Enjoying this issue?
Get tomorrow's AI & engineering digest in your inbox — hand-picked, summarized, and always spam-free.
TLDR
GPT-6 (Astra) can generate fully playable games like Fall Guys and Sim City from single prompts, and demonstrates strong browser control for knowledge work tasks. The model shows impressive 3D generation with minimal clipping and can create entire simulated towns with agent behavior. It is the best model the presenter has used, though it has a tendency toward similar design choices.
Key points
Astra generated a fully playable Fall Guys game from a single prompt.
Astra created a Sim City game over five days, generating every asset individually.
Astra can control a browser to complete tasks like searching eBay and creating slide decks.
Astra generates 3D worlds with realistic animations and minimal clipping.
Astra shows a tendency to use similar color palettes and flat design across projects.
Tools mentioned
Techniques
- browser control
- 3D world generation
- agent-based simulation
- single-prompt game generation
Stop scrolling. Start reading smarter.
Receive the day's most important AI & engineering updates in one concise email. No spam.
Transcript (captions)
All right. Yes, it is true. GPT6, I almost said GTA 6. GPT6 is here. I've had early access. I have so many demos to show you. And it's the best model I've ever used.
Oh my god. Wait till I show you the Fall Guys demo. And by the way, you can play with all of these. All of these demos are all hosted on here. Now, here is seven different biomes. And I've done
this with uh GLM 5.3. I completed this with Fable 5.1. This is definitely at the top. It's hard to say whether it's better or not, but it it's perfect. Like I don't see any mistakes with it, and it
is definitely at least equal to the best of the other ones that I've seen. Look at that. Okay, so very cool. Now, check this out. This is I'm going to open the full game in a browser so you all can
see it a little bit better. This is a fall, guys. This was one prompt. One prompt. Just a couple minutes. All right, check this out. So, it it's it has sound effects. Here's everybody else
following me. Okay, I shouldn't look. I should just go. Of course, I have diving. And it's actually fun to play. This is actually the updated version of the game. So, it was one additional
prompt provided by Brian. A little bit of feedback. And if you want to play this game, you can play it right now. Oops. Okay. Don't don't look at that. All right. Can you beat my score? Let me
know. 31 seconds. Okay, this is a really cool one. I had Astra create a 3D city using only asy characters. This is called After Hours. Okay, so you can walk through the city and if you look
really closely, the entire city is just made of little characters. It's all asy characters. And this took I think two prompts, but you can see everybody's walking around. There's a lot of life.
It's raining. There's a little mini map in the bottom right corner. I don't know if you can see that. I don't know. Yeah, I you can't see that, but there's like a little mini map right there. And it's
generative as well. So, I can walk infinitely and it'll just keep populating the world for me. Look at that. I think it's so cool. This wasn't an original idea by me. I forgot. I saw
it from somebody. I apologize. I can't give you credit, but I saw it from somebody and I was like, "Cool. I have to recreate that. That looks really cool." Okay, now this is the one I'm
really excited to show you. This is a full Sim City game that you can play right now. I did slashgoal with Astra and it was running for five straight days. Five days creating every single
asset one by one. Every single building that you see here, the fire station, the police station, the hospital, nuclear energy plant, the university, everything you see here was created one by one. And
I watched it over 5 days. The funny thing is it wasn't even done after 5 days. I just had to ship it though. So if I push play and I zoom in, I mean the world is alive. You can see people
walking. You can see cars driving traffic and it is a fully playable game. And the level of of depth that you get in this game, like the number of features, the the amount of
functionality in this game is really good. And so as I was making it, I had noticed that the frames per second were lagging so much cuz this is all HTML and JavaScript. But now look at it. There's
no lag at all. I told it I said, "Hey, make sure you're optimizing for the browser. Make sure you're optimizing for frames per second. Let's add some roads. I'll show you what it looks like. I
mean, you know, the city's growing. I have funds. I have a population happiness. I get, you know, emergencies. There's so much there. Okay, then I'm going to go into zones. I'll add a
residential zone right here. All this down here, this is all new population that I just added. So, it really does work and you can really go play it right now. So, this is just a simple prompt I
put in which was create a slide deck to talk about data centers and this is what it put together. I also told it to use our forward future branding which it is. The slides came out really well. I know
this isn't like super exciting but for any of you who are doing knowledge work, this is incredible. Astra is incredibly good at browser control and computer use. And specifically browser control is
important to me because I don't want to do everything anymore. Like I don't want to make a DMV appointment and I don't want to, you know, sell things on eBay. Whatever it is, I don't want to do it.
And so Astra's ability to actually control the browser and get real things done for me in the browser is incredible. So I'm going to show you a few examples of that. Now, the prompt
that I gave it was, okay, do this task in the browser. Record yourself. Don't use QuickTime, but write your own browser recording software. Record it and then put a timer on the screen. And
it did that all watch this. Okay, so it's drawing a research workflow in Excal. And you can see the timer going up. It is real time. It does skip ahead a couple times, so you can just see how
long things are taking in total. But yeah, I think it's really good. Here it is. Searching eBay for three Pokemon listings and comparing them. And these are like kind of high-end Pokémon cards.
So here it goes on eBay and it's just researching Pikachu expensive Pikachu cards. And yeah, it's just really good. 55 seconds to do all of this comparison. I mean, it's all under like two minutes.
Okay. And just inbox.com just released their own eval. And I want to show you that they are sponsoring this video. So super excited to show you because this is all about
knowledge work. Here is the box AAI complex work eval for GPT6 Astra. For the full data set, we get a 3% improvement. If we look specifically into the industry subsets for each of
the evals, media and entertainment got a massive bump. Technology a massive jump from 62 to 77. Legal 64 to 72. And if you remember, the legal benchmark for Astro was actually quite high. Consumer
products a modest 3% bump and energy a 77 to 86% jump. And if you're not familiar with Box, it's the easiest way to store all of your company's documents and actually get value out of them,
extract information from them, analyze them, and it's trusted by some of the biggest companies in the world. And so if you want to try GPT Astra, it's going to be released soon with Box AI. They've
been a great partner. So go check them out. I'm going to drop this benchmark down below so you can check it out and go sign up for Box. Thanks again to Box. Now, back to the video. Now, I told you
I created a lot of demos. Now, I want to actually pause here for a second. If you look at these kind of these three plus these two or these three, one thing I noticed there's a couple minor critiques
of Astra one, it still does have a little bit of that AI smell in the writing, but also in its design choice. And so these are five, six separate projects and they're all using some
variation of forest green, right? And and I didn't tell it what to do in terms of design. I didn't tell it the color palette to use. It just has this desire to use the same color palette every
time. A lot of flat design elements. That's also something like kind of the AI design smell, but it it looks good. It's just everybody's going to be creating the same thing. Now, the good
thing is Astra is extremely steerable. So, with a little nudge, you can get a lot out of it. A lot of different design. a Rubik's cube. Of course, it nailed it. Okay, so let's scramble.
There it is. Will it be able to solve it? Of course. Like, this is saturated already. Rubik's Cube Bench is saturated. So, it has a bunch of sliders
that you can change what it looks like, can change the colors, change the atmosphere, everything. So, impressive, but we've seen it before. This is another one
which I got the idea from a video I saw. There are five million pieces of hay in this hay stack and one needle. And the point of the game is to go through them one by one until you find the needle.
So, I thought this was so cool. I saw somebody else make this. This wasn't my idea. And apologies once again, of course, I just lost the reference. Uh, so I can't give you a shout out, but
here you go. Just one by one. If y'all want to play this, you can. Should I do like a 48 hour live stream where I just go through this one by one? Okay. Little planet. I thought this was really cool.
Look at this. Look how beautiful this is. And then I zoom in and I actually have a little dude walking around. Look at the detail. This is what I'm talking about with how good Astra is at 3D.
Okay. So, I don't see any clipping issues. Right. Not even right there. Yeah. So, I can zoom around really easily. Everything just looks good. No clipping spaced out properly. Let's see
if it lets me walk through stuff over here. No. Oh, so it doesn't let me walk through that, but it did let me walk through the the brush. Here's a sheep. I can walk through that. But overall, like
super impressive. Look at this. Yes, these are mostly one prompt. This one was one prompt, which is incredible. Maybe they're a little bit of issue with these uh icebergs. Yeah, a tiny bit of
um I don't know what this is called. Maybe this is clipping, but little bit of an issue there. But otherwise, fantastic. Right. I don't see any other issues in this whole game. Let's see.
Let's go to the beach. Why am I so excited about this? You should be, Chad. You absolutely should be. This is a lot of fun. Let's see what happens when we go in the water. Look at that. It
doesn't just continue the walking animation in the water. It actually changes the animation. So, he's swimming now. Can I get in the boat? No, I can't get in the boat. So, I I was really
impressed with this. There's actually different way points. And oh, look at that. It will actually navigate there by itself. So I can tell it a a waypoint to go to and then it'll go there. And then
it says press E to see what happens. There we go. Very cool. Okay. Let's try one more waypoint. All right. So it's walking. There's a volcano. And let's see what happens. There it is. I don't
know what this is. Some kind of radar measuring device. I think this is beautiful. What do I want to show you now? Commons. I don't think I had much time to play this, but this is a little
city simulation game. So we have number of residents. It's kind of like like Excel in a way, like almost Excel management. This is just a simulation of what's happening in the Excel document.
So, yeah, it's pretty cool. It's a full simulation. All of the agents in this little town were simulated by Astra, and it's basically just replaying what happened in that in the town. So, we can
see that right here. Here's the economy. I mean, it really is like a full simulation of a little town. Social fabric. Look at this. Oh, you can even record. You can run experiments. So, dry
season, patient zero, the lights go out. I didn't tell it to do any of this. My prompt was really, really simple. Okay, let's see. Oh, yeah. Okay, this is cool. This took a few prompts. I'll be honest
here, but this is a 3D liinal space horror game. Okay, so let's go into it. And I think this looks fantastic. And I basically said hyperrealistic 3D liinal horror game. There should be a baddie
somewhere. Uh, I I said to make it very subtle and and to do jump scares later, so I don't know. Maybe it'll happen in this demo, but maybe it won't. And it should get weirder. By the way, let's
see if I know how to get through here. Yeah, this was completely created by Astro. All the assets, the skins, everything, all created by Astro, or sorry, not Astro, Astra, excuse me. All
created by Astra. Here, let's see if I can put my laundry in there. Nope. I just think this is so cool. And I'm pretty sure it goes on forever. And the longer you play, eventually you're start
you're going to start to see the shadow guy. Oh boy, the nursery. Yeah, I sorry. I could just play this forever. This is cool. A little pool. But yeah, all of this just easily easily created by
Astra. Here is like a little mini GTA. I actually created a second GTA. That was my first prompt with Astra and I got pretty far, but it was it was taking so long to complete it. Here's a little
manga that I created. I mean, this is super impressive. Yeah, very very cool. This is another one I wanted to show. This is Choo Choo Rocket. This is a clone of it. Basically, all of these
little mice run around and your job is to get them to fall in your rocket and then so like I can place an arrow right here. So like they all run in a pattern and I'm trying to get them to land in my
rocket and it's multiplayer and everybody else is scrambling to try to block the mice from dropping in my rocket and to make them go into theirs. Yeah, these are these are much better
games than I was able to create with Fable 5.1. Some basic websites that I created. This is for the Galaxy Zfold. It's it's okay. You know, it still uses very flat design patterns. Here's one
for an apple orchard. Let's see. Quack Club. This is a rubber duck website. I don't really here. I think the color might be off because I have dark mode on. There we go. That looks better.
Yeah. So, you know, just a website for rubber ducks.