What would you say by the end of this podcast that everyone will have learned from you? The main thing I want to talk about today is how we can be the director of our coding agents. Everyone is hearing nowadays how large language models can support up to 1 million tokens in their context. That's like the Harry Potter book five times over. Large language models have what's called the dumb zone. With Opus right now, it's usually around 250,000 tokens and I feel like it gets into the dumb zone. It definitely comes with a false sense of security with people now thinking that they have the million. With coding agents, you spend more time planning than you actually do building. Without the verification checks, maybe it's 65 or 70, but now you can get something that is 92 on the first pass. If you tell it never to to wipe a database, it's still going to do that. If you don't allow it to delete a folder, it can still write a script to do that. Recently, something did happen to us. The agent was trying to be proactive and it actually saw something on its task list, but it misinterpreted it and it ended up sending an email to our entire list with a discount code and it was not supposed to go out. If you have the mindset that anything that the agent can read or can touch, you have to assume that it will, even if you never ask it to, that assumption is what's going to save you from having your database deleted. All right, Cole, thank you so much for being here today. I'm so excited to dig in. I'm excited to be here. Yeah, thanks for bringing me on to your podcast, Nate. I'm looking forward to this. Absolutely. Yeah, it's been a long time since we've talked, so I'm excited to hear what you've been up to and to hear kind of like the sauce that you're going to drop on everyone today. So real quick, what would you say by the end of this podcast that everyone will have learned from you? Yeah. So the main thing I want to talk about today is how we can really be the director of our coding agents and specifically cloud code because that's what most people use right now. That's what I use. But really, it's creating that system where you have your your way of working with cloud code that evolves itself over time. And we're going to talk about more than just using it to code. Really, I use my cloud code as my second brain. I like to call it. I know Nate kind of calls it as AIOS. Everyone has their term for it, but really like using cloud code as the tool to make your business AI native. We're going to get into all of that and just some highle strategies that honestly you can start applying today. I love that. Yeah, I'm I'm super excited to dig in because, you know, I don't come from a formal software engineering background and I think that I would I would guess that the majority of my audience doesn't either, but obviously with the the products being called Cloud Code, I think a lot of people that I bring that up to who aren't super deep in the AI space, they obviously think that it's a tool that is for coders and you need to understand code in order to use it. So, um I love that framing. And real quick before we jump in, you know, me and you have we've known each other for quite a bit. I feel like, you know, right when I kind of quit my job and started on the space, you were one of the main channels that I followed and I still follow to stay up to date and to to learn about how to work with AI in the right way. And um we've kind of just been able to see each other grow and and you know, check in. So, I'm really excited to dive in, but I wanted to make sure you got a chance to real quick give everyone a quick intro if they haven't seen your channel before on what you do and um yeah, what you're up to. Yeah, sounds good. You know, before I give an intro though, I kind of want to share something a little bit about what you're talking about. Like when we first met, it's funny because I I actually remember I had um about 50,000 subscribers when Nate first reached out to me and he had like 10,000 and now it's a little bit different. I have like 200,000. You're you're almost 800,000 now, right? Like it's pretty crazy. Um it's been really cool to see you grow, how fast you've grown. But yeah, we were both like smaller channels at the time. Um so yeah, it's it's been a long time. Wild journey. Uh yeah. Anyway, as far as what I actually do, so like Nate said, I come from a software engineering background. So, I've been an engineer my entire life. Ever since I was eight years old, actually, I I started with this language called Scratch. It's developed by MIT. So, I was just like building video games as a kid, like Super Mario Bros. and Pokemon, like really cliche stuff. Um, but that that's what got me into the world of coding. And so I took that through high school, college, got my bachelor's in computer science and um then I had just like a software engineering job in a Fortune 500 company and it was great but I always wanted to be an ent

you need to stop learning Claude and learn this instead. All right, so check this out. Literally every month we have a new AI harness or a new tool dropping and it feels like you are just starting over from complete scratch. So you have to rebuild your entire setup. You have to rebuild your prompts, your workflows, whatever. So look at this. We have every AI tool in just one layer that is called this engine right here. So this engine, it's always going to be changing whether you're using cloud code or codeex and chatbt 5.5 or open claw and just open 4.8 or fable 5. But right underneath that we have the bottom layer. This is going to be your folder. So obviously this is just going to be a folder on your computer. And these are just your files and your rules for how you want the work done and the repeatable jobs that you have actually taught it. You own that. It never goes anywhere. And here's why that matters is because every one of these tools, it is going to effectively just be opening that same folder and reading those same rules. So when a better one drops, you are not going to be starting over. You just point it at that same folder and you don't have to start over. You just keep on working. Now, this folder right here, this is going to be plugging into the applications, the tech stack that you already use in your business. So, things like your email, your calendar, your CRM, whatever. And under the hood, these tools are actually more alike than different. Now, all of these companies, they compete on everything except how they are going to be reading your folder. So, your setup, it was never a claw thing or an open eye thing or an open claw thing. It is actually yours. So you own this folder with all of your business contacts and everything about you and all of your processes. You just rent the engine like OpenAI or Codeex like whatever it is. You just rent that engine which that you don't even need to rent now because local AI is becoming insanely powerful. But that is another video. Comment neat if you want my exact AI strategy that I'm using inside of my

So, I've been playing around with GLM 5.2 inside of Cloud Code all day, and it's incredible. It feels faster. It's significantly cheaper, and it just fits right into the Cloud Code harness pretty well. It's been doing so well, in fact, that it edited this entire intro that you're watching right now from raw video all the way to what you're watching. So, in today's video, I'm going to show you just how quick and easy you can get set up with GLM 5.2 in Cloud Code. So, let's not waste any time and just get straight into the video. So, obviously that intro wasn't perfect, but that was literally one prompt. It was one/goal right here. It took a little over an hour, an hour and 15 minutes for, you know, a 23 second video. So, that did take a little bit long, but this was the session that we did it in. It was GLM 5.2 1 million context. As you can see right here, it used about 357,000 tokens. But, as I've been playing around with it more and more, there are some tasks where it finishes way faster than Opus. And then there are some like this one where Opus would have done this much quicker. So, I'm going to show you guys exactly how to get set up. But before that, let me just show you a few of the things that I've played around with and what GLM has been able to do. So, it's actually like really solid at design. I want you guys to look right here and see which one of these do you think was designed by GLM 5.2 and which one was designed by Opus. So, as we sort of scroll down here, you can see that we have, you know, similar style branding and it's obviously the same company, but we have elements on both that are very similar. We have all of these things come up dynamically as well on either side. And there's even a CTA at the bottom. I think the dead giveaway here is this right side was opus because it has these weird Fs that it loves to do. It loves that font. But either way, these are both very solid for a oneshot prompt. Especially when you consider the fact that you are getting this output for like five times cheaper. So these are the actual terminal sessions where we did those website designs. On the left side with GLM, we got this done in 3 minutes and 59 seconds. On the right side with Opus, we got this done in 14 minutes and 59 seconds. And not only did the lefth hand side GLM use less tokens, but its cost per token is also five times cheaperish. So in this case, it was quicker and it was much cheaper and it was a relatively similar result. I also shot off this prompt on each side where I gave them a homework assignment. You can see right here we've got GLM and then right here we've got Opus 4.8. I had Codeex create the homework assignment just so there was no like crosscontamination or anything like that. And then when they finished, I had Codeex judge both results and tell us what it thought. Now, in this case, it said that agent 2, which was opus, was better because it handled one subtle edge case that agent one missed, which were duplicate records with values like true versus one or one versus 1.0. So, the short version is that agent 1, GLM 5.2 was good, but agent 2 here was more precise. And generally, the way that I feel about this so far is that GLM 5.2 is really solid and it's pretty quick for most tasks that don't require heavy reasoning. Obviously, at the end of the day, Opus 4.8 is a better model. It's a closed source model. But realistically ask yourself how often do you actually need the power of Opus? Probably only maybe 10 to 20% if that of the tasks that you do all day. You could probably handle 80% or more of your knowledge work with something like GLM 5.2 or something more like sonnet 3.7. So that's really going to be a key skill as we move into the future of AI is understanding which models to use per task. But here's an example where you can see Opus took about 5 minutes and GLM 5.2 took about 24 minutes. And this was me on a $60 a month plan for um Z.AI for GLM 5.2. And I've played around with this for this was about four or five hours straight of just literally hammering it. Five different sessions open, testing GLM 5.2. And my 5-hour quota is a little bit over halfway used. And my weekly quota is about 10% used. I'll talk about the billing and how to get set up in just a sec. Let me show you guys what else I did with it. So I did a few more/goal prompts. And I hate when the terminal does this, but this first one that I did was I did /goal and I literally said like, "Hey, get creative. Show me how good your design skills are and just build me whatever you want. Just make me an HTML document." And then this is what it gave me. It gave me the anatomy of attention. You can see we've got like some stars moving around in the background. This obviously looks a little bit vibe coded up here, but not too bad. And as we sort of scroll down, we can see a language model has no grammar book and no dictionary. And then on this thing, the animal didn't cross the street because it was too tired. This i

이 남자는 콘텐츠 자동화 천재입니다. 예전에는 애니메이션 외주에 엄청난 돈을 쏟아부었지만 지금은 클로드 스킬 하나로 모든 제작 공정을 끝내 버리는 카리스. 그가 공개한 초보자도 1인 미디어 공장을 만드는 다섯 가지 공식 저장하고 끝까지 보세요. 첫째, 클로드 스킬로 시네마틱 애니메이션을 즉시 만드세요. 복잡한 프롬프트를 공부할 필요 없이 설치된 스킬에 대본 한 줄만 넣으면 전문가급 애니메이션 소스가 단 몇 분 만에 완성됩니다. 비싼 외주 비용을 지불하지 않고도 시청자의 시선을 사로잡는 고퀄리티 영상을 무한으로 찍어낼 수 있습니다. 둘째, 실시간 데이터를 연결해 무조건 터지는 아이디어를 찾으세요. AI의 추측이 아니라 400만 개의 실제 SNS 데이터를 추적하는 버룰로를 클로드와 연동해야 합니다. 조회수 790만 회가 터진 실제 포스트의 성공 패턴을 분석해 지금 당장 시장이 반응하는 주제만 골라 콘텐츠를 만들 수 있습니다. 셋째, 보전화 카드 뉴스와 이미지를 자동 설계하세요. 데이터 기반으로 검증된 슬라이드 구성을 클로드에게 맡기고 레퍼런스 이미지를 프롬프트로 변화해 비주얼을 완성해야 합니다.이 시스템을 활용하면 디자인 감각이 없어도 사람들의 지갑을 열게 만드는 압도적인 퀄리티의 개시무을 순식간에 제작합니다. 넷째, 지루한 영상 컵 편집을 AI 에이전트에게 맡기세요. 직접 타임라인을 보며 무음 구간을 자르는 노가다 대신 클로드 코워크를 활용해 자동 편집을 시작해야 합니다. 0. 5초 이상의 모든 정적 구간을 AI가 알아서 삭제해 주기 때문에 당신은 두 시간이 걸리던 작업을 단 10분 만에 끝낼 수 있습니다. 다섯째, 정적인 그래픽을 생동감 넘치는 모션 그래픽으로 바꾸세요. 단순한 이미지를 만드는 수준을 넘어이를 움직이는 영상으로 변화하는 자동화 공정을 구축해야 합니다. 유튜브 설명에 필요한 복잡한 개념도 세련된 모션 그래픽으로 즉시 구현하여 영상의 신뢰도와 몰입감을 극대화할 수 있습니다. 자세한 내용을 추가 정리했습니다.이 이 내용이 궁금하다면 구독하고 프로필 링크를 확인해 주세요.