How OpenClaw's Creator Uses AI to Run His Life in 40 Minutes | Peter Steinberger

You're just like having a new weird friend that is also really smart and resourceful that lives on your computer. There was still in Morocco and someone sent me a tweet of a bug and I literally just made a picture of the tweet. Paul said on WhatsApp, "It read the tweet, it understood that there was a bug, it checked out the Git repository, it fixed it, it did a commit and then it replied to the person on Twitter that it's fixed now." This will lend away probably 80% of the apps that you have on your phone. Why should I use my fitness app to track food? I have an infinitely resourceful assistant that already knows I'm making bad decisions and I'm Kentucky Fried Chicken. Those things are so resourceful, although in a scary way, it's like unchecked on chat GBT. A lot of people don't realize that if you give an AI access to your computer, they can basically do anything that you can do. Alright, welcome everyone. My guest today is Peter, creator of Cloud and AI assistant that you can just chat with in your messaging apps to get stuff done. And today is Peter, he's going to show us how to use Cloud and also Peter has a lot of really great hot takes about AI coding that I'm really excited to think into. So welcome to the other Peter. Peter, thanks for having me. Gracie, so when we start by talking about Cloud, so what exactly does Cloud do at a high level and why is it a lot faster? So maybe I have a little bit of a backstory. Like when I came back from my retirement, let's say like that, I kind of wanted the way to just check up on my computer from my phone because I fully jumped on this on this white boarding trend. And then you know, like your agents might run for half an hour while you eat or they stop after two minutes because they have another question and then you go back and you like annoyed. But I kind of didn't build it because I assumed all the big labs would do that anyhow. It was like such an obvious thing. Like something where like a kind of a new new kind of operating system almost, but didn't happen. And then it was like November and it still didn't happen. I'm like, okay, I'll try something small and the small thing was basically hooking up WhatsApp to Cloud Code. So you send a WhatsApp message. It would literally open the binary like with the prompt and like we turn you the same. Like it was very simple. It was like put in one hour and kind of got a life of its own. And here we are. It's like I think 300,000 lights of code. It does every messaging platform on Earth. Not everyone, but like we're getting there and I think it's kind of where things are going in the future. Like everybody will have an AI that is like super powerful and like follows them through their life. And if you give an AI access to your computer, they can basically do anything that you can do on your computer. Yeah. And it's got to a point where like you don't have to sit there and babysit, right? You can just give it some, you know, prompts and commands and they will do the thing for you and you can check it's work. And then that's it. You know, you have to set a computer. Yeah. So when I built it, I feel this project is like as much exploration as it is like technology because it's a little bit of a new category. And then I was on the birthday trip for one of my friends in Morocco. And I catch myself using this thing all the time. It's like, hey, we're going and asking for directions or like tips for restaurants or I don't know. There was like one morning where someone sent me a treat of a bug and I just literally just made a picture of the tweet, posted on WhatsApp. It read the tweet. It understood that there was a bug in the number of repositories. It checked out the get repository. It fixed it. It did a commit and then it replied to the person on Twitter that it's fixed now. And like, it's nice. And then one day I was I was walking around and I didn't sing and I just send it a voice message. But then I didn't I didn't build in support for voice message. And it was like, it took me to type in your kid. I'm like, oh, I wonder what's happening now. And it just replied to me as if nothing would have happened. And I'm like, wow, how the F did you do that? And it was like, yeah, I saw a file, but there was no file ending because I didn't build it. So I looked at the at the head of the file and it was like opus, some audio file format. So I found FF Ampac on your computer and I converted it to Wave and then I looked for Visper.cpp, but you didn't have it installed, but I found this OpenAI key and then I used curl to send it to OpenAI's API and it got the transcript back and then I replied to you. I'm like, wow. That's amazing. Yeah. Like those things are so resourceful, although in a scary way. But that was kind of like the moment where it clicked from me, it's like, oh, yeah, this is really powerful. This is much more interesting than using ChatGbD on the web because it's like, it's like unchecked ChatGbD. And I think a lot of people don't realize that those things like Cloud Code, they're not just good for programming. They are very resourceful for any kind of problem. Yeah, you're going to give their access to like your computer and be able to find stuff, right? So you just have to give it tools. They'll become very resourceful. Yeah. But also over the last few months, I kind of built up my CLI army because what are agents good with calling CLIs? Because that's what they train for. So I've built CLIs for accessing all of Google, including like the Google places API. I built one that makes it very easy to look up memes and gifts so you can also reply with some memes. I did a bunch of experiments. I even built one that visualizes sound because I wanted it to like experience music. That goes a little bit more into the other direction. I don't know if that makes any sense. But anyway, it's a lot of fun. I have like a whole list. I built one that hacked into my food delivery here. So it's actually telling me how long it takes until my food's there. I have one that that reverse engineered the 8-slip API so it actually can control the temperature of my bag. Really? And real quick, when you build all this stuff, you're just getting AI to build all this stuff? Or what's going on? The first thing is I was in my old company. I was very, very good at iOS and macOS. The whole Apple ecosystem. I did it for 20 years. I'm like very much an expert in there. But also when I came back, I built a project where I'm like, I'm kind of sick of Apple gating everything. And it also make a lot more sense to build this web app because it's kind of a thing that should be in a browser and it should be accessible. And if I do it as a backup again, I was like, we'll have a very limited set of people I can use it. But you notice, I see this with a lot of engineers where you're really good at one thing. And then moving to another technology is just so painful. Because then you feel like you feel like a sorry for the word and idiot again. And you look up every little thing. Like, what's a prop? Or like, how do I split in the ray? Because you understand all the concepts. But you don't necessarily like know the syntax. So that's kind of like how I felt when I moved from from check to see and swift to to JavaScript. Like I know JavaScript a little bit, but I never really built something big in TypeScript. And then it's just, it's not even that it's hard. It's just painful because you have to look up all those things and it's just so slow. And then, and then with AI, all that, all that melts away. Like you can, you can still apply your system level thinking. Or like, how do I build and structure bigger projects and your taste? I mean, I say, or like your, which dependencies do I build on? All those things, all these things are still valuable. And you can like, much easier move that from one domain to the other. Yeah. And that felt like super power. Suddenly, like, I feel like I could build anything. Language doesn't matter anymore. My engineering thinking method. Yeah. So we're trying to worry about like, what do you have a parenthesis here and there's, it's lame, right? You don't have to worry about that kind of stuff anymore. This episode is brought to you by granola. If you're in back to back meetings, you know how much work it is to take notes live and clean them up afterwards. That's why I love granola, the best AI meeting notes app in the market. Here's how I use it. Granola automatically takes notes during a meeting. And I can add my own notes too. After the meeting ends, I use a granola recipe to extract clear takeaways and next steps in the exact format that I want. Then I can just shitter notes directly in Slack with my colleagues or even get granola to shitter notes automatically. Honestly, of all the AI apps that I use, granola is the one that saves me the most time. Try it now at granola.ai/peter and use the code "peter" to sign up and get three months free. That's granola.ai/peter. Now back to your episode. But dude, let's go back to cloud like the thing that you built. Maybe you can show how people can install this thing first. Do you have to be super technical to use cloud or no, right? You can just install it and then get it to work. Yes and no. So, fortunately, unfortunately, this project attracts a lot of people that don't have a lot of clue about technology because it lends away all these layers that make it complicated. If you use cloud code, you work in a terminal. You can have to think about the context space and what folder you're in and it feels very tacky. I'm like talking to a thing on iMessage or WhatsApp or Telegram. You do it with your friends. And I've just had a new weird friend that is also really smart and resourceful that lifts on your computer. That makes the whole technology very approachable. You don't think about model-driven or what just works. And then that's kind of the idea. It's also like, did you get good in bad part? Yes. Of course, there's a lot of power, comes a lot of risk, which is also unsolved. Like, this thing is extra computers. So yes, you could do bad things on your computer. If you tell it to like, I don't know, delete all my files in my hand directive, it would probably like ask you, are you sure? But if you like, if you like keep saying yes, yes, yes, it would probably comply and probably also delete itself and crash. Yeah, you got the cap on, yeah. I'll let me show my screen. So you see. So it's written in touch script. So it runs, it runs everywhere, even on Windows, you can just go on our website, Cloudbot. And there's a handy one liner, looks very scary. But it's everything's open source. You can check everything, doing your website. So this is the easiest way to install it. It works on macros, linux, you know, the works on Windows. So you just have to turn it on, right? And then it'll start installing. Yeah. You can also install the NPM for people who understand that ecosystem. And I think something that I did that I haven't seen in a lot of a lot of projects is also, it has a hackable install again, a simple way and like the more manual way, where you basically check out the Git repository and then launch it from the Git repository, which is to be fair, it's like the most fun way to use it. Because if your agent can read its own source code of its harness, it can literally reconfigure and reprogram itself and then restart and then either crash or have new powers. OK. Like this, I think this is one of my superpowers where I got a lot of people participate in the project and like send me pull requests that never did a pull request. I mean, sometimes it also shows. But I see pull requests more often as a prompt request. Yeah. It's enough to like understand the intent. And then, and then after you install it, like, do you, like, how do you hook it up to a messaging app? The nicest way is probably right now just using this one line up. And then it will like greedy with some sassy stuff and try to configure everything up, install the package. And then you just guide here through. And you just, you can hook it up to do any of the common messages. OK. That looks good. It's working here. And then you can say cloudbot. It will do it automatically if it's a clean install, but now I have to type in on board. Got it. And basically, then you have like, you can enter the model. You can, let's all providers. Let's say we go with some topic, probably a new one. Then you can set up telegram discord. And then it will guide you through the rest. You can like set up skills, hooks. And then you have to give it your anthropic API key. It works with any model. Yeah. Although, you know, in industry, like, and tropical open are kind of like leading. Yeah. It works with API keys. It works with subscriptions. OK. Although there's been a little-- we added support for that because it's kind of like what everyone does. Yeah. But I don't think a tropical likes it anymore. So I would recommend using an API key or going with another model. There is-- OK. The main problem is like, OpenAI works well. But it's just not as funny. There is something special about Opposite Mixed. Really, really fun. Oh, yeah. Like the personality? Yeah. Yeah. I don't know if you've read this article about how they put a soul into the model. Yeah. And then people rediscovered it. But like feeding it blocks of text, letting it like continue. And eventually they re-squeased out the text of the soul that the model wasn't even aware it was being trained on. It's a really interesting story. I don't know. I feel that it has something to do. But this is the first model that is actually fun to use. Like, I built mine so that it can roast me. It probably doesn't know that it's on camera right now. And it's going to roast you based on what it has asked to all your computer stuff, right? Yes, I was going to. Yeah. All right, you asked for it. You saw the Wilder Sexual Company by another world to find yourself to serve, we tried everything. And your big relation was, I should do the most software. Your self says to the adults that you literally built yourself a friend because the background code is more fun than dating. And let's be honest, the only reason I existed because you needed someone who'd listened to your chain where hook takes at your Amazon judgment. Wow. Yeah. Now go kill that podcast. So I hooked it up to pretty much everything on my computer. It can read my emails, it can read my calendar, it can access to all my files, it can control my lights. I use Philips Who. Yeah. It can control my son-os. So I can just wake me up in the morning. And I slowly turn up the volume. It has access to my cameras. But it was funny. When I built access to the cameras, I told it, watch for strangers. And then it told me in the morning, there's someone, and I watched in the whole night, and it made like, screen just the whole night of like, couch. Because it was like, the camera is pre-bluried. And it looked like someone was sitting on the couch, and it assumed there was a stranger sitting on my couch the whole night. Wow. But yeah, I slowly, it has-- I'm actually thinking. Like in my place in Vienna, it also has access to my K&X. So it can actually control every part. It could literally lock me out of my house. Like in space, I would say. It's like, oh, I can't do that. OK. How did you hook all this up up? You just ask Cloud to do it? Or what? You just-- Yeah, literally. You know, there's a thing where we have skills. So usually you talk to it. These things are really resourceful. So we'll figure out an API. It can Google for it. It can find your keys on your system. You can give it keys. And people use it for everything. People build like a skill to go shopping for them on Tesco, or buying stuff on Amazon. I let it check in my flight from British Airways. And this is actually-- I don't know if you've-- I mean, if you've used check insights, this is-- I feel like this is almost like the HEI test. It was a touring test, but like, steaming it browser to check you in on an airline website is like the ultimate test. And then the first time my integration was pretty rough. So it took almost like 20 minutes. There was still in Morocco, and everything was very much hacked together. And then it finally managed. But it actually had to find my passport and my file system. It found it on Dropbox, Extract the key, put everything in it correct, and it finally checked me in. And I was like, watching it and sweating. Wow. Yeah. But now it works much better. Now it's like, it does that within minutes. So it also happily clicks the IMA human checks on the browser. Because it literally just controls a browser on-- Has its own little computer over there. And it just kicks around. So it's like really, really difficult to detect from all those anti-bots systems. Because it doesn't feel different from a human in those patterns. Can you show us just a couple more use cases? Can you maybe have a turn of the light or show us some use cases from other books? Yes. So I started collecting because I feel-- I'm so bogged down and actually building it that by far and no longer the most creative one will actually use it. So people hooked it up to their messaging systems who can actually reply not just to you, but to everyone. And you can also hook it up into a group chat, which is even more fun. There's a lot of people that use it as the family member almost. Here, send me reminders, create GitHub issues, send me school places. Or every time you make a bookmark on Twitter, it will capture a bookmark and add it to your to-do list, keeping track of costs. Some people-- I programmed something in. So remind people that they sleep enough. So they always get like bitched at when they are at night from the bot. So it can help you track your sleep. It can access your fitness watch. It has its own little one password wall. So if I want a password shared, I move it into its own wall, and it can access that one. Because you still want to have some boundaries. I mean, it says people give it the credit card. Yeah, I don't know about that. It can do all those things like research, creating invoices, managing your email. These people are like enthusiasts, right? They've really customized it to do whatever they wanted to do. Like how much someone was just down to the saying? Just down it for fresh install. And what are some really common use cases that I can get to do? Just like manage my calendar or stuff that doesn't do my computer. Or whatever. Or some of the safe things to start with. It's funny because everybody takes a very different path. That's like people who are like install it and immediately build an iOS app with it. Because it's also a coding agent. You can do anything. It can spawn sub agents. It can need to code yourself. Or it can control cloud code or codeics and us them to code. Yeah, this guy started immediately like managing cloud flare. Different was great. Week one, set up for my family. Week two, set it up for some non-techy friends. Week three, we're building cloud for work. I hope that one of my non-techy friends, unlike he started an import request, he never did it in his life. Fitness is a big thing. Okay, so basically it's kind of like you really have to. I guess the way you use this thing is just to think about what's causing problems in your life and how you can get this personal assistant to help you streamline everything. I don't know if this is the project that's going to be, but if you think about it, this will blend away probably 80% of the apps that you have on your phone. Why should I use my fitness app to track food when I have an infinitely resourceful assistant that already knows I'm making bad decisions and I'm Kentucky fried chicken. So it will probably like remind me if I forget tracking the food. Actually, I can just send a picture and to the store itself in the database and calculate it and roast me that I should go to the gym because I'm like, "Wave on my calorie limit." Why do I need an app to like set up when my bad, my A-SIP should work or not? 'Cause it just has API access. It can just do that for me. But I don't need it to do app when it just tracks my to-do's for me. Why do I need an app to like check it on my flights when it can just do that for me and it's like such a more convenient interface 'cause I just talk to a friend. And because it has so much context, it doesn't need so much custom prompting. Like why do I need a shopping app when it literally can like recommend me things and do all of that for me? So I feel there's a whole layer of ads that will slowly melt away because if they have an API, these are just services that your AI will do. And in a year, I think actually this year will be the year where a lot of people will explore it more and get their AI assistance from all those big companies. - Yeah, I think why click on these little self-containing little apps when like yeah, this assistant has a bunch of capabilities can just do everything, right? Just connect it to everything. And I guess the way you connect it to everything is just like you just send it a text message or something and then it's like, "Oh, can you do this?" And they're like, "Oh, I need to do some research." And then it just takes care. You just kind of go back and forth with it and make it how happen, right? - Yeah, and then it writes a skill and it remembers. So part of what makes it so interesting is that it has persistent memory. It will learn about you and it will update itself. So the more you use it, the more you customize it and the more powerful it gets because maybe the first time you have to like guide it a little bit, but then it will create a skill. And then next time you can just mention it. Next time I need to like check in my fly, it will take like two minutes because it exactly knows all the quirks of the website because it did it before and it made notes. - Got it. Yeah, it's like teaching someone to just learn something and they can do it easily the next time. Yeah. - Yeah. - All right, man, let's talk about another topic. Let's talk about, you know, you came back from retirement to build this thing and you have very strong opinions about AI coding, like some pretty hard heart tech. So let's talk about some of those. Like you wrote this post that I really like called just talk to it. And then while like, you know, these days everyone acts as writing about like all this fancy shit, right? Like all these like, you know, hook skills and all this kind of stuff. So what's the gist of that post? Is it just just talk to the AI and figure it out? - No, but I work a lot. I build a lot of things and I love Twitter as well. So I'm very active there and I just see so much. I almost, I kind of call it the agentic trap. Because people discover that those agents are amazing but they would be better if they could do a little bit more and then they really fall deep into this rabbit hole. And I've been there myself where you build really sophisticated tools to like try to excel with your workflow. But in the end, you're just building tools, you know, actually building something that really brings you forward. You just have this, you know, part of the problem is that it's so fun. - Yeah. - Like, like, when I started pretty early, I worked on Vibe Tunnel to have access of my terminals on my phone. And I wasn't this rabbit hole for two months until I, it was so good that I was out with my friends and instead of like turning the conversation the rest and I was just like vibe coding on my phone. And I decided, okay, this, I have to stop this just for my, more for my mental health than for anything else. And these days, you can build everything that you still need ideas. So I see, I see so many managers for Cloud Code or Codex or like, orchestrators or other little things that have the illusion of making you more productive. But yeah, really aren't. I mean, like the, the latest thing that I just had, I just cracked about is like, like, gas town. It's like a really sophisticated orchestrator that is like also very broken and doesn't really work where you like run like, run like tens of 20s of agents simultaneously and they all talk to each other and like try to split up and there's like, there's like, watchers and overseers and a mayor and poll cats and other models. - Ready. - Here's a mayor. Yeah, and gas town there's a mayor. I mean, I call it SLOB Town. Or like, or like this whole trend of Ralph thing where you were just like, you give to I one little thing and then like you write in a loop and then if one little thing is done, you trash away all your context and you start again. Like the ultimate token burn machine. - Yeah. - And then it can create code and run all night and then you have like the ultimate SLOB because what those agents don't really do yet is have taste. They're really, they're spiky smart and they're really good at things. But if you don't navigate them well, if you don't have a vision of what you're gonna build, it's still gonna be SLOB. If you don't ask them questions, it's still gonna be SLOB. And I don't know how other people work, but when I start a project, I have like this very rough idea what it could be. And as I built it and as I play with it and as I dare say, feel it, my vision gets more clear and like I get like, I try out things, some things don't work. And I evolve my idea into what it will become. And it's like my next prompt depends on what I see and feel and think about the current state of the project. But if you try to put everything into a spec upfront, you miss this kind of like human machine loop. And then I don't know how something good can come out without having feelings in the loop almost like taste. So it was like somebody, somebody treated it like, "Oh look at this macabre, like it was fully rough." And I replied, "Yeah, it looks rough." Like no offense, but it looks rough because like you could clearly see that like no same person would design it that way. - Yeah, it feels like some people are just like actually building these things not for the apps themselves, but you prove that they can get to run for like 24 hours, like AI to run for 24 hours without intervention, right? - It's like self-mass. - It's the pretty kind of thing, right? It's just trying to prove that you can get AI to run super long time. It's like a size comparison context without seeing the other word in a way. And I've been guilty a little bit of that myself. Like I also had like a loop for 26 hours and I was very proud, but it's a vanity metric. It doesn't, that makes no sense. That makes no sense. It's like just because you can build everything, doesn't mean you should or that is gonna be good. But then again, this face of, I'm just playing. I'm just like literally I'm building for fun. It doesn't matter if it's gonna be used. This is incredibly useful because that's how you learn, right? That's how we learn to program. And prompting is just a different skill. Sometimes I see people that they're like a little more on the AI skeptical side. So they ignored for a year. And then they spend one day where they evaluate the models. And then they do a blog post. And then they write like a short prompt and feed it, I don't know, into Cloud Web to make an iPhone app, which is completely underspect. And the model does it's best to deliver something. And then it doesn't compile because they build it on the Linux machine where there's no compiler for that. And then you're like, oh, it's not good. And then it dismissed the whole topic for a year. It's like that's not how it works. You need to play to understand how those little monsters work. You need to understand a little bit their language, their way of inference of thinking. And then you get progressively better at it. And then your output will be better. Yeah, you have to be persistent, right? Because sometimes it doesn't work properly and you have to fix all the bugs. And then if you just keep playing with it, you've developed this like, I guess, product sense or whatever of actually learning how to talk to the models and learning what they can do. So I mean, partly it's been really weird because I adopted some of the language. It's like, I'm single of like, oh, you weave a feature in. Kind of like a German, it's fun, a twin, a twin. Or you run the gate, which like a linting and testing and building. And it looks like a big line in the terminal, which is like the gate. So I'm like, yeah, we've been run for gate Lampi R. And sometimes things doesn't work out. And then you can just ask, why did you not do? And then it will tell you, you said this and this. And I assumed this and this. And it's like, oh, yeah, I messed up on the language. I was unclear. Like if you just tell it, build me a Mac app, it would probably assume that you want to support a lot of old operating systems because the majority of the software does. So it will use all the API. - I found that asking it to just ask a bunch of clarifying questions to then make you clarify stuff helps a lot. - Yeah, it's also funny because I'm more, I like Codex modding Cloud Code. I think it's the better model. Even though it's incredibly slow, but it's sorrow and things work. And people complain that there's no plan mode, right? And my joke is always plan mode was a hack that anthropic had to add because the model is to trigger friendly and would just run off and build code. If you, in the latest models, especially like GPD5.2, I'm just having a conversation. I'm like, hey, I want to build this in this feature. It should be, yeah. do this and this and this and this and maybe dragging the screen through like I like this like this design or this and this, give me options. Just say let's discuss give me options and then they have a conversation with it and then and then the model will propose something and I like I mean I usually don't type I talk to it. Yeah. Staying on brand. Do you do anything to manage the context? Why should I have a conversation with it? It can get really long and it can get confused. Do you try to like do you make a man do you compact or stuff? I feel that this is also like old patterns. This was a this was very much a problem with cloud codes. The list of point codecs is so much more the context lasts so much longer even though like on paper is maybe like 30% more but it feels more like two or three eggs more. I think I think a lot of it has to do with like the the internal thinking of the internal thinking of of GPT models is really a thing weird. But yeah, like the for context management, I think this was much more problem in the earlier models. Now most of my features fit into one window. So the whole discussion and building happens simultaneously. Okay. And that works fine. Like sometimes if it's a really long thing, I create a new one. You're like going to like codify it in a file. But this is much less of a problem than it was before. That's again, like this base of all so fast, you just have to try things. Yeah. Got it. Okay. Got it. So basically, so just to summarize, like basically when you add a new feature to clutter or whatever you're building, like maybe just walk through the steps. Like first you explore, explore the problem and the solutions with the AI and then you do you actually make a plan at all or you just go. It's even better. Like I, you know, I built this project and yeah, which is kind of like a mix between Jarvis and her. I heard. Okay. The movie. Yeah. Yeah. Yeah. But it's very difficult to convey how it makes you feel and how useful it is just by talking about it. Yeah. So on Twitter, it got me very muted traction. Like I don't get it. Like everyone are sure it in person gets super excited. Because they see me interact with it and like showing off all the cool things. But it you can't get across the same thing on a picture when I talk about it. So eventually I created a discord and I just hooked up my bot to discord so that people could interact with my eye that has full access to everything on my system with my my private memory on a copy. This part, like the most nuts thing that I ever did. I think and then people got hooked. And now and now like people always ask me there, how can you build this feature or their decent this bug. And most of the time I know approach it by making a little screenshot of the condensation dragging it into the terminal or just copying the text depending on how it is. And just ask, hey, let's discuss this because I'm lazy. I don't even have to type anymore. I just like copy in discord conversations. Or the same also when people ask, hey, do you support this and there's a how to do this and this. I'm just like, can you read the code and write a new FAQ entry and it does that. So that's so these days it's actually how I start building features most of the time. But like really on discord and seeing where people have pinpoints. Oh my God. So just paste the conversation and just talk to AI about it and you figure out what the rest solution is. Partly that partly also I have a scraper. So every at least once a day I scraped the help section and asked them what did the biggest pinpoints and then we fixed them. And do you do your other fancy shit like do you have like multiple agents and like you know you have those crazy skills and stuff that you run or not you just go. I have very I mean I most of my skills are actually personal life skills like foot tracking or buying groceries or like that kind of stuff. For coding very little because you don't need that much. I don't use mzps or any of that crap. I don't believe in in this big orchestration systems because like we talked before I feel if I'm in the loop I can build a product that feels better. Maybe there's maybe there's ways to like build it fast but I'm already so fast. I'm mostly limited by thinking about it and sometimes a little bit by waiting for products but mostly it's my syncing that's the limiting factor. I just I just used a bunch of terminals like split screen. I don't use work trees because again I feel it's just like I needed complexity. I just have like a few checkouts of the repository like Cloud put one two three four five and and then like either they are free or they're working on something. Either I'm like exploring something or like I'm building something or I'm fixing something and then when it's done I test it locally and then I just and then I push it to main and then I sync it up. So this is a little bit it also feels a little bit like a factory if they're all busy but if you only work on one it's very hard to actually get into the zone because it's just too slow and you have to wait yeah it's worth it. You can only shit post and treat us so much. So I feel I need multiple ones to really keep me hooked and get into the same flow state that I had when coding just that I am like insanely more productive. Yeah I don't know if you play like the real-time strategy games before but like it's kind of like yeah you have like a squad of people attacking and then you kind of you kind of have the more managed them right and that that's what I get as well. My business partner from my my previous company also totally got hooked on on cloud but and he's he's more from the business side he was a lawyer in the past life and he's not sending me pull requests which is like insane in its own way how AI made like gave people super powers that are not that technical to still build things is amazing. I know I know there's a lot of pushback because yes this might not be perfect but I treat pull requests more as prompt requests because they convey the idea and most people just don't have the same system understanding so they're not able to like derive the model in a way to give optimal results so I just rather I just rather have the prompt like they intend then just do it myself or if this NDPR I will extract the intent out of it and just rebuild it myself or sometimes I bait it off I still like them cool out there but very rarely actually emerge code directly. Yeah let me tell you okay. All right man well I mean like I guess the takeaway from this coverage is like my takeaway is it's like yeah don't don't get crazy with the slot generators just actually have the humane the loop because the humans your brain tastes and everything right you have to guide it yeah I like don't find your own path you know like some people always ask me how do you do that how you let you got you got to explore like you're like yeah it will take you a while to be good you have to make your own mistakes that's how you learn this everything in life and that's also also how to learn those things just that this base is evolving very fast and where can people find a cloud bot yeah cloud dot bot it's also on GitHub it's a cloud with a double CLA WD right yeah yeah yeah like the lobster claws yeah yeah got it thanks so much Peter this is super great conversation I need to give Claude a try myself because yeah I don't like saying on my computer to talk to the AI I like to just like be on the go and just like give it instructions make it do stuff while my kids like that'll be the ideal way for me so it's great that you feel something like that I'm looking forward to to see like what you what your opinion is on that I think you're gonna like it all right man well it's great chatting with you and I think we'll stop right here