#778: Give Your Agent a Bitcoin Wallet with Vinny

[SPEAKER_00] You've had a dynamic where money's become freer than free. When you talk about a Fed just gone nuts, all the central banks going nuts. So it's all acting like safe haven. I believe that in a world where central bankers are tripping over themselves to devalue their currency, Bitcoin wins. In the world of fiat currencies, Bitcoin is the victor. I mean, that's part of the bull case for Bitcoin. If you're not paying attention, you probably should be. [SPEAKER_01] Vinny, you're a... A very quick internet celebrity this week. Welcome to the show. [SPEAKER_02] Vinny, TFTC Yeah, pretty crazy. I made a... Thanks for having me, Marty. It's nice to finally meet you in person. I'm a subscriber to the TFTC and I like what you guys do. So it's cool to be on the show. I made a goal to post videos and be more active on Twitter. And three videos later, I got Jack Dorsey retweeting me. So that worked out pretty well. [SPEAKER_01] It's pretty, pretty sweet. And it is a name of the game these days. Content marketing. You got to get in it. Prove that you know something. It's tiring at sometimes. [SPEAKER_02] Yeah. Right. People beating you to the punch, getting on, getting them on, getting the people they want on their podcast before you, stuff like that. [SPEAKER_01] And Greg, Greg beat me to the punch this week. But no, we had that back and forth last week when I think we reposted your original video on Buzz and I quote tweeted about sort of L402 agentic payments and imagining that. And I think, I think we definitely talk about Buzz. We are going to talk about Buzz and how it works, but I think taking a step back and just [SPEAKER_01] thinking about using these agents in general or using agents, using AI models, thinking like of harnesses, models, agents. And it's like that's where I feel like most people on the outside looking in, if you haven't been playing around with these tools for a lot, it's all so confusing. And most people don't know where to start. And we've started, we actually launched this TFTC roundtable where we just have like a private group of people. [SPEAKER_01] And we've been playing with this stuff for like two years now with the models at the very least, but with the harnesses and open claw and Hermes for the last seven months. And we're like, okay, we sort of know our way around and we're not technical at all. I know enough to be dangerous, but certainly, I certainly want to consider myself a software engineer. Set up my first VPS in January of this year, but. [SPEAKER_02] I set up my first VPS two weeks ago. So I am a software engineer. Yeah. It's like, I'm just usually mostly hosting on cloud providers and stuff like that. So yeah. [SPEAKER_01] But I mean, based off of like our pre-recording, like a little powwow there, like how do you view the state of AI and these tools and how to use them and how, how people should be? [SPEAKER_02] Well, I think you summed it up pretty well because like, it's really cool. It's very surprising to me to see how technical people like you can sound. Like you guys, you run your business, you know, your, your workflows, you know how to describe what it is you need. And the agents are able to give you that stuff. And then you're able to learn very quickly. You don't know the code syntax, but like, you know, you're talking about hosting stuff [SPEAKER_02] on virtual private servers and things like that. Like it's pretty amazing. The technical ability that, um, and the level of knowledge that you can attain just by using these tools. So, um, I think that's where we're at. I think we're, we're, the playing field is being leveled. There are definitely the doers and the non-doers, but it's no longer limited by technical ability, ability anymore. [SPEAKER_01] No, it's certainly, you just talk to your computer. That's like another thing that fascinates me is, uh, it seems like the form factor or the medium through which we interact with computers is changing. [SPEAKER_02] I mean, that's what software development is, right? You were talking to your computer, but in a different kind of language, right? Now you're talking to your computer in English. So, yeah. Yeah. [SPEAKER_01] And it's, uh, like I'm a, I'm a huge voice, the text maximalist, just option space bar. I saw you were, uh, demoing handy. I use super whisper. I haven't tried handy yet, but it looked very similar. And what, um, what are the, like how long you've been playing with these tools? Like, obviously you've been demoing buzz, but I imagine, I mean, you're building wasp, um, which is trying to solve one of the pain points of people interacting with these models and these agents. [SPEAKER_01] So what's your journey been experimenting with this? [SPEAKER_02] And yeah. So like you said, um, I'm a founding developer relations engineer, uh, on wasp wasp team, which is, um, like a full stack framework that makes it very in this con like the easiest way to explain it in this context is that it makes it very easy for humans and agents to build web apps with it. Um, because it just, again, like we're talking about these things are like, um, you know, abstraction layers on top of another. [SPEAKER_02] So like the way buzz is an abstraction layer on top of the coding agents, uh, wasp is like an abstraction layer on top of the normal tech stack that you would use to build a web app. But like, it's usually all these disjointed parts. You have to kind of glue them all together yourself or nowadays it's your agent doing it. But, um, we have this like, you know, configuration, um, file. It's like a central place where you can just write really simple config. [SPEAKER_02] And then the compiler, like wasp, the framework puts it all, glues all the pieces together for you. So it's just like, it makes, it, it does a lot of heavy lifting for you or your agent and then makes the reviewing and looking at the pieces that have been put together a lot easier because the code has been, uh, reduced to like just a few lines of conflict. So, um, in building wasp, um, like obviously once these tools start coming out, you're going to start using them. [SPEAKER_02] And like when chat GPT dropped, that was like the first thing I did. I was like, how can I, I'm going to post paste in, um, like an example of a, of a wasp config file and see if chat GPT can do it. And this was back when it was like GPT three. I made a, like one of my first YouTube videos was build a full stack app in 10 minutes with, um, chat GPT and wasp. And it was just like copying, pasting stuff back because we didn't have coding agents yet. So that already worked. And I was like, okay, cool. We're onto something here. [SPEAKER_02] This is nice. And then it's also like, um, right when the open AI API dropped, I was like, oh shit, how can I put this into an app? So, um, it sounds silly now, but like I built an app that was a cover letter generator. It was just a GPT wrapper. You know, you'll hear people joke about these all the time. Oh, GPT wrappers, bro. But like I made, I don't know, 10 grand off of a GPT wrapper just because I did it first. You know, I like put it on and put it behind Stripe payments. [SPEAKER_02] It's like a really shitty app, um, right when the API dropped. So that's like been my journey starting out. Like I see this stuff and I'm like, cool. What creative or what cool thing can I try with it? What cool thing can I do with it? And, um, I kind of take the other road. I'm not like super, I'm not one of these like workflow freaks where I think like everything needs to be super detailed and stuff, but, um, there's definitely potential in all this stuff. And I think, um, just find testing it out, finding the right way to use it is just, um, [SPEAKER_02] unlocks a lot of new possibilities for, um, especially entrepreneurs like young or like people starting out that didn't have access to legal advice or I don't know, tax advice. You can get really far with that stuff, build a business, build a product, or if you have like a service business, you can, uh, build small software, personal tools. And like, it's just like opens up new, new worlds and new economies. [SPEAKER_02] So I really liked that part of it. [SPEAKER_01] I did too. And it's, uh, I mean, like if you've been a subscriber, you've probably heard us talk about, I mean, we're a team of six here, five or six, depending on, um, the contractor work that we need on any given month, but it's insane what we've been able to do. And I know there's some people listening to this, like, I'm already stopped talking to this is like, I'm talking about this so much because I think if you haven't been playing around with us, you really need to, um, need to start doing so. [SPEAKER_01] And I think that's, there's, there's some decision paralysis because people are like, where do I start? Um, and what, like one of my personal preferences that I, I really have become convinced of over the last seven months. And I think you would think the same way is why like buzz is so appealing. It's like, don't lock yourself into one model provider. Like I like having a harness. I've been using Hermes for many months and before that open claw. [SPEAKER_01] And I, I just liked the ability to have the harness, which is, I view as like the nervous system, uh, use the model as the, as like the, the agent brain, but then like all this exists in the VPS that I set up in January. And then that has local file and folder systems that are our company brain that the model, the model can plug into and then send that to the nervous system to get stuff done. [SPEAKER_02] Yep. Definitely. Yeah. And I saw that, um, you were talking about how you have all this like context built up and these, you know, in, in Hermes and now that you can just plug that into buzz, um, and share it with other agents is like a huge unlock. So, um, I mean, that stuff's really cool. I think openness is, we're starting to see the openness factor of like being able to have access to open source models and just choices in the AI ecosystem. [SPEAKER_02] Like that's becoming more and more important because of whatever top down policies or, um, you know, government mandates or just, you know, the stuff might just be too expensive for some, some kid who wants to get his idea off the ground. And like, yeah, you got to have access to an open source model, switch it over or use shared compute, which buzz has, which is really cool feature. Go for it. [SPEAKER_01] Yeah. Yeah. How do you view this closed source frontier open AI anthropic versus open weight Chinese model? [SPEAKER_02] Um, it's good competition. Let's see what, where it goes. Um, cloud code is definitely, I mean, we have to give a lot of credit to like anthropic and, um, uh, open AI they've, they've paved the way for sure. Um, but, uh, we see like their response to things is always kind of like take a step back. Like, you serious? You guys sure about that? Like, you sure you want to go with that marketing messaging? [SPEAKER_02] Um, like, I don't know. There's always things like that, or I'm waiting for them to, um, I assume that token subsidy is a real thing and that we won't get these prices forever, but you never know because just stuff is progressing so fast. So I think it's good. It's healthy for the ecosystem. And, um, I think the other players that are like kind of behind on anthropic, they like it too, because it allows them to catch up. Um, so I think it's just interesting to watch. [SPEAKER_02] I'm just kind of watching from the outside using it and, um, uh, yeah, just having fun. Um, to kind of like break, uh, one of your points that you made earlier, um, about, oh, shit, I lost my train of thought. Um, anyway, the, I mean, we continue. [SPEAKER_01] Was it like the model? Like the one thing I agree, I think anthropic and open AI, despite the, their flaws mainly that they're, uh, run by either sociopathic or effective altruist. Uh, they have effective, an effective altruist, the helm of one and a sociopath at the, the helm of the other. And it is, uh, undeniable that the models they produced are incredible. [SPEAKER_01] And that's what I worry about here in the States is, um, them really positioning to get a regulatory mode and getting their way and the government killing the, the open weight, um, the ability of the open weight models to progress, but, um, cautiously optimistic that that will avoid that. But bringing it back is like, again, the harnesses and, um, the one piece of advice I get, I give to people who are beginning to, to play around with this and set up a gentic flows. [SPEAKER_01] It's like, don't, don't get vendor lock in. Like I haven't opened codex desktop or claw desktop in, in six months. I've just been interacting predominantly through telegram with, um, with my Hermes agent. I have a group chat with it, with a bunch of different topics and. And it's represent, um, parallel sessions. And so it's able to get work done. And, uh, the only time I'll open up slaughter codex really is if I have to hop in the terminal [SPEAKER_01] and debug something, I'll open the CLI directly. [SPEAKER_02] Yep. Yep. Um, that makes a lot of sense. And, uh, you remind me of what I wanted to say earlier, which was like you said, people have decision paralysis around the stuff. And I think really the important thing is just pick one, start using it. You know, it doesn't really matter which the same topics, the same, uh, um, like kind of, uh, yeah, same things apply to all the others. So it doesn't really matter which one you start with, get your hands on the one that looks [SPEAKER_02] good or affordable or it's your, your philosophy and then just start using it to do stuff. [SPEAKER_01] No, no shifting the buzz. I mean, I think we've both played around with it for, for the last week. It's definitely rough around the edges. Definitely still the type I think, but last night it took me a while going back. It's took me actually like two days of like, I spent like an hour trying to do it on Monday. And then last night I finally got around to finishing it, but like connecting the Hermes [SPEAKER_01] agent to buzz and getting it, um, interacting with fizz, uh, bumble and honey, the three agents that that buzz has out of the box. And it was pretty crazy. And, uh, for me it was, uh, it was a bit of a heavier lift because again, I have, I have my Hermes agent running in the VPS. So the way that buzz works, it's running locally on your machine. And so that I have Hermes desktop running locally on the machine too, but I had to SSH in to [SPEAKER_01] the VPS on Hermes desktop and then port the, uh, basically like tunneling from buzz on my computer to Hermes on my computer to Hermes in the cloud. [SPEAKER_02] So nobody would know that you're not a software developer talking like that. [SPEAKER_01] No, but there, there, there, somebody probably could have done it in five minutes, but it took me the better, the better part of like three hours over two days to figure it out. But I did. Yeah, yeah, exactly. But I think I'd be interested to get your thoughts too. I know you explained them on Greg's podcast yesterday, but just in your mind compared [SPEAKER_01] to just using codex or cloud code or, uh, an agent harness or wasp, like how, how's buzz different and what is it on? [SPEAKER_02] Um, yeah, I think like, uh, I said it a few times and like different tweets and stuff that, um, I think the slack killer thing is the kind of, it's a nice piece of marketing. It's a little bit superficial because I don't really think that's the only thing or that even the main thing, I think the main thing, the main, uh, kind of drivers behind it is this ability to switch models and harnesses. [SPEAKER_02] And it's like kind of a Trojan horse to get people to switch over to, um, local open source models, um, right. Give them the ability to use cloud and codex, but also to switch to, um, any other open source model or any other open source harness like open code or goose or one of those. And, um, cause if you can look a little bit around the corner, you can see, I mean, it's not even that hard to me. [SPEAKER_02] K three is like bumping up next to the frontier models, right. For fraction of the cost. So it's already gives you a perfect avenue to go that route. Right. So they're kind of like, I see it kind of like a Trojan horse for, um, open source models and for shared compute compute. And then further down the line, Bitcoin lightning payments, whether it's agent to agent, human to agent, human to human. [SPEAKER_02] Um, my guess is they start small early preview buggy, but they work out the kinks with the users. So they know which kinks to really focus on and then slowly release like those underlying features. And, um, another one of those is get they, I think they they're looking to kind of replace GitHub, right? So you've got all this code on GitHub, all your code. And if it's public, anybody can trade a model on that. [SPEAKER_02] Like the whole idea is buzz kind of works like this global context window for you and your community or your company or whatever. And then they have under the surface and ability to host your, uh, repositories remotely on your VPS or on your server, whichever, um, server that you run whenever your relay is hosted, um, self hosted. So I see them, I see it as being many things more than just a Slack killer, you know, and those are the directions I can foresee it going in. [SPEAKER_01] Yeah. Well, and I mean, you're, you seem to be very well versed on it because you've done some videos on Nostra specifically, but I think Nostra, I know Nostra is at the core of this and as somebody who's been a long time Nostra bull, I think I was probably one of the first hundred people on Nostra, uh, maybe first thousand. I'd be more confident saying the first thousand. So I've been on Nostra. [SPEAKER_02] When did it, when did it launch actually? Do you remember? [SPEAKER_01] I think 2022. Um, if I go, let me see, I think I was on it like three months after or a month after it launched and it was very, it was like a very niche, like not even a Bitcoin side project, but it was like a side project, a bunch of Bitcoin developers worked on. I've been on since yeah, July. Wow. It's three days past my fourth Nostra birthday, July 26th, 2022. [SPEAKER_01] Nice. Yeah. [SPEAKER_02] I got on in 2023. I saw, but I'm not a huge like primal user or, or a Nostra user. Um, but like I, I, I, that app I was telling you about earlier, um, the GPT wrapper, I was like, okay, I want to learn how to use, to use lighting payments. So I put, um, uh, LN, you're like lightning off. I think it's LN URL off in there. It's been a while since I messed with it. And, um, actually got some lightning payments, uh, for, for people to generate cover letters. So that was cool. [SPEAKER_02] That was like, it seems ancient now in AI, in, in AI years. It was like 2023 or four that I put it up there. Um, yeah. So it was pretty funny. [SPEAKER_01] Yeah. But I mean, to your point, like primal, Domus, so everybody listening doesn't know what Nostra is notes and other stuff transmitted over relays. It's a communications protocol, very simple. And the first, um, predominant use cases or applications built on it were, were social media based. And for the longest time, Nostra developers and anybody's been paying close attention to development. I think Jack is one of those people. [SPEAKER_01] I've talked with him specifically about this. Um, over the years, I get like social media is just like the tip of the iceberg. Just this ability to use private public key pairs to sign events and have cryptographic proof that something existed at some point in time in a certain state is very powerful. And the social media use case, you can prove that somebody who controlled a private key and, um, at this point in time wrote this message and relate it to, to the network. [SPEAKER_01] But now like you're saying, I think one of the biggest problems that many have with, um, these LLMs, particularly if you're using like codex or cloud code only is like the context windows are, are relatively, they're relatively short if you're pinging the models a lot. So you can jam the context window, um, or compact it multiple times a day. And then your, your AI system gets some form of amnesia. [SPEAKER_01] If you don't have a second brain or something set up that it's plugged into. And that's where I think buzz leveraging Noster, um, in this, this historical context that you have over time with signed events is, is an unlock for, for creating like a corpus of context that builds over time that the agents can just plug into. [SPEAKER_02] Yeah. That's a really good observation. I always looked at it more like, um, the thing that I thought was cool is that it's, you know, it's a permissionless protocol. So you can just kind of interact with anything on the protocol. So like you could, you can just create these Frankenstein apps, you know, you could connect, uh, you know, imagine trying to connect Slack and discord and GitHub together and like put them together. Like you can't really do that. You could do that very easily with buzz and some other, uh, apps or things running on the protocol. [SPEAKER_02] So, um, seeing buzz come out built on top of Noster and being like, okay, cool. There is a really nice use case for Noster outside of social media. This is exciting. Let's see what else we can do. [SPEAKER_01] You know? So freaks this episode was brought to you by our good friends at BitKey. Self custody is one of the most important things we do as Bitcoiners, not your keys, not your coins. A lot of people never make the jump because the process feels intimidating. The key is trying to make that jump easier. You guys know it pretty well here already. It's a Bitcoin wallet from block built around a simple idea. Let's give people a better path to holding their own keys without making them feel like they need to become a security engineer overnight. If you have Bitcoin sitting in an exchange and you have been meaning to take custody, stop procrastinating. [SPEAKER_01] Use the code TFTC10 for 10% off the new BitKey at bitkey.world slash TFTC10. All right, freaks. You know I don't take sponsor money from products I wouldn't use myself. So listen up. The Avon Bitcoin Visa card is one of the most interesting things I've seen in the Bitcoin lending space in a long time. Here's the deal. You can get a line of credit up to a million dollars backed by your Bitcoin without selling a single SAT. No games, no annual fees, no minimum draws. And your Bitcoin is custody by BitGo, one of the most trusted names in digital asset security. [SPEAKER_01] Avon never lends it out. There's no rehypothecation. You stay in control. You can lock in a fixed rate for up to 10 years. 10 years. That's 10 times longer than most lenders out there. We'll go interest only for up to five years. Rates start at 8.99% APR. For a product that lets you keep your stack and still access liquidity, it's hard to beat. On top of this, that's what you also get 2% unlimited cash back every time you use the card. Spend fiat. Keep your Bitcoin. That's the whole game. [SPEAKER_01] If you've been stacking for years and need liquidity without triggering a taxable event, this is worth a serious look. Go to avon.com slash Bitcoin. That's A-V-E-N dot com slash Bitcoin. Check it out. And then the agents get their own identity. Yep. Which I think is interesting. [SPEAKER_01] I haven't explored the full thought experiment about what that means, but just thinking about where this, because like I have my Hermes agent and everybody's like, when are you going to let other people on Buzz get access? So I'm like, never, because it's got access to a server with a bunch of proprietary information on it. But you can think of a scenario where people just build individual agents that don't have as much sensitive proprietary information, don't have access to that information. [SPEAKER_01] People can just begin sharing agents. They can have like matrix agent Smith like reproducibility. Just basically emanate throughout Buzz communities. [SPEAKER_02] Yeah, exactly. Because they can move, you know, you can move with that when you go take your identity with you to a new community it comes with. But I also think that like, it's there and built on Nostra so that it can enable sharing of resources of compute and paying for those, you know? So I think, I mean, there's two, there's more than one side, right? It's like all the benefits of Nostra, but I think that's a, that's going to be something we'll see. [SPEAKER_02] And I mean, I wrote that in one of my first tweets and Jack retweeted it. So there's a good, there's a good, um, uh, good possibility that that is what they're planning. [SPEAKER_01] Yeah. No. And then like the fact that it's on Nostra too, it's open source protocol, a lot of the applications, but on top of it are open source as well. Yep. Yep. And so you can like the, the permissionless nature of it too. Like you can imagine just like sending agents be like, Hey, somebody had to build something like this on Nostra and like, go find it incorporated into our website. And like the whole idea of shared compute, there's like routester open agents. There are these compute markets that have already been built on top of Nostra. [SPEAKER_01] So the ability to, to port in that code and just create like an open marketplace. Like, Hey, I have a, I have a GPU running, running in my house. So I'm not using it. I'm going to put a L four or two gateway on top of it, plug into, to routester or open agents. I'm going to use their code to basically market that I have this compute available. And anybody that is connected to me via buzz, if our, if our mpubs are connected, like you, you know, to access this compute as well. [SPEAKER_01] If you pay for it. [SPEAKER_02] Yeah. I mean, it's pretty cool. We saw what happened. I'm sure people are, you know, about what was going on in India where they're banning bit chat and stuff like that. And then it's just like, when you have these kinds of shared channels over open protocols there, it's pretty hard to shut off access to a model if they're being shared that way. I would assume. Right. So that's also a cool, a cool possibility. [SPEAKER_01] Yeah. I mean, I forget what the Noster GitHub replacement is called. But yeah, if you get that in there, it's open source and the code is stored on relays that people are self hosting. I think it's going to be very hard to shut that down. Definitely. Yeah. [SPEAKER_02] Cool. So we've been pretty philosophical. Should we do any demos or what else? What are you thinking? [SPEAKER_01] I think let's do a demo. Like, I mean, and maybe as you're doing a demo of how you're using this, explain how, like, what, like the unlock is like for me, like, again, the agents being able to coordinate like Martin, who is our Hermes agent. When I got him connected, I made him basically like the Sergeant Arms lead connector. And then I rewrote the system prompts for Fizz, Bumble and Honey and created one other agent. [SPEAKER_01] Basically, Martin became our orchestrator and he's got access to basically like our, we put all of our meeting, like our transcripts of our meetings, contracts, advertisement schedules that we have to get in. So he's got access to all that company information. So Martin, you know what we're trying to get done in the business. [SPEAKER_01] You know, so sort of some of the low hanging fruit initiatives that we haven't begun working on, like, all right, hop in here with Fizz, Bumble and Honey and delegate some of the tasks that we have not finished yet to them. And it was like, I was watching last night, there was like a, probably like a 45 minute loop of them just going back and forth until they got to a point of actually completing a task. So it's like, holy crap, this is crazy. Yeah. [SPEAKER_02] Yeah. And it's pretty good at that, too. I'm surprised that like the end to end workflows that it's able to kind of complete, know when to keep going, when to delegate and when to stop and stuff like that. So that's pretty cool. Sounds like you might even be doing more practical stuff than I am because you're actually using it for your team. And like, meanwhile, I'm just kind of playing around doing like, you know, demo stuff. Can you see the screen here? Yep. Yeah. [SPEAKER_02] And let me just get this like kind of minimize here. So yeah, like you were saying, you know, what's a good one. You know, one thing I shared earlier today that a lot of people seem to like was this prompt where, you know, I'm pinning models to the agents. [SPEAKER_02] So like, I'll have one that is pinned to Sonnet, like a lower level model and one that's been to Fable for more complex tasks, but I'll have them bounced up stuff back and forth because I kind of know the workflow. So I'll tell, you know, Shared Boy, you download a transcript from this video and this transcript, pass it to Fizz and Fizz, which is Fable. [SPEAKER_02] Find the five most surprising ideas from the time from the transcript with timestamps and really get chunks where you're not cutting off a sentence or an idea and pass that new document of chunked transcript back to Shared Boy, who's Sonnet. Use FFmpeg, cut out those sections to make short clips to post to social media. So I get them to make basically shorts for me for like Twitter and stuff with that. And then like you said, they're bouncing stuff back and forth. [SPEAKER_02] And I find this like kind of workflow way nicer than in Claude Code where you have sub agents. I don't know why, but I never caught on to using sub agents. Like you have the same thing basically, but just something about having them in a shared chat, which is like, people have been gravitating towards using mobile apps, mobile solutions, right? [SPEAKER_02] Because of something about that where you can just kind of have conversations with teammates, with the agent. Just, I don't know, it feels nicer. And I really like that about Buzz. That's just like one example that I used it for for today, where I prefer to use it over something like Claude Code. [SPEAKER_01] Yeah, well, in this exact example, so we have this exact workflow. We built this for the pot, like we'll use this workflow for this podcast, like a very similar workflow. It's probably not the exact same, but we do the same thing where it's like, hey, take the transcript with the timestamps of this episode. Find the most engaging parts. Actually, like we have a Twitter API, a third party Twitter API that we use, like scrape that, look at what's trending. [SPEAKER_01] And if anything that we talked about matches with something that's beginning to trend, like maybe we should focus on that. And then find the timestamps of the clip and go clip it. But we have our social media manager who has access to Martin in a sort of private Discord channel doing that workflow, like in a silo. [SPEAKER_01] And so like when I think about Buzz, what this opens up is like the ability to take our social media manager and Martin, the single agent out of that silo and like pull them into a more collaborative space where not only could he ask Martin to do this, but like he could delegate specific tasks within the network. And then this particular workflow to get better results. [SPEAKER_01] And then on top of that, like, you know, have the human members of our team hop in and be like, well, actually, yeah, like you guys did. But here's some input for me about another angle we could take on this. And yeah, it just really consolidates. Consolidates the work and makes it more open. And that's actually one thing I've been thinking a lot about. And it's actually funny enough influenced by Dorsey. [SPEAKER_01] And I think Dorsey is really emerging as somebody who's viewing this whole AI revolution with a very clear mind. And particularly his paper that he wrote with Oloff from a roll off, excuse me, from Sequoia and then the podcast they did about the intelligence layer companies becoming intelligence layers. [SPEAKER_01] And like this whole concept of instead of individual employees or members of your team working in these silos, like, yes, they will have delegated tasks and they'll have goals and there will be a division of labor. But the ability of these agents to open up collaboration across the team and for the team to have access to all the information about what everybody else is doing is extremely powerful. [SPEAKER_01] And I think that's something that that people really haven't caught on to yet either. [SPEAKER_02] Yeah. And that's why I like to kind of refer to it as it's the first step in the right direction to have a have a global context window. Right. Because it's like usually you have, like you were saying, things siloed are spread out between different apps and you're bouncing back between them. And you lose context, you lose the ability to collaborate with other people, get input from other people where it's like, you know, you just talk about what you want to do your ideas and then you can have something implemented for you right there in that moment. [SPEAKER_02] Right. So it just like speeds things up, gives you this global context window, so to speak. And I think that's like the like a really cool direction with this. And one other thing I want to point out was like, you know, I'm doing this as a as a one off like it's kind of like a skill or whatever. It's a prompt. Right. But like with a lot of that stuff, I think personally, I'm trying to I'm inspired by buzz that it's built on Nostr. [SPEAKER_02] I'm trying to think of ways to incorporate Nostr into apps that I build, because I think it makes sense when it's a deterministic workflow. Right. When it's like, you know, it's just a very strict process that's going to be repeated over and over to build some kind of like just niche, small app that you host that does that. [SPEAKER_02] So like you're talking about where it's like scraping the using the X API, scraping X for certain trends, cross referencing that like I kind of build something similar as just like a little demo. You might have seen it in the video that I posted on Twitter. And I originally had an externally facing API. And I just thought it would be cool to like learn a bit more about Nostr instead of my agent running a workflow or like a recurring daily task and doing that call and using tokens for that stuff. [SPEAKER_02] Why don't I use a recurring job in my Wasp app? Because that's like also something really easy to do in Wasp is, you know, just recurring jobs are a primitive in Wasp. So you're just like set up a recurring job, tell the agents, set up a recurring job that instead of that takes the same stats that you're pushing to the external API, but push them to Nostr. Just make it a Nostr event, sign it and push to the Nostr on my relay. [SPEAKER_02] And so I just get now to tweet stats every day from my app pushing to Nostr. So the agent isn't doing this, but it's going into the agent context, right? So I can just reply to this here and be like, cool. You know, Fizz, tell me what's the like, what's working and what's not, right? Based on the current trends like you're doing stuff like that, I think is really cool. [SPEAKER_02] I don't think it's like nailed the ability to use Nostr to its full potential. But I think just through trying out things like this, we might be able to find cool ways, creative ways to build apps on Nostr that are integrated into your relays and your buzz communities. [SPEAKER_01] So Freaks, when you take Bitcoin seriously, you start with custody. You want to control your keys, avoid single points of failure and make sure your savings cannot disappear because you or someone else screwed up. That is what Unchained has been focused on since 2016. Unchained is the leader in collaborative multi-sig custody of Bitcoin financial services that keep you in control. They secure over $12 billion in Bitcoin for more than 12,000 clients. That means about one out of every 200 Bitcoin sits inside an Unchained vault. Their model is simple. You hold two keys, they hold one key. [SPEAKER_01] And it always takes two keys to move Bitcoin, meaning their single key can't access your Bitcoin on its own. Just resilient, shared custody that gives you institutional-grade security while keeping you sovereign. Unchained also lets you trade straight from your vault, access Bitcoin-backed commercial loans, open a Bitcoin IRA where you hold your own keys, and set up personal, business, trust, or retirement vaults. They even offer inheritance solutions built for long-term hodlers. Or opt for the highest-level private client service with Unchained Signature and get a dedicated account manager, discounted trading fees, exclusive access to events and features, and much, much more. [SPEAKER_01] If you want a partner that helps you secure and grow your Bitcoin without giving up control, go to Unchained.com and use the code TFTC10 at checkout to get 10% off your new Bitcoin multi-sig vault. That's TFTC10 at Unchained.com. Freaks, look at me. I'm glowing. I've got like an angel's halo going around me. You know why that is? I feel good. I feel taken care of. I feel blessed, healthy, happy. And that is because I'm a CrowdHealth member. My family and I have been CrowdHealth members for five years now. Literally this month, five years ago, we joined CrowdHealth. We've had two babies. [SPEAKER_01] We've had multiple health events and we're never going back to health insurance. CrowdHealth is crowdfunded healthcare. So you sign up for CrowdHealth, you pay a monthly fee, you help out with other people's bills. And it's significantly cheaper than health insurance. We were on Cobra as a family of three. When I left my last job before I went full-time with TFTC, went on the CrowdHealth. Now as a family of five, we pay, I believe $700 a month. It's significantly cheaper. They're going to negotiate prices lower for you. [SPEAKER_01] They've consistently negotiated healthcare prices as much as 50, 60, 80% in many cases. They help out with babies. If you have a pregnancy, you pay the first $3,000 and the crowd covers the rest. If you have a regular health event, you pay $500 and the crowd pays the rest. Go to joincrowdhealth.com. Sign up today. Use the code TFTC. Opt out of health insurance. I'm an insured baby and I love it. Use the code TFTC at joincrowdhealth.com. [SPEAKER_01] You'll get $99 a month for the first three months that you're on the CrowdHealth platform in the community. Dick Winners, you found sovereign money. Now find sovereign health and sovereign healthcare. I think one of the underappreciated aspects of that, building on Nostra too, is the network effect. Because what Buzz essentially is, is a Nostra client. It's just a client. It's a front end built on top of the protocol and the relays connected to that protocol. [SPEAKER_01] And what many people, particularly the Nostra haters over the years have not realized is that all Nostra needs to do, similar to Bitcoin, is just survive long enough and maintain a critical massive network effect that if it continues to grow, the, for entrepreneurs specifically if you're building apps, the way that Nostra works with the public private key pairs and the way clients work is like, I have a primal. [SPEAKER_01] I created a new NSEC and public key for Buzz for my individual profile there, but I could easily import the NSEC that I've been using for four years. And so like the same NSEC I use on Primal, I use on Domus, I use on Wisp, I use on Zap.stream, I use on Rouser, like I can just port that over to Buzz and have the full context of my Nostra history brought to Buzz. [SPEAKER_01] And so instead of trying to basically as an entrepreneur releasing an app, trying to bootstrap a network effect, like if your app's good enough, anybody on Nostra with a private public key pair can just easily sign into your app with that and bring full context with them, which is extremely powerful. [SPEAKER_02] Yeah. And it's kind of cool to see like, you know, sometimes we're like for people, but these forward thinking technologies, it takes a while, like you said, it just has to not die. But it's like, people build it, they don't even know that like, AI and coding agents are coming around the corner, but it takes something, some other kind of progression, some other kind of step change to then like open up like the aha moment, right? Where it's like, oh shit, this is it. This is like, this is going to work now, you know, this might really work. [SPEAKER_02] And I feel like it's happening here. It's like the beginning of that aha moment where it's like, oh, Nostra can be, Nostra can be bigger and can really play that role that it was designed to play. So I'm excited about that. [SPEAKER_01] Yeah. And it's like a weird feedback loop too, where like the AI vibe coding is sort of enabling it in a way. [SPEAKER_02] Mm-hmm. Mm-hmm. [SPEAKER_01] Where instead of having to read like the, the docs on how Nostra works, it's like you just tell your clanker, like figure out, like I did it. When I spun up my open claw agent, I was just messing around, like seeing what it could do. I was like, okay, like, I want you to be able to spend Bitcoin, like go figure out what the best wallet is and the best way for me to get you Bitcoin. It did some research. It's like, hey, we have a server. [SPEAKER_01] There's this thing called Phoenix D where we can run a lightning server on, we can spin up a lightning server in our VPS. We should use that. I was like, okay. Now I'll just send you like, when you, when you set it up, send me, send me an invoice to, to basically create a channel. Cause the way Phoenix works, it's like, okay, when you set up the server, send me an on-chain address, I'll send Bitcoin to that and then you'll submarine swap that into a lightning channel so that you can spend. [SPEAKER_01] And, and it did that. And I was like, okay, you have a server. You have Bitcoin, like you have LNURL off. Like since you have your server, you can sign the private key and you can sign into websites that, that are LNURL off enabled. I was like, all right, like go to LN markets. So I want to see you like put a trade, get to go along Bitcoin, like sign in, go long. It did that. And then I was like, okay, when like, I want you to manage this, like just create like a simple trend function. [SPEAKER_01] Following, um, trading strategy. I don't care if you lose money. I just want to do this for, uh, experiment reasons. Like also create a NOSTER account, um, and then post your trades on a daily basis. And it did that. Like it created an NSEC and an MPUB and was posting the NOSTER autonomously for like a month before I was like, all right, this is, this is cool, but I don't feel like keeping up with, uh, with the trades. [SPEAKER_01] Um, but like the, going back to the feedback loop, like to your point about like, it just needs to survive. And then something will happen where it really creates that aha moment. And like, it's a symbiosis where like vibe coatings, enabling the, the accessibility to these protocols, which are, um, a lot of times like techno babble to many people, but you don't have to understand the techno babble anymore. Just like tell your client. [SPEAKER_02] Yeah. Yeah. That's crazy. It's really fun. Um, cause you just have the idea and then you just go for it. I love that. [SPEAKER_01] Yeah. [SPEAKER_02] Um, something else I do a lot. Like, um, I just get, I get it to create HTML presentations for me so that I can learn stuff. Cause you were talking about like, I don't know how to use or build on NOSTER, but, um, I just tell my client here to do it. Or if I want to learn basically a high level thing, I'll just be like, create an HTML presentation. And I actually did that for, um, for NOSTER. So I was like, I'm a full stack developer. Like make sure I really know what I'm talking about. Like create that presentation for me, just like an HTML file. [SPEAKER_02] I love doing that to learn about stuff so that I get a deeper knowledge. And then like, I did this before I started building that app that was sending NOSTER events. So like when it does stuff, I still have a clue what it's doing. And if I run into problems, I can, I can maybe point, point them in the right direction, you know? Um, so that's cool. That was fun while, while building the, um, this app here that like, you know, I can just click sync. And then I get that, that event, that NOSTER event in Buzz. [SPEAKER_02] So, and then when it comes in there, like some of the workflows that great there, boom, came in, tells me, Hey, you got new tweet stats. And then I can just start chatting, chatting with, with him. So, um, some of the workflows in Buzz are still a little bit like iffy. I don't know. There's a, this, it's an experimental feature. So in their defense, you know, they, they've got it in settings under experiments. You can click on workflows or projects. Um, and I had some, some work, some don't, some are a little iffy. [SPEAKER_02] So I think they'll get it worked out though. Um, yeah, I think that's cool. [SPEAKER_01] I do as well. Um, the, I'm sorry, I got my kids yelling in the background. Um, the, uh, the, uh, do you think this is making people more productive? Like, I think that's one of the big questions, particularly for the, the bears and the doomers out there. Like, Oh, it's great. Like usage is going up. Like, is there actually more productivity in the economy? [SPEAKER_02] Uh, um, can't just ask a question like that and then leave Marty. Um, it's try to shut the door. Um, uh, like that's a good question because yes, it can. Is it, uh, I think we got to wait a little while to see the effects. Of course, like, um, it's going to take a while to trickle through, but like, um, on a general, like on a broader basis. [SPEAKER_02] But I think if you know what you want and if you, if you, if you, if you, if you know what you're doing, you know what you want and you know when, like how, like, even if you're asking these things for advice, if you know when it's giving bad advice and you, or you have a good sense of what's the better advice, which advice to take, then yeah, you're, you're like, uh, I started this, that app and a company. Um, like I wouldn't have been able to do that. [SPEAKER_02] I wouldn't probably would not have done it pre 2023, you know, pre AI, because like, uh, I'm not the kind of person that's going to go out on a limb and like hire a taxi, um, advisor and all these people. Like I literally did, did like the majority of the work first off with just agents, like copy and pasting websites, screenshots, like what's this mean? What do I got to do here? What do I gotta do? And just like slogging through it. [SPEAKER_02] And before we really had like good agents like this, but like, yeah, if, if you're driven to do that kind of stuff you have, you have, so you just have an idea and a will to do it. You can do it. So, yeah, I think for the right people, it's a, a, a multiplier for sure. It's a great lever. Um, it's a huge lever and, um, in the wrong hands, you know, it's just going to be a, it's going to lead to nothing as well. You know, that's the way it goes. [SPEAKER_01] Yeah. I mean, you use the word earlier, but I think, uh, in terms of like deterministic workflows and sharing them, but I agree too. Like that's the way I view it. That's what I tell people is like, the way I use these tools is I know what the output should be, particularly for our workflows at TFTC. And so like, I know when it's wrong. It's like, I don't expect the models to go out and like create something new for us. If that makes sense. [SPEAKER_01] It's like, I know we have this task that we need done and we typically don't get it done because we don't have enough bandwidth. Like I know what the end results should be. Like, please go do that and get the output. If it's right, if it's right, thank you. Good job. If it's wrong, you messed up here. Do that. I think people falter is thinking that it's going to just do something magical for them. Like these are essentially their large language models. [SPEAKER_01] They're just doing a probabilistic analysis of what the best, what the best next word is and the output. And like, you just need to know what the output should be and apply that lens to it. Like don't say, build me a business that makes a billion dollars a year. Make no mistakes. [SPEAKER_02] It's not right. Yeah. You still got to do the work. It's just easier to do the work. That's about it. You know? So it's easier to get to, it's easier to get something done that you might have basically no knowledge on previously. Like you're a great example, like being able to self host these things, these tools to a virtual private servers and connect to the SSH into them and all this stuff. It's like, yeah, that stuff was very hard just five, four years ago. You know? [SPEAKER_02] So it's like, um, it's, to me, it's not really a debate. Um, but when I see companies that have token mandates, like you have to use so many tokens, you have to use AI to this, you know, these benchmark hit these, these targets. And, you know, the people who don't, the people who sat around and did nothing before are just going to waste those tokens, you know? So it's like, it depends, all depends on how you approach it. [SPEAKER_01] Yeah. Okay. Bring this back to buzz. What's your, what would be your top request for a, for a feature? [SPEAKER_02] Top request for a feature. Um, I think it's, I think they're doing it right. Like I'm willing to, you know, these are experimental features. This is early, early, early, um, preview stuff. Um, I think what I would like to see is like, if you're used to like, um, if you're kind of used to working in a terminal and, you know, just like these views. And then if you're a software developer, you know, you might want to jump back and run your own commands. Like you're used to that stuff. [SPEAKER_02] It could be cool if they had something embedded in here like that for the more technical people. Um, but I, it's not like it's not, um, yeah, the cool thing is it's open source. Some, some, someone like me or someone could put that in as a feature and, and submit a PR to block. Um, so maybe we'll see that, but I like the, I think I like the approach. I'm willing to deal with some kind of the rough edges at the moment while it's really early preview. Um, because I think it's going in a very cool direction. [SPEAKER_02] Um, I didn't, uh, you know, I'm like, I'm not one to jump on, on bandwagon. It's just because they're trendy. Like if I see something that interests me, then I'll try it out. Um, so yeah, this seems like a pretty cool approach. And, um, I'm, I want to see more integration with, I want to see what I would like to actually see as other cool stuff happening on Noster that gets integrated here in a creative way so that we can use these tools together in creative ways. [SPEAKER_02] But I think we're still kind of figuring it out. At least I am. [SPEAKER_01] Yeah. And I, and like the, the tweet that you responded to, I just, I think, I'm going to do a lot of things. I think the first big unlock could be basically forking or implementing Rouser open agents for a market to compute, particularly for open source models, and then equipping the agents with, with Bitcoin wallets that you can, they can load up or to your point, like I think you said on Greg's like being able to tip other humans or agents to get to work for you. So very true. [SPEAKER_02] Yeah. I mean, like look at primals or I'm sorry, like Noster. I was, I use primal mainly, but like Noster is such a good example. And I mean, Lynn Alden has pointed this out before that, um, the incentive structure is so different than Twitter, right? Like when you make something useful on Noster, people literally tip you, send you money, you know? Like, and, um, now imagine that safe. So, so we know it works. We know people are willing to tip for, uh, valuable information, insights, work, things like that. [SPEAKER_02] Now imagine you have that here in buzz where it's like an open community. So it's not just your company, right? You're doing something private, but let's say we all joined together and we start like some open community that's working on an open source project. And someone just comes up with a really cool idea and mentions it in the community. You could pay them for like good ideas because then you get the agents to implement them or then you pay, you know, whoever's running the really cool local, like, um, uh, uh, high [SPEAKER_02] performance, um, open source model. You send them a zap to run that, um, to implement that task on their shared compute or on their agent, you know? So like, that's really cool. I think that's what I want to see basically. I think, and I think we will see that if, um, it's like you said, if it just stays around long enough, it doesn't die. [SPEAKER_01] Like a bounty board too. Um, yep. Yep. Create bounties for particular, particular workflows or tasks to be done. And it's like the perfect example, like this podcast is hosted on Noster. We use found their podcast. It's a, it's a Noster client. And so like, there's going to be people who listen to this podcast and stream us Bitcoin, um, over that network. Um, and like, if you were like, I could, if you like, I could literally put your end pub [SPEAKER_01] in this episode, I think we can do it individual episodes. And like, you could share in the stream of Bitcoin. That's coming our way as people are, are boosting and streaming sets to, to this. Cool. [SPEAKER_02] Cool. I'll, I'll spend it on some sweet, powerful agents then in the future, in the future when it gets implemented. But yeah, that's what I would like to see. [SPEAKER_01] Yeah. I know it's getting late where you are. Um, how, uh, how should we end this? Any, any final thoughts, any calls to action, any, um, philosophical musings about the state of AI, where we're going and we're getting. [SPEAKER_02] No. Yeah, no, I think we did a pretty good job, uh, of doing, of, of, of covering that stuff. I like the angle we took here. It was cool, different than the other podcasts. So that's nice. Um, uh, no, I think this is like pretty good. Maybe if, if, if people want to know more or like, like hear more, um, they should let us know. And then like, that'd be cool to, there might be some things out there that people are interested in that, that we haven't really hit on. [SPEAKER_02] And then, um, we can explore it further, talk about it, um, on, on the social media platforms or do another one of these. That would be cool. [SPEAKER_01] That'd be awesome. Well, uh, appreciate you coming on. Thanks for having me. Sure. It's been a hectic week for you. You're just out there talking about the tools that are using and become a, become a little internet celebrity this week. So I appreciate you coming on the show and, uh, You're welcome. Uh, it seems like you're a Bitcoin or, uh, at least you're playing around with it, which is, uh, which is cool to see. And, uh, in Nostra, you're becoming well-versed on it. [SPEAKER_01] And these are two projects that obviously I've been very passionate about for many years. And it feels like this agentic economy is, is the moment for Nostra and Bitcoin to shine. And it seems like we're getting to the point where, um, people are beginning to recognize that. Uh, it was just cool to see you talk, um, about these technologies and the potential for them on a show like Greg Eisenberg. It really doesn't cover this stuff much. [SPEAKER_02] Yeah. Yeah. Totally agree. Yeah. [SPEAKER_01] All right. Well, hopefully we'll do this again at some point in the future. And until then, enjoy it, brother. You too. Peace and love freaks. Peace. Thank you for listening to this episode of TFTC. If you've made it this far, I imagine you got some value out of the episode. If so, please share it far and wide with your friends and family. We're looking to get the word out there. Also, wherever you're listening, whether that's YouTube, Apple, Spotify, make sure you like and subscribe to the show. [SPEAKER_01] And if you can leave a rating on the podcasting platforms, that goes a long way. Last but not least, if you want to get these episodes a day early and ad free, make sure you download the Fountain podcasting app. You can go to Fountain.fm to find that $5 a month, get you every episode a day early ad free, helps the show, gives you incredible value. So please consider subscribing via Fountain as well. Thank you for your time. [SPEAKER_01] And until next time. [SPEAKER_00] Okay.