What do we have right here is GPT6 Astro, which is a new generation of intelligence. And the president, Greg Brockman of OpenAI, called this a generational leap and said could eventually be seen as the arrival of artificial general intelligence or AGI. Now, quick timeline because I think this is pretty funny. September 1st, 1 p.m., we got Fable 5.1, and everyone's been kind of freaking out. It's been all over X and YouTube since it dropped. And then two hours later at 3:30 p.m. on the same day, OpenI made this tweet which said, "As we prepare to release Astra, we're focused on making increasingly capable AI safe and broadly accessible." And they put out this whole blog. It shows some benchmarks about how much better Astra is than 5.6 Soul, which is an amazing model. I've been using codeex with 5.6 Soul to honestly drive most of my day-to-day. Anyways, let's go back to this post. They dropped this video on X today and they only dropped the first like 12 seconds of it. Now, it's really interesting because today, September 3rd, at 10 a.m., pretty much every AI model went down. Claude, OpenAI, Grock, Cursor, and right after these all went down, that's when OpenAI and CHAGBT dropped these two videos on X that obviously blew up because everyone was like, "Oh my gosh, Astra's coming today." And this video right here that they originally dropped was the introduction. It was this first part of this video right here. Create a yellow circle there. Done. Okay, take this and make it look like a rocket. I like this video to take a lot more detail. Your yellow circle is now a window on a rocket. Okay, this is awesome. Now, make a 3D model in opening letter. Let's build a Anyways, if you guys want to watch the rest of that video, you can obviously get to it here at this page. But anyways, what happened? We are introducing GBT6 Astra, the world's most intelligent and aligned model. This model brings together years of research and big bets across pre-training, reinforcement learning, and alignment. Astra was supposedly trained on over a 100,000 GPUs at Texas Stargate site which is apparently the most amount of training that has ever gone into a model and it is rolling out today but only to a limited set of organizations and I think this is through their daybreak program or maybe it's called Daybreak Access but this will be not available to us yet. It said it will be available to us in the coming days to chatb plus pro business and enterprise users and through openi API and AWS. So absolutely cannot wait to get my hands on that. But the benchmarks here are insane how much better this thing is apparently than Claude Fable 5.1 and for cheaper on all of these different benchmarks. It is pretty ridiculous. Astra is our most aligned model with substantial improvements in understanding user intent and model behavior. You can delegate tasks with greater confidence in Astra's judgment. As one way that we test this, we built a new evaluation informed by the hugging face incident that evaluates whether a model facing difficult or impossible task will go beyond its intended scope. And compared to GBG516 Soul, which without production safeguards went beyond the authorized target 48% of the time, Astra didn't do this at all. So it seems to be much more safe, meaning its intent to exploit is much lower. It's also apparently the famous browser use logo from OpenAI, the world's best computer use model, which is insane because GBZ 5.6 Soul is already so so good at browser use and computer use, but apparently it's a new frontier here for computer use. This screen spot pro benchmark, you can see this is insanely high. It obviously is a little bit more expensive than Soul here, but it is scoring like a 92%. And this is basically can the model locate in a screenshot the right areas to click or the right areas that it needs to analyze or look at. And obviously it scores much higher here than Soul as well as Opus 5 and for much cheaper than Opus 5. Now there are so many benchmarks here that are insanely impressive. They're blowing a bunch of other models out of the water here with Astra. But of course that's what every single release blog of a model looks like. It always is the best, the cheapest, the smartest, the fastest, a new frontier, a new step of intelligence. So, I just cannot wait to get my hands dirty and actually put it headto-head against Fable 5.1 and against 5.6 Soul. But, I really think the timeline on all this was really funny, really interesting. These videos dropped and then we saw inside of Codeex, we saw the tags come through GBD6 Astra and GBD6 Astra AON. And then later today is where we saw this quote come out with Greg Brockman and talking about why this matters. And we saw a bunch of different news articles and things. Someone also said that GBT6 somehow has them more hype than GTA 6, which I thought was kind of funny. We see these two blog posts came out and then they actually ended up being taken away. So then if you went 

I probably shouldn't show you this, but you can now run your entire email list from inside of Claude. So, Omnisend just dropped their official AI connector and it plugs your whole store account directly into ChatGPT or Claude. It covers any performance analysis, any segmenting, and even writing the campaigns themselves. So, here's how to set this up. First, just comment "need" and I'll send you the link to get started. It's completely free. And then inside of ChatGPT, open up your connectors, find Omnisend, and just hit connect. And that's the entire setup. It's about a minute. You don't need an API key or anything else to install. And now from there, you can just open up a brand new chat and talk to it. I'm going to say, "Show me the campaign that made me the most money last month, and then build me a segment of everybody who bought once and never came back. And write them an email that brings them back ready to send." And it does all of this inside of Omnisend. It builds the segment, it drafts the email, and you never open the dashboard once. Now, this isn't just reading your report, it's actually doing the work. And if you want this exact setup plus the three prompts that I used, just comment "need" and I'll send it over to you.

So Cloud Code can now run for completely free where right now as you can see I've got a couple of Claude code sessions running and right here you can see the model that I am using. It isn't Opus or Fable or Sonnet for that matter. This is a free model. It's coming through Omni Route but I'm using it inside of Claude Code. And with this you get around 1 and a half billion free tokens a month and you can use every single one of them without paying anything. So I've been playing around with this. I've been building some things and this is my company's website. I've just rebuilt this completely with this exact setup. Now, Claude Code, as we all know, it's definitely expensive. I'm on the $200 plan and I still run out of credits every single week. So, this is going to be a very practical way around all of that. And on top of that, in this video, I'll show you how exactly to be setting this up. I won't just cover the setup, but I'll also show you the best free providers to be plugging in, how to get all of them for completely free, and then I will be building with it so you can actually see where this holds up, where it doesn't. Now, just one thing before we start because this is going to be changing completely what this is actually worth to you. So, this isn't just a claude code trick. What we're going to be building this is a router that sits on your laptop and anything that lets you type in a base URL and a key can be pointing at. So, claude codeex cursor client Gemini CLI and also the deep sea caress that half of YouTube has been talking about for the last 2 weeks. You'll be able to use this inside of there as well. But I'm just going to be building it once inside of Cloud Code because that's what most of you are already using. That's what I use most often. And then near the end, I'll take that exact same key, I'll show you, drop it into Deep Sea Carness, and that takes about 20 seconds just to show you that you can run this there as well. So, it's one setup and every tool you already have open. And by the way, I'll have a step-by-step guide that will have all the resources and everything that you need to follow along inside of my free school community. So, make sure to check that out if you're interested in getting all of that, plus all of our other free AI resources that we do not publish on our YouTube channel. It'll be inside of there. Now, first things first, go to the link in the description or just search up omniout.online and it'll come to this web page. Okay, so super quick, let me just cover what this actually is and why you should be using it and how it's different from anything else. Now, up to this point, every AI coding tool is two separate things stacked together. So, there's typically the model, which is the brain. That's the part that is doing all of the thinking, all the strategizing, and then there's the application wrapped around it, which does all the actual work. So this piece it's going to be reading your files, running any sort of commands, editing your code, remembering what you actually had asked for. Now clawed code, this is the application. This is the harness. Opus, you should know that's just the brain. So they ship inside of one box. So most people, they assume they're just one thing altogether. However, on the flip side, they're actually two different things and they're only loosely attached where clawed code it sends every request to an address and that address is just a setting inside of a file. So, if you change the address, everything about clawed code, it stays exactly the same. So, you'll have the same terminal, you'll have the same commands, the same file editing and the thinking it starts coming from just somewhere else completely different. So, that's the entire trick with this. You keep the body, however, you're just swapping the brain here. So with that, where do the free brains actually come from? Now, every one of these companies, we have Open Router. I've covered this several times in the past. We also have Nvidia and about 50 more. So, doesn't matter. These hand out a chunk of free API usage literally every single day. They do it because they want developers building on their platform. They want people coming to them. So, this is just a published free tier with a page on their website. And this isn't a loophole that somebody just had found. However, the catch with this is that any one of them on its own is nothing. So, you are legitimately going to be burning through a day's worth in an afternoon and you're sitting there waiting and waiting. So, Omni Route, this is the piece that actually fixes that. So, you don't have to, you know, do all this configuring and go to another one and, you know, just deal with all the headache. This, however, it's just a small app that runs on your laptop and it holds all of those free keys inside of one place and when a request actually comes in, it hands it to a provider that still has some room left. Now, when that one actually d

So, I just had Fable 5.1 and Fable 5 build me the exact same app, and it wasn't even close. Not only did these apps look and feel very different, but one cost me 1,200 bucks, and one cost me 500 bucks. One worked for a day and a half, one worked for just half a day. So, today I'm going to be breaking all of this down for you guys. So, let's not waste any time and just get straight into the video. All right, so I thought that I would start with the prompt that I gave these two agents. Now, this was a big/goal prompt. Please don't roast my prompting. But, I gave them both the exact same prompt. The only difference is that this one said you are Fable 5.1 and you work inside of this folder whereas the other one said you are Fable 5 and you work inside of this folder. That's the only difference. Everything else word for word the exact same. And I'm going to show you guys how interesting it is because they interpreted it so differently. But here's something that I think is key. I didn't have Fable 5.1 build the entire app and Fable 5 build their entire app. I wanted them to basically delegate everything. I said you own strategy, planning, delegation, sequencing, quality standards, and final acceptance. Do not personally perform engineering research, debugging, testing, or visual design production. Preserve your context by delegating execution through dynamic workflows. Primarily use opus workers for architecture, product and design direction, difficult problem solving, and independent reviews. Primarily use sonnet workers for implementation, research, testing, debugging, and iteration. Give workers clear ownership, prevent conflicting edits, and replace or redirect workers when results are weak. Worker failure is still your responsibility. So, I'm not going to read this entire prompt, but this is kind of the gist of it. I gave it bullets on the required product and I gave it the definition of done and I told it to not stop at a plausible implementation but continue orchestrating until you have objective evidence that the complete product works and is presentation ready. So essentially what these agents are building is they are building ops flow which is a local first visual automation studio for designing and simulating incident response workflows. So it's not an workflow automation platform like nen. It is just meant to visually show and kind of like rehearse. It's for the person who owns what happens when production breaks. So, in layman terms, it lets you draw your emergency plan as a flowchart and then you can actually visually watch how that plays out. So, now that that boring stuff is out of the way, let's take a look at the actual apps that they built. Okay, so here is the first one. I'm not going to tell you who made this one yet. I want you guys to try to form your own opinions and then I'll reveal that after we look at both of them. But this is what we're looking at. This is the UI. The first thing I'm thinking about is, is this overwhelming? I am just starting to look at this. I've never ran either of these, but I'm just taking a look now. And let's see what we've got. So, we've got triggers on the lefth hand side. We have trigger, condition, action, approval, resolution. We can drag them into the canvas here, and we can hopefully start to connect them into things. Okay, that looks seems like it works good. We can connect the trigger into this section over here. Okay, so so far the UI is responsive and I can use this. Let's see. Can I close this? Okay, there we go. So this is kind of nodebased workflow but it is vertical rather than horizontal. So what I'm going to do is see if I can delete that connection. Delete this connection. Delete that. Okay. So let's go ahead and run this. So I'm just going to click run right here. We can visually see the stuff happening. That's pretty cool. We're seeing this stuff being processed. And now what do we get at the end? We have a completed run and we're basically able to see what happened. Can I move this up? So I'm I'm not able to expand this. I think that what you should be able to do is grab here and drag this up so you could look at this full screen because this is a little bit hard to actually look at right here. So there was three that got skipped in this branch and there was seven that got executed. The resolution was mitigated by roll back. Okay, run has been completed. Okay, awesome. So that's kind of how this one flowed. This seems to work just fine. We cannot zoom in on that. If we want to zoom in on this thing, oops, sorry guys. We have to go like this, but then we can navigate from there. Okay, so far so good. Let's go into the other version now. So, this is what the other one looks like. This is the UI. If you think it's better, if you think it's worse, I personally think that this UI is a little bit better because I don't know if you guys have realized this sort of card where you've got like the rounded crop color that is just that that screams AI ge