How to Use AI to Become a Learning Machine - Ep. 34 with Simon Eskildsen

[00:00] I think AI has certainly changed how I approach my learning. Absolutely. It's like an absolute dream come true. But I think also my life has also changed dramatically from 2020. I am running a startup, which is more demanding than anything. And I think if you want to make yourself into a learning machine, it's a pretty good path to take. There's nothing that challenges you more on your breadth and your skills than running a startup and building it from zero. [00:30] Thank you. [00:39] This episode is brought to you by our friends at Reflect. It's the ultra fast note taking app that's about to change the way you take notes. Imagine having an AI assistant right there with you, helping you jot down thoughts, transcribe your voice notes, and even chat with your notes to keep everything organized. With Reflect's advanced features like custom prompts and voice transcripts, note taking has never been this easy. So if you're looking to boost your productivity and keep everything in check, Reflect is your go to app. Give it a try by going on the link below to see how it can elevate your work. Simon, welcome to the show. [01:08] Thank you so much, Dan. It's good to be here. [01:10] It's good to have you. So for people who don't know, you are the co-founder of Turbo Puffer, which is a really cool AI startup doing better vector databases. Is that how you describe it? [01:22] Yeah, it's essentially a search engine starting with vector search, and we're trying to make it much more affordable and easy to run these things at scale, which is a challenge today that a lot of companies are having. That's awesome. I think you're one of the smartest founders in the space, especially at the stack and layer of the stack that you're working at.

[01:52] interviewees, we did an interview together called how to make yourself into a learning machine, um, which like, it just went super viral. This is in like 2020. Um, and it was like one of our first really, really big articles. Um, [02:05] And it was like really incredible. Like you have this energy about you in that interview. Like you're we go through like your reading habits and how you how you find new books and how you take notes on the books you read and how you how you turn the books you read into flashcards and all this kind of stuff. [02:35] is doing or adapting in the AI age because I think all the stuff that we were like nerdy about four years ago, it's like completely changed with the like level of tooling available. And so I just want to hear like what you're up to. I'm sure it's I'm sure it's amazing. [02:50] Yeah, I think AI has certainly changed how I approach all [02:56] like my learning, absolutely. It's like an absolute dream come true. But I think also my life has also changed dramatically from 2020 [03:05] I am running a startup, which is more demanding than anything. And I think if you want to make yourself into a learning machine, it's a pretty good path to take. There's nothing that challenges you more on your breadth and your skills than running a startup and building it from zero.

[03:35] condensed rituals look like now. And then on top of that, I have a four-week-old baby, which means that my schedule is even more ridiculous. Congratulations. Thank you so much. [03:50] And so I think like... [03:52] The reading has definitely condensed. Now I have perhaps an hour or so to read before I go to bed, oscillating between reading articles on Reader and then reading books. I can't get up to the 50 to 70 books a year anymore. So my selection process has gotten much tighter than it used to be. And so that's been a big one. [04:22] a lot of time writing about the books that I'm reading. And that's also had to go. I just don't have the time. But I still create a lot of flashcards. Like I joke with my wife that I'm going to have a party when I reach 10,000 flashcards. And I'm sure it will be absolutely, you know, my friends will probably come because they like to indulge and make fun of all of my [04:52] that wanna follow along and they're like, [04:55] you know, why do you have a flashcard about whether it's better to have the window down or the AC on at various, like, various, like, vehicle speeds, right? And it's just like,

[05:08] And it's funny when you've been doing this for 10 plus years because all of those things also carry memories of like, yeah, when you use this ridiculous fact or the time you created the flashcard in the first place. So the flashcards have definitely stuck. Like I review somewhere between 50 and 200 of them every single day. Can we see your Anki? Can you show it to us? I can show it. I can show it. I think in the original article you wrote too, I have on my things to do list like cut toenails. [05:38] Like my life is like completely in these systems that I regularly have nightmares about losing these systems because my brain is completely outsourced to it. [05:49] Um, this is what my Anki looks like. Um, I don't think I've reviewed it. So this is a really easy day with only 11 carts. Um, so we can take a look. I mean, this is like, this is a pretty ridiculous one, right? This is a restaurant that I used to go to. And I was like, the only distinguishing fact about this guy was that he had a really, like this really good radio deep voice. And, you know, everyone has this dream that of whatever restaurants they frequent that you get [06:19] It's back and forth and it's like the usual, you know, but it never happens. So this is like my weird attempt. This restaurant doesn't exist anymore. But I don't know. I haven't seen this guy in a decade. But again, it brings me joy to see this kind of thing. That's amazing. I actually do that with I put it in my notes app.

[06:38] rather than an iFlash card. So then I just search whenever I'm back at the restaurant. [06:42] That's perfect. And I think it's also it's things like your your colleagues, kids names and ages like these kinds of things where. [06:52] Some people might find it ridiculous that you put a note about this and it's like, why can't you just remember? But let's be honest, most people don't remember those things. And if you write it down, then you ask about it and then eventually you remember that note is not really valuable anymore. So I also in here have like the ages and names of like so many people I've worked with kids, like significant life events for them, like wedding dates, whatever. Because I really do want to remember those things, but my memory is not capable of it. [07:22] I was like, oh yeah, it's July. Isn't this when Scott got married or whatever, right? [07:25] Yeah, this one, how many glasses of wine per bottle? I actually don't remember this one. I think it's four. Okay, yeah. There you go. I didn't need the flashcard. You didn't need the flashcard. Yeah, I mean, I feel like having a newborn or all that, you forget the joys of a bottle of wine. [07:48] Good example, too, right, of just like something where if you don't drink a ton and you're constantly doing this, then this might be worth it. [07:55] people you don't you don't need a flashcard um you live in new york you're not going to need a flashcard for this one um so this one is going to be an again right i uh i i didn't actually remember i think i i the number i had in my head was six um but um you know i think for dan it's probably two um but it depends on how how heavy-handed you're on the poor

[08:18] Here's another one. So this is also, this is very common. Like when I peruse technical documentation, I'm constantly adding things into Anki again, instead of the note taking. To be honest, especially on the schedule I'm on now with the type of work I do, I don't take that many notes. Most things just make it straight into flashcards right away. [08:38] This is a Postgres column type. Postgres is the type of database. There's JSONB and there's JSON, and I constantly forget when you're supposed to use either. This is kind of a bad flashcard because I think this is just in my standard flashcard template. [08:53] that it shows both sides of the card. So this is not really a valuable flashcard. This is the best one, like when should you use JSON versus JSONB. Sometimes I just don't get the time to pull this up. [09:09] I'll show you actually just while I think of it, let me show you, [09:13] I have, I used to have like 20 different types of cards that I use, but I always use the same one now. And I think this might be worth it to some people because at some point I spent, you know, I had like a different card type for every single thing that I was doing. [09:43] is in a bottle. You might be [09:45] So that's the front of the card. Then you have to think about, okay, can this be reversed, right? So there's two glasses of...

[09:53] Thank you. [09:54] I mean, I'd say the model is the glass for me. Yeah, there you go. [10:02] This one doesn't have a good reversal, but let me just see if I can think of – [10:10] Six glasses in a of. [10:15] wine, right? So I'll just write something like that. Again, the reversal here doesn't really make sense, but it gets you to just, right? [10:21] Um, so you might be, if we're talking about an example from before, like, okay, you know, Dan's kids names are X and Y, and then you might have to back this as X and Y are whose kids, right? Yeah, yeah, yeah. You gotta go back and forth. You gotta go back and forth. And I just like, I don't deal with the clothes. Yeah. This is really making me think of some AI stuff. So there's this whole like debate right now about whether or not language models are like actually intelligent. Right. [10:51] entailed. [10:52] often. So like, um, if they see all the time in their training data, like how many glasses of wine does Dan think is in a bottle, they'll be able to answer six, but they won't be able to answer the reverse. And people are like, oh, that's because like, they're not actually intelligent. And, um, [11:08] It's really interesting that like... [11:09] At least in the flashcard example, humans actually have to practice this all the time. What do you think of that? [11:16] I think I haven't seen a ton of examples or tried a ton of examples of where they can't go in the reverse other than in these benchmarks where people pose them these problems to try to not make them think. I think I'm I don't really have any big ideas of what a language model is and what it isn't. I just think of a large language model as like an average of.

[11:40] human knowledge or whatever, like public human knowledge, or like public human knowledge plus what you can easily scrape. [11:47] And whether whether they can reason, it's just it's not something that I really use them for, probably because I don't really feel like they can right now. Like as soon as you get like two to three levels of reasoning down, it just doesn't really do the trick for me. So I'm sure a language model would do very well on something like this and probably even the inverse as well. So I don't know if I have any direct thoughts on your example other than that's. Yeah, I'm. [12:11] No, I don't think they're super intelligent yet, but I think they're like an incredible example of the average of the Internet. [12:19] Right. Yeah, that makes sense. I guess what this is making me wonder about is – [12:26] how this whole, how the process of or the idea of extending your memory, [12:34] changes for you in a world where language models are available. You have the average evolved human knowledge available at your fingertips, where like before you kind of did because like you had Google, but like Google itself is [12:45] just a much worse version of a language model where you can get exactly what you need in the context you need when you need it. And I'm curious how that's changed for you the function of and value of doing flashcards like this. [12:59] The way that it's changed my learning the most is that what Google is really good at is like you know roughly where to find what you're looking for and you can find it immediately.

[13:10] Thank you. [13:11] I read this paragraph once and I think about it every single day because I think the best people that I work with or like friends and things like that are like this where – [13:22] Yeah, Google is good when you know what you're looking for. But when you're just looking for associations, that's when you've got to go out and talk to people, right? Like, if you Google, it's like whatever is SEO plus like maybe a level out, right? But if we start to talk about something more interesting and like associations, like for me, it's like, okay, I'm using this data structure here. This is what my data looks like. [13:44] What might be some other things that I could do here? You just kind of got to talk to someone. [13:49] But this is what the language models have really changed for me, right? Where I can go to it and be like, hey, I think it could be done like this. I don't know a ton about this domain. [13:58] Can you just like riff on this with me? And then these models, right, like place that somewhere in that latent space. And then they can just find association around it and pump that back to you. So that is a ping ponging tool of whatever it is. When you have a rough idea of, you know, the island that you want to land on, it can paint the picture for you really well. I found that extremely well, work extremely well for learning. And that wasn't accessible to me at my fingertips before. [14:28] I couldn't be like, hey, something I did the other day is like, I like this brand, but they didn't have a product that I was looking for. What are some other brands like this? It will just tell me that again, average of the internet.

[14:46] That I find very valuable or [14:49] And like a year ago, we were having, you know, one of the wonders of living in Canada is that these little cabins in the woods are accessible for not too much money. And we have this retaining wall that we needed to build. And it was like near the water and it was this like whole complex thing. And there's all these legislations and it was all in French because it's in Quebec. [15:12] And I was using a language model, right, where, you know, someone had told me, oh, you need to build this type of retaining wall. I don't know anything about retaining walls. I don't care about retaining walls. I don't care to read, like, 100 pages of French, which I don't really – I don't know how to speak French anyway, about what you're permitted to do near a waterline as it pertains to the retaining walls, right? But you talk to a language model about this, and then they start to see, like, well, this retaining wall is not going to work for this reason. But actually, there is this retaining – the name slips me. [15:42] There's this type of retaining wall where you put it in a grid and then you put some rocks inside the grid. I'm sure you've seen one of these before. I don't remember the name of it right now. But it's like, oh, this might actually be a really good option that fits with these criteria. But no one had suggested it. Right. These types of association is just like, yeah, if you talk to someone who's an expert on retaining wall, they'll tell you that.

[16:12] with a PhD in whatever vertical you're going in, but also as you go through your daily life, and you often have to talk to, yeah, a contractor or a vendor who's... [16:22] an expert in some vertical, but certainly not an expert in teaching you enough about it. And maybe also you feel a little ripped off because, you know, if you don't trust them, that's been very, very good. [16:33] That's really interesting. And how does that relate to you to the practice of making these flashcards and using them, if at all? [16:39] I think it's mostly, flashcards to me is a sink, right? I don't really do anything with the intention of like, oh, okay, I'm going to sit down in my chair, I'm going to create some flashcards today, right? [16:51] Once I come across a bit of knowledge that I want to retain for like whatever reason, I'll put it in here. There might be a flashcard in there on the name of that retaining wall whose name slips me. Right. But probably not. Right. But that would be the type of thing that would make it in there. But I don't really like I think I used to open in the morning, set aside 45 minutes with the intention of like, OK, we're going to create some flashcards today. [17:16] I don't have time for that anymore, right? Now it's like, okay, I just encountered this piece of knowledge, make it into the sink of flashcards so I know that this is retrievable-ish, right? And the reason for the flashcards and maintaining this knowledge is that [17:30] That lets me make these associations in real time, too, that are interesting. And suddenly I have high bandwidth with a tool that's right in front of me to do that. Of course, the best person to do that association with technically is my co-founder, Justin, who normally sits in this chair behind me. It's just that free-flowing ideas of high bandwidth.

[17:51] I feel like I can get some bandwidth with the language model, but the breadth of where I can get it to and the verticals of knowledge that I can get is unencumbered. Like I don't have... [18:00] I don't have the network to know what the best type of heat pump is for these temperatures and what matters, right? [18:06] Yeah, yeah, yeah, yeah. That makes a lot of sense. So I want to, I want to, I want you to finish telling us about these flashcards and then, and then we'll move on to some of, some of the AI stuff. [18:14] For sure. And yeah, I think, I think, I think the best way to think about the flashcards is that they are a sink of your knowledge and they are just a way that these things resurface. This is the card that I really, this is the card type that I really like. It's the only one I use, like for the past thousands of cards I've created, I haven't used anyone else. [18:32] Then you, here for ad reverse, you just, whether you want to reverse the card or not, in case of something like this, you probably, in case of like how many glasses of wine does Dan think is in a bottle, six glasses. [18:44] You don't really need the reverse, so we're just going to leave that rank. And then extra will just be a picture or something like that. You saw it on the other card. [18:51] This is all you need. And then always put a source in. When you create a flash card, it's nice to know like, okay, this was in like 2017. I talked to this person and they set this thing. Because again, there's a little bit of nostalgia with these cards. Like if you're actually serious about making this a habit, right? You're like, oh yeah, that was Nage at Carbon in 2014 or whatever, right? Like you might not delete the card because that brings you a little bit of joy, but... [19:17] I think that's really interesting. I haven't actually heard anyone talk about flashcards from that perspective. It's sort of like when people talk about they get a whiff of someone's perfume and it reminds them of their mother or something like that.

[19:30] And, um, [19:32] like doing flashcards as a sort of, um, [19:36] evocative exercise or associated nostalgic exercise for different times in your life in the same way, like, Oh, I hear a song and I think of like, [19:44] being in high school or whatever. I kind of love that. It's like, there's something romantic about it. I think it's just because I've been doing it. It's a major part of my life, right? I've been doing this since I was like 17, 18 years old, right? So it's been like probably 12 years of flashcards. [20:00] Um, there, you know, there, there might be the, yeah, there's, there's, there's a lot of history. Um, I think a lot of people do flashcards for a period of their life. Um, but I found it valuable enough to just stick with it. Right. It's one of the three or so things that really have stuck with me. [20:17] Great. Um, [20:19] Do you want to do a couple more or – I mean if – let's do one where you get a good card that you know. I want to get that. Which prestigious university is in Pittsburgh? [20:32] I'm not. [20:35] Oh, you probably know this. [20:38] I do know this. [20:39] I don't remember this. Okay, Carnie B. Mellon. Yeah. You've got to give me a chance to answer before you flip the card. Okay, okay, okay, okay. Then there's, you know, I'm like, English is not my mother tongue. But so I used to do a lot of like a lot of flashcards with... [21:00] with words and definitions. And I would basically, I had this whole flow where I highlighted on Kindle, it syncs the Readwise, and then it syncs, then I processed that as part of my highlights, made a flashcard. Then at some point my wife said, it's funny, my wife has like,

[21:18] two reactions when I tell her one of these new words that I learned proudly, right? One reaction is, [21:25] Why don't you know that word? [21:28] And then the other reaction is... [21:30] Simon, that's a dumb word. No one uses that word. And I'm like, Jen, it's kind of like there's a missing third thing here. Like, what about like, Simon, that's such an amazing word. I can't believe it. Like, I'm so thankful that you taught that to me. So at some point, I started scraping Google with the number of results for the word as a proxy for how useful it is. That's something where you could probably use a language model today to ask it out, how common a word is. [22:00] you know, and admired or a nice person, right? Good nature. Yeah. That's another one. [22:08] what is the main industry of the Jilin province in China. Wow. [22:16] There's a lot of good tea. [22:22] This is a really hard day today. I don't know. [22:26] This is not a good flashcard because it's too hard to skim. So I'm going to mark this and then I'll look at it at some point. [22:35] All right. I'll close this down. But yeah, there was a time in my life where I found the origin of every vegetable. That mattered to me because then I could map back to... [22:47] Um, what vegetables were endemic to which cuisine, you know, and it's like before the Colombian transfer of tomatoes, you know, blah, blah, blah, blah. It's, um, yeah. Yeah.

[22:56] So what's the answer? [22:58] The answer is Asia. I don't think it's pinned down much further than that, which makes sense, right? It's not really used outside of that cuisine. [23:06] That makes sense. Cool. Um, all right. So we've, we've reviewed like our, our previous, um, [23:14] Thank you. [23:14] So we reviewed the previous interview. We've kind of like gone back in time and seen what's stuck and what hasn't. [23:20] Now I want to talk to you about AI stuff. So yeah, how are you using AI in your, let's start with your work. [23:27] Definitely. The biggest thing which I'm excited to show you because you've shared with me before this that you actually don't use this tool. [23:34] I would say that probably about 80 to 90% of my LLM use comes through this tool called Raycast. [23:43] Ray cast is essentially a replacement for spotlight on steroids. So when you bring it up, it looks like this. [23:51] Um... [23:52] So, you know, it can do my schedule, search my Chrome history, things like that. Open application can search my files. [23:59] But if you ask it something like, okay, a question that I actually asked it before this interview is that I have this little Yeti mic here, and the audio was really bad as I was doing my testing before our call, and I couldn't remember if you're supposed to speak into the side of the logo or the other side. So I asked it, okay. [24:21] For good audio quality, do you speak to the side of the logo on a Yeti microphone?

[24:31] Now you can't spotlight this, but if you press tab, [24:35] it will answer it right there. So you're just doing command space, type your question, tab, done. [24:41] Mmm. [24:42] And so what model is this? This is using GPT-4.0. So basically it's GPT-4.0 accessible with one hotkey command. [24:51] That's right. You can bring it up into a full chat window and then expand whatever. There's a history over here. I hit it because there's probably something embarrassing in there. So you can keep asking it. Is Yeti a good microphone? Should I use that or buy another one? Right. So. [25:11] This becomes a whole thing. You can upload files and all of that in here. I like this a lot for day-to-day use. ChatGPT for Mac and so on is not super interesting to me. That's a whole other workflow. But I was already using Raycast, and this was a really, really easy way to... [25:28] to do it. [25:30] uh so let me just show you because you can actually there's a couple of other things that i do [25:35] with Raycast. So you can configure inside of Raycast which model to use. You can use Claude. [25:43] You can use a, if you care a lot about the speed, you can use one of the other models. I think these ones are hosted on Grok, right? So these are, this works really, really well. Hotkey to bring up that full chat dialogue. You can do the, you can do all that. That works really well.

[26:05] inside of here, [26:06] I have a couple that I use all the time. So one, for example, that I might use is like I [26:14] If I'm cooking something, I don't really have like a collection of recipes or whatever, and it might be something that I'm doing not that often, then I have to cook to a bunch of dietary restrictions. So then I might do something like this to get a hummus recipe. [26:28] And then this is like a whole prompt that I've done and it gives me this format that is the most condensed list that I can think of that honors me and my wife's dietary restrictions, things like that. And it's just the simplest condensed version. And then I'll just put this in front of myself or send it to my phone or whatever. [26:48] Hmm. That's really cool. Um, and when you send it to your phone, like, is there a specific way you do that or is it just, you're just copy pasting it into your notes app or something like that? Yeah. I just, I just send a, send a text message to myself or something like that. Um, it's usually, usually nothing more elaborate than that. There might be a quicker way to do it, but it hasn't bothered me. Um, okay, cool. So the, the recipes idea is, is basically like you can create [27:12] Any common prompt you're doing, you can sort of create a recipe that's available by command. And so like this recipe is – so it's not called a recipe. It's called a command. It's called an AI command. And basically you put a recipe command in there so that whenever you want to get a recipe for something, it has like a very specific list of like all the stuff that – all the requirements you have. That's pretty cool. I like that. I use it a lot.

[27:42] I'm trying to share the things that I actually use rather than the things I've experimented with. I use this all the time because I gave it a couple of examples. So, yeah, you go into Ray Cash, you search for AI commands. We go here to recipe. We can edit the AI command. [27:57] And then here you can see, this is my prompt. So I'm like, please create a recipe for, and then the argument passed. Use the formatting from this example. So here's an example where I just wrote in how I like to make mashed potatoes. When listing ingredients, put in parentheses, optional extra ingredients, blah, blah, blah, blah. For optional ingredients, this. My wife is sensitive to this, like, carb called fructan. Please, like, provide substitute. Specify the approximate calories. Please, like, all of these things. [28:27] so good that this just works. That's great. [28:30] I love that. And no, you don't have to flip through the like chef's story about how like their their great grandmother's cousin like made this recipe for them or whatever. There's nothing about how they found it on a clay clay tablet in the attic. Right. There's none of that. It's great. [28:48] So I really like that. And again, I think of the LLM as an average of the Internet. And this is a great way to do that. And especially when you try to just boost its creativity a bit by like I'm a spirit, like I cook enough that I only really need the list of ingredients, not actually the instructions.

[29:18] for this anymore because this is great. I used to, or I still have this book called The Flavor Bible, which essentially is... [29:24] a thesaurus of, hey, this goes with this. So you look up butternut squash and it's like, [29:32] Maple syrup goes well with butternut squash. Sage goes well with butternut squash. [29:37] And ricotta goes well, right? And you just like you start getting ideas for how to use this in a recipe. Maybe don't combine those things unless it's Canadian Thanksgiving. But some of those things start to go create really interesting things. Now, these these these LLMs, again, as the average of the Internet, have that as far as it's built in. [29:54] Yeah. What about improve writing? What's your prompt for that? I don't use this a lot. Um, but I, so I haven't used it a ton. Um, so this is what it looks like. This is an experiment. So I don't use this, this a ton, um, for, um, I find that the standard, like just like improve this or giving suggestions is, is good. Typically I'll, I'll dump the whole [30:24] it like, here's the full document. Let's talk about this sentence. Give me some, give me some feedback. I do that for my blog posts these days. I don't have any more particular flow. [30:35] Any other commands that you think are worthwhile? [30:40] Define this one is one that I've spent a fair amount of time on and I use it a lot This is one where I do my daily I still review like 20 book article whatever highlights every single day and readwise and

[30:55] sometimes these will be singular words that I've highlighted that I don't know and I use this prompt to learn these words the word that I showed earlier in the flashcard which I think was affable and it just said you know like I [31:08] a good natured, like kind human being, that was not going through define here. So what I use here in define is I'm reading a book and I encounter this word place or person, and this is the word. Please help me learn what this word is, the place or person or whatever it is, this represents. Then I say, give me six example sentences of using this word. And please try to use some historical as example, something that's going to teach me something. Give me something with [31:38] like physics, computer science, geography, to try to make this example sentence as educational as possible. I wanna learn from the example. If it's a word that's always used in different forms, just like stem the word. Also, give me some related words, synonyms, concept, things that are related to this word. And finally, if you're capable of it, then generate an image that works for this word. Then I give an example of... [32:06] of what this can look like. Okay, Dan, give me a word. [32:11] I want to do Affable. [32:13] Affable. Let's do it. Define. Oh, it's because it does it from my clipboard. So I'll just do it like that and then define.

[32:25] So affable describes someone as friendly, good natured, easy to talk to. And then affable leaders like Gandhi often gain widespread respect and admiration due to their approachable and kind nature. [32:36] In computer science, an affable user interface is one that's easy to navigate. [32:40] Historical figures like Franklin was known for their affability. So it's just like, I love this because it starts to [32:47] Oh, yeah. Like, yeah, Frank, like it's you're it connects with that trunk of knowledge immediately. And it just makes it much more fun to create a flashcard. Right. It's like, oh, yeah, Feynman. Like, oh, yeah, I haven't thought about him for a second. Yeah. He seems like an affable guy. Right. So immediately you're making these contacts. You may be learning something. So this has really improved, like how fun it is to look up some of these words. Like when I see a word now and I'm reading, I get all like jittery to run this prop because it just works so well. I have a couple I have a couple more words for you. I want to try this out. [33:17] Let's do it. Let's do lambent, L-A-M-B-E-N-T. Okay. I have no idea what that word means. [33:26] Something that glows or flickers softly, often implying a gentle, radiant light. Oh, you were really indulging in some recent writing, huh? I love it. [33:38] Lambent flames danced on the surface of the water, reminiscent of – oh, I'm drawn in here. [33:47] observed that the lambent glow of a candle could reveal the nature of light and color, leading to groundbreaking work in optics.

[33:55] um the lambent auras in the polar skies are caused by charged particles from the sun interacting with earth magnetic field right this is pretty good that's good i'm i it feels romantic like i it also feels like i will reading those the diversity of sentences will i'll remember it better than just the like [34:17] the definition, which I think is exactly what you're going for. Yeah. [34:21] I think it also has in the prompt to try to make the images easy or the sentences easy to visualize because that's also a great mnemonic aid. [34:30] Like this lamp and auras in the polar skies. Like I might remember from that alone. Yeah. Wait, go down to related. I want to see whether – okay. [34:38] glowing flickering radiant okay cool all right i have one more word and then we can we can move on [34:44] Are you ready? Yeah. Eigen Grau. [34:47] E-I-G-E-N-G-R-A-U. [34:54] G [34:55] Hang on, I lost the... GR. No, that's G. [35:01] GR? Okay. AU. AU. [35:04] Yeah. Oh, my God. This is – okay, is this German? Yeah, it's German. [35:11] Thank you. [35:12] Intrinsic. [35:14] Eigengrau is a German term that translates to intrinsic gray. It refers to the uniform dark gray background that many people remember. [35:22] reports seeing in the absence of light, often described as brain gray.

[35:29] Um... [35:30] Is that a cool one? Astronaut? Yeah. How have you used this? I don't. I just have a list of words I like, and these are two on the top of my list. [35:40] Eigengrau [35:42] While Eigentrauch is not a true visual input, it highlights the brain's role in creating our visual world similar to how phantom limb sensations work for amputees. [35:53] I think it's just, this is just really showing the strength of LLMs, right? Where you take the average of human knowledge and then you just cause it to go nuts on associations, but draw it in a particular direction in the latent space. [36:08] around things that are educational and connecting. I just, I love this prompt. [36:12] That's great. That's awesome. [36:14] Um... [36:17] Another one that I use for a while is just like I tend to, you know, just growing up in northern Europe, often for especially a North American audience, like the writing is sometimes a little bit too direct. So I have this emoji suggestion that just adds an emoji friendlier. [36:34] Remove profanity. I don't know if this was just like me testing out or if that was a problem at some point. [36:40] They have a bunch of standard prompts. It's not something that I've used. Frankly, these prompt templates and so on, I've been very skeptical. It's only the recipe and defined ones that I really like. Other than that, I think the LLMs have gotten good enough that you don't have to worry too much about it. Yeah, yeah, yeah. That makes sense. [36:57] Cool. I love it. Okay. So I know you also have a bunch of ChatGPT and Claude stuff to show. So let's move on to that.

[37:04] Yeah, I think I'm most of my use today. I mean, I'm subscribed to all the tools, right? I feel like being an AI, you want to, you know, you have perplexity, you have cloud, you have chat GPT. [37:18] And you also pay for this. Like, it's just like, that's just... [37:21] part of the business now. You're spending $100 a month on these various subscriptions, jumping around them, getting inspired. ChatGPT is what I use for the most part. Now, I just sort of vacillate between Claude and ChatGPT. And ChatGPT doesn't have a search function, so I couldn't find the logs. But I have some fun examples of the kinds of things that I use. So at our cabin, it came with a really old [37:48] big freezer. And I have no use for a freezer somewhere that has like two nines of uptime on electricity. Like rural Quebec is not known for that. Actually, to the point where I have a script that constantly pings it. And then I have a website for the cabin that will show like kind of like a GitHub style, like uptime chart on how often the electricity is out. [38:12] Regardless to say you cannot keep anything in the freezer somewhere where the electricity goes out once every few weeks. So I wanted to convert it to a fridge. And I was like, oh, maybe this is like a fun project. You know, you have so much time before you have a newborn. And so I asked ChatTBT, how might I go about this? Because I've never done anything like that. I'm not that handy.

[38:35] And ChatTBT says, well, you go on like basically just like the canonical list. [38:42] device that's mostly used for home brewing, you plug it into the wall, you plug the freezer into that, and then you put the temperature probe inside the freezer. And then you just put it for five degrees, right? Celsius, I don't know what that is in Fahrenheit. And then the freezer will just turn on when it's above five degrees and turn off when it's below five degrees. And now your freezer is a fridge. [39:05] I thought I was about to buy a fridge for like these like what, like a thousand dollars or something like that. Now I have this. And yeah, it costs like an enormous amount of condensation because this compressor is going so hard. But it doesn't matter for this fridge because it's just for it's just for drinks. So fantastic. Like twenty dollar device from Amazon converting. I would never have thought to do that. [39:29] That's amazing. Wait, explain it to me again. So you're taking the temperature probe from the device that you just bought or the temperature probe from the original freezer and putting it somewhere else? You have the freezer. You plug the freezer into the wall. Now it's a freezer. [39:44] Now you plug out the freezer and you put in a, which you can essentially look at it as an extension cord. So you plug in the extension cord and you put the freezer onto the extension cord. The extension cord has a temperature probe. You put the temperature probe inside of the freezer, right? And so the, yeah, it just turns on and off depending on. You can even have it so that it can cool and cool.

[40:12] both cool and also heat if you have a device capable of it. But I think it's used for home brewing, right? Where you need fermentation ranges. That's amazing. Is the probe wireless? Or like, how do you get it in the freezer without it breaking the seal? [40:23] It breaks the seal. Okay. [40:28] You know, the – I think especially in rural Quebec, you become very resourceful. So this is like a good – it's a good hack, you know? [40:37] This is how you write the best software too. [40:39] Yeah, I love it. And then I think I what else do I what else do we use it for? I mean, while we're on the cabbage, like turning like writing Quebecois French is an art in itself. I don't know. Again, I don't know French, but my wife uses it all the time to convert something into the Quebecois French. [40:58] Um... [41:00] The biggest thing I use it for, I think, in business is that when going redlining and stuff like that, the clients often, when talking to the lawyer, it's easier to just send a draft paragraph to them and it'd be like, hey, something along these lines, and then they'll edit it. For drafts, I use it constantly. I think for most people, it's much easier to edit something, especially if it's something they don't know a ton about, than it is for them to actually start writing the first draft. [41:30] And for something legal, that's certainly the case, right? So you're like, okay, I need to explain the exact algorithm [41:36] for which we measure the uptime of Turbo Puffer in the way that we think makes sense, because I don't think what the lawyer came up with made sense. Let me just send it back in legalese and just minimize round trips like that. Same also, like, always, like, when talking to, like, for accounting and things like that, I use it constantly because, like, I don't remember what this term means, right? And then, again, it goes in the sync of the flashcards over time. But often a lot of these professionals will talk to you as if you already know everything about accounting and everything about legal and whatever.

[42:06] with these like vendors that are in some other vertical, I find it extremely useful. And then it makes it into the sync of the flashcards later. [42:14] Yeah, I have that too. Like, uh, I feel like I want, like for a lawyer, for example, it's like, [42:20] I needed to like push me into the latent space of like lawyer language and [42:24] And like once I see that language, like I can I can write in it, you know, but I just having an example of like close to what I want is enough. And like that's one of the things I think about a lot with GVT and Claude is it exposes how many dialects of English there are. [42:41] Because now you can do like subtle translations between different dialects that we didn't even think were dialects. So like from tech guy to like lawyer or like, you know, small business owner to like whatever painter or whatever. We didn't think that those were different forms of English, but they actually really are. And Chagipiti is like this amazing, like universal translator for those kinds of translations. [43:05] I couldn't agree more. I think you put it brilliantly. It's like, I have no idea how to access the legal latent space unless someone just puts me in it, right? And then I can edit and it's like, hitherto, you know, and it's like, yeah, let's go, you know? [43:35] iterating inside of Chachipiti or Chlad or just using Raycast, right? On, yeah, just like give me some other examples. It's rarely the thing that it spits out that I end up going with, but again, it just like comes up with words and things like that that I can use. The other thing that I found really useful for are physio exercises. So I had this, I had a problem with like, I had a tennis elbow or a golfer's elbow. I think it depends on which side it's on. I don't know. Ask Chachipiti.

[44:05] And it's just like – and so I just – okay, I'm just going to do an experiment. Instead of going to physio – [44:11] I'm just going to ask Jan-DBT, do whatever it tells me to do for a week and see if it disappeared. And it did, right? It was just like, oh, you have to do these like wrist curls. And I'm like, okay, great. Like that saves me a round trip and like $100 like physio fee, right? And I found that too with like one of the problems I have, and I think a lot of people who work at a desk have, right, is a very like just like tight shoulders and a tight neck. And I always thought, okay, yeah, I need to just stand more and then I have to roll and things like that. [44:41] I had this problem for five years now. Like it's not really going anywhere, right? And ChatGPT, and again, I was just like, okay, let me just do these exercises that ChatGPT is doing. I'm not even really gonna understand them. I'm just gonna do them somewhat blindly for two weeks. And it's been so much better, right? Everyone's just like, okay, soften the tissue. [44:57] But it's like, no, actually strengthen these muscles, right? So I find that it's pretty good for that. I do find for those things for exercise, stuff like that, you kind of do need to point it in a pretty, like, in a tight direction. And it's not always amazing at reasoning about how it got there. But again, as an average of the internet of, like, these are the things that work for this condition, it's pretty good.

[45:27] line. [45:28] Um, [45:29] It happens randomly every few months. And I couldn't figure out what it was. And when I talked to the optometrist about it, they're just like, oh, it's just stress. [45:37] I'm just like, well, so this is just going to be a problem for the rest of my life. Like, there's nothing I can do because it's quite debilitating, especially if it hits at a bad time, like we're driving or whatever. Like, then I just have to pull over and wait until it's gone. And apparently it's called an ocular migraine. And it can happen. [45:56] in the weirdest thing. One of the triggers for me is aspartame. Like it's, and I'm like after that, okay, well that's, that's kind of concerning. But, so that's another one. So, I mean, like Chachi BT has just, [46:10] become the thing that I ask all the time. And I think that Raycast on the computer has made a huge difference in just asking everything. And then on my phone, on the home screen, I have the voice chat for ChatGPT. [46:23] Um, my wife uses that a lot. Like she's always asking, she uses it a lot for gardening. Um, but that's been, that's been really good. And I'm really looking forward to their next rollout. Do you have access to that yet? Is it as good as it looks? It's really great. Yeah. I think if you're already a big voice mode user, you're going to love this. [46:41] I think I'm also I'm I'm really excited for. [46:46] for that part for my daughter, like, [46:49] I've seen that there are some toys where you can chat with these models and ask them questions. And I feel like she's going to grow up with these tools in a way where it's going to feel incredibly natural that she's just, you know, she's just talking to Wally the walrus, right? And there was that really cute Claude, right, where it's like tuned into the Golden Gate Bridge. And hopefully we get there.

[47:19] curiosity. That's really interesting to me. [47:23] I think you'll really love the new voice mode because – so I have a video about this. I'll send it to you after this on YouTube where I'm using the new voice mode, and it's really good for reading because what I do is I just turn it on. [47:34] And then it's just sitting there listening. And then when I'm reading something and I encounter a word I don't know, I'm like, hey, what's this word? Or like, it's like a historical figure. Or like, I'm like, I need more details on this particular battle in this book. Or like this particular concept that I don't, philosophical concept I don't quite understand. And it just gives me like... [47:53] the answer. And it's actually surprising how much when you're reading, how much there are things where you're like, I don't really know what that is, but like, I kind of do, but like, it's too much effort to ask. And when you have like a ChatGPT kind of voice mode assistant, they're listening, it lowers the bar so much that you're just asking all these questions. And you, I think you learn way more. It's, it's really fun. [48:16] I like that a lot. And especially if they're [48:20] I mean, APIs are going to get built on top of these things, right? But it's like if those can make highlights and then make it into my readwise or whatever down the line, like that's pretty exciting to me. [48:31] What I've always wanted, and I think it's going to take a little bit to get there, is I really don't care for VR and AR as an entertainment device. There's two things that excite me about that. One is can I use it instead of my monitor setup? When is this good enough that I can wear it all day and code and work inside of this thing? That's exciting for me. For video calls, I don't know when that will not be awkward anymore. It's not super exciting to me.

[49:01] is that the visual stimulus of VR and AR would help remember, you remember so much better. Like that's a medium for me to learn in that is quite interesting. Again, unless I'm like in this environment to work already, I don't know how likely it is. But if I can, you know, we're talking about these words, like eigengrau and what was the first one with the light, right? Like if I can see that, [49:29] it's going to be very hard for me to forget, right? If we can generate that kind of imagery. So that's really, really interesting to me as well. And of course, these things will play together and that might take a little bit longer. Again, I don't really care about it for any other use cases than that, but those two use cases do excite me. And it seems like that's starting to become in the adjacent possible. That's the thing that I think people miss about AI stuff and maybe miss about just how technology interacts with human beings in general. [49:59] good example is just the ability to read for example it like actually changes your brain and you like you take some of the stuff from your visual cortex and like reorient it to like help you read and that makes you better at like analytical thinking it makes you more likely to see sort of like particulars of a scene instead of like a more universal like holistic perspective [50:29] will do something similar in this way that I don't think it's scary. I think it's actually really cool. Like for your daughter, my nephew, who's a year and a half, like are almost two now.

[50:39] Like being in a world where any question that you ask has an answer, like an immediate answer, and no one's getting upset at you for asking is like a crazy upgrade to like children's brains, you know? Because like previously, like a year and a half or a two-year-old, or two-year-old is like still a little bit early, but like three or four-year-olds, they're like asking all these questions and parents are like, I don't know, like whatever. I don't know why the sky is blue or whatever. [51:09] They're like, you're stepping into like a scene that like helps you understand it in this totally new way. And I think people are worried about like, oh, like AI is replacing us or like, are we going to be like, have to be like bionic or whatever? And it's actually like, we don't even have to implant them into our brains. Like people will, we will be different people. We will, we will sort of like flourish in this new human way that was previously impossible because the conditions weren't there. And that makes me really excited. [51:36] Yeah, I it makes me it makes me really excited, too. I'm sure you were one of those kids, too, that drove your parents crazy with questions at some point. You know, I'd ask my parents. I remember this because I think I was like four or five years old. And this is one of my first memory where just, you know, you just ask questions like, Mom, what's the biggest plant in the world? Right. And it's just and they're just like, oh, my God. Right. I think it's like, I don't know, Simon, like, shut up, you know.

[52:06] Guinness Book of World Records, right? And then it's just like, well, this will shut you up for a while, right? And now I know who has the biggest nose ring, too. Great. [52:17] Yeah. [52:17] But I think that's I think that would be very stimulating. I think I'll be very stimulating for for a lot of kids. I I think also like one of the things. So, you know, my mother tongue is Danish by, you know, my grandparents, I'm fortunate enough, are alive. They only really speak Danish. But it's very important for my daughter to also speak Danish. But it will be a challenge. [52:41] for me to be the only speaker here, right? I live in Canada and no one around speak. It's a tiny community. I don't really have any friends here who speak the language. So other than FaceTiming with her Danish family, there's not going to be a lot of exposure. So yeah, we'll set, you know, all the UI interfaces to Danish. But maybe we can also set like, you know, Wally the speaking walrus, right, backed by whatever model to only speak with her in Danish. Or maybe she should speak [53:11] Like, I think one of the things that might be interesting for this generation as well is like, [53:17] you know, [53:18] I don't know how true this is. I haven't read the studies on it, but I feel like if all kids did was just learn languages before the age of 10, they could catch up on all the math and whatever they missed in like, you know, when they're 10 or 11 in like four weeks. But the language thing and hearing those sounds is just so special.

[53:38] And, [53:39] You know, I can't say THs and that will probably follow me for the rest of my life because I just wasn't exposed enough to that sound until the age of eight or whenever that gets locked in-ish. [53:51] And I think that would be – that's exciting if Wally the Walrus on Tuesday talks this language and on Thursdays this language, but primarily Danish, right? Right. [53:59] I don't know how that changes, but I think it is interesting. One of the things just on the pronunciation that I find funny is that, again, because ChatGPT is such an average of the Internet – [54:11] Chat TVT in Danish actually has an American accent. I don't know how true this is in other languages. I'm sure for French or Spanish or whatever, it's actually good. But the Danish one has an American accent, which is just hilarious. That's wild. I promise we're going to get back to some more AI use cases in a second. But I think this is too good not to share. I think you're going to love this. So I ran into this startup. [54:33] probably like maybe a year ago. And their whole thing was, you know, you said you can't say THs. And I think that that actually might be more flexible and plastic than you think. And the reason why, at least this startup said, that you can't say THs is – [54:53] It's really hard for you to hear and hear how off you are versus like what the actual sound is going to be because you didn't like learn that pattern when you're growing up. And what they did is they had this tool where if you were practicing, for example, TH, it would show you the waveform of the of the TH sound and then it went and you would speak to it.

[55:14] You would say or whatever, whatever you're doing or whatever the word is. And it would show a dot that would show you how far away you were in real time from that sound. And then you just like practice all the time and you can watch these like really like you can watch in real time. So you can see like these micro increments as you're getting closer and closer and closer, like tuning a string. And apparently if you do that, even non-native speakers who are like, you know, past the critical period can learn to speak fluently. And I think that's incredible. [55:44] That's a nuts way to approach it. I think at this point too, there's almost a little bit of an attachment to not getting completely rid of it. [55:53] I think, you know, any native English speaker can hear that this is I was not born in the new world. And but it doesn't you know, but also enough that it's like, oh, that's you know, it's just part of, you know, my own history. So I'm not going to put in the work, but it's so interesting that it's possible not to. And there are sounds where if you can't say them, it's really problematic. I just sound a little bit like a toddler sometimes when I say TH and I'm speaking fast. Right. [56:23] And but I definitely resonate with the I mean, the international phonetic alphabet. Right. Just sort of has it's really fascinating reading if you haven't read up on it. But it has this chart. And I love a good chart that simplifies something really complicated into a system that actually makes sense, like the periodic system or, you know, like how the planets are organized around the sun.

[56:53] but also predicts future things. Like the periodic system is like, well, there might be a heavier element or we're missing one here or whatever, right? And the International Phonetic Alphabet is that for sound. It's like... [57:04] The back of your tongue is here. The middle of your tongue is here. The front of your tongue is here. Your nose is doing this thing. And it's like all these parameters. And now you're making this sound. And so there's these permutation and every language has, you know, just making this up. But I think it's somewhere between 20 and 40 sounds. And then different dialects also have different types of sounds. So, for example, in in Danish, we have this sound that's also in my middle name called. Right. So my middle name is Hul. [57:29] this is not a sound in most English dialects. You probably can't say this sound. Maybe if you do. Yeah, good luck. And, you know, one of my friends said, Simon, saying your middle name is a little bit like trying to barf while saying Europe. And that kind of works, you know, not so much when you have to spell it over the phone, but it works for the pronunciation. But then, [57:56] What I discovered when I was looking into the international phonetic alphabet is like, oh, actually in New Zealand English, they have the U sound. So they will say – I can't imitate it properly, but they will say something along the line of like bird, like with the U drawn out. So they're able to say the sound, whereas in North American English you say bird, right? It's more of an I sound. [58:18] And French also has the U, so they have an easier time to say it. But it's like every language is just a mismatch of these like 20 to 40 syllables. And I was reminded of it again when we were choosing my daughter's name, right? Because it's like you want to choose some syllables that are roughly the same in the two languages and then combine together. So, you know, Simon is Simon in English, but in Danish it's Simon, right? And it sounds very different. So these syllables are very finite and every language is just like plopped together.

[58:48] it's hard but it sounds like not irreversible [58:52] Yeah, I love that. I had no idea that they had mapped it out. And like you can, it's like a periodic table of all the different sounds. That's, that's really amazing. I, that stuff, that stuff. I'm a nerd for that. So I want to get, I want to get further into a couple more, a couple more AI things that you, that you're going to share. So I know you, you said you use Notion AI a lot for writing. Tell us about that. [59:14] Yeah, this is a bit of a more recent thing. And generally when talking about tools, I like to not talk about them until I've used them for several months. But I think with AI tooling, it's changing so rapidly that it's worth sharing some of these things earlier. [59:28] There's [59:30] Writing inside a chat GPT feels a bit awkward, like iterating on writing. I think Claude is trying to change that with the artifacts. But Notion AI, I mean, that's where I do most of my notes and so on these days. And I just have a journal page where I'll just write about whatever's going on or I'm trying to think through a problem. [1:00:00] Like they're using some kind of semantic search behind the scenes to pull in context from around your workspace. So when you're writing and iterating on your writing, you can pull all of that in. And that's super, super interesting. And I found it great of like. [1:00:15] hey, you know, I was having this discussion with someone, and I feel like maybe I didn't represent myself well in this. And, you know, and it just gives you feedback, and it completes the writing. That kind of conversation has been really, really valuable to have. And I think Notion AI does it quite well. So I found that really valuable to use, yeah.

[1:00:36] Yeah, I actually use Notion AI a decent amount for writing. In particular, for example, like preparing for these podcasts, I – [1:00:46] I will often like just, I have a notion doc with like run of show. And then like when I had Tyler Cowen on, I was just like, okay, like tell me all the, all of Tyler's most recent books, give me a summary. Right. And then I was like, here are some of the points I'm going to make, like which ones relate to these books. And like it, [1:01:02] allowed me to create a document really fast with my ideas and a summary of his books and ideas so that I could – [1:01:11] talk to him about it on a podcast in a way that like, yeah, I could have totally done it with ChatGPT or Claude, but it would just have been hard. It would have been much harder to do. It's like having it in context is really helpful. Definitely. I think that that's, I mean, that's why we've also created, like that's part of why we've created Turbo Puffer, right? Is that it's clear that within the context window of what you're operating with the model with, [1:01:41] of. But I think Notion is showing that actually we can pull in a lot more relevant context from years and from other people and from things that have happened and perhaps even changes in how documents have evolved and you can get something even more interesting. And I think that's an exciting future. I think there's a lot of security and safety things that we have to get right, but that really can help augment. And I think the Notion AI is a really good example and

[1:02:11] probably one of the tools that are the furthest on that. Yeah. That's something I like to do is like I'll take a bunch of journal entries and I'll like throw it into Cloud or ChatGPT and be like, okay, like how did my... [1:02:22] Um... [1:02:23] like, how did I change over these, over these last years? Like, what's my trajectory? Or like, what do you notice about me? Like all that kind of stuff. Or if I'm journaling about a decision, I'll be like, I'll, you know, and I'm like, you know, going back and forth on what to do. I'll like put all my journal entries about that decision into it and be like, write the journal entry as if I decided A or write the journal entry as if I decided B. And it's so helpful for that kind of thing to like pick up on the like little things and how you [1:02:53] into the future. [1:02:54] Absolutely. And there are tools coming out where actually a tool that is using Turbo Puffer is this this app called Dot, right? That's trying to create a journal where you draw in the necessary context from your life to do basically what you're what you're what you're talking about there. [1:03:24] going on. And so that's, that's, I think that's really interesting. And I think also the context, the context when there's a growing would get better at pulling in context from billions of documents to do really interesting things. And the tools will grow alongside of that. But it will take a while. I think even now we're just like, even just using a, using a small amount of completion in your Raycast on your computer is something that most people are not using.

[1:03:54] co-pilot to complete rather than actually having a conversation with their code. So it's as much of an evolving of us as it is of the tools, right? But I think it's very, very exciting to be a part of. [1:04:08] Totally. So what else? What else should we talk about? [1:04:13] I think there's a couple of other places where I use the LLMs on a daily basis. So one is there's this tool called Super Whisper. Again, it's one of these tools that I haven't had the pleasure of using a lot, but it will allow you to just talk and then it will summarize. I'm experimenting with using that a bit more for journaling. So just tell it like, hey, these are the things that happened today or these are the things I'm going to do today. [1:04:38] fully incorporated it into my workflow, but I think it is interesting and the tools are constantly getting better. The main problem I'm having is still that it takes a little bit too long for the transcription and for it to pass the LLM and do the summary. I want that to be a couple hundred milliseconds, but it takes a couple of seconds at the accuracy that can tolerate, I guess, like my accent or whatever. So I think that's interesting, but the tools are still a little bit too slow, but that's fantastic because that will be fixed within the next probably six months. [1:05:08] Do you use that? [1:05:10] I don't, but I've heard great things about it. I just have not tried it myself. [1:05:15] Yeah, I think it's still a bit immature for unless you really want it. Or I think also, like I've lived on my keyboard since I feel like I was seven years old. So I can type faster than I can than I can speak. So it hasn't been a huge issue. But I think for a lot of people, that's huge. And I think probably part of where we're going to see that more is hopefully just that the OS dictation gets better in iOS.

[1:05:45] And when that makes it into the workflow of how we write messages, things like that, then I think it will spill over more. But it's just on the edge, I think, and it will take a little bit, I think, before it gets there for everyone, but it's definitely getting there. [1:06:01] What I want is, so like people send voice notes right now. And I think voice notes are really helpful when like you're, you want to communicate something that's like sort of complicated to someone else. And you don't want to like sit down and like actually like structurally write out, this is the thing. But what I want is like, I want a voice note that it's, I have a conversation with an AI. [1:06:21] And then I'm able to basically send the AI to someone else and have it explained to them very simply, maybe in text first, like this is the summary of what I said. So it's doing all the structuring for me. But then it has all of the background context of my whole conversation so that if people have follow up questions, they can just ask the AI and it'll be like, well, you know, in some other part of the conversation that didn't make it into the structured summary, we dealt with that. [1:06:51] you [1:06:52] And I feel like that would like really, really cut down on lots and lots of emails and Slack threads and [1:06:58] text messages and back and forth when you have something that's smart enough to like answer basic questions about like, you know, usually when you communicate something, you're only communicating the tip of the iceberg. But I think AI kind of allows you to send the entire context. [1:07:12] only present the tip of the iceberg, but then reveal different parts as necessary.

[1:07:17] Yeah, so you essentially just, you're shipping, you ship the TLDR and then the little model comes along with the FAQs, right? Yeah, yeah. And it has some confidence threshold on whether it can answer the context it has or whether that should be escalated. I think that's an interesting idea. And I think, you know, now, like I use Superhuman for email and they've started, I've started using their prompts more and more of replying to emails, right? And now they're shipping features where you can ask the AI and things like that. [1:07:47] And I think, you know, that's that's that's I hadn't thought about what the step after that was. Right. But this almost feels a little bit like it's like a support agent. Right. Where, you know, it has some confidence of when to escalate or not. The challenge is going to be to to make it still feel authentic. Right. It needs to be part of the client where you ship along this thing. And it's like, hey, I noticed you're going to ask about this. Actually, like this is probably the answer. Like, do you still want to ask? [1:08:17] Yeah, I think we're still so early in how this is going to be used. I guess there's like maybe two schools of belief of, okay, we get AGI and who cares? And then there's a school of like, well, the tools are just going to keep getting better and people are going to learn how to use this. I don't know which timeline we're on. I think it's really fun to be part of timeline number two for as long as that lasts. And that might last a very, very long time. It might not. I don't care. I'm having fun, right, like on that timeline. So I think that's really interesting for messages.

[1:08:47] I [1:08:49] The other thing where I use LLMs a lot is just through the Readwise reader. So when reading and, you know, you just, there are things that you do in line, looking up things, defining words, asking questions to the document. [1:09:03] And then, of course, inside of my editor, like I use a tool called SuperMaven to do completions. And then I use some plugins for Vim to try to emulate a little bit what the cursor editor does. The cursor editor, I think, is by far the best like AI code editor. They actually use TurboPuffer behind the scenes. So they're like great, great friends. And I really want to use cursor, but I can't take the cursor. [1:09:31] latency of VS Code. So I'm still in NeoVim. So I stitched together some plugins to send context to different models. But hopefully that's going to get solved. Either I'll move to KickCursor at some point or have some of these plugins. But it's like when you've been using Vim for 15 years, it's very difficult to go to something else. [1:09:54] That's great. Yeah. Um, I, I use cursor. I love it. Um, I've, I've not as, uh, not as Vim, uh, what's, what's the word for that? Um, [1:10:05] I'm not as vim-pilled as you, maybe. [1:10:10] But, yeah, I think Cursor's awesome. It's got a little bit of, like, it's a little bit weird, like, when it makes suggestions, if you're having it code in multiple files, you have to, like, click into, like,

[1:10:20] click into the file and then click to do the change or whatever. So I think there's like some stuff to, to be worked out there, but it's sort of clearly the future of, of these kinds of interfaces. I think they're just showing such a, you know, it's just like every few months they make some new release of, Hey, this is how we're going to do it. And they really just seem to be paving the way. Like, it's like, [1:10:40] One of the hot plug-ins now is just like trying to do cursor-like things in other editors. So I think they're doing really, really interesting things. And on that timeline of like, let's just make the tools better. And I don't think, you know, the VCs are tweeting that like, you know, these companies are like 10 times faster because they – [1:11:01] using AI. Like, I don't think Justin uses any AI. And it's still doing very, very... [1:11:09] It doesn't... I think it helps and it augments and especially for people to create that first draft and to have the conversations. But I don't think it's that like massive step change yet. But it comes, right? Like every single month, like these things are getting a few percentage [1:11:31] thing yet, that's certainly not the case. I think it sort of depends on who you're talking about. So if you're already a 10X engineer... [1:11:39] Maybe not, but if you can't code at all, [1:11:42] I think it makes you 10x better than you were. I mean, infinitely, right? Because you were just not going to bother. [1:11:49] And so, yeah, I think that's true, right? The same as like, okay, now I can become like a 10x retaining wall, like, you know, corresponding with my contractor. So I think it lifts from like novice or less than to being able to converse with an expert incredibly quickly.

[1:12:12] basically more about typing faster and having, you know, substituting a conversation about like, [1:12:20] what data structure should we use for this or which algorithm here or how to make these kinds of trade-offs, right? But a lot of that also comes from things that are just not the average of the Internet and therefore really hard to discover. Yeah, totally. Well, I feel like I could keep talking to you forever, but we are pretty much at time. Simon, this was, as always, a pleasure. We got to do these interviews more often. Thank you so much for coming by and telling us what you're up to. [1:12:46] Absolutely, Dan. This was really, really fun to nerd out. Cool. See you next time. See ya. [1:13:16] Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat. [1:13:23] 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. [1:13:31] So do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. [1:13:36] And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.