd like to analyze your log?

Anne-Laure Le Cunff (01:15:35)

Wait, 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—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 my leg going numb and just feeling like fidgeting and being itchy, et cetera. So that was, that's surprising. I would have not thought about this one.

Dan Shipper (01:16:20)

Hmm. Okay. So you want to talk to a physiologist. 

Anne-Laure Le Cunff (01:16:22)

I think I'm going to try and figure out if there is any physiologist that wouldn't think that this is a really weird request?

Dan Shipper (01:16:30)

No, with ChatGPT—ChatGPT will do it. Let’s do it.

Anne-Laure Le Cunff (01:16:32)

Ooh. Amazing.

Dan Shipper (01:16:34)

So, “You are an expert physiologist, 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 and experience with mindfulness and all sorts of meditation practice practices. I am a meditator who just did an experiment where I sat every day for 15 minutes, for 15 days, and I kept a log. As an expert physiologist, I want you to read my log and give me a detailed summary of everything you notice of everything you notice. Be specific, detailed, organized, and don't leave anything out. Be direct.” Okay. “Here's my log.” And we're just going to say send and we'll see what happens. 

“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.” Okay. Interesting. So it's giving me a summary of your own experience rather than its experience as a physiologist, and so I think it's possible that because the log is so long, it sort of forgot who it's pretending to be. And so I am going to redo this and we'll see if we can make it better. Let's see.

Anne-Laure Le Cunff (01:18:48)

I also think it can be helpful to ask for a very specific thing, like give me advice. We can definitely do that instead of summarizing.

Dan Shipper (01:19:00)

Yeah. We can definitely do that. One thing that I like to do first is like have it, give it a—compress what it sees first a little bit into a little bit of a summary and then start to give advice. But let's try this one more time. Let's see. 

We'll say, “You're an expert physiologist—.” I'm going to say, “Pretend you're an expert physiologist with a particular interest and an experience with mindfulness. Be direct. Here's my log.” And then what I'm going to try to do is I'm going to say at the bottom, “Remember, you are an, you're an expert physiologist.” So hopefully it will not forget this time. 

“You're an expert physiologist. I want you to read my log above of everything you notice about my body and what's going on with it.” Okay, let's try that again. See if it works. Alright. 

“Several key observations about the physiological and cognitive responses to your meditation practice emerge: These observations are categorized under several themes for directness, physical sensations—” Okay, so it's saying things that we know. “Initially, discomfort and itchiness: Initially experience physical discomfort and itchiness common for beginners as they become more aware of their bodily sensations during meditation. Over time, you learned 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 noticed 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. This 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 emotional processing, environmental awareness, noise sensitivity, your initial heightened awareness of background noises followed by the ability to incorporate or disregard these as part of the meditation experience, illustrating adaptive responses to the environment adaptability and experimentation.” So it's noticing a bunch of stuff around there. It notes your back pain and your numb leg during these sessions. And so 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 about anything related to your body or your body awareness during this practice?

Anne-Laure Le Cunff (01:22:15)

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 was really annoyed with them and I wanted to get rid of them. So just that reframing already is very helpful. That being said, I would like to feel more comfortable, so it would be great to ask if there are any ways for me to feel more comfortable in my body while I’m here.

Dan Shipper (01:22:48)

Okay, cool. “I would like to feel more comfortable in my sessions.” Oh, I gotta say “Thank you.” Gotta be nice to your ChatGPT. “I would like to feel more comfortable during my sessions. As an expert physiologist, do you have any suggestions based on my log for how I could adjust my posture or environment or otherwise in order to be more comfortable?” See what it says. “Given the insights from your meditation log, there are several tailored suggestions that 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 environments” so noise management. “Consider using soft background sounds or white noise to mask external disruptions. Alternatively earplugs.” Two is “your seating arrangements.” So telling you to experiment with different seating positions. “If sitting on the carpet causes this discomfort, you might try a meditation cushion or zafu or 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.” 

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. 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. 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.” And then it says adjusting your approach. “Movement acceptance: allowing yourself to adjust your posture, scratch and 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 best beneficial to meditate when you're naturally more relaxed or alert. Duration frequency. 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. Given your varied experiences, continue to explore different meditation styles.” 

I'm curious what you make of these. Are they good?

Anne-Laure Le Cunff (01:25:39)

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 decorative, I guess. I didn't even question it. I didn't even—yeah, 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 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 snail hands. It's not a real term. It's just me explaining what they look like and the prayer 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.

Dan Shipper (01:26:49)

Isn't it sort of wonderful? Because I think there's two interesting things to me here. One is I love the “which expert I should ask” question because sometimes you don't know what you're 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 are not necessarily super groundbreaking, they are basic meditation tips in a certain way, but they're very tailored for you. I've talked about this before on this podcast, sometimes the answers that you need or the tips that you need, they're simple, but they're hard to remember. They're hard to know that's what you need. And just having that resource that can proactively be like, here's what you should do. It just clicks in your head and you're like, of course, I should use a cushion or of course I should use earplugs. But, for whatever reason, that wouldn't occur to you in your day to day life. And it's so valuable just to have this little engine to give you those simple tips that you didn't know you needed. I just love seeing stuff like this. 

Anne-Laure Le Cunff (01:28:02)

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 when it comes to meditation, 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. 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 1,000 of them. 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. 

Dan Shipper (01:29:04)

Totally. And I think it's also worth noting the reason it's able to do that is because you gathered the data for it. And I think people that have these 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 to work off of. And so 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.

Anne-Laure Le Cunff (01:29:40)

Oh, absolutely, 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 little notes to be able to unlock that kind of really powerful features that you can implement in your work and in your life.

Dan Shipper (01:30:13)

Totally, totally. I love it. This was a wonderful, wonderful episode. I really appreciate you coming on and showing us all the ways to 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 today.

Anne-Laure Le Cunff (01:29:38)

Thanks, Dan. That was amazing. I learned so much. So thank you so much.

Dan Shipper is the cofounder and CEO of Every, where writes the Chain of Thought column and hosts the podcast How Do You Use ChatGPT? You can follow him on X at @danshipper and on LinkedIn, and Every on X at @every and on LinkedIn.