Claude Fable 5 is Banned... Do THIS Right Now

Claude 5 just got banned with no warning or notice. The best AI model on the planet can be taken away from you at any time. And so there are two things that you need to do right now, and barely anybody is talking about the second. And so in this video, I'm going to show you exactly how to run the world's most powerful models on your computer that can never be taken away from you, even if you're a complete beginner. And how to run world-class software like Notebook LM completely locally, so you can save thousands of dollars and hours of time. And if you're new, I'm Jack. I built and sold my last AI startup with like a gazillion customers, and now I build my own AI startups and share here the stuff that actually works. If you haven't already, grab that beautiful coffee, >> [music] >> and let's dive straight in. The US government has asked Anthropic to basically shut down their most powerful model. We had it for 72 hours, and yet we all feel exactly like this guy. People can't sleep, relationships are falling apart before our eyes because we don't have access to the best model. So it'll be a shock for many, but you do not own the most powerful models in in the world. And in this video, I'm going to show you some unlocks in local. We're going to cover exactly how to set it up, and at the end of the video, how you get alternative to some of the incredible softwares on the planet. You have to learn this skill. It is never been more important than it is right this second. So, here's the key thing. Just to re-emphasize the point, a bit of context if you're not familiar, that you don't own the models. And a couple of examples of this, in February 2026, GPT-4 was killed off. In August 2025, if you remember, Anthropic also cut OpenAI Claude's access over at basically a dispute months after cutting off Windsurf. And then again, in 2024, 2025, different regions were cut off at various different things. So if you don't own the model, it's not running on your computer, you effectively can be shut down at any time, which is really important to understand. And I'm not saying that local will currently outperform the best models. There are absolutely tradeoffs, but you want this in your stack. It's so important. But, the one of the cool benefits of why local's important that most people don't realize is A, it's 100% private. So, you can talk to it about anything. You have no limits. You can do it if you're in the sky on a plane or you're 500 ft on the ground. I don't know why you'd be 500 ft on the ground. Maybe you're digging, I don't know. And also, it's yours. Your data, your prompts, sensitive health information, private company data, it is completely locked in yours. I'm going to show you what the best models offer this right now and exactly how to set it up. It is, as I say, 100% private, works offline, no meter, no limits. Now, the idea here is when you download a local model and it runs on your computer, you can use it essentially infinitely and it will cost you a massive $0. Cuz it's just the computer on your computer. You don't pay a single dollar or cent for it. And it can effectively run forever. Your model you download it can't be retired, it cannot be revoked, it's not region locked, yours, and it's exactly good for what it is. It's basically going to run on your computer. Now, in terms of how good are these, the current estimation is that local models are roughly 6 to 12 months behind the premier front-end models. So, in a year's time, we'll probably have a model just like Fable 5 running on locally. That's generally speaking how powerful it is. For example, an RTX 5090, which you can get for a few thousand dollars, runs last year's frontier model at 70 to 85% of the quality, $0 for tokens, fully private. The gap only really bites on the hardest reasoning. is the part that everybody misses. It's actually way bigger, this whole trend is than just the model. You don't just want to basically own the model, you want to own the platform. What do I mean by that? You think about any SaaS application that you use, notebook, alarm, subscriptions that you have, CRM systems. We can build all of these and run them locally and not have to pay any dollars whatsoever for any of those subscriptions. We're living now in the era of the micro SaaS. Cuz if you can imagine it, you can build it, as as going to see in this video. Now, essentially, there are only three steps to running any model locally, whether you want to do that with your Hermes agent or Claude code. We have understanding our capacity, downloading the actual model itself, and then connecting to that, and then we are ready to rock and roll. Now, step one is just understanding the ceiling and the capacity of your model. So, more memory means bigger brains that you can actually run. So, some people run this on an old laptop. A lot of people are going out and actually buying it. You might remember the Mac Mini phase. So, the first thing that we're going to do is find out the capabilities of our computer. So, if you're a Mac, you click on the Apple icon on the top left, come down to about this Mac, and you're going to see some information. First thing we're going to do is we're going to come over and we are going to screenshot this information. And then we come over to Claude, paste the image in, and say, "Hey, based on the capacity of my current computer, what would be the best model that I could run on this at a reasonable speed that would be the most powerful given my system requirements?" You just ask a very simple question like this, and Claude will come back and recommend a couple of different models. And actually, remember, we want to download a couple, try a few, see what works, and then from that we can effectively do anything. And once you've basically asked that question, you'll get some recommendations. So, Qwen 3 is fantastic. It's such a good local model. So, this is really helpful for us, and it's fantastic. So, what we're going to do now, we've actually understood what we're going to go for. And bear in mind, you need some head room. So, if you had, for example, 20 GB of space, you wouldn't get a 20 GB model. You need some head room above that, as Claude very well knows. And so, now we have a personalized suggestion from Claude. Here's just some figurative examples that might help you understand it better. You know, you might run the Qwen 3 8 billion parameter on old laptop with 8 GB. If you've got a Mac Mini, that's normally like 16 GB, you can do Gemma 4, which is a powerful all-around model. We love that. 24 GB for your kind of RTX. Again, now at 64 GB, it starts to pick up a little bit, and you can do server clusters. And as you can see, basically, guys and gals, the bigger the actual computer that you've got, the servers and clusters, the more powerful and faster the local model actually is, which is fantastic. An interesting ROI, if you're spending over $200 a month on AI, a local rig pays for itself in 2 to 3 years, then runs at $3 per month for years. So, you can treat hardware as an investment. So, now we understand our capacity. The next thing to do is actually install a llama. Now, there's a few different ideas you can do with this. I personally always found a llama really great. So, what we're going to do is come down, come over to basically a llama.com and just download the application. And then you're going to find this code here. You just come down and copy this also. Then we're going to come up and open the terminal like so. And if you're thinking, "Jack, what on earth is a terminal? What does all this mean? It sounds like I'm speaking Chinese." I'm going to put a link down below for the full Claude code masterclass. It will take you from a complete beginner through building websites, power features, memory systems, features I have never shared on YouTube. It is the most comprehensive course I have ever done. It has 10 modules. It is fully up-to-date, and you also get immediate access to this incredible Claude code and Hermes Agentic operating system. It has like a googol and tillion cool things about it. That will get you up to speed in no time. Now, in the terminal, what we're going to do is basically enter in that code. Terminal, by the way, is just Think of it as like a chat window to have a conversation with your computer. And basically just you can give it commands and instructions. And then we can also open up the llama app once you've downloaded that. Now, what's really cool here is you can have conversations with free models once you've downloaded it. A llama is really cool because what it can also do is effectively like chat with anything on the cloud as well. Now, we can combine this with our Hermes agent. We can do many different things. But essentially, once you download a local model in this app here, when you send us messages, this is running 100% private on your computer. Which means if you had zero internet connection and you open up this app, you can talk to it about anything. And a lot of them are multimodal, so they can understand images and text, and some of them have tool calls as well, so they can build apps for you and websites. They can effectively do everything, which is why we talk a lot about different agent systems. For example, if I look at this operating system machine, your Hermes agent, one of the things I have as a skill for my Hermes' agent is it's connected to local models. So, effectively, I can delegate things to, which I'm going to show you in this video, you know, the kind of strategy behind it based on what the task physically is, which is really, really handy. Now, for the purposes of the demo, I'm going to go ahead and install this GPT OSS. So, all I'm going to do is I'm going to copy this and I'm going to come to Claude and I'm going to say, "Hey there, I'd like to install the GPT model for demonstration purposes. Could you give me the command that I need to run my And then come down and I'm just going to paste in that model and let it go live. Now, actually, Claude can do this for you itself, but I just want to show you the process just so you get more familiar about everything. If it feels complicated, that is completely normal. I promise, if you just follow these steps step-by-step, you will have this running in no time. So, as you can see, it's got it there and it's shown as a command. So, all I'm going to do is come down and hit play, which effectively is just going to run that command for us in the terminal, and that's going to install. Now, local is also fun to do. Like, it's really, really fun. I had a big conversation about this recently, just that I love the idea that you can have local models. And it's profoundly epic because you can effectively do it in any situation you want to. And I'm a [snorts] big believer in what we call model agnostic building, which means that we're not loyal to any particular company. We bring in the best model for that particular job. And if one day it's not this, it's something else, I will tell you that and we'll move over there together. Beautiful. And when that's complete, we can officially use it. Now, if you installed it like that on Claude, basically, have to give it a few minutes. You can ask Claude, "Hey, has it finished updating?" and it will give you an overview. So, all we're going to do now in the Ollama app is you can click this and we're looking for the GPT model OSS 20 billion parameters. And I can give it a prompt like, "Hey there, if I were trying to get a six-pack, what are three things that I should do to accomplish that?" Because, guys, obviously, we got to win in business, health, and relationships. Three big infinity stones. So, let's just get a bit of a six-pack protocol on that. And look at that, comes back with the thinking. Now, this is running completely locally. I could have no internet, no anything, and it'll come back. And it's pretty impressive. And all the different models have different trade-offs. Like, some of the open-source models are really good at tool calling. Like, Deep Seek, for example, is fantastic at that. Um obviously, if we're connecting to our Hermes agent, we can do like a million things with this. And then let's say you wanted to now use that with your Hermes AI agent, you could do the following. Hey there, I would love to connect this model to my Hermes agent. Could you please configure this and confirm when this is complete. And then once you've spoken with Claude, or you can chat with Hermes yourself, or you can do in the actual panel itself, when I've got my Hermes agent, let's come down {forward slash} model, and then we can come down, and you can see the current model is GPT 5.5. But, if I click on custom, check this out, I have all of my beautiful custom models. And if I click on GPT OSS 20 billion parameters, I'll now be having a conversation with that. For example, I click on this, and now I'm literally talking to it on my computer. And so, you can ask it question, hey, which model is this? And it comes back, and it tells you which model it's running. Speed will vary based on the model you download and the size of your computer. But, the key thing to understand is that this entire thing is running on my own laptop. So, if I had zero dollars to spend and I was entering the world, I could actually use my Hermes agent with this model. You just have to make sure it has at least a context of like 64,000 tokens. So, as you can see, we can drive the entire local model with Hermes agent as well, which is fantastic. So, let's talk a little bit about the best available models right now. You know, I've done some incredible videos on Deep Seek and the giant whale and what that looks like. And we're going to touch on a couple of that just to see a where of what is happening in the world with these beautiful local models. So, Gemma 4 is freaking amazing. This one is actually a Google model, which is very, very cool. It's best probably like 16 GB max. It's a good all-rounder. It has vision, so you can give it images of things, so it can read and analyze those. It's really freaking powerful. And there's like four or five different versions of it. Some, in fact, you can run on your phone, which is really cool. I just I love the idea you can run it on your mobile as you're running about. Quen 3 is the best all-round local model, good for agentic coding. Obviously, we've got GPT RSS, which is the one that I showed you. This is the best small reasoner. And it was really interesting actually in the agentic operating system. I actually added it in the bottom here, under models, this full breakdown. So, you can see like cheapest, average, fastest, most used, smartest. And you're able to have a look at all these different models and actually go, you know, double click into them. So, it was really interesting with Deep Seek V4 Flash, for example, which is number one on OpenRouter right now. I can get a good little bit of an overview, which I think is good. So, your AI, your Claude system, your Deep Seek system, excuse me, your Hermes system can plug in and understand what the best models are for any given particular time, which I think is super duper important. So, I'll let you screenshot and have a little bit of a look at those if you want to. But honestly, guys, a lot of it is chatting with Claude about what are the capabilities and trying a few of them out. And you can just download them and have conversations whenever you like. And so, this leads on to what do we actually do now? Because the answer isn't just to run 100% local right now. Because, you know, honestly, they're not the top-performing models. Like, they're just not. They're not as good right now as Opus 4.8 or GPT 5.5. And there are a lot of occasions, whether you're building websites or apps or creating copy or something, where we want the best model for the job, and local ain't it, as Shakespeare would actually explain to us. So, the core idea here is that we use basically the best model for the job. We have a specific task, and we have what we call a decision engine that will dynamically route that specific query to the specific model based on what is physically required. This is going to be especially important once we regain access to Fable or a Fable-level model again. So, we we can actually get the right token economics nailed down. For example, if it is a private query or something that's sensitive, or maybe you just want a model that's good enough to run in the background 24/7 on the thing, we can use local. Cheap AI, you can get a kind of 95% of the performance quality of the top-tier models in the world using like the latest deep seek V4 for example for roughly 1% of the price. So that's pretty amazing. Obviously don't have the data in that scenario. We've got things for long contacts. We don't want a million contacts window. Generally speaking we don't want that cuz we know performance goes down the longer the conversation is. And then you have ones for hard reasonings, your brainiacs. And there's other things that we can do to increase these numbers. Obviously we cover a lot of them on the channel like make sure your first prompt is correct. But effectively we have this decision-making matrix and it decides which of the four groups do we send it down based on the task. And by the way I'll put down my routing intelligence prompt that you can use with Claude or Hermes that helps you understand where to orchestrate and send tasks dynamically based on what the query is, whether it should be free, it needs a heavy thinking model, which will help you save a lot of money on tokens and get maximum bang for your buck. And I put a few decision-making heuristics for you down below so you can check it out. If it's private and sensitive, you may want to go local. Again, the thing is if you've got GPT uh what? In other words, in English, if you have a ChatGPT subscription for example and you're using like a personal AI assistant, you can just use that and that's not running out but that's fine, right? But we can basically tag in the different models. Now if we're using the Hermes agent, we can access these via Grok sign-in. So you you can use your Grok subscription, you can use your ChatGPT subscription, you can use OpenRouter, which effectively if you give a model an OpenRouter key, you can effectively connect to any model in the world, which is amazing. I mean check this out. Literally if I come down to models up here then I click on rankings, you can see right now in real time just like in my dashboard what are the most popular models. You give it an OpenRouter key so it connects to your your agent and it can access any models dynamically and you can effectively decide which ones I want to tag in at which specific times. Even in Hermes for example right now, when I change the model I can see what model I'm dealing with, which is really handy. And now of course we can get into create specific skills and say hey I want to create a deep reasoning agent, okay? And that deep reasoning agent I want to use this model and here's the prompt, here's the description. So, when I call that skill, it uses that specific model by using something in the in the Pantheon. If you're using Hermes agent, and if you're using Claude for example, what we do is we use something called a command line interface. So, you can say to Claude for example, "Hey there, I would like it to connect to Codex via the CLI, okay?" And it will basically open up ChatGPT in a new window. You'll sign in, and then you can actually ask it questions to delegate it. So, you could say to Claude something like "Hey, I want you to check over your work, and then I want you to also spin up a sub agent in Codex to also verify." I never release anything unless I verify it with Gemini. I use Google's model. I use Codex as well. So, I have ChatGPT, I have Gemini, Google's model, and Claude all together review my work, and you would be amazed, by the way, the amount of times that Codex catches something that Claude completely missed. Honestly, make sure you don't Whenever you're doing any work of significance, you want to make sure that you're using that kind of test. But, this then leads on to the biggest trend that actually accompanies this local revolution. And we already covered the fact that local is 6 to 12 months behind the premier model. But, there's something that is at the available at the best standard today, which people are not discussing enough. And this idea that you can actually build Microsoft where Somebody in my community on a call on Friday, we have coffee, we hang out, it's a great time, was explaining to me that they had a service they were paying for a significant amount of money. And they basically rebuilt it himself using Claude in a matter of hours. And this is not an isolated incident. I do it myself on a daily basis. Effectively, it's so easy now to build beautiful software that you can actually do it yourself. And beyond this, we have the open-source community behind us. What do I mean when I say that? For example, if you look at Notebook LM. Notebook LM is the world's number one design and research intelligence platform. Really cool. But, what if I, you know, what if one day Google says, "Sorry guys, we're shutting it down." or "We're only going to let you add 10 notebooks unless you pay us $100 or $1,000 a month." Well, we're what is known as screwed, right? Well, maybe not cuz we can use open source versions of this, which is the exact same software. We could build it ourselves if we wanted to. Or we can use open source versions of this and have any model we want to to do anything. This also happened with cloud design, where with open design, we effectively reskinned the entirety of this, meaning that we could effectively create anything with any model we want to on an unlimited level. So, this is best understood by taking an example. So, let's take open notebook as an example, okay? What I'm going to do is come over to this website right here, and we're going to check this one out to see what it's like. All you ever do is you come down to GitHub, again, open notebook. And the first thing we do with the software is we check to see does this software already exist somewhere else? I'm going to come down. All I'm going to do is you come down to code, copy this code, go straight over to Claude, and say, "Hey there, I would like you to clone this repo and open it up for me in a local host." Now, if you're not familiar, GitHub is just fancy speak for place we store files. So, essentially, all this is is a load of different files that do various different things. And when you click on this and copy a link, effectively, if it's open source, it just means that all the code in the files are openly available for everybody. And oftentimes with products, uh you know, projects like this, you have loads of contributors. There's 59 people that are contributing to improve this, which means it just grows so much faster. This is one of the reasons why Wikipedia grew so big and defeated paid alternatives because it was just running on the generosity of individuals that want to grow up. And it's the exact same thing that's happening with Hermes Agent. Loads of different contributors all coming together to make it epic. And the cool benefit of this is that like it basically takes the power and influence of any individual company away in a sense because you can build versions yourself more with AI. We're only limited by our imagination. Beautiful. And now we have this fully thing available called open notebook, and it's got localhost 3000 just above. So, I can copy this if I want to. And if I put that into a browser, we should see. So, localhost just means running on your computer. And effectively, this is a notebook LM clone. We can make any adjustments I want to. I can change it from blue to red, whatever I like. So, if you come on the left-hand side now to models on the top left, you can see effectively we can just connect different models. And so, it's really cool, guys, actually when you can decide any model you want to use here. I can use a llama, that beautiful llama we downloaded. So, I could technically use this locally hosted. I'd recommend that you use like an API key, but you can do all of these different things here. So, we can basically configure it. We can even come back, like I told this guy here. I said, "Hey, dude, go and connect it to a llama." And basically, it will go ahead and do that for you. And then we've got all these different local models. I can come off and I can delete ones that I don't want to be in there. It's got different embeddings. And effectively now, we can just go ahead and use this. So, now for example, I can come over there, I can click on new, I can click on source, and I can give it like a URL. So, let's give it a sample one. I'll go ahead and give it Glide app.com, which is the dictation tool that I've been using in this video. Come back over here, drop that in for instance, uh click on done. There we go, and it's going to be added in. The source is now going to be indexed. And then the source will appear. Then I can basically just do notebooks. So, I can go on notebook here, I might just say like, I don't know, interesting websites, and come down here, click on create new notebook. There we go. I can click on this guy, and then we can add in all the sources we want to. Come down here, click on source, add one of our existing sources. So, we can use the same sources on multiple versions. Come down, click on this, click on add selected, which is cool. And then I can have a conversation, right? So, I might say something like, "Hey there, what is Glide about?" And as you can see, we've got the model selector. So, I have if I have different models, I can literally change that. So, I can chat to any thing. And obviously, I can do as many of these as I physically want to without any kind of limitation at all, which is fantastic. And like near instantaneously, it comes back. Glide out is a real-time voice-to-text tool. And guys, this was all 100% local. Now, if I wanted best performance, I would go ahead and grab my API key from Anthropic, and I would use the, you know, basically Opus 4.8 or ChatGPT. But hopefully, you can see that again, we can create podcast models, transformations. And if I want to build on this, I can do. For example, I can come back and say, "Hey, I don't like the color blue. Go ahead and change blue to green." And now it's not blue, it's green. And just like that, I can basically make any amendment I want to this. This is just how powerful AI models actually are. So, we understand now that effectively we can build any of your softwares, we can use open source stuff, run it on our computer. And again, no internet, no problem. I can run this with local models. I can do anything I want to. You can use it to bring down the cost of subscriptions. Honestly though, I don't see this as a compelling use case. Somewhat because I think I would probably opt to use something like Deep Seek. Again, 95% of the performance, 1% of the price. Free isn't always free in that sense because the model performance can kind of lack. So, you have to use it for the right tasks, not just for any task. High volume repetitive stuff it's pretty good for and building offline for true independence. And again, in a year's time, we're going to have models that are as good as the frontier models today. So, you have to learn the skill. It's going to be incredible for the future. Now, you want to stay on the frontier. Again, if you want the very best reasoning, we use the frontier models. Again, for $20, you can get like 80, 90% of the results. And you may want to stick using exclusively frontier if you don't have the hardware to actually go ahead and do it. Cuz remember, the performance is always going to vary with the hardware. But, it is very fun to do and I highly recommend it. Now, running locally is great, but if you don't have an agentic operating system, you're leaving too much value on the table, which is why the next thing that we're going to do is learn how to build one of those together and we'll do that in this video right here.