Limitless: An AI Podcast

OpenAI's GPT Images 2.0 is out, and it's pretty wild what it can do. 

Remember ghibli-gate? Remember when it couldn't write words? Things are changing so fast these days.

------
🌌 LIMITLESS HQ ⬇️

NEWSLETTER:    https://limitlessft.substack.com/
FOLLOW ON X:   https://x.com/LimitlessFT
SPOTIFY:             https://open.spotify.com/show/5oV29YUL8AzzwXkxEXlRMQ
APPLE:                 https://podcasts.apple.com/us/podcast/limitless-podcast/id1813210890
RSS FEED:           https://limitlessft.substack.com/

------
TIMESTAMPS

0:00 ChatGPT Images 2.0 Unveiled
2:24 Realism
4:42 Design Applications
6:59 Professional Use
8:55 The Risks of Misinformation
16:27 Benchmarks
18:37 Digital and Physical Worlds
22:55 The Future of Visual AI
25:03 Closing Thoughts

------
RESOURCES

Josh: https://x.com/JoshKale

Ejaaz: https://x.com/cryptopunk7213

------
Not financial or tax advice. See our investment disclosures here:
https://www.bankless.com/disclosures⁠

Creators and Guests

Host
Ejaaz Ahamadeen
Host
Josh Kale

What is Limitless: An AI Podcast?

Exploring the frontiers of Technology and AI

Josh:
Just yesterday, OpenAI released ChatGPT Images 2.0, and the model blew my mind.

Josh:
I was up until two o'clock last morning playing around with it because of how powerful it is.

Josh:
As I was watching Sam announce this model, he was talking about how image gen

Josh:
wasn't really that important to him. He felt like they already had a good image generation model.

Josh:
When he was presented with the outputs of this one, he had his holy shit moment.

Josh:
It's actually really phenomenal.

Josh:
And through trying it ourselves, we have uncovered that it's actually true.

Josh:
I mean, we've really frequently used NanoBanana as the go-to default image generator.

Josh:
But now it's getting close to being indistinguishable from reality entirely.

Josh:
And we have a series of examples that we're going to show you that are probably

Josh:
useful for your actual applicable life.

Josh:
Things like interior design or generating comics or generating sales graphics.

Josh:
I don't think there's anyone who wouldn't find a beneficial use case of an image

Josh:
generator model that is as good as this one. So let's get into the actual announcement.

Josh:
Let's walk through the examples. It's pretty amazing stuff.

Ejaaz:
Around midday yesterday, OpenAI tweeted this very mysterious post and it goes,

Ejaaz:
This is not a screenshot, which is weird because it looks like a screenshot

Ejaaz:
of someone's Mac desktop,

Ejaaz:
except this is completely AI generated.

Ejaaz:
And this was the precursor to their official announcement, which is ChatGBT Images 2.0.

Ejaaz:
It's their new image model, and it absolutely blows every other image model

Ejaaz:
out of the water. And I don't mean that as an understatement.

Ejaaz:
It is number one across every single image benchmark.

Ejaaz:
It's beaten nano banana to and any

Ejaaz:
of the chinese image gen models just completely don't weigh

Ejaaz:
up so what are some of the new things here well the fidelity and

Ejaaz:
quality of these images are incredibly high you're seeing a demo video here

Ejaaz:
where we have a chameleon in various different positions the wording text is

Ejaaz:
typically such a hard thing for image models to nail especially when the ai

Ejaaz:
world it would like jumble up the letters or it wouldn't spell things correctly

Ejaaz:
now we have that completely and utterly resolved.

Ejaaz:
And so you can see some of these examples come to life here.

Ejaaz:
For example, look at the fidelity of this image of rice.

Ejaaz:
Typically, this would just look like a gobbled white mass. And now you can individually

Ejaaz:
see each grain, which is pretty nuts.

Ejaaz:
And then you have examples which are a little scarier, where this looks like

Ejaaz:
a real screenshot of a handwritten note in someone's stylistic way,

Ejaaz:
but it is very much completely AI generated.

Ejaaz:
So you can imagine this could be used for various different nefarious purposes,

Ejaaz:
which might get more malicious.

Ejaaz:
But there's a ton of different examples and we want to get straight into it,

Ejaaz:
starting with ones that we've generated ourselves. There's one around furniture, right?

Josh:
Yeah, but I actually want to start with the rice one, because what you mentioned

Josh:
with the rice is that it's precise enough to show the grains of rice,

Josh:
but it's also precise enough to write a single word on a grain of rice.

Josh:
And that fidelity is new. So what I did is I actually went to ChatGPT myself

Josh:
and tried to emulate this.

Josh:
And I asked it to create a piece of rice with the word GPT Image 2 generated

Josh:
on it. And this was the output that I got.

Josh:
Or actually, this was the first output that I got. And I spent maybe five minutes

Josh:
trying to find the grain of rice. I don't think it worked.

Josh:
So I asked it to draw a box around the grain of rice and it drew a box and then

Josh:
actually etched it in the middle.

Josh:
So there are some edge cases that don't quite work. I mean, that grain of rice

Josh:
was not in the original one.

Josh:
But for the ones that do work, it's pretty incredible. And you mentioned furniture.

Josh:
I am currently living in an apartment that can use a little bit of extra furnishing.

Josh:
This, unfortunately, is not what my apartment looks like. This is a much nicer

Josh:
variant of something that I would like to aspire to.

Josh:
So what I have prepared here is a reference image for ChatGPT along with the

Josh:
prompt of what I would like it to do.

Josh:
And that involves just doing things like...

Josh:
Adding lamps and adding different furniture basically swapping out the existing

Josh:
furniture that exists in this living room and moving it into a totally new vibe

Josh:
and style that i think i would more likely appreciate and resemble so while

Josh:
that's thinking i guess we can kind of get into some more of the interesting parts of this model.

Ejaaz:
Well i have a example that i actually have ready to

Ejaaz:
go here um i was kind of obsessed i don't tell anyone this i was obsessed with

Ejaaz:
manga as a kid and so i was like you know what would be cool if we could turn

Ejaaz:
our show you and i josh into a manga comic so i created this detail prompt i

Ejaaz:
gave this beautiful photo of us but look

Josh:
At those handsome guys.

Ejaaz:
Look at those handsome very handsome guys um and uh i basically asked chat gpt

Ejaaz:
to generate the prompt for me so i gave it a rough idea of what i wanted to

Ejaaz:
create the scene as it were and it created a very detailed prompt with stylistic

Ejaaz:
references details stuff that I wouldn't know because I'm not a storyboarder.

Ejaaz:
I'm not a manga creator, but funnily enough, I have an AI that can do it for me.

Ejaaz:
So I don't know if anyone is paying close attention to this storyline here,

Ejaaz:
but if you're not, that's great because I want to show you the end output.

Ejaaz:
So as you can see, very long prompt, and this is the finished result.

Ejaaz:
So what you are looking at here is Josh and I,

Ejaaz:
Let me explain this. Josh and I have been filming a podcast.

Ejaaz:
As you can see, we've got us set up over here.

Ejaaz:
But then we look out the window and there is a shadow.

Ejaaz:
And we notice that it is Sam Altman, Godzilla size, coming down upon us,

Ejaaz:
terrorizing New York City.

Ejaaz:
This is, I'd say the time estimate is roughly five years in the future,

Ejaaz:
maybe even three. Don't know how quickly AGI gets here. We grab our weapons.

Ejaaz:
It is clawed. This is not a sponsored video, by the way. I just came up with

Ejaaz:
this randomly. and it shoots out prompts that wrap around Sam Altman and eventually

Ejaaz:
bring down GPT-5 from taking over the world.

Ejaaz:
Now you know what's going on in my head, but if you just notice this,

Ejaaz:
like look at the fidelity of this.

Ejaaz:
This like took five seconds to create the prompt and then another two minutes

Ejaaz:
to create the actual image.

Ejaaz:
Look at the fidelity of this. Like the writing is all accurate.

Ejaaz:
The, like this would cost like thousands and thousands of dollars and weeks,

Ejaaz:
maybe months of time to actually create from scratch. and this did it in a bunch

Ejaaz:
of seconds for a couple of cents like it's pretty

Josh:
Impressive oh it's so good so if manga

Josh:
isn't your thing we have the furniture example it's

Josh:
ready to go so here i have the original that we're seeing on screen right now

Josh:
this was the original living room i fed it the prompt and here is the new one

Josh:
it totally maintained the integrity of the room while swapping out just a few

Josh:
key pieces of furniture to change the vibe and i think it's a testament to a

Josh:
practical use case that a lot of people might have,

Josh:
They want to design things. They want to make things look good and maintaining

Josh:
the personalized fidelity of whatever space it is.

Josh:
If you have a piece of clothing, I know this works for try-ons.

Josh:
It's really good at maintaining continuity throughout these images.

Josh:
So I thought that was a pretty interesting thing.

Josh:
If you have an apartment, if you have a closet worth full of clothes,

Josh:
you can just place those clothes out, take a picture of you,

Josh:
take a picture of their clothes, ask it to address you, ask it to redo your

Josh:
living room, whatever it may be.

Josh:
Super powerful and works fairly quick. I mean, this output took maybe a minute to generate.

Josh:
And for those not sure this is actually available to all users of chat gpt i

Josh:
believe very limited instances for the free users but if you have the plus plan

Josh:
for 20 a month you can just go off and start creating images and it will look

Josh:
just as good as this one yeah.

Ejaaz:
I mean if you're a professional that has been toying around with using ai but

Ejaaz:
it's just never been good enough it's always got some form of error whether

Ejaaz:
minor or big now we have a tool that actually works for you so if you're a designer,

Ejaaz:
if you're a floor planner,

Ejaaz:
there's a bunch of other examples I'll show here. This becomes a practical tool.

Ejaaz:
Like GPT Images 1 was very much a novelty and a toy. It was fun to see everyone

Ejaaz:
in Studio Ghibli versions of ourselves.

Ejaaz:
But now you can use this to create certain things.

Ejaaz:
Now, not all use cases are good. If you're like me, I use social media to disseminate

Ejaaz:
a lot of the breaking news that happens in the world of technology,

Ejaaz:
AI, or whatever it might be.

Ejaaz:
But you now have reached a point

Ejaaz:
where we can't necessarily believe everything we see and images

Ejaaz:
too from chat gpt doesn't make that any

Ejaaz:
easier what you're seeing on the screen right now is not

Ejaaz:
an official take or update on the bloomberg terminal that is also not my desktop

Ejaaz:
monitor this is completely ai generated and you can probably tell parts of this

Ejaaz:
like kind of gives it away it's a little too zoomed in unless of course you

Ejaaz:
can like change the default settings in your the Bloomberg terminal,

Ejaaz:
but some of these things are really good.

Ejaaz:
This is exactly where this is on the Bloomberg terminal.

Ejaaz:
The percentage mark isn't that large on the actual thing.

Ejaaz:
It's got all the sections pretty much nailed. So you know that the model looked

Ejaaz:
up official Bloomberg terminal layouts and like recreated it,

Ejaaz:
but it added a completely fake kind of like bit of news.

Ejaaz:
So you could change that bit of news to represent real news,

Ejaaz:
but it would still be fake.

Ejaaz:
So there's a lot of like avenues here for misinformation or disinformation.

Ejaaz:
So like not entirely accurate, but somewhat accurate.

Ejaaz:
You can imagine the kind of social media frenzies that this would create if

Ejaaz:
people were to believe and buy into these things.

Ejaaz:
Like imagine if you read an announcement that wasn't actually real,

Ejaaz:
bought a stock, and then it realized that it was fake, and then it crashed.

Ejaaz:
You could end up losing money.

Ejaaz:
You could fake data. There's a lot of avenues of this go down.

Josh:
Yeah, there's two points on this. One is that we're at the point now where even

Josh:
if you pixel peep, it is almost indistinguishable from real life.

Josh:
You can't really tell what is AI generated and what is not. And as that kind

Josh:
of gap converges, I imagine it will create a lot of chaos where there's just

Josh:
no way to tell what's real when these images are so good.

Josh:
The second thing that I'll mention is from this model in particular,

Josh:
anytime it's asked to generate a visual asset of a piece of software,

Josh:
for some reason, it's exceptionally good at understanding the nuances of every

Josh:
frame of every piece of software.

Josh:
Last night, I had it do DaVinci Resolve, which is what I edit a lot of videos in.

Josh:
I had it emulate Photoshop, and it got every single slider down to the correct pixel,

Josh:
which leads me to believe that it appears as if

Josh:
there was some training customization around the software

Josh:
project in particular and you have to ask the second order

Josh:
question why why is it so good at all the software and I guess the answer for

Josh:
me is well it's probably because they want their agents to understand how to

Josh:
navigate it and then eventually emulate it and then eventually replace it and

Josh:
this nuanced understanding of how everything works is training for the image

Josh:
generation model but also training for.

Josh:
Just i mean the future of what these agents are going to look like so

Josh:
there might be some hidden stuff going on behind this image generation

Josh:
model as well so back to the demos in addition to these capabilities

Josh:
we have another one teed up right here which is to create a premium

Josh:
infographic poster another strong suit of this model is

Josh:
text and how well it's able to render text that looks lifelike looks accurate

Josh:
and is able to kind of create a like a storyboard if you will a poster it can

Josh:
create multiple outputs what i've asked it to do here is create an editorial

Josh:
infographic and this is the first time I'm actually seeing the output of this

Josh:
and it seems pretty cool.

Josh:
So this is for Limitless as you are familiar with and it kind of walks through our week in review.

Josh:
So the things that Limitless mentions, this is the poster that serves as like

Josh:
the weekly roundup, the weekly review.

Josh:
It is pretty good.

Ejaaz:
Is it accurate? Yeah, I'm curious.

Josh:
You check the accuracy, I'll check the QR code, see if that works because word

Josh:
on the street is that QR codes work pretty well. wow.

Ejaaz:
I might need to replace the entire roundup newsletter josh with something like

Ejaaz:
this just a quick a quick glance quick take away

Josh:
You can imagine how this can kind of carry out

Josh:
to other applications right it's like if we want to juice the

Josh:
newsletter up a little bit we could just create a graphic with one prompt

Josh:
by feeding it the context of everything we spoke about to give you

Josh:
this detailed infographic this also applies to educators

Josh:
and people who are teaching things it's really

Josh:
easy it to make graphics on particular lessons or

Josh:
mathematical equations or diagrams or anything you want visually represented

Josh:
it's exceptionally good at that so i thought this demo was kind of fun it creates

Josh:
the limitless we can review as a poster that's printable the qr code does not

Josh:
work but i've asked it to make the qr code scannable so while it finishes that

Josh:
up and we test that maybe we could go on to another example yeah.

Ejaaz:
I was just going to say before we move on um the educational traditional

Ejaaz:
point is a very precedent one, mainly because if you're like me,

Ejaaz:
you could read as much text as you want, but sometimes a visual that summarizes

Ejaaz:
everything really helps.

Ejaaz:
You can now plug an entire book's worth of text into a single prop.

Ejaaz:
A lot of these frontier models now have a million contexts, which is a couple

Ejaaz:
of novels or many, many novels.

Ejaaz:
And so if you can imagine, if you're trying to learn about something and you

Ejaaz:
want the key points, you can not only ask the AI to summarize things and give

Ejaaz:
you a bullet pointed list, you can get them to transform it into an illustrative

Ejaaz:
poster that just you can look at in a glance before you go to bed and learn something brand new.

Ejaaz:
So I can imagine this being used in science as well.

Ejaaz:
Back when I had a biology degree or back when I was doing my degree,

Ejaaz:
I remember we used to have these like research poster conferences and they used

Ejaaz:
to be like, I don't know, A1 size.

Ejaaz:
It was absolutely massive. And you would have so much condensed information

Ejaaz:
there and it took me weeks to make and the fact that i now have a tool here

Ejaaz:
where you can just probably plug in a bunch of papers

Ejaaz:
get out extract the right information and then put it out in a

Ejaaz:
very visual way just blows my mind like we are condensing a

Ejaaz:
lot of frontier research and education tools like

Ejaaz:
with this one simple update it's very very cool but to move on to uh one more

Ejaaz:
example that we generated um one thing that's cool about images too is you can

Ejaaz:
play around with one image and make it into several different aspect ratios

Ejaaz:
so what we have here is an individual i don't know who this individual is,

Ejaaz:
but it has generated it looking out onto the greatest city in the world,

Ejaaz:
in my opinion, New York City.

Ejaaz:
And it's in like a nice little sunrise or sunset. I can't tell which one is which.

Ejaaz:
But as you notice, it gives us different aspect ratios of the guy.

Ejaaz:
Like over here, we see him on the left.

Ejaaz:
Over here, we see him from a distance back. Over here, we see a panoramic view

Ejaaz:
where we can see him looking out onto what is this? This is Brooklyn Bridge.

Ejaaz:
So the details of it, you know, you can see some of it is like kind of like

Ejaaz:
blurred aspect ratios as well.

Ejaaz:
It's just very impressive and you could start creating like

Ejaaz:
storyboard sequences from this or just kind of like pitching visuals to whatever

Ejaaz:
you whatever kind of like idea or concept you want to make you could use this

Ejaaz:
in the product realm if you're like trying to figure out whether a model looks

Ejaaz:
good advertising your product in like let's say the product was a coat in this

Ejaaz:
particular way or it could just be something advertising completely different it's it's very cool so

Josh:
How does this model perform so well i think

Josh:
is the question and one of the novel breakthroughs that this image

Josh:
model has that others don't is the detailed reasoning capabilities this is an

Josh:
image generated model that will think before acting and will reason through

Josh:
the steps required to get the best image output so generally it's just pure

Josh:
inference you give it a context you give it input and it just spits something

Josh:
out this one actually reasons through the,

Josh:
i guess the reasoning of why it's doing these things and that's part

Josh:
of the reason why even though you're not giving it necessarily the

Josh:
best prompt it's giving you a really powerful output and i

Josh:
have another fun example here of um just like more comic books

Josh:
that you can make this was a single prompt and that generated like

Josh:
an entire comic book with a really accurate character that's carried throughout

Josh:
another fun feature is the character continuity where

Josh:
you can generate a character it will be prevailing throughout all the images

Josh:
and then also one last example that we have here is of

Josh:
anyone who's involved in social media or just creating any sort of

Josh:
marketing material i asked it to create an ad package for

Josh:
a monster shop in williamsburg called sagebird and

Josh:
sagebird now has a full kit of various aspect ratios to be posted on any platform

Josh:
that looks photo accurate if you'll notice there's even a street sign that says

Josh:
bedford avenue which is a street in williamsburg which is very funny so i think

Josh:
the the fidelity the quality the capabilities of this model.

Josh:
Are really endless and again the constraint is your imagination with how far

Josh:
you can push this thing because it's just it's so powerful i had so much fun

Josh:
using this i must have generated at least 100 images so far just in the last

Josh:
24 hours and it is like it's so fun i recommend everyone go and try it and figure

Josh:
out what use cases are best for you so.

Ejaaz:
A question that came to mind immediately is okay it's good but how does it compare

Ejaaz:
to some of its competitors primarily nano banana 2 from Google,

Ejaaz:
who has previously held the number one spot here.

Ejaaz:
Now, if you look at this image over here, it's not just number one,

Ejaaz:
it's number one by a far mile.

Ejaaz:
I think it has like 150 point increase on Image Arena.

Ejaaz:
If you don't know what this is, this is like the number one benchmark to test these image models.

Ejaaz:
GPT Images 2 isn't just number one overall, it is number one across every single

Ejaaz:
category that is measured within this benchmark. By a long shot.

Ejaaz:
So it has a very distinctive lead. And if you're looking at this and you're

Ejaaz:
saying, okay, well, whatever, people can like orient benchmarks around this.

Ejaaz:
So like, we don't know if it's real.

Ejaaz:
I have a direct comparison for you. So the same prompt fed into GPT Image 2 versus Dano Bonata Pro.

Ejaaz:
And you can see that there is quite a lot of differences. You can see GPT Images

Ejaaz:
2 over here on the left, the lighting is much brighter, the fidelity is arguably a lot better.

Ejaaz:
And as you can see, like, you know, there's more expression on her face, she's smiling.

Ejaaz:
And there's a lot more things in the background. Like if you look at the plants

Ejaaz:
in the back, it's way more hyper-realistic and harder to create for an image model.

Ejaaz:
Now, if you look on the right, Nano Banana 2 is very good, but there's less

Ejaaz:
complicated things going on behind them.

Ejaaz:
The lighting is a little bit off. And you can kind of tell that

Ejaaz:
I don't know, like maybe still on both sides, you can tell that they are kind

Ejaaz:
of slightly AI generated.

Ejaaz:
I would actually argue that images too, now that I'm looking at it for longer,

Ejaaz:
looks like the glisten just seems too glistening-y.

Ejaaz:
But Nanobanana 2 can get away with it because the lighting is a little less.

Ejaaz:
But the point is these models are getting way, way better.

Ejaaz:
And the examples keep coming, but it's not just visual things.

Ejaaz:
Like social media influencers don't have to be worried here.

Ejaaz:
You can start using this for very practical purposes. Now, there was this awesome example over here.

Ejaaz:
Where a guy took an image of a book, right?

Ejaaz:
And he said, could you generate me a barcode for this book?

Ejaaz:
And he generated the barcode. And when you scan the barcode,

Ejaaz:
it takes you, it's basically an embedded link.

Ejaaz:
It takes you to a page where you can then purchase or buy the book.

Ejaaz:
Now, this is very impressive for if you are like trying to sell a particular

Ejaaz:
product, especially if it's physical, you now don't need to go through the complicated

Ejaaz:
process of generating barcodes, getting it printed.

Ejaaz:
You could feasibly create your own design book cover, print it out,

Ejaaz:
and then wrap it around your actual product and it actually works.

Ejaaz:
It works with your internal system. So I just thought this was pretty cool.

Josh:
Yeah, it's amazing. The clarity. And again, I think this is a testament to the

Josh:
reasoning where it can actually recent its way through and generate an accurate

Josh:
barcode in a world where it previously couldn't.

Josh:
So now not only can it make infographics, but it could link these dynamic elements

Josh:
to real world artifacts, to a custom domain, to your book.

Josh:
They're actually usable without needing to take it into Photoshop and take it

Josh:
that final mile. And that's like a really cool unlock.

Ejaaz:
We have another example here as well of the front page of the New York Times,

Ejaaz:
which of course is entirely fabricated um or

Ejaaz:
at least partially so like this isn't a real article this

Ejaaz:
isn't a real image of a paper but all the information on

Ejaaz:
it so if you actually dig in here and read it um all the information about open

Ejaaz:
air unveiling gpt image 2 is accurate they pulled it from the blog post they

Ejaaz:
didn't you didn't have to provide the blog post they independently did it it

Ejaaz:
reasoned through it pulled out the most important points and then wrote it in

Ejaaz:
a stylistic manner of a New York Times writer.

Ejaaz:
So you can start imagining what this could do for press and media.

Ejaaz:
If you are a reporter, you might be thinking, huh, so you're telling me I could

Ejaaz:
just feed this the bullet points that I want it to make, and it could write

Ejaaz:
it in my voice, in my DNA that I stylistically write an article for?

Ejaaz:
That's amazing. You could also ask it to generate the image for you.

Ejaaz:
So there's this metro approach where you're talking about the product,

Ejaaz:
but then you use the product to generate an example image that you then put in.

Ejaaz:
This is, of course, also generated by images too.

Ejaaz:
So there's a lot of applications here. Again, I mentioned earlier,

Ejaaz:
disinformation is a very real thing. So you can imagine people sharing fake

Ejaaz:
news articles about things that aren't real, that might sway markets or inform

Ejaaz:
people in the incorrect way, but cool nonetheless.

Josh:
Yeah. And then there's more examples for people who are involved in architecture

Josh:
at all, if you're doing floor plans.

Josh:
I mean, this one was cool where you fed it an image of a house and then it generated a floor plan.

Josh:
But the next example I think was even cooler because this was a digital rendering

Josh:
of a large building that had all of the specs listed next to it.

Josh:
And using that spec sheet and using that 3D rendering, it

Josh:
created a fully rendered floor plan

Josh:
that you can actually use and send to an architecture to

Josh:
send to an architect to to actually make blueprints and build the

Josh:
building i'm not sure if this is up to code i'm not an architect but

Josh:
i imagine you can probably iterate your way through this with a proper architect

Josh:
to get it to be compliant to get it up to spec if it's not already and train

Josh:
it to do that so this there's this unbelievable unlock that happens for pretty

Josh:
much any profession that's generating any sort of image all you need to do is

Josh:
put a stamp on the bottom it looks like it it already stamped it with some fake stamp approval.

Josh:
But I'm sure if you do this type of work, you can kind of, you can put your

Josh:
own spin on and throw your own stamp on there.

Ejaaz:
If any of you are architects listening to this, I encourage you to try this

Ejaaz:
out because I'm actually curious whether this is accurate or if not, like how accurate is it?

Ejaaz:
Because obviously like architects in training, like train for seven years at

Ejaaz:
school, which is just insane.

Ejaaz:
They have to understand the physics behind the buildings that they're designing.

Ejaaz:
And I'm wondering, is this physically accurate?

Ejaaz:
Are the estimates, like, do they make sense? Or is this completely made up and

Ejaaz:
we still have a long way to go?

Ejaaz:
It looks legit to me, but then I'm not an architect. So if you're listening to this, let us know.

Ejaaz:
There's another cool thing here where, again, I mentioned earlier,

Ejaaz:
if you are a visual learner, sometimes you just, there's too much information.

Ejaaz:
You can create these posters bracketed by a particular subject and it kind of splits it up.

Ejaaz:
So like with here, we have like all the things going on in AI,

Ejaaz:
you got AI models and agents, robotics, semiconductors.

Ejaaz:
And you just have images which explain the start to end process of creating

Ejaaz:
these different things and what they actually do with a few words underneath

Ejaaz:
it, which I thought was cool.

Ejaaz:
And then there was this final example over here from Matt Schumer,

Ejaaz:
where I can relate to this because I formerly worked at a big four consultancy

Ejaaz:
and we had to create slide decks and it would take so long because you had to

Ejaaz:
move things in a specific way or reformat the text.

Ejaaz:
And Matt Schumer one-shotted an entire slide deck by just providing it a bunch

Ejaaz:
of information and it created it in the style of Spotify by the looks of it.

Ejaaz:
So very cool, loads of different applications and I can't wait for more people

Ejaaz:
to actually use this for professional purposes.

Josh:
Yeah, the model's awesome. And I guess the ask is to share whatever you're using it for.

Josh:
Because again, like those prompts, those examples are the only limiting factors

Josh:
to really what this can do.

Josh:
Because it has the reasoning, because it's so capable, it has the like pixel perfect fidelity.

Josh:
It's really just a matter of massaging it with prompts to get the output you

Josh:
want, not really a limitation of the model anymore.

Josh:
And like to Sam's point early in the episode, it seemed like it was great before.

Josh:
Now this is just unbelievable.

Josh:
I can't imagine going back to Nano Banana Pro knowing that this exists.

Josh:
And it's just a testament again to how fast we're

Josh:
going and like what the downstream implications of this may be in

Josh:
the future when you can generate infinite images for

Josh:
cheap that are pixel perfect and indistinguishable from reality

Josh:
what type of downstream effects does that have on

Josh:
every visual artifact that we interact

Josh:
with on a day-to-day basis i mean there's no way you could be sure and this

Josh:
this has a lot of implications that i'm not sure we're fully aware of now but

Josh:
will surely become known well as we kind of navigate through this it creates

Josh:
a weird dynamic that seems a little uncomfortable like i and now i have to navigate

Josh:
the internet with such a strong filter to just try to parse through what's real and what's not.

Ejaaz:
I'm curious whether this tool can be used to generate visuals that humans hadn't

Ejaaz:
thought of before necessarily.

Ejaaz:
Like as the AI becomes smarter and is trained on our prompts and largely our

Ejaaz:
flaws, like, you know, you can ask an AI to generate a detailed prompt to then

Ejaaz:
prompt it itself because we don't know how to prompt it itself.

Ejaaz:
Like it can do the same with images where it's like, I get that Ejaz probably

Ejaaz:
missed this point. And so maybe if I create this visual in this particular way,

Ejaaz:
it's one that he hadn't thought of, but now it like breaks new ground for it.

Ejaaz:
So I wouldn't put it past this model to like the model that we have to today

Ejaaz:
to generate something, a visual artifact that will soon be kind of like groundbreaking

Ejaaz:
for humans to use. Like maybe it's not a poster.

Ejaaz:
Maybe it's not a slide deck. Maybe it's something completely new that we haven't

Ejaaz:
seen before. Pretty exciting stuff.

Josh:
Yeah. So that's ChatGPT Images 2.0, the newest and hottest image gen model in the world.

Josh:
I encourage anyone to try to displace it because uh that would

Josh:
be amazing if it gets better than this but it's worth trying

Josh:
it's worth sharing what prompts you use that

Josh:
give you some specific outputs that you may find helpful interesting

Josh:
the use cases are the currency please share yours in the comment section down

Josh:
below if you enjoyed this video don't forget to share it with a friend who may

Josh:
also want to generate some images perhaps they're involved in social media perhaps

Josh:
they just want to redesign their hypothetical apartment whatever it may be it's

Josh:
fun it's worth testing it's It's worth trying to just like feel it and understand the intelligence.

Josh:
But yeah, I think that's pretty much it for today's episode.

Josh:
Are you there any final thoughts here?

Ejaaz:
Nope. If there's one request that I have, I want to see the images that you

Ejaaz:
generate and try and surprise us, try and do a use case that we haven't covered

Ejaaz:
on this particular video, because I'm curious of the creative purposes around this.

Ejaaz:
Our social media profiles will be linked below. DM us there.

Ejaaz:
And yeah, I look forward to seeing what you have to make.

Josh:
Awesome. Cool. All right. We'll see you guys in the next episode.