Transcript

Simon Eskildsen [1:07]:
Thank you so much, Dan. It's good to be here.

Dan Shipper [1:10]:
It's good to have you. So for people who don't know, you are the co-founder of turbopuffer, which is a really cool AI startup doing better vector databases. Is that how you describe it?

Simon Eskildsen [1:22]:
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.

Dan Shipper [1:34]:
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. We've also, we also go back a long way because you are one of the original, I used to do these interviews called Super Organizers interviews on Every, and you were one of the original interviewees. We did an interview together called "How to Make Yourself into a Learning Machine," which like it just went super viral. This is in like 2020, and it was like one of our first really, really big articles. 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 find new books and how you take notes on the books you read and how you turn the books you read into flashcards and all this kind of stuff. And it was like, I think super inspiring for any sort of note-taking nerds, of which I am one. And I'm really excited to get to talk to you again and sort of hear how your brain and your mind 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 level of tooling available. And so I just want to hear like what you're up to. I'm sure it's amazing.

Simon Eskildsen [2:50]:
Yeah, 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 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. So that's been absolutely incredible. But it also means that some of my habits and systems have taken a little bit of a loss. But it might also be interesting to hear what the 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.

Dan Shipper [3:46]:
Congratulations.

Simon Eskildsen [3:46]:
Thank you so much. And so I think like the reading is definitely condensed. Like 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. Another thing that I used to spend a lot of time on, and I think we talked about in the article as well, is that I used to spend 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. I joke with my wife that I'm going to have a party when I reach 10,000 flashcards, and I'm sure my friends will probably come because they like to indulge and make fun of all of my ridiculous rituals. But sometimes when I'm doing the flashcards, people want to follow along and they're like, you know, why do you have a flashcard about whether it's better to have the window down or the AC on at various vehicle speeds, right? 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 that, when you use this ridiculous fact or the time you created the flashcard in the first place. So the flashcards are definitely stuck. I review somewhere between 50 and 200 of them every single day.

Dan Shipper [5:25]:
Can we see your Anki? Can you show it to us?

Simon Eskildsen [5:27]:
I could show it. I think in the original article you wrote too, I have on my things to-do list like cut toenails. My life is completely in these systems that I regularly have nightmares about losing these systems because my brain is completely outsourced to it. This is what my Anki looks like. I don't think I've reviewed it, so this is a really easy day with only 11 cards. So we can take a look. I mean, 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 this really good radio deep voice. And you know, everyone has this dream that at whatever restaurant you constantly frequent, that you get to know the waiters and it's back and forth and it's like the usual, you know, but it never happens. So it's just 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.

Dan Shipper [6:34]:
That's amazing. I actually do that with, I put it in my notes app rather than an Anki flashcard. So then I just search whenever I'm back at the restaurant.

Simon Eskildsen [6:42]:
That's perfect. And I think it's also things like your colleagues' kids' names and ages, like these kinds of things where 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'll remember it. 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, right? But then at some point I was like, oh yeah, it's July. Isn't this when Scott got married or whatever, right? Yeah, this one, how many glasses of wine per bottle? I actually don't remember this one.

Dan Shipper [7:32]:
I think it's four.

Simon Eskildsen [7:32]:
Okay. Yeah.

Dan Shipper [7:34]:
There you go.

Simon Eskildsen [7:35]:
I didn't need the flashcard.

Dan Shipper [7:38]:
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. Good example too, right? Of just like something where if you don't drink a ton and one glass at the end is like, then this might be worth it. I think for a lot of people, you don't need a flashcard to live in New York. You're not going to need a flashcard for this one. So this one is going to be in again, right? I didn't actually remember. I think the number I had in my head was six. But you know, I think for Simon, it's probably two. But it depends on how heavy-handed you are on the pour. Here's another one. So this is also 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. This is a Postgres column type. Postgres is a 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 that 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. I'll show you actually just while I think of it, let me show you. 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. This is the golden card type. It doesn't matter what app you use. This is the template I like. So you might be like, how many glasses of wine does Simon think is in a bottle? You might be. 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...

Dan Shipper [9:55]:
I...

Simon Eskildsen [9:55]:
This can...

Dan Shipper [9:55]:
Mean, I'd say like the bottle is the glass for me, you know.

Simon Eskildsen [9:58]:
Yeah, there you go. This one doesn't have a good reversal, but let me just see if I can think of... So six glasses in a bottle of wine, right? So I'll just write something like, again, the reversal here doesn't really make sense, but it gets you the gist, right? So you might be, if we're talking about an example from before, like, okay, you know, Simon's kids' names are X and Y, and then you might have to phrase this as X and Y are whose kids, right?

Dan Shipper [10:32]:
Yeah.

Simon Eskildsen [10:32]:
So, yeah, you got to go back and forth.

Dan Shipper [10:34]:
You got to go back and forth, and I just like, I don't deal with the reversals.

Simon Eskildsen [10:37]:
Yeah.

Dan Shipper [10:37]:
This is really making me think of some AI stuff. So there's this whole debate right now about whether or not language models are actually intelligent, right? And one of the big ones is that they don't understand when things are logically entailed often. So like if they see all the time in their training data, like how many glasses of wine does Simon 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 they're not actually intelligent. And it's really interesting that like, at least in the flashcard example, like humans actually have to practice this all the time. What do you think of that?

Simon Eskildsen [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 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 human knowledge or whatever, like public human knowledge or like public human knowledge plus what you can easily scrape. And whether they can reason, it's not something that I really use them for, probably because I don't really feel like they can right now. Once 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. 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.

Dan Shipper [12:19]:
Right. Yeah, that makes sense. I guess what this is making me wonder about is how this whole process of or the idea of extending your memory changes for you in a world where language models are available. Like you have the average of all human knowledge available at your fingertips where like before you kind of did because like you had Google, but like Google itself is 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.

Simon Eskildsen [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. 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, 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. What might be some other things that I could do here? You just kind of got to talk to someone. 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. 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. It worked extremely well for learning, and that wasn't accessible to me at my fingertips before. I couldn't be like, hey, like, you know, 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, right? It will just tell me that, again, average of the internet, right? That I find very valuable or, 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's this whole complex thing, and there's all these legislations, and it was all in French because it's in Quebec. 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 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'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 associations are just like, yeah, if you talk to someone who's an expert on retaining walls, they'll tell you that. But anything associated like this, I have found the language models incredibly useful both in my daily work because it feels a bit like conversing 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 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, and you don't trust them. That's been very, very good.

Dan Shipper [16:32]:
That's really interesting. And how does that relate to you to the practice of making these flashcards and using them, if at all?

Simon Eskildsen [16:40]:
I think it's mostly like 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? 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, okay, we're going to create some flashcards today. 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 retaining this knowledge is that that lets me make these associations in real time too that are interesting, right? And suddenly I have high bandwidth through the 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, Justine, who normally sits in this chair behind me, right? It's just that free-flowing ideas of high bandwidth. 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 the network to know like what's the best type of heat pump is for these temperatures and what matters, right?

Dan Shipper [18:06]:
Yeah, yeah, yeah, yeah. That makes a lot of sense. So I want you to finish telling us about these flashcards, and then we'll move on to some of the AI stuff.

Simon Eskildsen [18:14]:
For sure. And yeah, 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 type that I really like. It's the only one I use for the past thousands of cards I've created. I haven't used anyone else. Then here for add reverse, you choose 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 Simon think is in a bottle, six glasses. This was in like 2017. I talked to this person and they said 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 nostalgia at Carbon in 2014 or whatever, right? Like you might not delete the card because that brings you a little bit of joy.

Dan Shipper [19:17]:
I think that's really interesting. I haven't actually heard anyone talk about flashcards from that perspective. Like, it's sort of like when people talk about they get a whiff of like someone's perfume and it reminds them of their mother or something like that. And like doing flashcards as a sort of evocative exercise or associative nostalgic exercise for different times in your life in the same way like, oh, I hear a song and I think of like being in high school or whatever. I kind of love that. It's like there's something romantic about it.

Simon Eskildsen [19:49]:
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. There might be a lot of history. I think a lot of people do flashcards for a period of their life, 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.

Dan Shipper [20:17]:
Great.

Simon Eskildsen [20:19]:
Do you want to do a couple more or which...

Dan Shipper [20:21]:
I mean, if let's do one where you get a good card that you know, I want to get that.

Simon Eskildsen [20:29]:
Prestigious university is in Pittsburgh? Oh, you probably know this.

Dan Shipper [20:38]:
I do know this.

Simon Eskildsen [20:40]:
I don't remember this. Okay, Carnegie Mellon.

Dan Shipper [20:43]:
You got to give me a chance to answer before you flip the card.

Simon Eskildsen [20:46]:
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 flashcards with words and definitions, and I would basically, I had this whole flow where I highlighted on Kindle, it syncs to Readwise, and then it syncs, then I like process that as part of my highlights, made a flashcard. Then at some point, my wife said, Simon, it's funny, my wife has like two reactions when I tell her one of these new words that I learned proudly, right? One reaction is, why don't you know that word? And then the other reaction is, 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 see that. 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 how common a word is. So affable, I mean, that's someone who's, you know, amiable—a nice person, right? Good-natured, yeah. That's another one. What is the main industry of the Jilin province in China?

Dan Shipper [22:12]:
Wow.

Simon Eskildsen [22:16]:
A lot of good tea. This is a really hard day today. I don't know. I mean, this is not a good flashcard because it's too hard to skim. So I'm probably going to mark this and then I'll look at it at some point. I'll close this down. But yeah, these are like, there was a time in my life where I found the origin of every vegetable like that mattered to me because then I could map back to what vegetables were endemic to which cuisine. You know, it's like before the Columbian exchange of tomatoes, you know, blah, blah, blah. It's, um, yeah, uh...

Dan Shipper [22:56]:
So what's the answer?

Simon Eskildsen [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.

Dan Shipper [23:05]:
That makes sense. Cool. All right. So we've reviewed like our previous. So we've reviewed the previous interview, we've kind of like gone back in time and seen what's stuck and what hasn't. 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.

Simon Eskildsen [23:27]:
Definitely. The biggest thing which I'm excited to show you because you shared with me before this that you actually don't use this tool, I would say that probably about 80 to 90% of my LLM use comes through this tool called Raycast. Raycast is essentially a replacement for Spotlight on steroids. So when you bring it up, it looks like this. So, you know, it can do my schedule, search my Chrome history, things like that, open applications, can search my files. 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 for good audio quality, do you speak to the side of the logo on a Yeti microphone? Now you can't ask Spotlight this, but if you press tab, it will answer it right there. So you're just doing command space, type your question, tab, done.

Dan Shipper [24:42]:
And so like, so basically what model is this? This is using GPT-4, so basically like it's GPT-4 accessible with one hotkey command.

Simon Eskildsen [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 hid 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 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 do it. So let me just show you because you can actually, there's a couple of other things that I do with Raycast. So you can configure inside of Raycast which model to use. You can use Claude. If you care a lot about the speed, you can use one of the other models. I think these ones are hosted on Groq, right? So these work really, really well. Hotkey to bring up that full chat dialogue, you can do all that. That works really well. But then you can also define these custom commands. So inside of here, I have a couple that I use all the time. So one, for example, that I might use is like, 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, and I have to cook to a bunch of dietary restrictions. So then I might do something like this to get a hummus recipe, 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.

Dan Shipper [26:48]:
Hmm. That's really cool. 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?

Simon Eskildsen [26:57]:
I just send a text message to myself or something like that. It's usually nothing more elaborate than that. There might be a quicker way to do it, but it hasn't bothered me.

Dan Shipper [27:04]:
Okay.

Simon Eskildsen [27:04]:
So the recipes idea is basically like you can create any common prompt you're doing. You can sort of create a recipe that's available by command. And so like this recipe is, it's not called a recipe, 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 all the stuff that all the requirements you have.

Dan Shipper [27:36]:
That's actually pretty cool. I like that.

Simon Eskildsen [27:39]:
I use it a lot. Like, that's why 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 Raycast, you search for AI commands, we go here to recipe, we can edit the AI command. And then here you can see this is my prompt. I'm like, please create a recipe for, and then the argument passed.

Dan Shipper [28:02]:
Mm.

Simon Eskildsen [28:02]:
Use...

Dan Shipper [28:02]:
Hmm.

Simon Eskildsen [28:09]:
When listing ingredients, put in parentheses optional extra ingredients. Blah, blah, blah for optional ingredients. My wife is sensitive to fructans, please like provide substitute, specify the approximate calories, please, like all of these things. And these models these days are so good that this just works.

Dan Shipper [28:30]:
That's great. I love that. And no, you don't have to flip through the chef's story about how their great-grandmother's cousin made this recipe for them or whatever. There's none of that. It's great. 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 the sort who cooks enough that I only really need the list of ingredients, not actually the instructions. And yeah, give me like a bunch of optionals that might make it interesting, and I can quickly see, oh, that's kind of a fun idea, right? So you can kind of tune this to how you like to cook. And I really like that. And I just don't use Google for this anymore because this is great. I used to, or I still have this book called The Flavor Bible, which essentially is a thesaurus of, hey, this goes with this. So you look up butternut squash, and it's like maple syrup goes well with butternut squash, like sage goes well with butternut squash, and ricotta goes well, right? And you just 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 create really interesting things. Now these LLMs, again, as the average of the internet, have that thesaurus built in.

Dan Shipper [29:56]:
What about improved writing? What's your prompt for that?

Simon Eskildsen [30:00]:
I don't use this a lot, but I haven't used it a ton. So this is what it looks like. This is an experiment. So I don't use this a ton for, I find that the standard, like just like improve this or giving suggestions is good. Typically, I'll dump the whole thing into Claude or ChatGPT or whatever is in whatever I use that week. And then I'll ask it like, here's the full document, let's talk about this sentence, give me some feedback. I do that for my blog posts these days. I don't have any more particular flow for that.

Dan Shipper [30:34]:
Yes. Any other commands that you think are worthwhile?

Simon Eskildsen [30:37]:
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 in Readwise. And 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 a good-natured, like kind human being that was not going through. Define here. So what I use here and 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 represents. Then I say, give me six example sentences of using this word. And please try to use some historical examples, something that's going to teach me something. Give me something with some well-known people like physics, computer science, geography to try to make this example a sentence as educational as possible. Example, I want to 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, concepts, 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 what this can look like. Okay, Justine, give me a word.

Dan Shipper [32:12]:
I want to do affable.

Simon Eskildsen [32:14]:
Affable, let's...

Dan Shipper [32:15]:
Yeah, do it.

Simon Eskildsen [32:16]:
Define. Oh, it's because it does it from my clipboard. So do it like that and then define.

Simon Eskildsen [32:20]:
So affable describes someone who's 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. In computer science, an affable user interface is one that's easy to navigate. Historical figures like Franklin were known for their affability. So it's just like, I love this because it starts to, oh yeah, like, yeah, like it connects with that chunk 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 connections, you're maybe learning something. So this has really improved 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 jittery to run this prompt because it just works so well.

Dan Shipper [33:20]:
All right, I have a couple more words for you. I want to try this out.

Simon Eskildsen [33:23]:
Let's do it.

Dan Shipper [33:23]:
Let's do lambent, L-A-M-B-E-N-T.

Simon Eskildsen [33:27]:
Okay, I have no idea what that word means.

Dan Shipper [33:29]:
Something that glows or flickers softly, often implying a gentle radiant light.

Simon Eskildsen [33:34]:
You know, you were really indulging in some ornate writing, huh?

Dan Shipper [33:36]:
I love words.

Simon Eskildsen [33:38]:
Lambent flames danced on the surface of the water, reminiscent of, oh, I'm drawn in here. Isaac Newton once observed that the lambent glow of a candle could reveal the nature of light and color, leading to groundbreaking work in optics. The lambent auras in the polar skies are caused by charged particles from the sun interacting with Earth's magnetic field, right? This is pretty good.

Dan Shipper [34:05]:
That's good. It feels romantic. Like it also feels like when I'm reading, the diversity of sentences will help me remember it better than just the definition, which I think is exactly what you're going for.

Simon Eskildsen [34:12]:
Yeah, yeah. I think it also has in the prompt to try to make the images and sentences easy to visualize because that's also a great mnemonic aid. Like these lambent auras in the polar skies—like I might remember from that alone.

Dan Shipper [34:23]:
Yeah, wait, go down to related. I want to see whether...

Simon Eskildsen [34:25]:
Okay, glowing, flickering, radiant. Okay, cool. All right, I have one more word and then we can move on.

Dan Shipper [34:31]:
Are you ready?

Simon Eskildsen [34:32]:
Yeah.

Dan Shipper [34:32]:
Eigen Grau, E-I-G-E-N-G-R-A-U.

Simon Eskildsen [34:36]:
Hang on, I lost the G. G-R. No, that's J. G-A...

Dan Shipper [34:40]:
R? Okay.

Simon Eskildsen [34:41]:
-U.

Dan Shipper [34:42]:
Yeah.

Simon Eskildsen [34:43]:
Oh my god. This is... Okay. Is this German?

Dan Shipper [34:45]:
Yeah, it's German.

Simon Eskildsen [34:46]:
Intrinsic gray. Eigen Grau is a German term that translates to intrinsic gray. It refers to the uniform dark gray background that many people report seeing in the absence of light, often described as brain gray.

Dan Shipper [34:56]:
Is that a cool one?

Simon Eskildsen [34:58]:
Strange, yeah. How have you used this?

Dan Shipper [35:01]:
I don't. I just have a list of words I like, and these are two on the top of my list. Eigen Grau. While Eigen Grau 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. I think it's 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 around things that are educational and connecting. I just love this problem.

Simon Eskildsen [35:36]:
That's great. That's awesome. 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, remove profanity. I don't know if this was just like me testing out or if that was a problem at some point. 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.

Dan Shipper [36:20]:
Yeah, yeah, yeah. That makes sense. 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.

Simon Eskildsen [36:30]:
I think most of my use is there. So today, I mean, I'm subscribed to all the tools, right? I feel like in AI, you want to, you know, you have Perplexity, you have Claude, you have ChatGPT, and you also pay for this. Like, it's just like, that's just part of the business now. You're spending a hundred dollars 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. ChatGPT doesn't have a search function, so that's a limitation, but I have some fun examples of the kinds of things that I used. So at our cabin, it came with like a really old 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 uptime chart on how often the electricity is out. Needless to say, you cannot keep anything in the freezer in a 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 ChatGPT how might I go about this because I've never done anything like that. I'm not that handy. And ChatGPT says, well, you go on like basically just like the canonical is like go to Amazon, buy this 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. I thought I was about to buy a fridge for like these, like what, like $1,000 or something like that. Now I have this, and yeah, it costs like an enormous amount of electricity because this compressor is going so hard, but it doesn't matter for this fridge because it's just for drinks. So fantastic, like $20 device from Amazon converting. I would never have thought to do that.

Dan Shipper [39:05]:
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?

Simon Eskildsen [39:14]:
You have the freezer, you plug the freezer into the wall, now it's a freezer. Now you unplug 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 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.

Dan Shipper [40:00]:
That's amazing. Is the probe wireless or like how do you get it in the freezer without it breaking the seal?

Simon Eskildsen [40:06]:
It breaks the seal. Okay. You know, especially in rural Quebec, you become very resourceful. So this is like a good hack, you know. This is how you write the best software too.

Simon Eskildsen [40:15]:
Yeah, I love it. And then I think I like, what else do I, what else do we use it for? I mean, while we're on the cabin—like, translating into 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 Quebecois French. The other, the biggest thing I use it for, I think in business is that when talking to, 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 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. And for something legal, that's certainly the case, right? So you're like, okay, I need to explain the exact algorithm for which we measure the uptime of turbopuffer 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 when talking to like for accounting and things like that, I use it constantly. I don't remember what this term means, right? And then again, it goes in the sink 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. So when you have those conversations with these vendors that are in some other vertical, I find it extremely useful. And then it makes it into the sink of the flashcards later.

Dan Shipper [42:06]:
Yeah, I have that too. Like, I feel like I want, like for a lawyer, for example, it's like, I needed to like push me into the latent space of like lawyer language. And like once I see the language, like I can write in it, you know, but I just having an example of like close to what I want is enough. And it like, that's one of the things I think about a lot with ChatGPT and Claude is it exposes how many dialects of English there are 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 ChatGPT is like this amazing universal translator for those kinds of translations.

Simon Eskildsen [43:00]:
I couldn't agree more. I think you put it brilliantly. 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. And I find iterating on copy, especially if it's very crisp copy, right, then it's great also to just get suggestions. For this kind of stuff, I'm not using any particular tools, like depending on the context I'm in now, they're all iterating inside of ChatGPT 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 it really useful for are physio exercises. So I had this, I had a problem with like, I had a tennis elbow or golfer's elbow. I think it depends on which side it's on. I don't know, ask ChatGPT. And it's just like, like, and so I just, okay, I'm just going to do an experiment. Instead of going to physio, I'm just going to ask ChatGPT to do whatever it tells me to do for a week and see if it disappears. 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 a hundred dollar 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? Just 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 the roll and things like that. And then at some point I was like, I have 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 tells me to do. I'm not even really going to understand them. I'm just going to do them somewhat blindly for two weeks, and it's been so much better, right? Everyone's just like, okay, soften the tissue. 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 in a pretty 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. Another problem I had that no one really could help me with was that I have this random thing where I just get a blurry vision for like three, four hours and go like half blind. 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. I'm just like, well, like, 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 it apparently is called an ocular migraine, and it can happen in the weirdest thing. One of the triggers for me is aspartame. Like it's...

Dan Shipper [46:06]:
Oh wow.

Simon Eskildsen [46:06]:
And I'm like, after that, okay, well, that's kind of concerning. So that's another one. So, I mean, like ChatGPT has just become the thing that I ask all the time. And I think that Raycast on the Mac 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. My wife uses that a lot. Like she's always asking. She uses it a lot for gardening, but that's been really good. And I'm really looking forward to their next rollout. Do you have access to that yet? Is that as...

Dan Shipper [46:38]:
Good as...

Simon Eskildsen [46:39]:
It looks really great. Yeah, I think if you're already a big voice mode user, you're going to love this. I think I'm also, I'm really excited for that part for my daughter. Like 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. Like that's like what makes me most excited about the safety is like, okay, can I just hand this to my daughter and she will just ask and it will just help with the curiosity?

Dan Shipper [47:24]:
That's really interesting to me.

Simon Eskildsen [47:26]:
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, 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 need more details on this particular battle in this book or like this particular concept that I don't quite understand. And it just gives me like 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 there, they're listening, it lowers the bar so much that you're just asking all these questions. And I think you learn way more. It's really fun.

Dan Shipper [48:14]:
I like that a lot. And especially if they're, I mean, APIs are going to be 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. I think what I've always wanted, and I think it's going to take a little bit to get there, is like I really don't care for VR and AR as an entertainment device. Like it just, there's two things that excite me about that. One is can I use it instead of my monitor setup? Like when is this good enough that I can wear it all day and code and work inside of this thing, right? That's exciting for me. For video calls, it might, I don't know when that will not be awkward anymore. That's not super exciting to me. But the second thing that I've always been excited about is that the visual stimulus of VR and AR would help 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 Eigen Grau and what was the first one with the light, right? Like if I can see that, 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.

Dan Shipper [49:38]:
That's the thing that like I think people miss about AI stuff and maybe miss about just how technology interacts with human beings in general. Like a really 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. So like it actually changes humans to be able to read. And I think like having language models 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 or my nephew, who's a year and a half, like or almost two now, 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 year or two year old or two year olds, 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. And all those questions are answered. And maybe they're not even just answered. 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? 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 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.

Simon Eskildsen [51:14]:
Yeah, 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 memories 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. And then I just remember I just got the Guinness World Records, right? And then it's just like, well, this would shut you up for a while, right? And now it's like, okay, well now I know, like now I know who has the biggest nose ring too, great, you know. But I think that would be very stimulating for a lot of kids. I think also like one of the things, so you know, my mother tongue is Danish. My grandparents only speak Danish, and it's very important for my daughter to also speak Danish. But it will be a challenge for me to be the only speaker here, right? I live in Canada, no one around speaking. It's a tiny community. I don't really have any friends here who speak the language. Even with FaceTiming her Danish family, there's not going to be a lot of day-to-day exposure. So yeah, we'll set, you know, all the user 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 it should speak to her in Mandarin or, you know, or like Thai or like whatever. Like I think one of the things that might be interesting for this generation as well is like, you know, 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. And, 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. 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? 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, ChatGPT 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.

Dan Shipper [54:06]:
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 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 the startup said that you can't say THs is 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 were 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 TH sound. And then it went and you would speak to it. 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.

Simon Eskildsen [55:30]:
I think, you know, any native English speaker can hear that I'm not a native English speaker—I wasn't born in the New World. It doesn't really bother me; it's distinctive enough that it's just part of my own history, so I'm not going to put in the work, but it's still fascinating that you can improve anyway. 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 a TH and I'm speaking fast, right? And it turns into an F. 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 what I discovered when I was looking into the International Phonetic Alphabet is like, oh, actually in New Zealand English, they have the UR 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. And French also has the UR, 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 then different dialects also have different types of sounds. So for example, in Danish, we have this sound that's also in my middle name called "ø." This is not a sound in most English dialects. You probably can't say this sound. Maybe if you do, it's cool. Yeah, good luck.