[00:01] Today we're going to be looking at Sakana Fugu Ultra, which is a new model Sakana Fugu Ultra, which is a new model that's just dropped. This is from Japan. And if you look at the benchmarks here, Sakana Fugu Ultra 1.1 is actually
[00:15] Sakana Fugu Ultra 1.1 is actually beating Fable 5 on the benchmarks. Now, you what they look like in a second. Um, but yeah, basically Sakana Fugu 1.1 just dropped and it's unlike any other AI model you've used because you can give
[00:30] it one prompt and it sends a whole team of AI experts to build it for you. I actually put that team through the hardest game builds on my benchmark and it actually matched the best model on the planet on its very first try. So,
[00:45] the top builds so you can see it yourself. Now, if we go over to we've created, let's have a look at some of the stuff we have built with this.
[00:57] We've had it running for hours just to see what we can create with it. So, this see what we can create with it. So, this is Fugu Ultra 1.1. And you can see some pretty nice stuff. I mean, this game is super fun to play. Um, 3D looks pretty
[01:14] super fun to play. Um, 3D looks pretty cool. I'll also compare it to Fable 5 and the same sort of tests in a second so you can compare them side by side. So is like an open world game as you can see. You might say, well, why don't you
[01:28] use it for business automations? I usually do, but the the difference is that when you're using this for coding out games, you get a good feel for how well it can plan, how well it's good at logic, um how well it can code, etc.,
[01:41] right? and also what the UI is like when it designs stuff. So, it's a really good test of of what works and what doesn't. Um, this one is pretty cool. Like, wow. It can create some amazing stuff as you can see. And bear in mind, this is one
[01:54] shot. So, what happens with Sakana is that it uses several different AI models um to put things together and then create them, right? So, for example, if we look at this right here, it's basically got a council of models, and
[02:08] that's how it gets better outputs than, for example, Fable 5 on its own. And if we have a look at this one, it's kind of like a a Skyrim style game, fun to play,
[02:20] easy to use, open world. All of this stuff is really, really good. Right. The only downside with Sakana, and this is what actually blows me away, is that back and forth with it because it takes like 15 minutes to generate one shot.
[02:33] stuff that you're seeing right now was was created first time around, right? We anything like that. Um, but it it creates some amazing stuff. It's like a parachute game as you can see. Pretty cool. I like the detail and everything
[02:47] like that on the game. And this is a flight simulator. Pretty nice. Everything worked first time round as well. Let's have a look at this one. Yeah. Yeah. Pretty cool. All right. So, how does this work?
[03:02] Basically, you give Sakana Fugu a prompt. Then you get the orchestrator that routts to one to three experts and then you can use the system to get one build. So, it merges all of the answers together. And the expert team is working
[03:17] together separately and then these get fused inside one final answer. And so if we have a look at this system, we've actually got it inside the agent operating system. If we scroll down to Sakana Fugu, we can ask the council of
[03:32] models questions over here. And then we can see everything inside our workspace over here. Right? So all this sort of stuff has been built directly using uh before. So everything that we create with this as well, it lands in our
[03:47] workspace so that we can reuse it later. Now why do we do this? Well, the thing is there's a one brain ceiling problem. So every model you use has the same
[03:59] hidden limit. One brain does a whole job. So the same brain plants your physics um paints its graphics. Why is it scorebook? And when the job gets big, that one brain can start dropping things for example like context. And so the
[04:13] graphics might land but the controls break or the physics might work but part of it never renders. And so we've all been there like a long build comes back 90% right and 10% broken. Now with Sakana Fugu 1.1 particularly the ultra
[04:28] model you stop using one brain and you route the job to a team of experts and merge what comes back and that's fugu 1.1. Now you also might say okay fugu uh
[04:41] and multi- aent sounds bit like it might be slow uh it is a lot slower right so it takes about 25 minutes of orchestrated thinking but if you need like the best quality outputs and you need something better than fable 5 this
[04:55] is well worth looking into one thing to bear in mind as well is in the EU and the UK this seems to get blocked uh so it doesn't seem to work I
[05:07] I think that's because UK um hasn't allowed it or sometimes like AI models just don't work in the UK. But if you're in Asia or the US, you can run the request and it actually works which is pretty cool. Um and if not, if you want
[05:20] an alternative to this which isn't using Sakana, you can actually use fusion and fusion is a similar sort of idea. This comes from open router. It's API based again and you can use the council of models to get better outputs that way.
[05:34] pretty cool. If we have a look at the benchmarks here and we compare it against, for example, Fable 5, we've got Claude Fable 5 versus Fugu Ultra 1.1 Claude Fable 5 versus Fugu Ultra 1.1 here. So, this is the game that Fable 5
[05:48] created, which is pretty nice, but it's a little bit laggy in parts. Um, and it doesn't seem to work that well when it comes to actually using the controls. right? Whereas if we have a look at this
[06:02] example from Fugu Ultra, it created a better less linear version with better graphics. It's smoother to run, easier to use, and a lot less buggy, right? And
[06:14] so because it's using a combination of different models, you tend to get better outputs. You can also use something like mixture of experts directly from Hermes models. If we have a look at the flight simulator, for example, this is Fable 5,
[06:29] which doesn't have that much detail, not that interesting. And then if we compare that to, for example, Sakana Fuger Ultra 1.1, you can see it's a lot more fun to use. It's a lot more fluid. Um, it seems to work better. The controls are nicer,
[06:42] etc. So, it does actually create better output side by side versus uh Fable 5 and any other model that I've tested. potentially. By the way, if you want to test and try this stuff yourself, check it out on Goldiebench. You can see a
[06:57] can also go to the compare section and actually play everything that we created. Also, what I like about this system is because we built it into the agent OS, we don't have to go and grab the API from somewhere else and then
[07:10] orchestrate it or anything like that. It's all inside this one tab here so workspace and everything saved there along with the chat here where we can use it, right? So, it's just ready to go whenever we need to, which saves a lot
[07:25] of time. Now, some people think like I should just pick one model and stick Fable 5 or something like that. Honestly, every model on Goldie Bench
[07:37] wins somewhere and loses somewhere. So the people winning with AI right now will run a stack like the agent OS and then switch and route the jobs to whichever brain or team of brains fits it. Also other people will say well slow
[07:50] models aren't worth it. Like if Google is thinking for 25 minutes it's not worth it. But if this is just running in the background and you go off and do something else actually works really well. And bear in mind this is beating
[08:02] all the Frontier models on the same test I've run. And you can see that on Goldie Bench. And I've shown you Fable 5 versus Sakana Ultra 1.1 today. Other people say, well, the benchmarks tell me what I need to know. I don't need to to test
[08:16] this stuff myself. But honestly, I never listen to benchmarks. That's why I test out inside the HOS and and you you can see what we've built with it directly. So, the thing that I would say is like don't pick your favorite fish. Own the
[08:31] whole aquarium and root the job. Right? When you've got Sakana Fugu, you can route the job to a council of models to multiple different models and have them mastermind so that if one makes a mistake, the other one covers up for it.
[08:46] Now, if you're wondering how to get access, you can go to console.sakana.ai or you can use open router if it's not available for you on sakana.ai depending on where you are and then you can store it inside the agent OS as well. You also
[09:00] But it's like, well, if you want the best model in the world, it's probably, jobs where you need something super frontier. Now, you you know, like if you're just coding out a website, you might not use this, but if you're coding
[09:15] out something big and interesting and powerful, then Sakana Fugu can help you outputs than something that's frontier alone. So, just to recap here, you understood the whole setup, right? So, one prompt, an orchestrator,
[09:29] up to three experts, and then one merged answer with Sakana Fugu. You saw my it and shown you the evidence that it actually is pretty good. All right, you you're in certain regions, you would just use the API on open router instead
[09:45] of going to sakana.ai. And I've shown you the live uh scorecard as well. And I've shown you how to build it into an agent operating system so that you can with it and come back to it later as well. Now, if you want the full Sakana
[10:00] system and and all of this system built for you, you could wire it yourself with the steps above that I've shown you or you can get it inside the agent you can get it inside the agent operating system, right? And inside the
[10:13] AR profitable portal, right? So all of this system that you can see right here with the HOS, this is all available inside the AI profit boardroom. So you plugged in. You can get all these different orchestration tools. You can
[10:28] get uh we've got a system for Hermes mixture of agents which is very similar to Sakana Fugu in the way that works. We have Fusion over here which also works in a similar way and we have Sakana Fugu with Sakana 1.1 plugged in as well. So,
[10:41] can get it inside my AI automation community, the AI profit boardroom link in the comments in description or just go to the AI profitbboard.com. And if you go to the classroom and then go to new daily updates, you can grab
[10:55] the agent OS system right here with a video tutorial. You see when it's last install it, plus we add new daily tutorials based on what's actually useful and it's just dropped. Now, inside the community, you can also ask
[11:09] questions, and I personally answer them every day with a video tutorial. And on weekly coaching calls, share your screen, ask questions, meet other people using the agent OS. And then inside the
[11:22] map, you can meet people locally near you who are building with AI agents like you. Now, some people going to say, isn't a agent operating system technical isn't a agent operating system technical to use? So, we actually have over 205
[11:37] pages of testimonials and wins. So, you can see for example, Andrea posted, "Thank you. My mission control has been a game changer. I love being ahead of the AI curve." Again, thank you, Julian Goldie. And also, she set up with tail
[11:51] scale so she can access uh the agent OS anywhere she goes. Rich said, "Is anyone boardroom? I've been working through the training and I'm genuinely impressed with how everything is organized." So, you know, I'm non technical and all
[12:03] these people are getting great results with the agent OS. You might not be non it doesn't matter, right? You don't need to be technical to use this. You might also think, okay, well, I don't want to use Sakana because it costs a lot of
[12:16] you know, the super frontier stuff that you need. And then finally, some people say, well, doesn't an agent OS use a lot of tokens? But we actually have a full system inside the AI profitable boardroom in the classroom on how to use
[12:31] the agent operating system for free. So if you're on a budget or if you have limited tokens, no problem. You can use this system right here to save tokens free. So either way, you can win with it. So thanks for watching. Hope to see
[12:45] you inside the air profit boardroom. See you on the next one. Cheers.