WEBVTT 00:00.000 --> 00:05.000 Quen 3.8 Max just dropped. I've already plugged it into Hermes Agent and it's pretty powerful 00:05.000 --> 00:09.660 from what I've tested so far. So what I'm going to show you today is how to use Quen 3.8 Max 00:09.660 --> 00:14.320 with Hermes Agent and also how to get the most out of it and some of the cool stuff that we've 00:14.320 --> 00:20.900 created with it so far. So the great thing about Quen 3.8 Max is that it's basically Fable 5 level 00:20.900 --> 00:25.620 and you can use your coding plan with it to plug it in directly into Hermes, which you actually 00:25.620 --> 00:31.660 can't do with Fable 5 unless you use the API. It's also a 2.4 trillion parameter brain and it 00:31.660 --> 00:39.320 actually beats Fable 5 on some of the key benchmarks. So basically Hermes Agent is the hands and then you 00:39.320 --> 00:46.220 can change the brain so you can plug in Quen 3.8 Max. It's also 2.4 trillion parameters, 1 million 00:46.220 --> 00:52.340 context window and also designed for agentic tasks. I'll show you some things we've built with it so 00:52.340 --> 00:57.760 far. So it created like some pretty cool coding apps as you can see right here, but also we actually 00:57.760 --> 01:03.060 linked it to MCP. So we linked it to Hicksfield MCP just to test it out and see what it could do. 01:03.400 --> 01:09.880 And we actually used and gave it our book image as an example to see if it could code and build some 01:09.880 --> 01:18.020 cool stuff with Hicksfield MCP and Quen 3.8 Max inside Hermes Agent. So this is some of the stuff 01:18.020 --> 01:22.000 that it created, which is pretty nice. And it was super easy to use. The other thing that would say 01:22.000 --> 01:27.720 about Quen 3.8 Max is pretty fast to respond. Here's another example. So what we actually have 01:27.720 --> 01:31.880 inside our Hermes Agentic operating system is all of our different profiles with different models 01:31.880 --> 01:36.500 plugged in. Now, one thing I'll say about Quen 3.8 Max is it's very fast to reply. So we say, 01:36.560 --> 01:41.760 for example, learn and then give it access to a guide. And you can see here, it says skill learned 01:41.760 --> 01:47.140 and registered. Here's a skill. Here's the path that is saved locally as a skill MD file, which we can 01:47.140 --> 01:52.200 open up in a second. And here's what it captures. And so we've taught it a new skill in the space of 01:52.200 --> 01:56.940 a couple of minutes. And if we open this up, we've got the full skill that's written here based on the 01:56.940 --> 02:02.240 guide we actually trained it with. Now, one thing I definitely recommend with this is that when you're 02:02.240 --> 02:06.880 using new models, whether that's Fable 5 or whether that's Quen 3.8 Max or whatever comes out next, 02:07.220 --> 02:11.800 you can actually plug in a memory system here. So that has context. And the great thing about this is 02:11.800 --> 02:18.140 if we use, for example, Hermes Agent OS like this, you can see that actually saves a skill inside the 02:18.140 --> 02:22.920 Obsidian memory. Why is that useful? It's useful because, for example, if we're switching between 02:22.920 --> 02:29.980 the memory system inside Hermes, and then we go over to and we use, let's say, DeepSeq, 02:30.180 --> 02:34.520 where it's got that memory stored from Hermes Agent OS. The same, for example, if we go over to 02:34.520 --> 02:41.480 Claude Code over here and we select Quen 3.8 as the brain, we can now use Quen 3.8 02:41.480 --> 02:46.740 as the brain of Claude Code, but then also switch over to Hermes Agent OS as well whenever we want 02:46.740 --> 02:52.680 to. And so you can describe what you want. The 2.4 trillion parameter brain thinks it through. 02:53.200 --> 02:57.520 Hermes creates whatever you ask it to do. And then you can actually open that up in your browser. 02:58.180 --> 03:02.820 Also, some people say, like, this is difficult to set up a new model inside Hermes Agent OS. 03:02.820 --> 03:08.260 You can literally just go to the Manage tab or your dashboard with Hermes Agent. I would make sure 03:08.260 --> 03:11.420 that you update first, so you can just click the Update button. And then from here, 03:11.480 --> 03:17.260 you can create a new profile with Quen 3.8 Max plugged in. So you can see here that we have a 03:17.260 --> 03:24.800 separate profile for Quen 3.8 ready to go. Now, also, when they were training Quen 3.8 Max, 03:25.440 --> 03:32.140 this model is very good at coding and actually ran 10 days autonomously with self-evolving development 03:32.140 --> 03:39.020 from an empty folder to production without hand-holding. So basically, it updated and you 03:39.020 --> 03:45.640 can trace what it's done inside the GitHub for this model and see exactly what it built. 03:45.980 --> 03:50.820 And so it can code autonomously for hours. Now, why is that important with Hermes Agent? Well, 03:50.880 --> 03:54.380 essentially, if you're using the goal mode, and we have a separate section for goal mode over here, 03:54.500 --> 04:00.320 we can give it a goal and then it can go off and complete the goals and run autonomously for hours 04:00.320 --> 04:05.560 without us even having to touch it. So we can set the target and then just walk away with goal mode. 04:05.560 --> 04:10.480 And Quen 3.8 Max is designed to actually do that. The other benefit of this, and this is something I 04:10.480 --> 04:15.340 haven't tried yet, but would be super interesting, is you could use Hermes mixture of agents and you 04:15.340 --> 04:22.120 could use, for example, Fable 5 combined with Quen 3.8 Max. And that fuses the answers together. 04:22.300 --> 04:31.640 So you can get even better outputs than if you were coding with Quen 3.8 Max alone inside Hermes. 04:31.640 --> 04:36.260 And so if you combine the models, you could get even better outputs. Now, additionally, 04:36.260 --> 04:41.380 if you're coding with Quen 3.8, you can build some awesome stuff and you get Hermes Agent to 04:41.380 --> 04:47.240 actually build that with Quen as a brain. So for example, we actually tested 50 different builds 04:47.240 --> 04:51.780 of this and it can create some amazing games, some apps, tools, websites, whatever you want directly 04:51.780 --> 04:56.520 with it. And so whether you're using MCPs, like I've shown you today, or for example, you're building 04:56.520 --> 05:01.680 out games with this. Maybe you are trying to create a website, or maybe you're just using 05:01.680 --> 05:06.820 some of the tools, like for example, forward slash learn, as we covered before, you can get 05:06.820 --> 05:12.520 very good outputs from this. Here's an actual promo video it created for us with Hermes Agent, 05:13.200 --> 05:19.060 Quen 3.8 Max, and then the skill of ReMotion. So it can create animated videos. So if we take a look 05:19.060 --> 05:23.920 at this, you can see it's super clean. It looks really nice. Very beautiful design. It's actually 05:23.920 --> 05:28.940 very good at front end as well. And then this can create like a fully animated video for us 05:28.940 --> 05:36.720 with one single prompt. And so you can leave Quen 3.8 Max coding autonomously. You give it a prompt to 05:36.720 --> 05:41.400 create a video like this, and it can create something absolutely amazing. Now, what we've 05:41.400 --> 05:46.000 actually got inside this Agent OS is we have the video section here. So we can type in a prompt, 05:46.160 --> 05:51.500 then it can generate the B-roll, the script, the research, put it all together, edit it beautifully. 05:51.500 --> 05:56.360 And also the great thing about this is we have our workspace here where we can come back to it and 05:56.360 --> 06:01.560 see what we've built and watch it back later. And that's fantastic because what we can do is make 06:01.560 --> 06:06.100 sure that we never lose a project again. We never lose something that we've coded and we can watch 06:06.100 --> 06:12.480 back and see what it's built, which is super useful. So that's basically how to use Quen 3.8 Max. If you 06:12.480 --> 06:17.720 want to switch the model inside Hermes, you can actually go over to the manage tab here. And then from 06:17.720 --> 06:24.380 here, you would change the model. And you can see if you type in Quen 3.8 inside the set main model 06:24.380 --> 06:30.120 section, you can select it inside this portal and you can choose Quen 3.8 Max there, or you can go 06:30.120 --> 06:36.580 over to open router and select Quen 3.8 Max there as well. So super easy to switch the models. And also 06:36.580 --> 06:42.440 Hermes have just released version 0.2, which actually makes it faster and better with voice too. 06:42.440 --> 06:46.780 So if you want to get our full agent operating system with Hermes, all the systems I've shown you 06:46.780 --> 06:51.400 today, you've got Claude working side by side here, the full memory system as well, and everything else 06:51.400 --> 06:55.460 I've shown you, you can get that inside the AI Profit Boardroom. Link in the comments description, 06:55.720 --> 07:01.120 or just go to the AI Profit Boardroom.com. This is my AI automation community that shows you how to 07:01.120 --> 07:06.000 train agents, set up systems like this. And it gives you the full Hermes agent operating system as well. 07:06.060 --> 07:11.200 So if you go to the classroom here, then new daily updates, you'll find the agent OS with a video 07:11.200 --> 07:15.960 tutorial, his last update date, and a zip file to install it. We've also got a full one hour course 07:15.960 --> 07:21.520 on Quen 3.8 Max if you want a full masterclass on it. Additionally, we have loads of great trainings 07:21.520 --> 07:26.420 on Hermes agent as well. And you can jump on weekly coaching calls where you can share your screen, 07:26.780 --> 07:30.600 ask questions, get help in real time. Inside the community, you can ask questions as well. 07:30.840 --> 07:35.020 And I personally answer them with a video tutorial every single day. You can also direct message me 07:35.020 --> 07:39.580 whenever you need help. Inside the map, you can meet people in your local area who are building out 07:39.580 --> 07:44.260 with agents like Hermes and Quen 3.8 Max. And that's all available inside the AI Profit Boardroom. 07:44.440 --> 07:47.960 Link in the comment description, or just go to the AI Profit Boardroom.com.