China's NEW GLM 5.2 AI Super Agent is INSANE!

Today I'm going to show you how to build and automate anything with GLM 5.2. Now this is a super powerful way to use a frontier level AI agent. I mean you can see all the stuff that we've built right here. I mean this is something that we literally built just in the morning for fun and it's actually super impressive in terms of you look at the graphics, you look at the way it's been built, you saw the other game that we created a second ago and you can use this to build and automate anything. I mean look at the quality of this stuff. Here's another example. Let's have a look at some other stuff that we'll build here. So this was pretty interesting. This is like a full 3D game as you can see and it's absolutely amazing what you can do with it. I've just been playing around with it this morning, super fun and easy to build. Here's another one. All sorts of interesting things. The other thing is it's very visual so if you look at the quality of it it's like you know this stuff wouldn't have been possible a year ago. And also the other thing that blows my mind here is like you can get it on the coding plan and we've not run out of tokens even though we've been using it as much as we have for building all this stuff. Also we've already plugged it into our AI agents like for example Hermes and it can build websites. It can build games, apps, tools, whatever we want using this full process. I want to show you exactly how to do that in three simple ways today and what you can build with this. The other thing that I like is like all this stuff that we built we can always come back to it later and make it even better. Right. So for example this is fun to build but we can make it better and better. We can build out. We can improve it. We could create something even more interesting with this whole process. We even built our full operating system with many apps like you can see. So this is literally an OS built inside an agent OS and you can see the potential and the power of this. So how do you use it? How do you automate anything with it? What is GLM 5.2? Let's get straight into this. So GLM 5.2 is a Chinese AI model coding plan. And it's comparable with frontier level intelligence like for example Opus 4.8. It's actually quite a big step up from GLM 5.1. And this comes from Zed AI. So it's MIT licensed and open source. It's available on Hugging Face which means people can run it locally if they have an amazing setup. And also it's comparable on benchmarks with other models like Opus 4.8, GPT 5.5. And it's actually outperforming on pretty much everything in Gemini 3.1 Pro which is wild when you think about it. This is you know the latest version, the most powerful version of Gemini's model. Gemini 3.1 Pro from Google and GLM 5.2 is outperforming it by a long way on every single benchmark. How mind-blowing is that? So if we look at the benchmarks here you've got SWE and for example GLM 5.2 is right up there with Opus on SWE. It's outperforming GPT 5.5 on there. On post-trained bench it's outperforming GPT 5.5. On humanities last exam it's right up there with Opus 4.8 and again outperforming GPT 5.5. So if you're thinking oh this is not as good as chat GPT or it's not on the same level as Opus 4.8. I think today's the day that all changed. And when I saw the benchmarks it shocked me. But I'm kind of like well you know I wouldn't believe it until I see it. But then I built all this stuff with it as you saw earlier. And it is pretty amazing what you can build with it and how it works right. Benchmarks are one kind of proof but here's the other. And here's all the stuff that we build with it. And it's super fun and easy to build as well. So it's so cool. It's really really interesting as a time to just go off and build things. And I think with this coding plan it's even better. So how do you actually start building stuff with it? That's probably the question you're asking right now. I'm going to show you several ways and what you can do with this and how it works. So there's three ways that I look at this in terms of building anything. Number one. You've got GLM 5.2 as a dashboard. So you can use for example the CLI in the same way you would use CLI from Claude. And then you can start building that. So you can type in what you want in plain English. It can then start using the code and it lands inside your workspace. And I think that's really the most powerful and best way to use this. So for example if we go to GLM 5.2 inside our agent operating system. This is what it looks like. This is how you can use it. And it's really easy to just chat with it inside here. And then see everything that you've built inside the workspace. So you can come back to everything you've built. It's easy to see. And it's just like the same as using Claude. You just talk to it. You don't need to be technical as well. That's a great thing because you can just type what you want in plain English. It goes off and it builds it. No technical expertise needed. And so you can take advantage of one of the most powerful AR models in the world without being even technical. Now the second method I like is you can use Hermes agent. So you can plug in GLM 5.2 into Hermes agent. If you're not sure what Hermes is basically it's an open source AI agent and you can change the brain of it. So this can go off and do stuff. And then it's an agent that can build things. How do you set it up? You just use the one click command here to install it. How do you add the new model for GLM 5.2? You just go inside your terminal once it's set up. Type in Hermes model like that. And then you switch to ZAI which is GLM 5.2. That's how easy it is. So if you want to set up Hermes agent, one click install, change the model, boom, jackalack, you're in. Then once you've done that, you can have it as the main API. Now there's some interesting ways to use it with Hermes. And it gets a lot more creative than just using the CLI. So the CLI is like great for building stuff. But if you want it to actually go off into the real world and do things for you, let me show you how that works. So we have a separate agent profile for GLM 5.2 and we can chat with here. We can schedule tasks and everything else. We can also talk to it. So we can talk to our AI agent inside the chat. We can also voice activate it, which means that we can get it to build things and do things for us using this Hermes Java setup. I've created this custom voice agent that activates Hermes. And then we can go off and you can see all the conversations I've had with it. Plus all the stuff we've built with it so that we can preview and build basically anything with Hermes Jarvis. And we can use GLM 5.2 as the brain of this. Then we've got the studio where you can generate images, you can generate video voice, etc. And also where it gets even more powerful is when you can start using it inside a Kanban board. Now, this is a native feature with Hermes agents. If you've never used it before, it's already built in. You don't need to worry about it. And so the Kanban board is basically a system where you can give a team of agents tasks. So you can drop in a task here, an orchestrator agent. So the leader of a Hermes agent team, for example, it could be like just GLM 5.2 as a general profile, can then delegate subtasks to everyone else on the team. So if we look, for example, at this video that we've created, if we look, for example, at this blog post that we created, this was using our content machine Kanban board here. And so we just drop in a task. It gets triaged. They delegate the tasks. And then we end up with something like this. Now, the great thing about this is number one, yes, you can create amazing content like you can see. But also with this whole system, it gets judged and improved over time because we have a judge agent here. So we have a team of agents working together. They build stuff. They create stuff. And this is using something I call the content machine with Hermes. So what you would do is you plug in your topic and the keyword or the topic that you want to create. Then the writer drafts it, which is a separate Hermes agent. An editor sharpens it, which is a separate Hermes agent. Then we have a judge that quality controls it and says, this is good. You can publish it. Well, this is bad. We'll send it back to the writer. And so it's an iterative loop, a positive feedback loop, where your team of agents are coordinated together using GLM 5.2. At least all you need to do is just drop in the task. It's as simple as that. That's it, right? And that's how we created both this and this. You might say, well, okay, what does the finished video look like? Or what does the published blog post look like? So let me show you an example. This is the published blog post. We actually plugged it to our website here, as you can see for the airprofitable.com. And you can see it's a fully edited, beautifully drafted, published blog post that we used GLM 5.2 to create. You might say, okay, what does the video look like? So here's an example of the video. And this is pretty powerful stuff because it's nicely edited. It was iterated. Obviously, first draft, it didn't look like this. But the judge keeps iterating and asking the team to improve their work until it's finally ready to go. It's pretty insane when you think about it. So that's the content machine. And that's how you can use it. So method number one, if you want to code stuff out like an app, a tool, a website, a game, you can use a CLI. If you want to build, for example, an agentic workflow where you have a team of agents working together, use Hermes with GLM 5.2. Have them as a team on that Kanban board setup that we just talked about. And then you can automate anything that way. And then the final method is so you can actually run the whole brain yourself. And how does that look like? So you can use something called Alarma. And Alarma is basically a free app that you can download. Then once you've done that, you go to models and you go to GLM 5.2. And they have new models coming out all the time. And then you can plug this in in one single click to Claude Code, to Codex app. It can power OpenClaw, Hermes Agent, Codex, and OpenCode. And so you can use it that way as well. Now, I recommend option one and two personally because you don't really want to change the settings inside your Claude Code or your Hermes Agent to be hardwired with like Alarma. But you can do it however you want. That's the third option. And so between those, you can build code websites, games, apps, tools like we did before using the CLI. To, for example, use GLM 5.2 with Hermes, you would use this system, which is door number two. But between those, you can build and automate anything that you want. Pretty amazing and pretty wild when you think about that. And so when we look at this, right, the old way is like if you're using the API with Claude Opus, for example, or Frontier model, it can get quite expensive. And you're locked into one pricey frontier model, you know, the meter is ticking every time you use the API. You kind of avoid the big jobs because you're worried about tokens. You have to refeed it context every day as well because it forgets stuff. Like if I go into Claude Desktop, it's forgotten stuff about me already. And then also you're kind of stuck with one system, one vendor. And like if they take down Fable 5, which they did recently, then you don't have a system. You're just relying on that model that just got taken down. With this system, with GLM 5.2, you get frontier level results, but cheaper. You can run the long jobs freely because you get so many tokens on the coding plan. It's crazy. Then for the long horizon tasks, like for example, building out all the stuff that we did a second ago, you can just give your Hermes agent access to GLM 5.2. And also it's open source. So if you have an amazing setup, I mean, you do need a good local setup to run it, then you can actually download it and run it yourself locally and for free and privately. So pretty amazing stuff. Now, some people say, well, cheap models always means worse, but you've seen how powerful this is. You saw the amazing stuff that we got with this. And open source is just getting better and better all the time. So it's absolutely mind-blowing what you can do with this. And again, it can use tool use and everything else. Other people say, well, open source models are not that great, but you've seen that it's competing with frontier level now. And also, if you look at the speed of these models getting released, it's only speeding up. It's only getting faster. So for example, GLM 5.2 came way quicker after GLM 5.1 than, for example, the first version of GLM. It's only getting released faster and quicker, and it's only self-iterating better and better because it's open source. So anyone can improve it. And also, it's a self-iterating model, so it can incrementally improve itself anyway. And then other people say, well, I'll wait until the next model comes out. But honestly, the people learning now will be way ahead of everyone else when, let's say, for example, there's a final winner with AI. So my honest advice is try this now. Get onto it. Don't come back to it later. Start doing this stuff now and implementing it right now. So in terms of what you learned, you learned how to build anything with GLM 5.2. For coding tasks, use a CLI. For example, content creation or anything Long Horizon, I would use a team of agents where they can just work together like I showed you on the Kanban board so they can get stuff done. You learned how to use a pretty cheap model to get frontier-level results. You learned how to plug this into an agent operating system as well. And you learned how to quality control this stuff with a judge system inside your AI agents as well. And also you learned how to voice activate Hermes and use Hermes as a powerful agent for automating anything with GLM 5.2. So if you want to get my full system and make agents work for you daily, you can grab my agent operating system inside the AI profile for coding. It turns Claude, Kimi, GLM 5.2 into one system with shared memory, shared context in one dashboard you can control so your agents understand your business. They remember everything. And every new model like GLM 5.2 just makes the whole system more powerful and stronger. And I built this so you can get the zip file, you can get every prompt, you can get the memory set up, you can get coaching calls where we set up together. And there's 3,600 business owners using our agent operating system together. Like you don't need to be technical to set this up. You can see, for example, Amanda built hers. And you can customize this as much as you want as well, which is great. Ken built his. Marlon built an amazing dashboard with the agent operating system too. Nick created a setup with this. Eric created an awesome stuff and was super excited about it. So there's just so many people getting great results of this. Mike, look at this as well. Got his mission control running. I know that, you know, Rabbit as well got their setup. David set up a virtual office with his agents working together. If these guys can do it and if I can do it, and if everyone in the group can do it, then you can do it too. Right. And so I would definitely recommend setting this up. So if you want to do that, feel free to get my setup inside the AI profile board. If you go to the classroom and then agent OS is pinned at the top inside the new daily updates. And we add new daily updates to that every day. This is my AI automation community for learning and growing with AI automation. Inside the community, you can ask questions, get help and support. I personally answer these with video tutorials daily. Inside the classroom, you can get access to all my best trainings. So every time something like GLM 5.2 comes out, we actually add new tutorials and a full step-by-step guide on how to use it. And then inside the calendar, you can drop a weekly coaching call, share your screen. You can set up that system with everyone else inside the community. Also inside the map, you can meet people in your local area who are building with AI agents like the agent operating system and GLM 5.2. And that's all inside the AI Profit Board. So feel free to get that link in the comments description or go to the AI Profit Board. Thanks for watching.