WEBVTT 00:00:00.080 --> 00:00:01.934 Quen 3.8 Max just dropped. 00:00:01.934 --> 00:00:06.309 I've already plugged it into Hermes Agent and it's pretty powerful from what I've tested so far. 00:00:06.309 --> 00:00:16.070 So, what I'm going to show you today is how to use Quen 3.8 Max with Hermes Agent and also how to get the most out of it and some of the cool stuff that we've created with it so far. 00:00:16.080 --> 00:00:29.002 So, the great thing about Quen 3.8 Max is that it's basically Fable 5 level and you can use your coding plan with it to plug it in directly into Hermes, which you actually can't do with Fable 5 unless you use the API. 00:00:29.002 --> 00:00:35.389 It's also a 2.4 trillion parameter brain and it actually beats Fable 5 on some of the key benchmarks. 00:00:35.389 --> 00:00:40.415 So basically Hermes agent is the hands and then you can change the brain. 00:00:40.415 --> 00:00:42.630 So you can plug in Quen 3.8 Max. 00:00:42.640 --> 00:00:50.275 This was a 2.4 trillion parameters, 1 million context window and also designed for agentic tasks. 00:00:50.275 --> 00:00:53.040 I'll show you some things we built with it so far. 00:00:53.040 --> 00:00:56.490 So, it created like some pretty cool coding apps as you can see right here. 00:00:56.490 --> 00:00:59.652 But also, we actually linked it to MCP. 00:00:59.652 --> 00:01:03.510 So, we linked it to Hicksfield MCP just to test it out and see what it could do. 00:01:03.520 --> 00:01:16.194 And we actually used and gave it our book image as an example to see if it could code and build some cool stuff with Higsfield MCP and Quen 3.8 Max inside Hermes agent. 00:01:16.194 --> 00:01:21.239 So, this is some of the stuff that he created, which is pretty nice and it was super easy to use. 00:01:21.239 --> 00:01:24.878 The other thing I would say about Quen 3.8 Max, it's pretty fast to respond. 00:01:24.878 --> 00:01:26.711 Here's another example. 00:01:26.711 --> 00:01:32.331 So, what we actually have inside our Hermes agentic operating system is all of our different profiles with different models plugged in. 00:01:32.331 --> 00:01:36.132 Now, one thing I'll say about Quen 3.0 Max is it's very fast to apply. 00:01:36.132 --> 00:01:40.233 So, we say, for example, learn and then give it access to a guide. 00:01:40.233 --> 00:01:42.802 And you can see here it says skill learned and registered. 00:01:42.802 --> 00:01:43.764 Here's a skill. 00:01:43.764 --> 00:01:48.207 Here's the path that saved locally as a skill MD file, which we can open up in a second. 00:01:48.207 --> 00:01:49.673 And here's what it captures. 00:01:49.673 --> 00:01:53.011 And so we've taught it a new skill in the space of a couple of minutes. 00:01:53.011 --> 00:01:58.997 And if we open this up, we've got the full skill that's written here based on the guide we actually trained it with. 00:01:58.997 --> 00:02:09.559 Now, one thing I definitely recommend with this is that when you're using new models, whether that's Fable 5 or whether that's Quinn 3.8 Max or whatever comes out next, you can actually plug in a memory system here. 00:02:09.559 --> 00:02:10.560 So that has context. 00:02:10.560 --> 00:02:19.395 And the great thing about this is if we use for example Hermes agent OS like this, you can see that it actually saves the skill inside the Obsidian memory. 00:02:19.395 --> 00:02:20.333 Why is that useful? 00:02:20.333 --> 00:02:29.911 It's useful because for example, if we're switching between the memory system inside Hermes and then we go over to and we use, let's say, Deepseek. 00:02:29.911 --> 00:02:32.828 Well, it's got that memory stored from Hermes agent OS. 00:02:32.828 --> 00:02:39.463 The same for example, if we go over to Claude Code over here and we select Quen 3.8 8 as the brain. 00:02:39.463 --> 00:02:47.396 We can now use Quen 3.8 as the brain of Claude code but then also switch over to Hermes agent OS as well whenever we want to. 00:02:47.396 --> 00:02:53.110 And so you can describe what you want the 2.4 trillion parameter brain thinks it through. 00:02:53.120 --> 00:02:58.067 Hermes creates whatever you ask it to do and then you can actually open that up in your browser. 00:02:58.067 --> 00:03:02.868 Also some people say like this is difficult to set up a new model inside Hermes agent OS. 00:03:02.868 --> 00:03:07.769 You can literally just go to the manage tab or your dashboard with Hermes agent. 00:03:07.769 --> 00:03:09.110 I would make sure that you update first. 00:03:09.120 --> 00:03:15.722 So you can just click the update button and then from here you can create a new profile with Quen 3.8 Max plugged in. 00:03:15.722 --> 00:03:21.558 So you can see here that we have a separate profile for Quen 3.8 ready to go. 00:03:21.558 --> 00:03:24.889 Now also when they were training Quen 3.8 Amax. 00:03:24.889 --> 00:03:36.520 This model is very good at coding and actually ran 10 days autonomously with self-evolving development from an empty folder to production without handholding. 00:03:36.520 --> 00:03:47.939 So basically it updated and you can trace what it's done inside the GitHub for this model and see exactly what it built and so it can code autonomously for hours. 00:03:47.939 --> 00:03:50.599 Now why is that important with Hermes agent? 00:03:50.599 --> 00:04:02.171 Well, essentially, if you're using the goal mode, and we have a separate section for goal mode over here, we can give it a goal and then it can go off and complete the goals and run autonomously for hours without us even having to touch it. 00:04:02.171 --> 00:04:05.871 So, we can set the target and then just walk away with goal mode. 00:04:05.871 --> 00:04:08.873 And Quinn 3.8 Max is designed to actually do that. 00:04:08.873 --> 00:04:19.560 The other benefit of this, and this is something I haven't tried yet, but would be super interesting, is you could use Hermes mixture of agents and you could use, for example, Fable 5 combined with Quen 3.8. 00:04:19.560 --> 00:04:20.068 8 max. 00:04:20.068 --> 00:04:31.191 And that fuses the answers together so you can get even better outputs than if you were coding with Quen 3.8 Max alone inside Hermes. 00:04:31.191 --> 00:04:35.262 And so if you combine the models, you could get even better outputs. 00:04:35.262 --> 00:04:44.452 Now, additionally, if you're coding with Quen 3.8, you can build some awesome stuff and you get Hermes agent to actually build that with Quen as a brain. 00:04:44.452 --> 00:04:52.497 So, for example, we actually tested 50 different builds with this and it can create some amazing games, some apps, tools, websites, whatever you want directly with it. 00:04:52.497 --> 00:05:05.030 And so, whether you're using MCPS like I've shown you today, or for example, you're building out games with this, maybe you are trying to create a website, or maybe you're just using some of the tools like for example, forward/arn as we covered 00:05:05.040 --> 00:05:08.583 before, you can get very good outputs from this. 00:05:08.583 --> 00:05:16.783 Here's an actual promo video it created for us with Hermes agent, Quen 3.8 8 Max and then the skill of remotion. 00:05:16.783 --> 00:05:18.405 So it can create animated videos. 00:05:18.405 --> 00:05:21.382 So if we take a look at this, you can see it's super clean. 00:05:21.382 --> 00:05:23.626 It looks really nice, very beautiful design. 00:05:23.626 --> 00:05:25.590 It's actually very good at front end as well. 00:05:25.600 --> 00:05:31.067 And then this can create like a fully animated video for us with one single prompt. 00:05:31.067 --> 00:05:35.494 And so you can leave Quen 3.8 Max coding autonomously. 00:05:35.494 --> 00:05:40.374 You give it a prompt to create a video like this and it can create something absolutely amazing. 00:05:40.374 --> 00:05:44.794 Now what we've actually got inside this agent OS is we have the video section here. 00:05:44.794 --> 00:05:51.857 So we can type in a prompt then it can generate the B-roll, the script, the research, put it all together, edit it beautifully. 00:05:51.857 --> 00:05:58.740 And also the great thing about this is we have our workspace here where we can come back to it and see what we've built and watch it back later. 00:05:58.740 --> 00:06:03.990 And that's fantastic because what we can do is make sure that we never lose a project again. 00:06:04.000 --> 00:06:08.568 We never lose something that we've coded and we can watch back and see what it's built which is super useful. 00:06:08.568 --> 00:06:12.283 So that's basically how to use Quen 3.8 Max. 00:06:12.283 --> 00:06:16.915 If you want to switch the model inside Hermes, you can actually go over to the manage tab here. 00:06:16.915 --> 00:06:19.832 And then from here, you would change the model. 00:06:19.832 --> 00:06:34.422 And you can see if you type in Quen 3.8 inside the set main model section, you can select it inside news portal and you can choose Quen 3.8 Max there or you can go over to open router and select Quen 3.8 Max there as well. 00:06:34.422 --> 00:06:36.128 So super easy to switch the models. 00:06:36.128 --> 00:06:42.497 And also Hermes have just released version 0.2 which actually makes it faster and better with voice too. 00:06:42.497 --> 00:06:51.996 So if you want to get our full agent operating system with Hermes, all the systems I've shown you today, you got Clawude working side by side here it the full memory system as well and everything else I've shown you. 00:06:51.996 --> 00:06:57.996 You can get that inside the AI profit boardroom link in the comments description or just go to the AI profit bomb.com. 00:06:57.996 --> 00:07:06.088 This is my AI automation community that shows you how to train agents set up systems like this and it gives you the full Hermes agent operating system as well. 00:07:06.088 --> 00:07:09.141 So if you go to the classroom here then new daily updates. 00:07:09.141 --> 00:07:11.805 You'll find the agent OS with a video tutorial. 00:07:11.805 --> 00:07:14.297 It's last update date and a zip file to install it. 00:07:14.297 --> 00:07:19.581 We also got a full 1hour course on Quen 3.8 Max if you want a full master class on it. 00:07:19.581 --> 00:07:23.549 Additionally, we have loads of great trainings on Hermes agent as well. 00:07:23.549 --> 00:07:28.723 And you can jump on weekly coaching calls where you can share your screen, ask questions, get help in real time. 00:07:28.723 --> 00:07:33.848 Inside the community, you can ask questions as well, and I personally answer them with a video tutorial every single day. 00:07:33.848 --> 00:07:36.081 You can also direct message me whenever you need help. 00:07:36.081 --> 00:07:41.794 Inside the map, you can meet people in your local area who are building out with agents like Hermes and Quen 3.8 Max. 00:07:41.794 --> 00:07:49.800 And that's all available inside the air profit boarding link in the comments description or just go to the aiprofit.com.