Full transcript
Deep Seek V4 Flash just came out of preview. There's a brand new version and it's a giant leap. I actually tested it out so you don't need to. And I want to show you what I built, over 50 builds with it.
So I'll show you side by side, how that compares against Deep Seek V4 Pro. So you can see the huge leap and the huge difference. Now, if we go straight to the builds over here, we can see what we've created and how we're side by side. So the first thing that I would say is like, out of everything that I've tested, Deep Seek V4 Flash 0.7.3.1 is number one, way, way better than the original preview.
Number two, it is even better than the Pro version. So the Pro version is on the right-hand side over here, this version right here, and it doesn't really do anything in this particular build. Whereas for example, we look at Deep Seek 0.7.3.1 and look at this, like it's created some amazing stuff. And I actually can't wait for the new Pro version to come out, which is coming out soon.
That's going to be even better. That could be like Fable 5 level technology, but open source, like how crazy would that be? So who knows what's going to happen next? We actually did build some stuff that didn't work so well, but I'll come on to that in a second.
This is another game that we built over here, and it's just way easier to control and nicer to control than the Deep Seek V4 Pro version. And it can create like some really interesting builds and some 3D games. And, you know, some people say, oh, you can't code with Deep Seek V4 Flash. You absolutely can, as you can see right here.
And if you want to check out these builds, you can check it at GoldieBench. Now, if we have a look, for example, at the Deep Seek V4 Pro version, I can't even view what we're creating here, right? Like the camera angle and everything else is pretty bad over here. So most of the builds were like this.
They were just way nicer with V4 Flash overall. Now, if we have a look at this one, for example, and this is actually something that surprised me as well, was when I was using this, it actually created a lot of stuff that was better than some of the frontier models I created. Now, I'm not saying this is better than frontier models. It isn't.
It's not better than Fable 5 or GPT 516 Sol. But my point is, like, it can hold its own. It can actually build useful stuff. It can build interesting stuff.
And when I built out and coded out games like this, they were smooth, they were easy to use, and it actually worked, which, you know, quite often, these sort of builds, especially if it's complex, if it's 3D, if it's like a game like this, usually they don't work so well. So that was interesting as well. I mean, if we compare this side by side, look at the difference in graphics. This feels a lot more, like, sort of basic in terms of the 3D effects and everything, whereas DeepSeek V4 Flash definitely did a better job overall as well.
Now, if we have a look here, we've got some other games that we created. It was just, just creates some nice things. Now, it's not always like this. So if we have a look at this one, for example, it's kind of buggy.
Like, you can see through the floor, which doesn't make any sense. It looks like it's floating, which it shouldn't be. And also the graphics here are pretty basic, right? It's not that interesting.
Along with the controls. So it does fail sometimes. Now, what DeepSeek are actually trying to do with this model is they are trying to build something that's designed for AI agents. So this model is not really built for, like, coding or to be a frontier model or anything like that.
It's built to be super fast, lightweight, and small so that it can code out with AI agents. So for example, if you're using Hermes or OpenClaw or Pi, DeepSeek V4 Flash is actually really good. And the other interesting thing about this as well is that you can actually get access to DeepSeek V4 Flash for free via OAT. So if you go to OpenCode, we've got it set up inside our agentic operating system.
We can code for free with DeepSeek V4 Flash, and they've updated it to the new version, which means that you can get the latest version of DeepSeek V4 Flash for free, and you can code and build out with it. Now, also what's interesting about that is there's a skill for Hermes agent from Noose Research, the founder of Hermes agent, that allows you to automatically delegate coding tasks out to OpenCode, which means that you could use DeepSeek V4 as a brain, you could set up the OpenCode skill, and then when you're coding out with Hermes, you can use OpenCode for free to automatically build cool stuff out as well, which is really cool. I've got another tutorial on that. So overall, it's pretty nice.
Now, there is some stuff where I'm like, you know, it's just not that fun and interesting. You also might say, okay, why do I build out like games and stuff like this? Why not like websites and landing pages? Number one, because it's not that interesting to view.
Number two, when you build out games, it's a much better test of like, how does it understand reasoning? How does it understand logic, coding, physics? How does it create UI and that sort of thing? So also it gives me an idea of how fast it can perform when it comes to creating something bigger, which is super useful to know.
Like speed is a big and important factor when it comes to using AR models. Like there's models out there like Sakana Fugu 1.1 that can actually build better stuff than for example, Fable 5, when I've tested them side-by-side on GoldieBench. But that's not the point. Like the point is with, for example, Claude, like I can go back and forth faster and I can build out stuff faster with Fable 5 than I can with Sakana Fugu.
And so I use Fable 5 way more than I would use Sakana Fugu. That's the point here. And that's what it's all about. Now, if we actually have a look at this one, this one was interesting.
So what you can see here is we're creating like this flight simulator game and it worked with DeepSea V4 Flash. But if we have a look, for example, at V4 Pro, like it totally failed. Like I don't even know what this is or how it's working or anything like that. Let's have a look at some of the other builds.
Yeah, it's pretty cool. It creates some cool stuff. I won't like explain every single build because like it just doesn't make sense, but here's another big difference. So if we have a look at this one side-by-side, like the game, the UI, the style, the graphics, the vibe and the feel of the V4 Flash version is way nicer than the Pro version.
Even like the parachute game, like the, I would say it's super buggy with V4 Pro from DeepSea, whereas this version is way nicer as well. There's some stuff like it totally failed out. So, I mean, look at this pool game. It's terrible.
It's really, really bad. So just bear in mind, like it doesn't get everything perfect, but yeah, it's created so many cool things. Now, if you want to see all the builds that we created, you can check them out on GoldieBench. We've got builds for pretty much every model that I've tested recently.
And I set this up about a month and a half ago and ever since then, every single model we test, if you're wondering what's right at the top, actually Fusion is right at the top from OpenRooter, but that's using like a council of models. If you look at, okay, what's performing best as a standalone model, Opus 5 is pretty good, but actually day-to-day when you're coding out with Opus 5, it's not as good as Fable 5 because it gets distracted and it can be quite slow, but it can build amazing stuff. If you want to get a full agentic operating system with a DeepSeek coder, where you can build stuff, preview it, save it. So you'll have, for example, Hermes Agent and the Hermes Agent OS, which means that we can use DeepSeek with Hermes Astros or Hermes Oracle or the voice agent over here.
And we have a memory system plugged in as well. You can get that inside the AI Profit Boardroom. Link in the comments description or just go to the AIProfitBoardroom.com. And inside this community, you can grab the Agent OS over here.
So we've got the full agentic operating system where you can get the zip file to install it. You can also, for example, get our full masterclass on DeepSeek, how to use it, how to use it step-by-step and get the most out of it. Every time something new and useful drops as well, we create a tutorial on it. Inside the community, you can post questions and I personally answer them with a video tutorial.
Plus there's always people online 24 seven, so you can get help and support whenever you need to. Inside the calendar, you can jump on weekly coaching calls, ask questions, share your screen, meet other members in real time. And then inside the map, you can meet people in your local area who are building out with AI agents like you. So feel free to get this, link in the comments description or go to the AIProfitBoardroom.com.
More episodes