Kristian Freeman - Professional Synthesizer ｜ The Clanker Chronicles - Ep. 0

Hello and welcome to the Clanker Chronicles, I'm Craig and I'm here with my co-host Zeke. Hey party people. On this show, this is our pilot episode if that wasn't clear. Episode zero. Episode zero here we go. On this show we dive into how people are using AI agents or as they're often lovingly referred to as clankers. Everyone's doing this a little bit differently and today on our show we're going to show you how someone is utilizing their clanker. On today's episode that happens to be the wonderful Christian Freeman. Welcome Christian. Hello, hello. How's it going man? So many things to show you, so many unique minis stored in closets and uh like tokens being burned at the speed of light and just all sorts of great things going on. Yeah, thank you for having me. Awesome. Full disclosure Christian's my boss and Craig's boss for that matter so we have to be careful about what we say here. Totally. I just want to add that we also all work at Cloudflare. Oh yeah, take us down rabbit holes. You can't say no to you, like I have to take you down whatever rabbit hole, you know, you're like oh we're doing this agent stuff? Okay, well okay. Yeah, whatever you say boss. I just wanted to add that even though we all work at Cloudflare, the purpose of this show is not to talk about Cloudflare the whole time. It's to talk about how we do creative coding and build stuff on the Internet. Yeah, and everybody's doing this differently. We know that Christian does this a little bit differently. Christian has been using tools, like I haven't heard of actually even the tools that Christian's using, but before we get there, Christian, what is it that you, what is it that you would say that you do here? Yeah, so manager developer relations. What do I do on a daily basis? I would say I actually spend a lot of like moments of somewhat crisis trying to figure out if I'm doing the right things, but I feel like primarily what I do now is like information synthesis, which is funny because I'm in like my synthesizer dungeons right now, like over to the side, there's all my synthesizers. So I'm like a professional synthesizer, like the synthesizers next to me. But like really, I feel like I'm like unblocking people. Interestingly enough, I spend a lot of time, obviously my career as like a developer. And I think the way that we all write code has changed so much in the last, I don't know, year or two, but like, shoot, I wasn't even writing that much code anyway, at that point. So like, it's interesting. In some ways, I'm writing more than I was. And in other ways, like what I'm doing is like some interesting and we'll get into it. Just yeah, interesting amount of kind of like remixing of information with LLMs. And yeah, we'll get into it. It'll be, I think, interesting. Yeah, for sure. I like, I love that you're using it in all walks, right? I think that's really interesting about what you've been building here, like from the bits that, the little bits that I've seen, I'm excited to share. Yes. Yeah. Christian, you said that you've been staying up until two or three in the morning lately working on some stuff. And like, sometimes that's a sign of, you know, a problem with your work-life balance, but it could also just be an indication that you're really excited about stuff. So I want to go, I want to talk about that. What's keeping you up until two in the morning? So, I mean, yeah, at some point I'll share my screen and we can kind of dive into it. But I guess the big unlock for me at like a very high level, I think all three of us have felt this in the last, I don't know, probably year or so, like it started when Cloud Code came out. And I used it pretty quickly. And I was like, Hey, this is very cool for writing code. This is great. Like I was copy pasting stuff from the browser or I was using Copilot or whatever. And this, this is awesome. And then I think what sort of happened is, especially as like some of the better models came out. And I think also as the like time, sort of the round trip inference time got better. And I started to realize like, it does have sort of this propensity to like reach towards things on my computer. And at first I was a little hesitant of that, you know, like, boy, it sure wants to write a lot of Markdown files that like is quite noisy when it comes to that sort of thing. And then after a while, I think I transitioned to more like, maybe that's actually kind of the superpower that it has, like that these tools have running locally on the machine, like what we would now call coding agents. And then at some point, it sort of transitioned over to like, actually like producing code is, like I said, it's like not, I don't spend as much time writing code as I used to, but like maybe that's fine, because the model of like, these coding agents are also just quite good at like doing things on your computer became very interesting to me. And then it's just fully spilled over into like, I mean, we'll get into it, but just like every single aspect of like, I like live in this like environment, like longer than I should every night, right? Like just new ideas and like new things. And like, yeah, we'll get into it for sure. Before we share your screen, is there anything that we should know outside of work? Are you using this thing outside of work for stuff too? I mean, it's all holistically in one place for better or for worse, right? I try and be a little bit careful about like some internal work stuff. But like I do spend a lot of time, like again, information synthesizing. And what I think I'll do is I kind of have two things that we can talk about. And maybe I'll let you guys pick which one is more interesting to start with. Like, you can sort of think of it as like, everything does revolve around open code, basically, like in one form or another, I spend pretty much almost all day in open code and just in various environments. One of those is like kind of 2e environment on my work laptop, which is I'm on right now. And that is where I have sort of this like work second brain, where I spend a lot of time like dumping information into it, and then pulling things back out and just doing a bunch of stuff there. And that's kind of like, I think the simpler one to wrap your head around. The other one that I have talked a little bit about, I know with you guys, and also I did talk about it in Austin, we did like this little meetup thing is this tool called KeyMaki, which is basically a like open code wrapper inside of Discord. And that is like, basically spans every single part of my life, like work, personal health, music, like every little side project, every little website idea, to do list management, and manages my media server in my closet, like it does like everything. So like, you're all in. Yeah. And so they're like, essentially the same thing, because it is just all open code under the hood. And there's some interesting ways that that actually looks in practice. But I'll let you guys decide, like how you want to what you want to start with. And I'm sure we'll get to all of it, though. Cool. So I'm assuming anybody who's listening to this is already kind of like AI pilled and figuring out how to do all kinds of agentic stuff. But for those who may not be aware, you talked a little bit about, you know, using GitHub Copilot and copying and pasting code from different places. I think what we're focusing on here is this sort of new world where we have tools that we run on our own computer that have this sort of same AI language model superpowers as chat GPT, but they also have the ability to run programs on your own computer. So I think, I don't know about you, Craig, but like, I've been kind of following along with a lot of these people who have embraced this sort of like open claw Mac mini, let an agent go wild that you can like, send a bunch of tasks to a world that we're in now. I'm not there yet. So I'm actually really excited to hear about that. Yeah, same, same. And I'm actually a little jealous when I and Christian, you weren't kidding when you actually said that there are Mac minis literally in your closet. That's Yeah, technically, it's in my it's underneath my TV in my living room. But there is also there's a NAS in the in the closet, because it's right next to the router. And I feel like they're sort of like, symbiotically like converging on each other, because they just like talk to each other. So I mean, so I can speak a little bit actually, just as like introduction. So I did use open claw, like when it was coming out, and I did like the meme thing of buying, buying a Mac mini, I'm like a very big Apple guy and have been forever. So it's like a lot of the stuff I wanted to do, like reading my calendars and stuff. And there's actually like a really great thing that's existed forever, which I'm sure you both have used, which is AppleScript, which like works quite well for this. And it's like pretty well defined for it, which is funny kind of coming back full circle, like, oh, we're doing like AppleScript stuff again, but it's worked quite well for me for grabbing some of that basic stuff. And, and I wanted something that ran 24 seven, right. So like, I started with open claw, I think the rate that it was like developing was like a little intense, and like, it was hard to keep up and feel like I had a good handle on it. But then I think what really happened, and you can speak to this too, is like a Cloudflare, we are pretty, pretty all in on open code, at least for the time being, like we're really heavily invested in it, everyone is using it. And I just kept having this thing where I was like, open claw like seems cool, but I'm like running in a telegram thing, which feels really janky. Like, I really just wish I was using open code, because I'm learning so much about it and how to use it well from there's no lack of experts internally at Cloudflare who are showing like best practices and stuff. And that's how we can converge on this Kimaki tool, which is just like a wrapper around open code. And it's functionally ends up feeling a lot like open claw, but it really is just open code. I'm actually proud of myself so far, I haven't like mixed the terms of there's so many different like weird project names. I'm like, Okay, so far, so good. I haven't like, I haven't mixed them up yet. Why are we using open code at Cloudflare? Oh, that's a good question. I feel like you might be better. Like, do you want to speak to that, Craig? I mean, like, I can give my take on it. But maybe you all have like a better, like holistic story around it. Well, I think, you know, we're all stoked on open code internally. But I think mostly the outside world is still largely using cloud code for the most part. And people are using all kinds of different agents. But I think what's really cool about open code is that it is provider agnostic. So you can use it with anthropic models, open AI, Gemini, or you can bring your own models, which is really exciting. And it works really nicely with Cloudflare's AI gateway. And this is at risk of turning into an advertisement for Cloudflare. But really, this is like a pretty cool thing in that like, you can basically situate Cloudflare as this layer between you and whatever language model providers you're using to have like centralized billing and control over which models you're using and ways to fall back without having to rewrite your code or your, you know, your infrastructure. Yeah, and to safely control. And if everybody's running through the same thing, then we're able to set up the configuration at the front there. So we're able to like say, Hey, these are all the external servers that you're connecting to. And this is how you authenticate to them and that sort of thing. So like running it all through one place where everybody's at the same thing is a win. And then Christian got a little open code pilled and then went a little deeper there, which I think is cool. I think we're ready to open. I think we're ready to have him share screen. Should we should we get our minds blown? Yeah, yeah. So what would you like to see first? Which two of those are more interesting? I think we should just jump straight into this Kimaki 2am chatting with the thing and it does everything for you workflow. Yeah. And I am like, hopefully there's like a I was like, I don't think there's anything that's like weird for me to share in here. But like, I can kind of do some creative editing. And I really want to emphasize like, I'm going to keep pulling up things that are like, so random that I'm using for this that I'm like, Oh, yeah, this is great. So like, let me start I know you can already see like pictures and stuff. And you're like, probably Wow, what's going on? By the way, make it a little bigger. How's that feel? Is that good? That's somewhere on there. So like, conceptually, I think the first thing that you need to know is like this project. And we'll I guess we'll put a link to it and like whatever the description of the video, it's called Kimaki. It's an open source project. This guy followed me on Twitter, I thought he's doing interesting stuff. I followed him back and he was building this and I was like, Whoa, this actually seems really cool. Like the model here is essentially each one of these each one of these channels. So this is a discord. Obviously, each one of these channels is a different open code, or it's a different directory on my computer. And this, by the way, is running, like I said, on my Mac mini. So I'm on my Mac laptop right now my work laptop, but this is like connected to my my Mac mini. And each one of these a discord server. Basically, yeah, yeah, yeah. And like a bunch of and a bunch of open code servers to like, this, this is a project. Each one of actually not sure exactly how you'd think of the mental model and someone can come correct me if they want in the comments or whatever. But like, essentially, each one of these like threads, and these are using like discord threads is like a different like session, it's a different open code session. Yeah. And then so I believe that would mean that each one of them is like a different process running. Also, I'm not 100% sure how that works. But like from the top level, just to kind of recap, I guess how open code works, I think is actually very relevant to this is is open code, it uses the agents dot MD specification. And so each of these projects all refers to the same global agents markdown file. So I have like a global open code config. But then each of these projects is also its own thing with its own agents dot MD. And interestingly enough, like actually have a open code, like channel in here, which is very meta, like points to my open code global directory, and is how I manage the global configuration. Now that I would try and explain this. And if I getting too crazy, you can let me know if I'm going like full, you know, like always sunny, like me and with the like the pinboard or whatever, like, if it's turning into that, you let me know, this open code global configuration is also synced to my Mac, like my work laptop. So this is the same configuration pulled back and forth between the two. And they're like constantly sort of refining, refined, I really use this for everything. Just give you an example, except this is like a fun one. So I left it up here for us to look at is like, I went to AI engineer Miami and react Miami. And I brought my camera and took a bunch of pictures. It was like kind of the unofficial Cloudflare photographer. And I just really didn't like a lot of pictures. And so I jumped in to I posted all the images. And I was like, these kind of suck. Like, what can I do? I had a lot of conversations about like lenses. And like, okay, do I need lenses? Or do I just like not know how to use cameras. And like, I think this is like a sort of testament to like, just how good the models are that like, you can just have these random conversations with it about literally anything. And it's like, so smart. But then the thing is, it is open code under the hoods. And there's like tools and stuff like that. So at any point in time, I can do like a web fetch, and it'll just provide more information and more context. So like, there's one thing like talking about pictures, like, there's also just a lot of like ideation in here. So like, I make music in this program called Ableton Live. They have this thing for like macros, which are basically the way to like affect sound, like different filters and stuff like that. And you can build these little shortcuts for it. And I was just like, Hey, I think I was like, at the airport walking around, and I just kind of kicked this off in the background. I was like, Is there a way that we can just script those manually using code? Like, if so, you know, let me know how it works. And like, it kind of went and did its thing. I was like, No, not really. There's no way. But like, How many? Wait, hold on a second. How many of those things are going on at once for you? Like, you said you walk around the airport. Are you walk around the airport and you did Ableton and you did pictures at the same time? This was no, this is like when I was back at home or whatever. But like, I mean, I'll kick these off in all these different projects, like all the time, like all sorts of different things. And I think one thing that's probably worth kind of mentioning, I think like, Discord is not a perfect model for this because like threads are, they're okay. Like it's an it's an okay chat. Like, this is just me in this discord, by the way, it's me. And, and also like, I don't think I've actually mentioned it yet. But I gave the agent like a little character name. His name is Kage. It's like a like Ninja Rabbit guy, which is pretty cool. So I do end up spending a lot of time referring to it as like Kage, which like people cringe. I'm like, Yes, that's the name of my, that's the name of my agent. Sorry, I've given it a personality. Yeah, I know. Yeah. Did you design that? Did Kage make Kage's picture? Or is that does that exist? Is Kage a thing I don't know about? I did it in replicate. So I made the character and replicate. And I'll actually get to that. I want to show you as this too, because I am fully like doing AI asset generation in here too now, which is pretty cool. Sweet. But like, so you can jump. Yeah, good. You can use different like chat interfaces to interact with this thing. So you use this use Discord, but you could also use like, I've heard people you're using like iMessage or, you know, like messages, Telegram, stuff like that. How does that work? I think this one is specific to Discord. And it's actually something I don't love. I've gotten very close to like, slop forking my own version of this just to like kind of decouple it from like anything specific. But like, technically, this is just open code sessions under the hood. And like, I think you both know and poked around it a bit like open code, I think the sessions are basically like a SQLite database on the computers. Like in theory, you could poke around at it like that. This one is one of the things I don't love about the system is it's like pretty heavily coupled to to Discord. But yeah, that's, that's kind of how it works. Let me pull up one thing. I just want to mention it to you guys, because we talked about it, like, generating replicate stuff on here. So like, I did this video last week, it was like a sort of anime trailer for Cloudflare stuff. The, like basically doing that inside of open code, like, a lot of the time I think of this as doing this in open code, but it just happens to have like a UI wrapped around it. Like I continue to just find like new things around like, this is so much better to do in open code than like, Zeke, no doubt, you know, like the replicate playground, I use a lot and I use use it a lot too. Or basically, it's like a web browser. But like being able to sort of converse back and forth with the artifacts as part of the timeline is super valuable. So like the idea was like, I told it like, I want to strip together like four or five pieces of video, and then put them together. And like, frankly, I don't even really know what it did under the hood, I would assume it probably did like FFmpeg, like joining videos, but the idea is I could say like, clip one is good, clip three is good, clip two is bad, can you go and swap that out? And it would just like have all of that context enough to like, you know, mush it all together. So like, there just continues to be I've been running this for, I don't know, probably about a month and a half now at this point of having moved through a couple different solutions. And I love this, I could watch this like over and over again. It's very cool. I haven't seen this before. But so yeah, I feel like this is one of the main, like, problems that I have with open code right now is that even though it's in some ways beneficial, that is just a text based interaction. As soon as you're starting to generate any kind of media, you have to be like, Oh, can you like turn that into a web page or like open it in my finder so I can go look at it, come back here. But this is like fully integrated into the conversation, which is way cooler. I agree. Yeah, the fact that it's unfurling and you're able to play and talk specifically and you're not you're not losing context as you switch, which is important, I guess, like if you're on your phone, right, like you were talking about at the airport, you're on your phone, you're walking around, it's right there. You're not like, how do I switch into that app or whatever. Now, so when you are on your phone, talking to this thing, it's not running FFmpeg on your phone. It's running on your Mac Mini. Yeah, it's all it's on the Mac Mini. And it's not even that nice of a Mac Mini, honestly, like it's probably the mid mid tier one, but I've had no, the only problem I've ever had with it was I tried to get this. I tried to get this whole tool to like script a self reporting tool, which I just was tweeting about this a couple days ago. And we can kind of talk about it if it's if it's interesting, but like the idea that like, the whole server, the whole like, not even just one project, but all of the projects as a whole sort of bundle up this like report of what they've been doing, and then like use that to refine, like improvements to open code config and stuff like that. Totally vibe coded that, of course, like 100%. And it caused like some infinite loop, and it kept crashing, like, like literally the whole machine would crash over and over again. And I was like, clearly something I've done in like the last day or two, like this is one of those like 2am ideas was like, oh, like it can self report, and it'll, it'll get better. And everything will be smarter. But like, for whatever reason that like, I don't even remember what the real issue was. But like, that's, that's probably the worst part of the setup, because people have these on like, on a cloud VM, or they'll run it like distributed, you know, you can run it on Cloudflare and like a bunch of sandboxes. The funniest instance of this, and I still, my friend gives me a really hard time for this all the time is like my friend who lives in the same apartment complex as me, I literally called him I was like, dude, my my like Mac mini is down and I cannot talk to it. Can you go get a key from the front desk? Can you go in? I'm going to show you where it is. Can you turn it back on? And like that way I can like self diagnose from inside like I can reconnect to the discord thing. He was just like, dude, you are cooked. Like this is insane. Like that you actually asked me to do this. He did. And then I did connect and it's like, oh, like clearly something we did in the last day or two was was wrong. And so we figured it out. But it was just like, you know, what a weird world, right? Like we're sort of back on these like on prem. I want to own the hardware a little bit like it's interesting in that way, at least for this use case, right of what I'm building here. So that thing that went south that you were working on is something that I've been thinking about a lot too, which is like every open code session or every session with an agent contains all of this sort of like exhaust or like a paper trail of all the things that went right and all the things that went wrong. And theoretically, you could analyze all of that data to improve your own configuration, your own set of skills, like the projects that you're interacting with, like, there's a lot of really useful data there. So don't give up. Yeah, I think there's a there's a way to do it. I think it probably requires a bit more planning than I sort of it was a throwaway idea. And not only is a throwaway idea, but I think it's like pretty intensive in terms of like, the amount of information that's coming in, you know, and so like, I think it's probably something I needed to spend more time planning. But I mean, I built like a full, like two things. I built a full like to do list API that the agent primarily used, like I was going to use it myself as well. But I just never really got around to it. Or like it would report back on like, open to do's and close to do's. And it was actually built into the global open code where it would like write its own to do's and then go and complete them. You can actually see there's one right here that is called tiny to do. And it was interesting to see. I mean, like certainly it was motivating to see like the I had like a bar chart of like how much time I was using it for. I was like, well, I'm getting a lot of things done. Like, I actually look at like what I was, what I was doing, like, look at the to do's themselves. I'm like, Oh, this is a lot of like, it would start making to do's to like do a web search, you know, it's just like making to do's because he because he prompted it adds its own. Yeah, yeah. So like, I thought that would be an interesting reflection point. I'm not sure it really was. And then the other thing was like, I had it start blogging to itself. Like I had it generate like an astro blog, and then it would write like a nightly blog post of like, here's what I did today in this project. And then there would be like the scheduled weekly tasks were like reingest it. And in my mind, I was like, this is gonna be so cool. Like, and it's, it's interesting, like to look at it certainly cool. And then you read the blog post, and it's like, well, it's some combination of like get commits and like, maybe a little bit of like my chats, but my chats, like my actual messages I write to it are so like, I mean, I don't, I've had this open for a while. So like, we haven't actually looked at like what I wrote here. But it's like, so use the replicate skill to generate a video and style of anime cyberpunk y2k that is amazing, like an infinite racer with character designs, etc. Like, just nonsense, right? And I'm like typing, sometimes I'm voice dictating to it also. So that makes it even like sillier, like, because I just talk like a goof. Yeah, yeah. All of that sort of reflection, like, I think you're right, Zeke, like, there is some version of that that's quite cool. But I think it's maybe much more human, like intervention than this, like fully automated. I don't think it's able to, I don't know, maybe this is like a total nerd snipe for someone to figure out. But like, I found that it was just, it was like some true token maxing, like tokens for the sake of tokens. It was just like, whoa, to do's and blog posts going back refining. It's like, I don't know, I don't think anything super valuable came out. What were you trying to, what were you trying to get from that, though? Like, what was your end goal there? Like, what were you chasing after? Just like, making it more automated, right? Like, I think that's like the thing that I, like, take this video thing, for instance, like, in my mind, there's probably, there's like, so much where I could look at that and say, like, there's a process here that could be really refined. And like, it's like, I think it's like chasing one shotting, you know what I mean? Like, I think that's like, kind of, that's where I, my mind wants to go. But then I think when you look at it realistically, like, in some weird way, it still is like creative work, you know, like, it's, it's like, prompting is kind of, interestingly enough, a form of creative work. And so I think it's, it just requires you, like, going back and forth with it. I'm not sure there's really any way around it. And I don't know, maybe you guys feel differently. But that's, I think that's kind of where I landed on is it's like, there's just still too much human, like creativity, whatever that means in this context to like, to be able to one shot something like that properly. And that applies to a bunch of these different problems that I have, like, in the history of all of these different projects. Yeah. So speaking of that, do you, do you have some equivalent of plan mode when you're in this world? Yeah. Do you say like, don't do anything until I agree that we're actually ready to do something? Let me just like, kick one off. And we can like, just see what it kind of looks like. So like, you have a bunch of slash commands in here. And so like, you actually can switch it to plan. And then you can switch back to build. I think there's a whole bunch of other like, if I actually just search agent, like, there's a whole bunch of other agents here. And I know that the developer keeps adding stuff. I know I obviously can build my own. And educationally. So if we're in plan mode, it won't write files, it won't. Will it webfetch? What's blocked, you know? Off the bat, I think it's write, right? Like, it won't write a file. Zeke, correct me if I'm wrong, but like, it can webfetch, but it's mostly like editing files and like writing files. Maybe it can't do also. Yeah, it's not a guarantee because it'll still do stuff like, oh, yeah, I made that post API call for you, which modified data. But the idea is it's intended to be something where it doesn't really make any meaningful changes. It's like a research mode. Yeah. And there's like some funny things where I think it does. I mean, like a cool. So right now, it says you can't do things as we're in plan read only mode, but I'm pretty sure it's like more than happy to make like API requests that are like, actually destructive. So like, it's Yeah, you know, and I actually the reason that I know that is like the to do list thing that I hadn't that was part of that, like pre prompt, like I would be in plan mode and would happily write to do this. And like, that's probably fine for this case. But like, it was like, there was a to do this, like plan this thing. And it's like, Oh, my gosh, like, it's a little little much. In this mode, like, like, you just kicked this thread off and you kicked another one off. How many do you have open? Or how do you know when they're done? Or and we're in I see that we're in I don't know my discord term terminology, but we're in pound main. Do you do different like projects that way? Is that how you? Oh, yeah. No, I just like you're like playing around. No, no. So that's kind of what I was saying at the beginning. And we can kind of scroll down here. Like each one of these is a different project. So main is like where I start things off. And actually one thing I wanted to mention that I think is quite cool here is let me kind of hide this. Oh, that was the Oh, no, I can see you guys the screen sharing silliness. I can actually tell it to like go kick off a new session in these other projects, which I think is quite interesting. So I can say like start a new session in open cone and evaluate my current config. Nice, which is quite cool. Yeah, I don't I like buried the lead here. That's like actually quite powerful. And that includes scheduled. So like the other thing that kimaki has on top that I use sometimes, but I think it's a little noisy is is like scheduled. And he actually can't do exist in plan mode. So there so that's part of I guess something it's a destructive or whatever, right action. But yeah, like scheduled tasks will show up, it'll basically has the ability to has like a CLI and it can send new threads. So that's, that's quite interesting. So a lot of time I'll start in the main channel, and then I will. Oh, yeah, but no, it just like it did that wrong, actually, right? Like it made it in the same channel, which is funny. Trust me, it is capable of doing it just decided not to do it here. Just funny. Yeah. But like each one of these is different projects. So like, this is my open code global configuration. Like I have crazy stuff in here. Like, I want to talk about QMD. By the way, I think I think this is something I don't know if you guys know QMD. But I think we should chat about it. This Dr. Dr. Kage is like, basically, I'm very into this guy, this guy on the Internet named Ray Pete, who's like a biologist who died a couple years ago. And he just had this like really incredible, like website full of like interesting writing on like health and like kind of nutrition stuff. And so I basically took like his entire website, and then like all of these other people who have been writing about his work and like his tweet, like he didn't tweet, but like other people's tweets about it. And I ingest into this like big local database with this tool called QMD. And then I have this project, like Dr. Kage, which is basically like, you know, look at this tweet, ingest it. What do we have in here about I was like, I'm tired, like a week ago, I was like, I'm tired at like 2pm. What did Ray Pete say about this, you know, like, just like silly stuff like that. And each one of these is just like a directory with like a database inside of it. And I'll show you that in a little bit. But like, there's just random, like anything that could be like a little project here. Like this, this one's pretty wild. This is like, my media server, I have it set up to do like it, it downloads movies and like downloads music and stuff like that. And I can like kick it off from here. So like, if someone's like, this is a cool movie, I'm like, go download that movie. We're not talking about how that works. We can leave that for another, another YouTube show. But like, it is set up to do that, right? Interesting. And your flow, you start, you start in main with like an idea, and then they're like, Oh, this is worth a project. And then you switch to project. Totally. Okay. Yeah. Cool. And then so these are like, these are all like, archived projects that I started that I basically like, I'm not using these anymore. So like, I'll just collapse them a lot of the time. I mean, I certainly spend like the majority of my time up here and like the main section. But yeah, that's how it's organized. And you get notifications on your phone. Is that like how you so the thing comes back and you get a notification on your phone. So now I'm starting to think I'm understanding your 3am morning. It's just back and forth, back and forth, multiple projects back and forth is like, now we're cooking. How's that feel? How's that? How's that feel in your brain? I've been I've been hearing different, different things from people on this. Like, like, what do you enjoy that? Your context? It's like context switching, right? That's a really good question. I think that there are certain things that are good for that context switching. Like I think there's certain types of tasks and certain projects if I'm exploring, like researching a couple different ideas. So like, I mentioned I may give you like, I think this is like pretty much a real, like example, like in real time, like I was at the same time, I wanted to switch to this new to do list app, I stopped using this to do thing. So this is thing called OmniFocus, which has been around on the Mac for a very long time. And I was kind of like, yeah, he's OmniFocus like a decade ago, like what's new in it in the last 10 years, go research that, like get all the like, who's blogging about it? Let's and like, that's not super, it doesn't require a lot of my like, brainpower, but it's just something I'm gonna go kick off a couple different ideas. And then like, eventually, I'll come back and read the whole thing. And then at the same time, I was also like, I would like a new drum machine. What should I get here is my like, and also like, one thing that's kind of getting into like Sillyland is I have this like modular synthesizer here to the left, which has like, if people don't know what a modular synth is, it's like a bunch of little module synthesizers, and you sort of route cables between them to like, build a synthesizer from scratch, basically. Something I'm going to do tomorrow is like literally write down all the different modules on it and like have a markdown file that lists out all the different connection points. Because then I can say like, hey, I want this drum machine, like how will it best interact with my modular synth? Like are there good connection points or are there not? And so like having that captured as data is like quite interesting to me. I don't know. This is crazy, dude. Like I'm on some crazy nerd shit. But I'm like, this is great. It's interesting. You know, I think it's wasted time, right? Like it's wasted time if you do that yourself, right? Is that what you're feeling? You're feeling like that? Yeah. I'm like, I say it out loud. I'm like, this is slightly insane. But like, it is quite cool. I think because it's like, it's definitely crazy nerd shit, right? Like, but like, I look at I mean, I don't know if I can let me try and grab and show you like it's absurd, right? Like it's, I'm going to move it over. Like, there is like, it's insane, right? Like, like, there's there's like, 30 places to plug shit in here, right? Like, it's absolutely crazy nerd shit there for sure. So yeah, so like, how am I going to read the manual for each of these? Like, I certainly couldn't. But I think it's probably better if I just have it all in like markdown. This is like screen. This is is this the this is a thumbnail. Like this is the thumbnail. Thank you. But like, it's just I think the way that I'm thinking about it, and I think you guys be curious if you are on the same kind of thought process about it is I do just think it's like a different way of it's not like outsourcing your thinking, but it's just like moving to a higher level of abstraction, which I think is quite interesting. And also, this is another thing when I talk to people about this, I sound crazy. I think unless you've done it, like I think you kind of understand, like, it's, it's just providing, like you basically, I think have like two jobs. One is to like provide a huge amount of data as like input into the system. And then you also like synthesize the output. So like, well, I guess that information synthesizer, right? Like, if I give it all this data about my modular synth, or like practically at 2pm, if I'm like, here all the meetings I had today, here all the transcripts, like, my job is to like, feed it all this data, see what comes back out and then like act upon it. And for sure, I think the optimistic viewpoint of that is like, there's a lot of stuff there that I did not want to do and that I had to do in the past. And now I don't have to. I think that's how I think that if I make it like optimistic and like feel happy about it again, not be like, Oh, my God, I'm crazy. Like, that's I think, that's how I think about does that make sense to you guys? Yeah. And it's stuff that you might not have done because you didn't want to deal with it. And it's creative stuff, too, right? It's creative stuff. Like that drum machine thing, you were probably blocked by not knowing how to plug it in there, right? You're gonna get that thing and you're gonna have time to play with it because you've got all this other... Like, there's like, I mean, I think actually no weird way the modular synth is like a great example of this because like, there is, like Zeke said, there's just like building stuff I wouldn't have been able to do. There's like a whole sort of scape of sounds that like I probably could have eventually discovered. And it's not like I want open code to make the sound for me. Like, obviously, I don't want that, right? Like, that's not fun, right? But what I do want it to do is sort of like orient my brain towards like, a new pattern of like, whatever modulating sound or whatever that like, other people have certainly figured out and understood. And like, I guess, in a way, you could say that's like a shortcut to that. And like some people are gonna frown upon that. But like, to me, that's part of like an interesting new way of like exploring stuff. And like, am I fully sold on it? I don't know. But like, I understand that it's at least available to me, right? So I'm going to explore it because it's available to me. So I find that stuff quite interesting. So I'm curious about the actual process by which you'll do that. So like, there are a couple of different things you could do, right? You could type a bunch of words about the specific model of synth that you have. You could record your voice and blab about it. You could take a photo of the thing. You could wear like a GoPro on your head and be like, I'm looking at this thing, like, what the hell is this? What's this button where my finger is? Like, where are you in that sort of like, what is your means of like, input into the process for something like that? I really think that voice is my favorite way of doing it. My biggest issue is that I think the best place to do voice still is on a laptop. And so there's like tools like Super Whisperer. Someone on our team at Cloudflare has a open source tool for this, like an open source voice dictation thing. Oh, I have to mention there, he's going to be sad. It's Kaze. Wow, it's actually very similar to mine. So my agent is Kage. Faya's on our team. But like, there's no good, like I'm a big iPhone user. And I think like iPhone voice dictation is quite bad. And then all the other tools for it are not like they're just not native. I really just wish they would have like the Whisperer model or something similar like built in like that level of quality. And I just think it's not there yet because I love doing voice. Like in this Discord server. That's what I was gonna ask. Go. Well, so you can you can do like voice notes into it. And that gets sent to Whisperer. And that works great. That's that's the ideal scenario for me. But you don't see it, right? You're sending a recording. It's not doing the translation on your... It's okay. I think it submits to OpenAI Whisperer, like API, which I'm like, I don't know. But like, whatever. I mean, that's I'm already cooked, man. Like, I'm already sending all this stuff up to my heart and soul up to OpenAI anyway. So what are you gonna do? You know, like, every idea I have is in here also. So there is a there's a model called Parakeet from NVIDIA that's open source, that is small enough that you can run it on, you know, a regular so on the computer, I have that. So that's like, that's what I'm saying is like, I have like a one key, like hot key thing that's like hyper, hyper key W for like Whisperer. And it's, and it just starts recording anywhere and goes into any text field. And I think that's great. But like, it's not there on the phone, which sucks, because that's like, actually, what I want is to just like, I don't know, I don't I want to not be like on the screen. I want to be like walking and talking. Yeah, but we'll get there. It's not a hard problem to solve. It's just like, when they solve it, I'm sure it'll be great. You're you're into this pretty deep. And one of the things that Zeke and I are always looking for is like, are there are there assumptions that you see that people have about coding agents that are just like completely untrue? I think that it is still as much as the models have gotten better. I do think it's significantly wrong a lot of the time. Okay. And I think that's part of the inspiration for why I wanted to like start feeding it better context and information. I'm not sure that it really solved that. But I found like, especially for coding stuff. And I think that's probably because coding is quite hard. And like, it's gotten a lot better, like, for sure. But I do feel like it's significantly wrong a lot of the time. Okay. And so I think there's like this interesting, like, we talk about it in, like on x or whatever, like, look at the benchmarks and like how much better it's getting. And like, it is getting better, like noticeably better. I think we all like feel there's some inflection point. I like the end of last year where it became like really, really wildly good. But it's like, I mean, I give you an example of something like I had a side project thing that I wanted to do is going to be a bunch of like data scraping of different companies and their blog posts and their social media. And it was going to kind of construct a score of like, how people like what what is the sort of like, metric of like, kind of health of a company and like, look at different dev tools, startups and like all this stuff. And like, I spent a really long time, I had been talking to some people who were doing similar side projects and stuff. And they had written this huge planning doc. And there's like, like really one shot at it or whatever. And I was like, Okay, I'm gonna try that and do that as well. And so I did spend a really long time writing the entire project plan and stuff. And I threw like, extra thinking at it. And I was like, Okay, this is gonna probably be like the only thing I can run on my codex plan today, because it's gonna use so many tokens. And like, what it generated was, like, absolutely like nonsense, like nothing connected to each other. It was so like, it had gone off it like it done that thing where it started down a thing. And then I was like, No, that's not quite right. Let me iterate. No, it's not quite. And it like, it just sort of like looped itself out into, I don't know, wherever, like, it was just complete nonsense. And it was funny, because it's like, who cares, right? It's like a side project. And it was an idea of the side projects. It was like, it didn't really matter. But I think it's useful to like, sit back sometimes. And like, I'm so used to this, like, sort of like, like writing little messages, one, one, one, like you, we all know that, like, you can sort of talk back and forth with it, right. But like, again, the I think ideal that a lot of people and the way that people think about this sort of stuff when they're maybe farther out is like, it's one shot or nothing. And I think it's like, clearly not there yet. For anything. Like, like, it's quite good at making markdown files. And like, it's good. It's up to you. But like, one thing I always I'm like, laugh to myself about is like, what is the percentage that there's gonna be a markdown file that gets generated for like, whatever prompt I'm gonna do? It's like, brah, I made a file. Here's your report. And I'm like, I didn't ask for one. But like, it also just messes it messes things up all the time, too. Does that does that make sense? Like that train of thought? Yeah, yeah, yeah, I totally follow that. What do you guys think? I'm curious. Is one shotting like even really the goal, though? I don't know. Like, it seems like a good aspiration in some way, but also you're almost guaranteed to have a better result if there is a back and forth and some kind of interaction before you come to a result because you need to like, build context. Yeah, I feel like the the UI suggests that we're supposed to be able to do that. What do you want to build today? One box thing and then all of a sudden it shows up and then your chat starts and then the real work starts. You know, I feel like I feel like we are we are in a that's the trick. I think I think you're right, Christian. I think that like, we've been tricked into thinking it's going to do this. And then like, I often think about this as a little this is a little capitalistic thought here, but it's like, you want me to do the other thing? Hey, you know, you did that thing. You want me to keep going? Because I would like the money for the tokens. You know, like that, that that loop is like very much like, so I think we're seeing like, kind of more of that, too. I think there's more of like, I that wasn't where exactly what I was thinking. But no, it's a good idea. And I don't know, Chris, I find that like, every if I go and I try some of the stuff I did originally and go back to it now, it's a totally different game. Like it's every week, it's a totally different game. Yeah, that's fascinating. By the way, real quick. I'm gonna stop sharing my screen so I can see yes, because I feel like we covered we covered the Kimaki thing. I think this is like an interesting high level kind of talk. So I think one thing that's interesting to Zeke's point of he mentioned, like, like, was the goal one shotting and then Craig, you're saying like, well, it kind of asks, you know, do you want do you want to do more stuff? So like Zeke has built open code school, which is super cool. Everyone should check out open code dot school. And like in open code school, you sort of start with this fresh configuration, right? And it uses the big pickle model, which is like the free model. And it was so fascinating helping people through that you can literally see the moment like when you switch from big pickle to any what like they usually switch to open and you see the change in the you know, like what the responses were immediately does do that thing of like, would you like to do this? Would you like to do that? Here's some ideas. And like, the thing is, it is very helpful. Like those ideas are great, right? But like, it also is oriented towards like, next message, next message, more tokens, more tokens. And this is very interesting. Yeah. And like, on the one hand, it's like fascinating to see like the quality of model switch, like literally from message to message, like, holy shit, this is like the it feels like you're, I don't know, talking to like a vacuum versus like a AI, right? Like, it's just like, Whoa, cool. I'm like, but it was really interesting. It was like, Oh, yeah, like, there it is. There's, there's the hook, right? You can see like, in real time of like, boom, now I'm gonna ask you these like awesome questions. And like, yeah, that is going to help you iterate on whatever you're trying to build. But it's very fascinating to see. That's one of the challenges with open code school is like, for the first few sessions, or the first few lessons, you're sort of in this sort of chasm of like prayer that you're gonna be able to get to the point where you get the good model set up, and then everything's gonna be okay after that. So I think that'll continue to improve, though. I mean, like, there's the the Kimmy model, I think it just version three just came out of that. So I think it won't be long before we're in a world where even the sort of like, you know, standard issue runs on your own computer, open source models are still actually going to be really amazing. So yeah, yeah, I would like to run, I think we're not quite there yet. But I think whatever the like, next Mac studio is, like, I would like to have some degree of all the stuff I just shown you on the local setup. Why is that? I don't know. I just talk about like weird shit, dude, you know, like, and it's like, it's like looking through my I'm like, sending it like my blood results and stuff. Like, I'm like, yo, like, literally, here's like my testosterone levels, like, am I good? Like that kind of stuff? Like, just things where I'm like, I don't know, like, it's probably who cares? Like, but there's something about it where I'm like, I think the mental, like model of like, can I just ask it any crazy shit that I want? Like, what would happen if I like, I like I was sick yesterday. I'm like, like, how much zinc can I take? Actually? I mean, like that kind of stuff. I'm like, it's probably fine. But like, it's also just like what happens if the models get slightly more restrictive, and they're like, you shouldn't take that much zinc or like, you should only take zinc from the Bayer Corporation or like, you know, some that kind of stuff, right? Like, I don't know what's gonna happen. And like, but I mean, I also think it's just cool. There's something cool. Like, if you're like, I'm on the plane a lot and stuff. I'm like, it'd be cool if these models could like run. I see people like tweeting from the plane, like, Oh, I can still work on my, you know, like, I feel like my work is very dependent on like, the LLMs now. So I'm like, kind of cooked when like, they don't work. I mean, like, I can still just like take notes normally. But I'm like, this is painful. You know what I mean? So the olden days. Yeah, yeah. Cool. I think we're getting close to the end of the pilot episode here. That was that was wonderful. I felt that felt really great. Thanks, Christian, for sharing that, for sharing those insights. It was fun. Can I mention one more thing I didn't mention? I didn't get to. Please. I think it's quite interesting. Do you guys know QMD? Have you heard of this before? No, I know OMD. That's a band from the 80s. I don't know QMD. QMD is like this. It's built by Toby from Shopify. It's like an open source project. And it basically builds like a local vector database of markdown files for any like directory on your computer. And it's really, really fast. And it's sort of easy. It's kind of like we did this recently at Cloudflare. We updated like our rag tool to do something similar to this, where it's sort of like a now a combination of different like best in class searching models. I'm kind of getting into this mode where I just like put so many markdown files into a directory and then just run it all through this QMD project. And it is like really, really good and very smart. It's some degree of like semantic search. It's like vectors. And I guess vector searching is like kind of semantic searching. There's some other stuff too, like just like cutting out like different like suffixes of words and like searching for like, I don't know what that's even called, but you know, like the base of the word stems. Like all these things put together and it basically has like two commands. One's like embed, which is like generate new embeddings. And then there's like query, which is query. And like the amount of stuff, like I mentioned, like my transcripts, like I put all of my Google drive transcripts of every meeting I'm in, into a QMD backed folder. And I just like throw open code at it. Like, what did we say last week about this? What did we say last week about that? That's a- It uses the CLI. It uses like a CLI. That's cool. And I haven't, it's, it's pretty like duct taped together right now. Cause there's a lot of like NCP tool calling. That's like a little unreliable. It's like getting the transcripts is not great. Like, I don't even think it's to the point where I could share it with you guys, like internally is that a Cloudflare? Like it half works. Like when it does work though, and like I can search stuff, like once things are in that database, it's really, really cool. I'm like so fascinated that Markdown has become like the thing, you know? Like it's just cause I like, I read Daring Fireball way back in the day and like really like that guy. I would have never guessed that like all the AIs were speaking Markdown, but it's great. And like, I think it's awesome. So I just keep throwing like more and more Markdown into everything and like indexing it. And this QMD tools is really great. So like a lot of those projects in there. Sorry, does it, does it hyperlink where you can like jump to the- Well, it's kind of, yeah. It like, what it returns is like, I think some form of like a, yeah, I don't know if it's like a line number. It's probably something like a grep style, like a line number or something. Like a path or, yeah, right. I mean, the funny thing is like, I so rarely use it directly that like, I think that's how it works, but it's been, I only used it like once or twice to like, I was like, this is good. And I was like, oh, this seems cool. Boom, throw the agent at it, right? Yeah. This is yours now, Clanker. Yeah. Yeah, exactly. Good. Yeah. That's a good, good segue. Yes. Back to the Clanker. Like, yeah, it's, I think it's super interesting. There's just like, I think there's been a lot of talk about that recently of like, sort of Vault, Wiki, Markdown, Corpus stuff. And I just spend a lot of time like, figuring out what, like, can I turn everything in my life into Markdown? You know, like, and then just throw it at QMD. Like, that's, that's the other thing I spend a lot of time thinking about right now. That'll be my new, like, 2am Nerd Snipe or whatever. Yeah. Discord notifications. Yeah. I mean, I want to take the transcript of this call and turn it into Markdown. Exactly. Throw it into my agent and have it look up all the things we talked about. Like, Kimaki, AppleScript, slop, twerking, maxing, QMD, like, yeah. Awesome. Christian, thanks for helping us see what you're building there. I think that you are, that was really wild. I hadn't, I hadn't seen that. I hadn't thought like that before. But I love, I love that you're getting time back, man. I think that like, you're, you're moving tasks that you might not have done. Totally. And getting time back. And also like, you're in a lot of meetings and you're still coding. You're still like, able to go and do this. I think you're also, that's, that's really impressive too. I think that that's super cool. Yeah. Not, I'm not just saying that because you're my boss. Thanks guys. Now, someone actually, someone recently was like, it's so cool that you still have time to code and you're a manager. And I feel like it was the equivalent of like, or it wasn't even, it was, wow, you're still coding and you're a manager. It was kind of that, like, it was like a pat on the head, like, ah, I was like, dang, what happened? You know, I used to be cool. Um, yeah, it was very funny. I had like, it made me laugh out loud then. And I still think about it occasionally. It was, it was meant, obviously I'm like the best or whatever, but it was a little bit of like a, you know, there, there you're still, you can still, this just requires an agent to do it. So, uh, yeah. Thanks guys. I'm very, very excited and interested to, I like, I, I would just like to learn more from how other people are doing this stuff and, uh, and continue to iterate and improve. So I'm excited to see who's next in the Clanker Chronicles. So yeah, I'll, I'll, uh, thanks everybody for hanging out. We're always looking for humans behind the Clanker. We want to talk to you. So if you'd like to show us how you use your agent and show off your framework, or, you know, somebody that we should talk to, we'd love to chat. Christian, where can people find you? Uh, at Christian Freeman on X is probably the best place. Uh, christianf.dev is my blog that I don't, I actually don't update that much. So just on, on X really. Well, Kamak has got some work. Yeah. It's, uh, yeah. Christian with a K. Oh, that's right. K-R -I-S-T-I-A-N. Yeah.