So, I'm running Fable 5 inside of C
marks, inside of Cursor's agent window,
as well as inside of Claude. And while
most people will tell you, "Oh, the
benchmarks are crazy. This is the new
model." which you can just get by
reading the official Anthropic article,
or by asking Claude to explain Fable 5.
In this video, I'm going to take a
completely different approach, and I'm
going to focus on my workflow, because
I've been testing this model non-stop. I
slept like a couple of hours, cuz this
is perhaps the biggest improvement, the
biggest model jump since the release of
GPT-4. It's incredible, but again, all
of that is useless if you don't know how
to use it, and that's going to be the
central focus of this video. So, first
of all, you might be tempted to use it
through Open Router, which is what I
did. That was a mistake. There is a few
reasons, right? First of all, it's a
very expensive model. It's one of the
most expensive models in the world. It's
double the cost of Opus. But, the reason
it's a mistake is because the biggest
issue when using Fable is that it can
trip the safeguards, and it can
automatically reject a good amount of
prompts. A lot of people are reporting
it rejecting normal stuff, and it
happened to me, as well. You can
literally ask something like, "Tell me
everything there is to know about Fable
5." and just a prompt like this can trip
the safeguards, and it will downgrade
itself to Opus 4.8, which obviously, we
don't want. We want to be using Fable.
So, there is a lot of tricks that I
developed over the last 12 to 14 hours.
And the first thing is not using it
through API, because you need to have
this built-in mechanism of downgrading,
right? That's why I think currently, the
two best places to use it is inside of
Cursor, and inside of Claude code, or
the Claude app, is because these have
the built-in mechanism for when there
are hap- There it is. You can see,
switch to Opus 4.8 for no reason. I
didn't do any bio weapons. I didn't do
any hacking. So, there is a specific way
to prompt it, and after I cannot change
my mindset about how to prompt this
model versus previous models, this
happens to me way, way less. So, first
of all, I would advise you to actually
avoid the Claude app. This is where most
people are going to be using it, and
obviously, like, it's convenient, right?
You can use your Anthropic subscription.
It's a simple user interface. You have
the effort level you can switch easily.
The issue is here it's way more limited.
It has a lot of prompting around it, lot
of guardrails. And that's because this
app is going to be used by hundreds of
millions of people. I mean, tens of
millions at the bare minimum, but
probably hundreds of millions since
Claude is quickly becoming more popular
than ChatGPT. So, Anthropic made this
very limited in the app, so I would
avoid that. So, then the second thing is
like, okay, I'm going to use it in the
API, right? So, for example, here I'm
running Pi Agent inside of Cbox. It's
powered by Fable. And this is still
really good for a lot of different
workflows, and I'm going to explain how
I'm using it. But, it has some issues.
And the main issue is that it doesn't
have the fallback. So, when it trips the
safeguard, it just throws errors, and it
doesn't try again. It doesn't gently
downgrade to Opus. So, I wouldn't use it
in the API, either. So, if you're
planning to use it inside of Hermas,
inside of Open Claude, inside of Pi,
it's not the best for most usage. There
are still use cases for it, but it's not
the best. Currently, I think the best is
inside of Cursor. This is where I'm
using it, and specifically in the Cursor
Agent windows. So, this is what the
default one looks like, you know, highly
similar to VS Code. After all, it's a
fork of VS Code. But, this one is more
similar to the Code X app. It's called
Agent window, and or Agent view. And
this is how you can run many, many
agents at once. So, I've done a lot with
this model over the past 14 hours. I've
built a new tool, which I open source,
which I will going to show you later on,
called Auto Git. And I also released
that to NPM. So, I built it for me me
and my team, and I also open sourced it.
I also reviewed all areas of my life
with Fable. I completely revamped some
of our internal software to make it more
stable, better designed, uh more
reliable, faster. This is incredible
model, okay? Let me just say that. It's
incredible model, and I'm going to show
you a lot of different things it can do
in multiple different areas of life and
business. Before I go into my workflows,
let me show you a little taste of what
Claude can cook up with Fable 5. This is
like a 3D graphics game for, you know,
backrooms Slenderman. Look at the
animation. Look at the feel. This is
built all inside of Cloud Artifact. So,
this is not a full stack web app. This
is not inside of an IDE. This is just a
Cloud Artifact. Here's a second example
of the type of games and assets Fable
can cook up. This is a 3D app where
Fable 5 logs network packets and
displays them as cars. So, this is not
just some pointless animation. These are
the actual packets going to this
computer
rendered as 3D cars in a nice cool
animation. And stuff like this Fable can
one shot without any issues. All right,
so let me show you how I actually use
Fable currently. And as I said, most of
my usage is currently happening in
Cursor in the agents view. So, what I do
is, you know, I work on a project. So,
for example, here is our internal
software. I just create a new chat, new
thread. I select Fable. I have it
default. And I either do extra high or I
do max.
Obviously, this is going to take a lot
of credits and cost cost a lot of money.
But, I'm going to be honest with you
guys.
Um if you aren't prepared to spend
multiple thousands of dollars per month
on AI, you're not going to have an
advantage. Like, the models are becoming
more expensive and there is going to be
a bigger and bigger gap between people
on the cutting edge with the best models
who can run them for older agents and
people who simply cannot afford them.
So, some people call this the permanent
underclass. You can call it whatever you
want, but that is the harsh reality.
Now, for a new project, something like
AutoGit, which again, I just built that
in a couple of hours with Fable, helped
me get clarity about new project I want
to build. And then I basically described
what I know about it and what I'm not
sure about. And it started like
interviewing me, right? This model
really puts in a lot more effort. It
writes a lot more tests. It is competent
in terms of
when it makes a change, it doesn't just
make it and push it. It tries to render
the browser, tries to see what it looks
like, tries to test it in multiple
different ways to make sure it didn't
break other things, that it works the
way it intended, that it looks good in
the front end. It really is like when it
was refactoring, for example, the canvas
here, previous models were struggling
with making this easy, especially when
you have a lot of generations. Now, we
have only like eight images generating,
but once you have 50 or 100 on a on a
single canvas,
other models, including
GPT-5.5-Extra-High,
were struggling with this, and they were
struggling to fix uh some of the bugs we
had here.
Fable just one-shots them. It is
expensive, you know, so be prepared to
burn through your limits,
but it is really, really good. Now,
let's talk about how to avoid the
guardrails and not have Fable rejecting
unnecessarily.
First of all, you don't want to talk
about any like cybersecurity or anything
that looks like model distillation,
right? So, even before, when I asked it,
"Tell me everything there is to know
about Fable 5,"
this is enough to make it think like I'm
some Chinese lab trying to distill it,
right? So, just be careful, okay? Be
careful by
not making it sure that you want to know
everything about the model. Don't prompt
it in a way that seems like you're
building a data set out of its responses
for distillation. None of that. Second
thing is cybersecurity. So, if you ask
for your app, like,
"Check my app for security," sometimes
it can reject that as well. What I did
inside of uh cursor here, when I was
improving the security for YouTube
Alpha, what I did is I first told it to
analyze the middleware authentication,
all that, to see if if, you know, all
endpoints are properly secured, if
someone we found an account, could
someone get access, just basic stuff. It
actually tripped the safeguards on that,
and I think Opus ended up finishing it,
the analysis, and then giving me a
verdict. So, what I did is I copied that
verdict, and I gave it to Fable 5 1
million context window max, put it into
XML tags, take the output even if it's
from Opus or GPT-5.5, and then resend
that to Fable in a different window,
tell it, "What do you think of this, you
know, would you implement this in our
codebase?"
And usually that doesn't trigger the
safeguards. The most cost-efficient way
to run it is obviously inside of Claude
Code, because uh you're going to get the
subscription, so just make sure you do
Claude update, right?
Claude update
for the latest version, and then launch
Claude code, boom, and do {slash} model
to switch to Fable 5. There it is.
You can do effort uh like usual. I
recommend staying on high for most of
you,
but because otherwise you're going to
run through limit. Extra high is like
for most tasks. Max is Max is really
when you need the most, right? Uh
personally, I'm I'm running it on these
two modes, but really the jump from X
high to max is not that substantial. So,
if you want, you know,
really really good outputs, but you
don't want to be unnecessarily burning,
stay on ex- extra high. For quick
chatting with it inside of, you know,
Claude app, stay on high. So, the Claude
code is going to be the most
cost-efficient way to use it because the
Anthropic subscription is subsidized.
What that means is that you get way more
usage than you would with API credits.
So, if you pay $100 a month for the
Claude Max plan or $200 a month for the
highest Claude Max plan, you're probably
getting like $2,000
worth of API credits. So, if you go, for
example, to OpenRouter
and you want to use it here inside of
Pi, like I do, you know, here we can
launch a second agent. Inside of Claude
code, you'll probably get roughly eight
to 10 times more usage for that same
$200 than you will get inside of Hermes
agent, Pi agent, OpenClaude, anywhere
where you have to use the API pricing
because it is not subsidized. Now, on
that context, I think Anthropic said
that
subscription,
they're going to remove it from the
subscriptions, right? Here it is. On
June 23rd, we'll remove Fable 5 from
those plans. So, it will only be
available with uh credits, with API
credits. So,
that's bad news for anybody who is
running multiple Claude code
subscriptions to take advantage of these
subsidies.
And really, this is why people are
saying now is the moment when the
permanent underclass is starting to
happen. Because now, sure, you maybe
you're able to pay $100 a month for a
Claude subscription, and you can, you
know, chat with Fable here.
No problems.
Maybe you're even paying $200 a month.
But the moment you have to switch to API
credits and you have to pay the full
price for every single prompt, your
costs are going to skyrocket and I know
that because I'm speaking from
experience. I can show you my OpenRouter
spendings here. So, this is just the
past 1 week. You can see 1K spent. We go
just past 1 month.
Uh I'm at 6K spent, right? And
this is before Fable was even released.
So, imagine how this will change now
when I'm switching most of my agents to
Fable. I'm still using Opus 4.8 fast, by
the way, because this model is the same
cost as Fable and it's way, way, way
faster. So, for the agents where I need
speed and I need a highly competent
model, I'm still going to be using this.
For example, my calorie tracking agent
in Open Claw. But for any agent where I
need the best model, I'm going to be
switching to Fable, right? So,
I'm if I'm currently spending roughly
5K, 6K a month on OpenRouter alone, this
is not even factoring my Claude
subscription, right? Like, Claude Claude
subscription is not factored in here.
Cursor subscription is not factored in
here. This is just OpenRouter. So, my
current AI spend is probably
8 to 10K a month.
Imagine how that's going to change once
I switch everything to Fable. Now,
another thing that
Fable really excels at is 3D models and
creating 3D graphics. So, if you're
working with Blender, Maya, or any other
3D modeling software, this is by far the
best model in the world at this. Yeah,
this prompt it was asked to create a 3D
robot and it did that one shot, no
problem. That's going to going to be a
theme, right? Like, a lot of the apps
you have, it can just one shot without
issues. In fact, Riley Brown had a good
tweet on this, where basically Fable can
uh
copy any software, right?
Any software you want,
you give it, you describe it, it can
just copy it. Now, if you think about
the implications of that, but in this
example, it just copied the Lovable,
which actually
lets you build apps, right? So, it's not
just a web app front end. This is a
builder. It built a full app builder
where you can create any app. And it did
that in two prompts. Not 20 prompts, not
multiple weeks of development, in two
prompts, okay? So, the implications are
any software can be cloned with a couple
of prompts. And that means it has never
been more valuable
to open source the software cuz a lot of
people are not going to be building with
your software at all if it's not open
source.
And also the implications are you need
to know how to use it. And you need to
give it these ambitious prompts. Give it
tasks that you previously wouldn't even
consider giving to AI
just because this model is completely
different. You cannot treat it like the
previous models.
You need to give it more ambitious
things, less constraints, less
restrictions, and give it harder, bigger
goals, and explain why you're building
it, and let it figure out the best
solution for you instead of limiting it
too much with too many details and
specifications where in fact the model
is probably smarter than you. I would
say this is probably the first model
that I feel like it's close to my
intelligence. Like most of the models
when you talk to them you can feel like,
you know, they're yes-men, they're kind
of agreeable. With Fable you don't have
that feeling. Like it will push back
when you have a bad idea. It will call
out patterns in your messages that you
don't see. Sometimes they're wrong. It's
still not like super intelligent,
definitely not.
But there is a strong argument that this
model is AGI. But also I've used it for
analyzing startup ideas, right? So, I'm
getting the appetite to build something
again, to launch another AI startup. If
you have anything you want me to build
actually, feel free to comment below.
Tell me what problems you have with the
software you're using, you know, what
type of apps you wish existed, what
issues you're facing with the agencies
you're using, and maybe I'll pick your
idea and build it. So, if you have a
clear startup idea you want me to build,
make sure to comment below. But anyways,
I have more than enough of my ideas, and
I used Fable to analyze them, uh picked
the best ones, disqualified the worst
ones, to analyze it through the optics
of people that I respect, right? Like
people I had on my podcast, uh people on
other podcasts like successfully I found
this and review those ideas as if those
people were looking at them directly.
It's going to be way better at that than
Opus Sonnet GPT. It's a lot less
agreeable and it's a lot more objective.
So here I asked it what to review my
ideas that I'm doing which you know has
a lot of things in there.
Maybe like 50 plus ideas and I asked it
which of these are small enough to build
a quick MVP during a YouTube video and
to give me top five candidates. So here
they are. So let's see what we could
actually build here. And again I'm
inside of the cursor agents view in case
you're not familiar with this app. It
looks highly similar to the Codex app.
So there's definitely some copying going
on, but I think that's
between everybody on the cutting edge of
AI. So let's see. Auto repost to
YouTube, poll channel download post a
caption. New API glue demo mobile in one
sitting. Okay, this is interesting.
For project token spend tracker. Yeah, a
lot of people are just vibe coding and
they have no idea how much they're
spending on that project. So let's go
with this one. Let's go with this one.
I'm going to create a new folder for
this. So we have this idea, right? I'm
going to say idea boom idea.
I want to build the following idea. So
first of all create a readme file and
write a clear description of that. Keep
it super concise. Do not add anything I
didn't tell you.
Boom, let me start that off.
Actually, this is a prompting tip. Do
not write super long prompts because you
can just send a prompt halfway through
and already have the agent working on it
while you're sending the second half,
right?
Now I want you to interview me until you
understand 95% about what this idea
should look like.
I can pre-send this. There it is. And
actually I can use my auto get in here.
So here in the left sidebar inside of
the cursor agents view, I can just go to
a different thread here. And here's the
description of what Auto Git is. So I
can just copy that. Boom.
And I can launch a new thread in this
new project. Say, "Set up AutoGit for
this
uh project."
Boom. And I just paste in this.
Honestly, this
I just overcomplicated that. The setup
is way simpler. It's literally this. npm
install AutoGit, AutoGit setup, and then
for the repo, just do AutoGit on. So,
that's what I should have done.
Um
You can actually use the integrated
terminal here.
AutoGit on.
Okay, that It's There's no Git It's a
public repository, so I can actually
turn it off here.
Let me instead say that, first off,
create a Gitignore and start a Git repo
in here.
So, we're going to do that in this
thread. In the second one, it's
interviewing me. Whose YouTube channel
are we polling? For the MVP, let's do my
channel only. And I'm going to give it
the link to my YouTube channel here.
Boom.
But, make it clear in the readme file
that we want to extend it for any
YouTube channel in the future. All
right, I answered that. Let me see if
the Git repo has established. It is
established. So, now if we do AutoGit
on, it should work. AutoGit auto push
on, every agent turn in this repo will
push to Git. Amazing. So, now I never
have to worry about Git staging, Git
commits, or pushing ever again.
And one Let me make this clear, this is
not ready for large apps with hundreds
or thousands of paying users in
production. This is for internal
software. This is for, you know, hobbies
projects, your side projects that you
want to build quickly, and you don't
want to be constantly pushing to get up,
or even telling the agents to push to
get up, because all of that slows you
down, right? So, um if you are an
agentic engineer, and you want to move
as fast as possible, definitely check
out AutoGit. It's fully open source.
It's completely free, available on
GitHub. I'm going to link it below the
video.
All right, so let's see. Uh here, Cursor
is interviewing me with these questions.
What gets reposted? Twitter caps video
length.
Uh that's not true at all.
That is not true at all, actually. I
don't know where you got information.
Boom, we can start that. Also, here I'm
going to say, create an agents.md file
in this project, which is going to
explain how AI agents should behave in
this project. The first sentence you
should add is to make all your responses
very concise and clear. That's a
classic, always create an agents.md file
in every single project. Now, while
we're going here, like you can literally
switch to somewhere else,
and we can, you know, do something. So,
I can say,
"What would be the next extensions for
this? Analyze our codebase, see what's
currently implemented, and tell me what
is the next sensible move. How could we
make this even better, even more useful,
even more intuitive? Be very concise."
And this is literally the future. You're
running multiple agents, switching
between projects, speaking uh at the
fastest speed you can, tr- like turning
your thoughts into reality.
This is a taste of what the future look
like. The time it takes for your idea to
become reality has never been lower. Um
it's all about a setup and you knowing
how to use these AI models, right? So,
if you can set this up, if you can set
up Cursor with, you know, multiple
projects, with Auto Git, and you just
have the setup where you can use Fable
as efficiently as possible without
running into token limits, and without
triggering the safeguards, and that's
the setup side. And then, if you can
actually use it efficiently and clearly
verbalize your thoughts and describe
what you're trying to achieve, how you
want it to look like, how it should be
used, you can build anything. Like, the
people with the best ideas and the best
work ethic are going to crush everybody
else.
I don't care if you have 15 years of
developer experience, you're going to
get destroyed by somebody who's an
entrepreneur who can solve any problems,
because you really need that
problem-solving mindset. With Fable,
there is no problem you cannot solve.
Also, when it comes to simulations of
stuff like 3D fluid dynamics, Fable is
significantly better than other ones.
So, these are other cutting-edge models.
Like, this is not small models. We have
Opus 4.8, Gemini 3.1, GPT 5.5.
None of them is as realistic as Fable or
detail-oriented as Fable.
They're not bad. These are still really
good models, but if you can look at the
wheels, right? The black hole.
Like, you can see this as qualitative
improvement. This is not a small
incremental tweak. This is significantly
better at understanding the world. It
has better understanding of the entire
world. One thing it is limited on is AI
or machine learning research on purpose,
but other than that, it's basically
better all across the board. All right,
back to Cursor. Let's see what's
happening here. Understood, I have
enough
What actually is Okay, so I'm going to
say, "Make your answer simpler and
shorter." Let's see what's here. All
right, so basically, I think I have a
good clarity about this.
Um
let's see.
That's not true, either. Oh, maybe the
API. Okay. Maybe the API That's true.
Uh uh uh
So, long videos will be down at 720p.
Yes.
Okay, we should implement a simple
mechanic that if the video is over 512
MB, we should use FFmpeg to re-render it
to compress it to 720p. And if that's
still an issue, we should use a lower
bit rate until it is below 512 MB.
So, just make that clear in a very
concise way. So, um our program has
these fallbacks.
Okay, I think we should have enough
clarity to start building this. So, how
do we make this happen? What do you need
from me?
Can we start running this locally? Can
we test this locally before deploying
this on a VPS? Or what are the next
steps?
Do you need me to set up the X API?
Work Work with me. You are my partner in
this. Help me complete the MVP as
quickly and efficiently as possible. And
by the way, we should have the
auto get here set up. So, let me Let me
see if that's true. Okay, I think I
activated auto get here. Let me know if
it's working or not. Check the get
commit history. Yes, it added this auto
get undo, and it got automatically
committed to the go auto get repo. So,
that's kind of meta, you know, this
There's auto get running on the auto get
repository, so
it's a self-developing, I guess. I mean,
not really self-developing, but
self-pushing, you know, it's like a meta
concept here. And then, the second thing
is readable commit messages. Now, the
commit message is the prompt you give to
your agent. That's much better. Okay, so
investigate how we installed it
or how we set it up here on my MacBook
for this project and then update it to
the latest version. We're not pushing
because the GitHub is not configured.
So, maybe we can configure it out right
now. Check if the
GitHub CLI is configured on my MacBook
and if so, create a new GitHub repo with
it and uh
yeah, push everything to GitHub. Okay,
we can delegate this task to it.
Mhm, mhm,
All right, let's do that.
Open this up.
Sign up for your X account, add 10 hours
of credits, create project plus app.
All right, so it's going to help me
through the setup. Oh, by the way, I did
more deep research on the best power
user tips for Fable. So, what I'm going
to do is I'm going to do web or a text.
Just paste all of this in here.
Boom, I also have one from Perplexity AI
computer. Let me reload that. Lagged.
ChatGPT 5.5 Pro extended. Let me paste
that in.
And we're going to do this one as well.
And basically,
I'm going to have Fable summarize the
results of these three deep researches
to see what are the shared tips that
power users have. Let's see what's
happening here with the Twitter reposter
one. Scroll down. All right, so the
GitHub CLI was configured and it did
push it. Let me click on that.
Hopefully, it made it private. It did
make it private, okay. See, like these
agents, they can do so much. Like, I
don't even have to go to GitHub, create
a repo, just use the GitHub CLI to do
that. I have auto get which
automatically pushes. Auto get has now
has a remote to push. So, all all is
good. Boom, paste that screenshot. Here
is what I see now. Tell me where to go
next. Be very concise.
Okay, what's Let's look at the top power
user tips, okay?
Consensus across all three reports. When
to use it? Only for hard long horizon
work. I completely disagree.
I completely disagree. You should use it
always if you can afford to. If you
can't afford to, then you know, that
makes sense. But you should use it as
much as you can afford. Like
don't use it only for big tasks, you
know? Use it anywhere where that
intelligence could be squeezed, which I
think is most tasks. Anyways, how to
prompt it? Commissions, don't
micromanage. Okay, that's what I said.
Give it a goal, some constraints,
success criteria, and let it run. Stop
trying to
think you know the implementation
better. These models are way too
competent. They are very very competent.
They probably know better than you.
They're probably better code base
architect than you. They're probably
better software engineer than you. Just
describe what type of app or program you
want, how the software should work,
how it's going to be used, and let it
figure out the details. Delete all the
verbose scaffolding prompts. They now
degrade output. Yeah, so all of your
prompts that were like for less powerful
models,
they're just wasting tokens for Fable.
You should be more vague while being
very clear about what it should look
like. Be more vague about the
implementation. Add a scope guard.
Simplest solution that works, no extra
refactoring. It's very important. Agent
loop. Run it in a harness. Yes,
completely agree. Uh Claude code or
Cursor, as I mentioned in this video,
are the two best harnesses right now to
run it. Not raw chat. Don't use it in
Claude.ai. Guardrails and API plumbing.
Refusals, HTTP 200, stop reason refusal.
Handle explicitly. So, when you're
building apps, like if you have an AI
agent inside of your software, you need
to handle this properly.
Because
you know, for example, right now using
it inside of Pi,
it doesn't really handle it properly.
That's why it's better to use it in
Claude code or Cursor. Oh, yeah, and
this is important. Anthropic added a
mandatory 30-day data retention. So, and
a lot of enterprise clients are not
going to use Fable because of this.
I think a lot of their employees are
going to use it secretly.
But, what that means is basically
Anthropic has to
or has the option to look at your data
for 30 days, no matter if you use it in
the API, no matter if you use it inside
of Claude.ai. In the past, if you used
it through the API, they didn't retain
any data. But, now with Fable aka
Mayforce, they do look at everyone's
data, and a lot of companies will not
use it because of that. So, we'll see if
they change that or not. All right,
let's look at what's happening here.
It's guiding me more how to set it up.
So, let's do that. Gear icon, user
authentication, read and write. Okay, so
I'm getting this error from the
developer API. I don't know if it's down
or not.
I'm getting this error when trying to
access anything in the X developer um
dashboard. Let me check if we have
agents.md. We do.
And uh
that's not how it should be rewritten.
Update agents.md
by removing any and all information
about this project architecture.
That should be inside of readme.md.
Instead,
agents.md should be very focused on the
response style of the agents, such as
make your answers clear and very
concise. It's I'm getting this here as
well.
That's crazy. Check the built-in browser
here inside of cursor. I'm still getting
the same error. All right, while that's
running, let me show you a bit more
insane stuff that people have built with
Fable.
Here's a mechanical engineer task. It
can generate intricate working
assemblies and mechanism in a single
prompt. Let's look at it.
Pick up the cube.
Damn.
Guys, I I don't even know. Like, these
models they they basically do anything.
Like really, giving it the right
harness, the right environment,
and an ambitious enough of a task,
and it can just do it. Another thing
that Fable just one-shotted in a single
prompt is this city's traffic simulator
with all these boxes, all these
3D properties,
physics,
one-shotted day-night cycle. If you're
not building stuff with AI, I don't know
what to tell you. Like, I don't really
care what you're building. You need to
be building something.
Internal software, an AI startup, some
open-source repositories, just build
something.
Improve your skills, get familiar
with these tools. Get your hands dirty
with these tools. This is the future.
The people who know how to control them
and how to get the most out of these
tools,
they're going to have such an immense
advantage. There's no even
There's no way for me to put it into
words even.
How big of advantage we'd have. Like,
imagine you competing against somebody
who cannot use electricity, cannot use
internet, cannot use computers.
Like, you would destroy that person in
business, in communications, in life,
in fitness, in health. You would just
completely destroy that person in
anything, especially in business, okay?
Like, imagine competing to somebody
who doesn't have a computer, doesn't
have a smartphone, doesn't have the
internet,
doesn't have spreadsheets, calculators,
or electricity.
You could crush that person so easily.
That's going to be 100 times less of a
difference than somebody with access to
the latest greatest models, who actually
have the has the budget to use them, and
who has the competence and skill to get
the most out of them. Okay, so this is
kind of insane.
While I was demoing the other things,
Fable managed to fix the bug where this
was not loading, you know, I was getting
this error as I showed you.
It managed to figure out it the issue is
only with the deep links, and that
basically it works, you know, some of
these
link redirects are broken, and And
started setting this up by itself. I had
to stop it because I got scared a bit
because it was making too much progress
and this is my main Twitter account, so
I don't want it to do anything
anything crazy.
But it managed to figure out the bug
that I couldn't do myself in two
different browsers because the deep
links were broken. It figured that out
and now it started setting this up.
Man, this is
this is a bit scary in a good way
though. Like it's a bit too good. All
right, so at the same time I asked it to
do a deep research
on idea number four here
and to give us a step-by-step plan. You
know, basically analyzing comments and
creating a pain map, all of that. So
again, I'm going to give it my channel
and say
let's start just for my channel
and
I need you to go into /documents/code
on my MacBook. Create a new folder there
and just fully build the MVP end-to-end
completely and fully.
All four phases.
You know, what is this? One to two
weeks?
No, one to two weeks. We're doing it
right now. These models, they never
learn, you know, they always think this
is like weeks or months.
Week three to six?
No, we're building this right now,
Fable.
Um I don't think Fable It's kind of
crazy how like Fable legit doesn't
understand how powerful it is.
Um it's kind of funny. Okay.
Nothing saved yet. Both steps knees are
okay.
Fill the form permissions.
Yes. Okay, this is another great example
of what Fable can do.
Here we have a 3D uh shooter game.
You know, if you played
Krunker Oh, wait, wait, the bunny hop
works as well.
Oh, need to reload.
These mechanics, okay. The bunny hop is
not as good.
You know, I'm kind of try-harding now,
but this is built I think one shot. I
would need a green crosshair. Anyways,
um
this game is pretty cool.
And yeah, this is just a small taste of
Like imagine everything that Fable can
one shot, it can uh what can it two
shot, you know? What can it three shot?
Imagine doing
10 prompts. Imagine actually putting
some thought and effort and energy into
it. Like you you could build a full
business faster than ever before. Like
really, if you
if you don't think so, you're just full
of limiting beliefs. So,
whether it's building mobile apps, video
games,
B2B SaaS, internal software, open-source
packages. I mean, just do do something,
guys. Like that's the main message. Do
something. Stop making excuses. Fable is
insane. I'm literally building two
different MVPs right now.
Um
And yeah, like
all of the ideas I had on the list are
just like one prompt away. So, now
whether it's, you know, okay, you
shouldn't have multiple main businesses,
right? So, just pick one bet and put 80%
of your time towards it. But the next
20% you should build some like tools for
yourself, automations, um
things to speed up your workflows,
whatever it is.
Whatever it is, just start building it.
It's literally one prompt away. When you
have a setup like this inside of the
cursor agent view, you could just start
a new thread
and launch it. So, like build this
end-to-end or do extensive research how
we could build this and ask me the five
most important questions about the
biggest technical and software design
decisions.
Something like that. Boom, it does the
research, comes back 15 minutes later,
asks you a question, you answer them how
it should be used, you know, how you
imagine it, stuff like that. And then it
just builds it, one or two prompts, and
it's done.
And like internal software has never
been easier. External projects at
businesses have been really easier. Man,
it's going to be crazy. The next one or
two months we're going to see incredible
renaissance of business, of products, of
software. Things that were never
possible are now possible.