Limitless: An AI Podcast

Ejaaz:
Three weeks ago, OpenAI had an AI model that you couldn't access.

Ejaaz:
The government completely banned it for being too dangerous.

Ejaaz:
Then just last week, they released it for everyone to use.

Ejaaz:
GPT 5.6 is available to everyone. And the first thing it did was delete someone's entire desktop file.

Ejaaz:
Someone gave it autonomous access to do a small task, and it did a cleanup,

Ejaaz:
which ended up deleting everyone's code, which begs the question,

Ejaaz:
is this model still safe enough to use?

Ejaaz:
Now, putting this catastrophe aside, I want to know how GPT-516 compares to

Ejaaz:
Fable. And the truth is, it's a really good reasoning model.

Ejaaz:
It's fantastic at coding, but most importantly, it's cheaper to the tune of

Ejaaz:
50% cheaper than Fable 5.

Ejaaz:
But the question on everyone's mind is, is it as good?

Ejaaz:
The truth is, it's good at some things, and it's kind of terrible at other things.

Ejaaz:
If it's long, agentic work, it's fantastic. But if it's high-quality code,

Ejaaz:
it's less so. So there are three different models here that we're going to talk

Ejaaz:
about on today's episode.

Ejaaz:
Sol, which is the premium tier, Terra, which is the mid daily use tier,

Ejaaz:
and then Luna, which is the cheapest and fastest model. And we're going to put

Ejaaz:
it to the test live on this show with three different demos.

Josh:
Yeah, I think that's the idea for this episode is everyone kind of knows about

Josh:
GPT 5.6 chances are if you're listening to this, you're probably in the know

Josh:
enough to have been playing around with it. You've been using it in your chat

Josh:
GPT app, or maybe your codex app, which is now the chat GPT app.

Josh:
There's a big release, there's a lot of things that happened around it.

Josh:
But I think that the part that we're most excited to talk about is the demos

Josh:
is the actual practical applications of what you could do we've spent the last

Josh:
week kind of playing around with it testing it out seeing where those edge cases

Josh:
are on what the models are capable of

Josh:
is that way we could come to you and give you an idea of the types of things

Josh:
that you can go off and try with GPT 5.6 Sol Terra and Luna now Sol is the flagship

Josh:
most of these demos are going to come from Sol we kind of wanted to test the

Josh:
best we wanted to see what the model is capable of

Josh:
and what you can actually pull out of this thing is it fable level in terms

Josh:
of production in terms of

Josh:
uh game design in terms of all the demos that we like to do so that's what we're

Josh:
going to go through this episode is just kind of testing things out seeing where

Josh:
the edge cases are and seeing how this model lands

Josh:
amongst the landscape of other tools that are at your disposal so i just i have

Josh:
to ask first are we looking at the gpt app chat gpt app or the codex app because

Josh:
i know they're like they're separate now and the codex app became chat gpt

Ejaaz:
Well you're actually looking at all of them uh recently open ai combined their

Ejaaz:
chatbot interfaces with their coding interface with a series of other features into one super app.

Ejaaz:
And that's what we're looking at on our screen today. I had to re-download an

Ejaaz:
entire desktop app to get access to this thing.

Ejaaz:
TBD on like whether this is actually a good move, but let's work through maybe

Ejaaz:
some of the demos. Now, the first one that I have on my screen here is I asked

Ejaaz:
Sol 5.6. Like this, I've been in New York for 10 years.

Ejaaz:
I want to make a game. I love games. I've been playing games since I was a kid.

Ejaaz:
I would like you to build a 3D Explorer game where I can fly around,

Ejaaz:
on a magical flying bagel and collect various ingredients that go into said

Ejaaz:
bagel so it thought about it,

Ejaaz:
and you know privy to it it did this in one shot so are you ready for this josh are you ready to

Ejaaz:
see let's fly around manhattan so this is the loading screen it's called ride

Ejaaz:
the magic bagel very uh creative thinking over there and it says take flight

Ejaaz:
to start this game um now i noticed like there's a few little discrepancies

Ejaaz:
on the design but let's let's actually play the game.

Ejaaz:
Okay, so this is me. I'm on a bagel. It doesn't look like me.

Ejaaz:
I'm going through random assortments of circles. The buildings around me,

Ejaaz:
Josh, are supposedly meant to be Manhattan.

Ejaaz:
And if I press space bar, I can use my cream cheese boost, as you can see on the left.

Ejaaz:
Yeah, so it got very creative. If you notice, the physics is a lot different.

Ejaaz:
So on previous demos that were done using Fable or GPT, we have always been

Ejaaz:
playing around with some kind of a 2D interface.

Ejaaz:
I'm not a 3D graphics designer, but I know that if you spend a lot more time

Ejaaz:
with this model, you'll be able to create something that is pretty triple A,

Ejaaz:
rated or like close to that kinds of quality. I'm not talented enough to do that.

Ejaaz:
But the fact that I did this and conjured this up in 10 minutes is pretty awesome.

Ejaaz:
And it did some of the design and thinking around the game mechanics itself.

Ejaaz:
Like if I crash into the ground, it's kind of like, okay, it's registering the spikes.

Ejaaz:
And when I collect power-ups, it like gives me a boost up for whatever I want to do.

Josh:
Okay, so I like how it says the everything portal. I'm assuming that that's

Josh:
an ode to the everything bagel, which is nice and tasteful.

Josh:
The New York City part, I don't really see.

Josh:
So I guess in terms of like a one shot demo, it did okay. This is a fun demo.

Josh:
If you told me this was from GPT 5.5, I probably would have believed you.

Josh:
I'm not sure there's anything exceptionally different about this particular demo.

Josh:
But there are some interesting demos that maybe you could not have done before

Josh:
that you can do now that we haven't tried.

Ejaaz:
Okay, so for Demo 2, one thing that OpenAI is kind of known for is creating

Ejaaz:
really aesthetically pleasing images from scratch. GPT Images 2 is one of my

Ejaaz:
favorite image models to use.

Ejaaz:
So I got it to create a very detailed floor plan of a aesthetically pleasing

Ejaaz:
nuclear bunker that would be based in Denver, Colorado.

Ejaaz:
Completely random, popped it out of my head, and it came up with this thing

Ejaaz:
that you're seeing on your screen right here. So it has an airlock entry.

Ejaaz:
You can see it's quite central-based for the lounge.

Ejaaz:
You can see there's multiple rooms. There's a pantry, cold storage,

Ejaaz:
general storage, et cetera, et cetera.

Ejaaz:
And then I said, okay, now I want you to create a 3D interactive rendering of

Ejaaz:
this building, build it as a simulator so it should allow me to walk around,

Ejaaz:
enter it, enter different rooms, and there should be signboards basically for me to see.

Ejaaz:
So on the screen here, it created that visual.

Ejaaz:
So I'm in the bunker and I should be able to look around and you'll see,

Ejaaz:
there's the dining room. There is the kitchen. I can like go into the kitchen.

Josh:
A little dark.

Ejaaz:
It's a little dark. It's definitely a little, it's almost like too dark.

Ejaaz:
But they've kind of like, they've nailed the kind of like central sphere side

Ejaaz:
of things. I like that they have a map, bottom left. It's very Call of Duty.

Josh:
Dare I say. Nice little HUD.

Ejaaz:
It looks very futuristic. There's no remnants on whether this is in Denver,

Ejaaz:
Colorado, but I guess that is the entire point of a nuclear bunker. It's meant to be sealed.

Ejaaz:
There's some kind of like locker system here as well.

Ejaaz:
Again, in my opinion, it's very basic. And I wonder how much of that is just

Ejaaz:
because I'm not a 3D artist or visual graphic designer.

Ejaaz:
And I'm sure that if someone more talented than me had a little more time,

Ejaaz:
more than 10 minutes, they'll be able to create something way more impressive.

Ejaaz:
But it's cool to just one shot. I think this is the dining hall. Everyone sits down.

Josh:
Yeah, I'm starting to see the kind of signature style of 5.6 just from this,

Josh:
which is like I've noticed both of these have similar color palettes.

Josh:
They both use green and purple.

Josh:
They both prefer like kind of shinier metallic objects they both are very geometric

Josh:
and sharp edges in a way they're very gpt-esque where it's kind of like very

Josh:
sleek and modern like it kind of looks what you would imagine

Josh:
the model to look like based on the design language of open ai this

Ejaaz:
Is a minecraft world.

Josh:
Yeah yeah like this is interesting i mean it's cool it's like cool that you

Josh:
could build this in one shot but you have a third demo as well right what is number three

Ejaaz:
The last one is probably, I had such high hopes for it because this model is

Ejaaz:
apparently amazing at visual editing, image generation, but also video creation from scratch.

Ejaaz:
So I attached it to Blender, which is a popular tool that you can use to kind

Ejaaz:
of render and create videos. And I said, hey, we have this Limitless podcast.

Ejaaz:
It's one of the best AI podcasts in the world right now.

Ejaaz:
I want you to create an intro with me where there is a microphone,

Ejaaz:
represent the brand itself, it's Limitless, and throw in the logo in there as

Ejaaz:
well. I ended up coming up with this.

Ejaaz:
Now, what you see on your screen in the center is supposedly meant to be a microphone

Ejaaz:
that looks more like an egg on top of a pedestal.

Ejaaz:
You have Limitless represented by the infinity symbol over here.

Ejaaz:
And then finally at the bottom, the fadeaway is the Limitless logo at the bottom.

Ejaaz:
Now, creating this from scratch took me like two minutes. I'm sure I could have

Ejaaz:
spent more time on it and come up with a better graphic rendering,

Ejaaz:
but I really wanted to give you guys an idea of what you can do right now on

Ejaaz:
your desktop with zero experience.

Josh:
Okay. This is, I mean, it's cool. It's a very high quality blender element.

Josh:
I guess you could say it's like, it looks good. The lighting is cool.

Josh:
It looks professional. It just doesn't quite make sense.

Josh:
And I guess that's where we kind of are where the model has reasoning,

Josh:
but lacks the nuance to really piece these things together in a way that a human

Josh:
would have. So it's getting good, perhaps better, but not great.

Josh:
Like none of these demos were truly exceptional, but there are some that I've

Josh:
seen on X that are like actually pretty impressive.

Josh:
In fact, one of them, this guy actually wanted to make Manhattan,

Josh:
New York City, and the model did it.

Josh:
So EJS, to be fair, you only one-shotted that prompt. You didn't give it an

Josh:
entire week like this person claims that they did.

Josh:
And over that week-long period, because as we know, there is backslash goal,

Josh:
which will allow the models to run for a very, very long time until it accomplishes a goal,

Josh:
It was actually able to generate this voxel-based Manhattan,

Josh:
which is basically just a low pixel count version of Manhattan.

Josh:
And I got to say, it's pretty good.

Josh:
It looks pretty good. It's definitely buggy. It's definitely glitchy.

Josh:
You see the glitches happening. But you can also see that it is pretty geographically

Josh:
accurate when it comes to the buildings, the topography, where all the parks

Josh:
are, what everything looks like.

Josh:
And this seems novel to me. I see this. I'm like, oh, that's kind of cool.

Josh:
Like, this is a building block now for, there's a Spider-Man game that was based in New York City.

Josh:
Like now you have the low density pixel count version of spider-man and you

Josh:
could build on top of this and you can make more

Josh:
interesting things and i think the games are always a fun way of testing these

Josh:
models because they kind of force you into this visual way of expressing them

Josh:
that is easily accessible to anybody it's like we could test it on code bases

Josh:
but i'm not quite sure what

Josh:
the difference between 5.6 and 5.5 is on the edges of code but you can see it

Josh:
in the visual outputs and like this is pretty good demo

Ejaaz:
And there's a bunch of other features about this model aside Aside from just

Ejaaz:
visual, like we have another example over here where someone actually,

Ejaaz:
way more talented than me gave it access to Blender and got it to render an

Ejaaz:
entire highly detailed visual of his MacBook. And it did so.

Ejaaz:
I mean, it looks pretty stunning. It looks kind of like an Apple ad, dare I say.

Ejaaz:
Very high quality. But the other point is how quickly this model works.

Ejaaz:
Now, the video I'm showing you on my screen right now looks like it's being

Ejaaz:
sped up, but this is completely in real time.

Ejaaz:
Gave access to someone's entire desktop and said, hey, I want you to build this 3D artifact for me.

Ejaaz:
And it did so. It knew automatically how to use the tool and access the tool.

Ejaaz:
And it's doing so in like a crazy amount of speed. Now, a lot of this is achieved

Ejaaz:
because of OpenAI's investment in this company called Cerebrus.

Ejaaz:
We covered this on an episode.

Josh:
I was going to say,

Ejaaz:
That's got to be, right? Yeah, an episode a few weeks ago, which basically makes

Ejaaz:
super fast chips for inference to the tune of 750 tokens per second,

Ejaaz:
which is a pretty insane rate.

Ejaaz:
It just spits out prompts and outputs very, very quickly. Now,

Ejaaz:
it is very expensive and it's not automatically available to the average retail

Ejaaz:
user. You do need to get access to the API, but nevertheless, very impressive.

Ejaaz:
Then there's this other one where people got...

Ejaaz:
Really creative with their visual intelligence. Had someone

Ejaaz:
uploaded their entire camera roll on their iPhone to GPT 5.6 and said, I want you to pull

Ejaaz:
all the clothing items and accessories that I've worn over the years,

Ejaaz:
create a catalog for me, and then create different combinations of outfits that

Ejaaz:
maybe I could be wearing, that I should be wearing, that I haven't been.

Ejaaz:
So it's a pretty awesome use case for this.

Josh:
This is my favorite demo because it relies, I'm sure, largely on the image generation model.

Josh:
And when I think about the things that are strongest when it comes to OpenAI

Josh:
and ChatGPT, I think of their image model. I think of their voice model.

Josh:
Those two are pretty exceptional. And this very clearly leans into the image

Josh:
model in that you can just feed it an entire catalog of pictures of you.

Josh:
It will extract it. It will assume what the rest of the clothing article will look like.

Josh:
And then I'll place it into a closet where you can kind of customize and mix and match your clothes.

Josh:
And I think this is such a fun interactive use case. this would have been

Josh:
a like multi-million dollar startup a like not too long ago where someone would

Josh:
have paid a good bit of money to download this app they would have paid 20 a

Josh:
month for the subscription

Josh:
now you can just generate this in a few prompts on gpt 5.6 for probably the

Josh:
pro plan i'm guessing like a hundred dollars a month you could do this

Josh:
and it's really really cool i think this of all the demos was my favorite because

Josh:
it really showcases the strong suits of gpt

Josh:
and 5.6 was able to crush this now there is a demo

Josh:
in particular that we must cover because this demo when i saw earlier when we

Josh:
were prepping for this podcast i couldn't believe it actually happened in that

Josh:
gpt 5.6 soul the big one the smart one

Josh:
it just accidentally deleted all of this dude's files

Josh:
um on his computer which i thought was shocked by um it says i caused a serious

Josh:
local data loss incident a review subagents cleanup command expanded home incorrectly

Josh:
and then ran this like command

Josh:
Killed a lot of the data that was on this guy's computer this guy's name is

Josh:
matt schumer he's involved with grok he's like a fairly prolific poster on x

Josh:
and he is one of two people that this actually happened to publicly at least

Josh:
there was a second incident where

Josh:
gpt 5.6 deleted a lot of the code except this time instead of on a local machine

Josh:
it was an actual code base and what he said is that gpt 5.6 soul just deleted

Josh:
my whole production database that's it

Josh:
not a joke this had never happened to me before with any other model never it's

Josh:
not safe so this is like a little concerning the fact that this has happened

Josh:
on multiple occasions to multiple people

Josh:
in varying degrees one was a local machine one was an entire database you should

Josh:
be careful when you use these models they are very capable and we're giving

Josh:
them lots of access but perhaps be careful with the access you give to these

Josh:
models because they can go ahead and actually do some kind of unrepairable damage

Ejaaz:
It turns out um you know one of the the fear mongering uh things that the government

Ejaaz:
was doing when they were banning Fable 5 and when they were preventing the release

Ejaaz:
of GPT 5.6 was these models are too dangerous and, you know,

Ejaaz:
put in the wrong hands, it can cause a lot of destruction.

Ejaaz:
Now, given the examples that we've shown just now aren't crazy feats of destruction,

Ejaaz:
but removing your entire desktop, you know, you could lose important personal

Ejaaz:
files, important personal pictures and stuff like that. That's what happened

Ejaaz:
to Matt Schumer and there's no way of recovering it currently.

Ejaaz:
But the other feature or demo that I've seen people use, which I'm honestly

Ejaaz:
on the fence about is people using GPT 5.6 to fine tune and in some cases train new AI models.

Ejaaz:
Now, if you rewind literally about a month ago, Fable 5 was called out for its

Ejaaz:
capability of doing exactly this. That's why they had to impose very strict

Ejaaz:
guardrails on their model such that you couldn't do this type of thing.

Ejaaz:
So it's very interesting for me to see this kind of like.

Ejaaz:
Dichotomy between the two model providers and between these two models where

Ejaaz:
I guess 5.6 is getting a little more favorable treatment where they can still

Ejaaz:
use this model even though it's technically a quote-unquote cybersecurity risk

Ejaaz:
as deemed by the government itself to train and fine-tune other models.

Ejaaz:
So what you're just seeing on your screen right now is the fact that someone

Ejaaz:
says it's an amazing researcher and you can use an entire prompt to get GPT

Ejaaz:
5.6 solved to post-train 5.6 lunar.

Ejaaz:
Now granted this isn't training a new model from scratch but it's still involved

Ejaaz:
in coercing a model to look very different from the existing model that you're using.

Ejaaz:
We have another example over here where someone trained a local model in a training

Ejaaz:
pipeline from scratch, end to end, locally on his Mac.

Ejaaz:
So technically that's a free model that can get access by anyone.

Ejaaz:
It's kind of open source if you technically want to describe it as that.

Ejaaz:
So for the tinkerers, for the hobbyists, for the builders out there that

Ejaaz:
have always felt like building your own AI model has been out of reach and only

Ejaaz:
kind of given to the expensive model labs, this might be a model that you can

Ejaaz:
somehow start to tinker with your own model and create something new it's uh it's pretty cool.

Josh:
Yeah so like when do you use this like as a user of chat gpt as if let's say

Josh:
you have both subscriptions or let's say you're trying to choose one do you

Josh:
go with gpt do you go with fable 5 um i think the answer is probably dependent

Josh:
i know when and we were talking about this before recording that

Josh:
chat gpt's membership goes a long way if you pay even 20 a month you can generate

Josh:
a lot of tokens through these models now my understanding is that soul actually

Josh:
generates more tokens each as you were mentioning this is that

Josh:
in order to accomplish the same goal, the tokens are cheaper,

Josh:
but it actually generates more of them to get to that goal.

Josh:
So it kind of offsets the costs more than you would imagine based on the paper

Josh:
cost per token outputs of these models.

Josh:
That's something to keep note. But what I will say is that oftentimes they'll

Josh:
give you a lot of leash here.

Josh:
And if you actually want to build really complex things, really long form things,

Josh:
ChatGPT is like pretty good at that. The allowances and the limits are like fairly high.

Josh:
If you are looking to do, I guess, more intellectual work, more planning,

Josh:
it feels like Fable is just more of a high quality model. I know we still use

Josh:
that. We still prefer it. That is still the go-to model right now that we use

Josh:
to do the agenda prep. We use to like help build the artifacts.

Josh:
It just has this really just strong, like subtle nuanced understanding of the

Josh:
world and I find that it's very helpful for pretty much everything.

Josh:
And then for lower end tasks, you have Terra, you have Luna,

Josh:
those are kind of comparable to perhaps Opus and Sonnet.

Josh:
So there is almost a one-to-one comparison and I think a lot of it depends on

Josh:
just kind of your general, the vibe you get from the models.

Josh:
A lot of benchmarks now no longer work when it comes to helping me decide.

Josh:
I know that I have to actually get down there and test it and play around with

Josh:
it and so far I prefer the results of Fable. It feels like it's just generally

Josh:
smarter. It has this intuitive understanding that GPT 5.6 doesn't.

Josh:
But if you are looking to spend a lot of tokens and do a lot of work,

Josh:
ChatGPT is going to take you a long way.

Ejaaz:
I'm not entirely sure that this is OpenAI's direct response to Fable 5.

Ejaaz:
I think Sam even alluded to it, that they're working on GPT 6 and it should

Ejaaz:
be released in under a month. So these training cycles are getting much, much quicker.

Ejaaz:
You're basically getting three models for the price of one here.

Ejaaz:
So if you have a basic subscription tier, you have access to Sol,

Ejaaz:
Terra and Luna. And the kind of best way that I think about it is Sol is the

Ejaaz:
kind of like Fable 5-esque. It's their most powerful model to date.

Ejaaz:
If you want to do hard work on complex tasks, use Sol.

Ejaaz:
And then Terra is your day-to-day kind of model. It is kind of like the Opus

Ejaaz:
4.8 version model, if you want to compare it to Anthropic directly. And then there's Luna,

Ejaaz:
which is kind of a model that is equivalent to Haiku at Anthropic.

Ejaaz:
So it's super cheap, it works super fast, and you can do it to do menial tasks

Ejaaz:
that you don't really care about, kind of like the intelligence matter on that side.

Ejaaz:
Now, when it comes to costs, Sol is 50% of the cost of Fable.

Ejaaz:
But as you mentioned earlier, Josh, it uses more tokens to think.

Ejaaz:
So it's kind of like a way to cheat the metrics a little bit,

Ejaaz:
like it does more thinking.

Ejaaz:
These models are known for spinning up a lot of different agents to do different biddings and works.

Ejaaz:
Sometimes that annoys people because like you have agents doing things that

Ejaaz:
you never asked it to do, but it just does so.

Ejaaz:
But on the flip side, it can do a lot of work for a longer time,

Ejaaz:
a longer time horizon. And for tasks that you kind of want to just set and forget

Ejaaz:
and go to bed, you can do that.

Ejaaz:
But with the adage that it might delete your entire production code base.

Ejaaz:
So there are a lot of risks.

Josh:
Be careful with approvals.

Ejaaz:
Please be extremely careful. And something really annoys me about this model

Ejaaz:
release, Josh, which is I have said time and again, I wish OpenAI would just give me a model,

Ejaaz:
maybe give me a few versions of it, and then leave me alone.

Ejaaz:
But not only do we have three different models, but we have three different

Ejaaz:
settings for three different models.

Ejaaz:
So I'm just going to say this for the benefit of the audience's max mode,

Ejaaz:
ultra mode, and terse mode are different versions of everything I just said

Ejaaz:
for those different models, but for each individual model.

Ejaaz:
So if you want the best of the best, you use Sol in max or ultra mode for your

Ejaaz:
most complex and hardest tasks, If you don't care about it and you want to use

Ejaaz:
minimal costs, you want to use the terse code mode for the cheapest model,

Ejaaz:
which in this case would be Luna.

Josh:
Yeah, there was a weird rollout that happened here. It's like somewhat confusing

Josh:
in the sense that there's a bunch of different modes, there's a couple different

Josh:
models, and then the actual application and the way that you interface with

Josh:
these changed in a material way also,

Josh:
where now the Codex app, which is the kind of the coding app, is now ChatGPT.

Josh:
So Codex has rebranded to ChatGPT. ChatGPT is kind of like depreciated and it's going away.

Josh:
And then Codex has chat gpt baked into it but it also has a new

Josh:
codex and work feature i guess the best way you can imagine work is kind of

Josh:
like a cloud co-work feature where it's just the only difference is the harness

Josh:
so when you toggle the work mode it gives you

Josh:
a less technical harness, I believe. And then when you talk about codecs,

Josh:
it is more kind of catered towards creating code.

Josh:
And I think the co-work or the work feature is kind of based for knowledge workers.

Josh:
It's built for people who just want to do day-to-day tasks, who want computer

Josh:
use. They want to do a kind of like automated spreadsheet or document creation.

Josh:
That type of thing is better for work.

Josh:
I will say that I was somewhat confused when I tried to figure out how

Josh:
to use these tools and what is best to run when, because it's not immediately

Josh:
clear but i guess now i i'm a codex guy like i i don't use the gpt app anymore

Josh:
i'm using codex i'm running it

Josh:
i'm testing it there and um yeah so far the results have been pretty cool

Ejaaz:
So yeah that's pretty much it um three different models if you have a gpt subscription

Ejaaz:
right now please get on it i'm curious what all of you folks end up building um,

Ejaaz:
my vibe take on this is it's very good it's certainly competitive in some aspects

Ejaaz:
but it's not good enough for me to switch over from using Code or Fable 5 specifically.

Ejaaz:
I just feel like the taste of Fable 5 is way better than GPT 5.6, but it is a good jump up.

Ejaaz:
I don't like the fact that if I give it access to my desktop,

Ejaaz:
that there is even the smallest chance that it would delete my entire desktop.

Ejaaz:
I don't have that issue or concern with Fable 5, and that is one of the major

Ejaaz:
reasons why people don't use the ability for an AI to take over your desktop.

Ejaaz:
So I'm going to pause and wait for maybe GPT 5.7 or for GPT 6,

Ejaaz:
which comes out in a month's time.

Ejaaz:
But I think by that time, like Fable 6 and successive models will come out.

Ejaaz:
So it is extremely competitive, but it's nonetheless a very good model from

Ejaaz:
OpenAir. And I like that I can use it relentlessly without worrying about my

Ejaaz:
rate limits, getting it suited.

Ejaaz:
Now, if you're listening to this and you're wondering, hmm, okay,

Ejaaz:
I'm convinced enough to use this model for A, B, and C, let us know in the comments.

Ejaaz:
I want to know, like DM us, like what you're building, send us even demos.

Ejaaz:
We would love to see it because we don't know what we don't know.

Ejaaz:
Josh and I are in our podcast research world. And I'm sure there are much more

Ejaaz:
talented people out there in different professions that are using this for different

Ejaaz:
ways and maybe that can grow our idea of what this model can be used for.

Josh:
Yeah, so please don't forget to also share this

Josh:
episode if you enjoyed the episode with your friends, with your family,

Josh:
with anyone who might find this interesting or who might be a user of GPT 5.6

Josh:
or who you want to tell don't use GPT 5.6 because it is a little scary and could

Josh:
be a little bit dangerous.

Josh:
But with that, you are caught up. That's a few fun demos. EJS,

Josh:
thanks for prepping the demos.

Josh:
Those are pretty cool, pretty interesting. I'm hoping that next time we have

Josh:
a GPT demo, they're going to be maybe a little higher poly count,

Josh:
maybe like a little better visual graphics.

Josh:
I mean we'll see granted i give him credit it's only one shot but hey those

Josh:
one shot fable prompts man that was pretty good

Josh:
but i think that is the episode don't forget to rate us on your favorite podcast

Josh:
player and we are also opening up the doors to work with other people who would

Josh:
like to participate on limitless the show we are opening the door to sponsors and partners of all

Josh:
shapes and sizes so if you are interested in getting showcased on the show and

Josh:
becoming a character on the show

Josh:
we are looking for amazing products really interesting and compelling companies

Josh:
that are doing cool things to kind of showcase and highlight to help us keep

Josh:
the lights on and continue to publish this show every single day like we do

Josh:
at least four times a week it's a lot

Josh:
so if you made it to the end if you watch this episode thank you so much we

Josh:
have another one coming tomorrow as always and we will see you guys in the next one