The Exchanges

Q All right. Well, I'm, I'm intrigued. I, I'd love to see some, you know, what you got. You want to start sharing your screen?

A Let's, let's go. So this is how I do my email. Um, so this is a little app that I, I built. Uh, by the time this comes out, you'll probably be able to get, get this app. Um, it's called tend, but you'll probably be able to get it as an open source library I'll release. But honestly, you can literally just feed this video into codex and just be like, make something like this and it will do that. So, you know, do whatever you want. Um, but basically what this does is it goes through my inbox every day, and it just finds every single unread email, and then for each email it makes a card, and the card summarizes what was in the email, and then it has a little draft reply that it, that it drafts for me, and then, uh, what I can do is, um, I can say, can you, um, Well, I, I didn't deal with this yet. Can you find some more times like later this week and, um, show them to me in a draft? Um, and then it'll go do that. And now we're onto the next email. Um, and, uh, I just go through my emails like this. Uh, let's see. Uh, we want to keep writing.new. Um, it's on, it's on Namecheap currently. Uh, I can get you the Cloudflare credentials. Uh, and now we're on to the next one. I'm going to just, uh.

AI assessment note: “Let's, let's go. So this is how I do my email.”

Q So what is the media? What is the media distribution arm, um, for whatever it is you're creating? Um, I actually tend to think that like, And I'm curious your thoughts on this. Like, I don't know if I would, you know, in 20, 25 start with, like, essentially a blog and a newsletter as, as the way to get traffic. Like, why, why, why do you recommend starting there?

A That's a good question. I actually, I was not thinking about that from like, uh, what I would do in 20, 25. It's a really interesting one. Um, definitely like we got lucky. Cause when we started every, it was like right before the big sub stack wave. And so we got a lot of subscribers and like, that was the whole thing. And I do think that like email is just really powerful to have. Um, but it's much harder to grow a newsletter now than it was five years ago. I'd probably start with YouTube actually. Um, I think, and funnel people into, from YouTube into a newsletter, um, that feels like the right move. Um, and we have a YouTube channel and it's growing really fast and it's, it's been really great. It's like, it's definitely a little bit less effective to like get a YouTube subscriber to like Read an email, like that, that conversion is not, not, not nearly as good as it was like back in the day in like old Twitter, you know, the heyday of Substack. Um, but, uh, yeah, I'd probably start with YouTube.

AI assessment note: “I'd probably start with YouTube actually. Um, I think, and funnel people into”

Q So what is LFG and what is Goal?

A So LFG is, again, this is our compound engineering plugin. It's a plugin by Kieran Klassen, who runs Quora, which is just, he's like an insanely good AI engineer, and he's just taken all of the stuff that he knows and put it into a plugin. Um, and LFG, it basically just loops through the whole cycle of plan, like, execute work, review the work, Compound the learnings, and then just keep going until it's, until it's made. And then goal is Codex's version of, like, give it, like, give the model a high, a high-level long-term goal that it just, like, keeps going until it's, it's achieved. Like, for example, one of the things I'm doing, I told you I was doing model training. Um, I'm training a model to do copy edits. And this goal is four hours, it's been going for four hours, and I just like let it go, but four hours is honestly very short, like I, over the weekend I had one or two that went for like 20 hours each, and so it's just a really nice thing to be able to say, here's where I want you to get to, here's verifiable criteria that would tell me that you were actually done with this, I'm gonna go do something else, and, or theoretically I'm gonna go do something else. What I've actually found, I don't know if you have this, but I've actually found that I'm incredibly addicted to just like watching the stream, which I hate, but I just, I just am like that for whatever reason. U…

AI assessment note: “LFG is, again, this is our compound engineering plugin... And then goal is Codex's version”

Q Yeah, and like, you know, I think people would be interested in knowing, like, how does Dan Shipper take a vibe-coded project from 70% to a hundred percent with Codex and 5.6?

A Good question. Well, what I just said is, do it. Um, because, you know, I was like, here's what I need to do, and I was like, yeah, just, just do the full v one, man. Um, I think What's interesting about me, I have this, I make this, um, distinction between two different types of people in the AI age, um, or two different types of builders, um, between pirates and architects. So a pirate is like, I'm just going to get it to 70%. I'm just going to like explore the field of possibilities and build something that, that just works enough for me to tell is this valuable. And I think an architect is really good at being like, this thing is valuable. But it's not thought through well. How can I make it into a well-oiled machine that really works well? And so what I do is because I know that I'm like this, I'm like, oh, I have this idea. Like I'm going to go build stuff. I'm going to go train this model over the weekend, or I'm going to go like make this little app or whatever. Because I know that I'm like that, um, I pair myself with an architect who just, it's usually, it's, it's always now someone who works internally, but someone who is good at that and likes to get some energy from feeding off me being like, oh, I've got this like really exciting new thing, but, um, is good at being like taking some pleasure in taking that 70% formed thing and turning it into something that's real…

AI assessment note: “I pair myself with an architect who... is good at taking that 70% formed thing”

Q this, bootstrap founders, indie hackers, um, yeah, like, there's obviously some consumer media that they can do, but maybe they're interested in more B to B stuff, stuff that they can sell to businesses, prosumers. So with your idea, you know, that you're, you're sort of giving, you're talking about right now, like, how do you think about monetization of it? Um, and how big could it, could it be?

A That's interesting. I, I have to think about that. I, I think, I think like the, the way that I think about it is new technologies create the opportunity for new media formats. Um, every new technology, like YouTube videos, new media format from the, just because of the internet, right? Um, killing Hollywood. Um, I think, uh, the, and the, the thing that is true about this Wave of AI is it's taking storytelling and it's making it way cheaper than it has ever been before. Um, and I don't think that that replaces professional storytellers, but what it does is it allows you to tell stories in places that was way too expensive previously. So like, for example, I would never hire a really good storyteller to like go summarize our meetings for me. Um, but I'll have the AI do it because it doesn't cost me any money. Um, and so looking for places where Um, uh, there are stories to tell that were previously too expensive is like the, I think that's the total addressable market of this sort of idea. And then in terms of charging for it, we've been, we've been thinking about this cause like, uh, like our strategy is like everything we incubate, we bundle it into the every subscription. Um, and, but we've been thinking to ourselves like, okay, for, uh, something like this, like, would people pay more for it? And if so, like, how do we charge for it?

AI assessment note: “I think that's the total addressable market of this sort of idea.”