Got a really fun Fable usage

optimization hack. Takes like 30 seconds

and it saves approximately 30% of all

Fable usage with next to no downsides.

Check this out. So, I'm going to include

this down below. You guys can download

this and use this in one click. But, to

make a long story short, this allows you

to cut Claude code's input tokens by

rendering bulky context as images. You

get the exact same system prompt, tool

docs, and history. It's just you get it

in a fraction of the tokens. And it's

because of the way that Claude currently

does image-based billing versus

token-based billing. You know, an

image's token cost is fixed by its pixel

dimensions, not how much text is inside

of it. Which means if you're sneaky, you

can make the text in the image super,

super small. Obviously, it still needs

to be legible, but super, super small.

And then you can have Claude render

that, bill you a significantly reduced

amount, but get all of the context that

you otherwise would have for, as

mentioned, 30% off. And so, you know, am

I going to use this on every single

query that I'm running? Probably not.

But, if I have really massive queries

that are hundreds of thousands of tokens

and I'm expecting these to run for a

long time, to to be recycled constantly

and used pretty constantly for a

business function, this is a quick and

easy way you can immediately save 30%.

Okay, so I just have Claude Fable 5 open

in a terminal here called Ghost TTY.

This is the exact same thing that you

guys can get in Claude Desktop or if

you're using Anti-Gravity or whatever. I

was just experimenting with Ghost TTY

because I like the way that it looks.

And as you guys see here, I ran a test

across the text version of this prompt

and then the image version of this

prompt. And the text version of this

prompt cost $1.03,

whereas the images version of the prompt

cost $0.69.

Mathematically, that's a little over a

30% reduction in token usage. The

important part here was we used, instead

of 59,822

cash rate tokens, only 38,142.

And there was zero difference in the

model's ability to recall various

components of the text, which I know

sounds crazy considering this is now a

super crazy small compressed image, but

the OCR, the optical character

recognition, and like Fable's ability to

understand text even if it's really

tiny, um is essentially probably the

best in the world right now. And as long

as it converts that into tokens, it's

the same thing. Okay, so how do you

actually implement something like this

for yourself? Really easy. I'm just

going to clear this demo, and I'm going

to speak into my Claude code terminal.

Uh I'm using a free open-source

voice-to-text system called Hex. It runs

on Parakeet. It's all entirely local to

my computer. So, what I'm going to do is

I'm going to tap the voice transcript

button, and I'm just going to ask it

what I want in a really simple way. Hey,

there's a new token reduction strategy

available. I've detailed it in the below

GitHub repo. What I want you to do is I

want you to build a simple system that

every time I feed in a prompt, converts

it to an image first, presumably using a

cheaper model, and then takes that and

then feeds that into Fable. Uh we're

going to be building it in Fable right

now. That's just to build the

architecture. After this, I want to be

able to pass off extremely long prompts

to Fable in order to arbitrage on

tokens. Okay, so I'm going to then feed

in this actual repo. Let's just go back

here, pxpipe, and then I'm going to

paste this in.

And the whole idea is,

you know, obviously I'm going to have

Fable itself do this, and it's going to

be doing this with pretty high effort

cuz I wanted to build a really efficient

system. Um but afterwards, you know, I

want to be able to take in whatever

super long prompt I have, and then just

one-shot convert this to an image using

a skill. So, you know, you can imagine a

future instance where I'm building some

business infrastructure. That business

infrastructure relies on some sort of

crazy long prompt that, I don't know,

details every possible conversation

route or whatever the heck it is that

you're doing. Um I I I just want to be

able to one-shot that massive prompt

into an image using this skill. So, it's

going through the repo right now. It's

summarizing it. We'll loop back, and uh

I'll show you the results in a sec. Now,

rather than feeding in prompts directly,

what we're going to do is we're going to

basically have Fable build a brief

little pipeline, some sort of script,

and then I'm just going to store the

prompts that I wanted to run in a file.

It'll then run the script on the file,

generate an image, and in that way this

pipeline will significantly reduce total

token consumption. As you can see here,

the logic is pretty straightforward. A

1928 by 1928 image costs approximately

this many vision tokens and holds that

many characters. Whereas a real Claude

code traffic averages that many

characters a token. That's how you make

image and profitable. We're basically

just arbitraging the cost of an image

right now versus the cost of tokens. And

as mentioned, they're probably going to

patch this pretty quick. So if you guys

have any business infra that you want to

save, presumably a few hundred dollars

on, Lord knows I'm feeding in every

single one of my prompts like this for

foreseeable future,

then make sure to do this now. All

right, and now we have the script

pxpipe.py.

So I'm going to just come up with a

really long prompt, and then I'm going

to show you guys how to use it in

practice. Okay, so I just created a

super mega long prompt. As you guys can

see here, it's massive. I've stored

every single video that I've basically

ever uploaded into a giant text file

along with some of their performances.

And now I'm just going to ask it a bunch

of questions about this and just use

this knowledge essentially to

significantly improve the probability

of, you know, I don't know, minimizing

churn reduction strat, something like

that. At the same time, I've also

created images. These images are very

similar to that prompt. It's just

instead of being arrayed in text, it is

arrayed in an image. So I mean, like you

can zoom way in here. You can see it's

kind of like compressed and stuff like

that. The idea is it's still legible,

which is the important point. Um I could

probably optimize this far more by like

justifying the text and stuff like that.

But just as a demo, I'm going to run it.

And now we're just going to run a quick

test. And the test is going to ask a

bunch of questions about content inside

of this. Like, "Hey, you know, um what

are the strategies that work really

well? What did you find like member 4289

do that other members didn't?" Whatever.

And then we're just going to test the

two and then see how much better this is

as a token optimization technique. Okay,

what it's doing now is it's actually

running the head-to-head test, and it's

doing so by passing this through Fable 5

using API pricing, which we might all

have to be using in 24 hours anyway.

Now, because this was a knowledge-based

task where literally like isolated

extracting components from this text,

combining them, and and so on and so

forth, more than just re-reasoning over

and over and over again on this, there's

a massive delta. There's a 68.7%

reduction in input tokens. With all that

in mind, the cost didn't decrease by 25

to 30% like I showed you before in the

example. It's actually 59%,

which means if you have these sort of

needle in a haystack type queries,

obviously you have significantly higher

quality, or rather larger alpha in using

a strategy like this. Anyway, to make

your life super easy, I've included this

down below. Do whatever the heck you

want with it. Anyway, this announcement

doesn't really need to be more in-depth

than that. Hopefully you guys

appreciated the video. Have a lovely

rest of the day, and if you guys want to

get that, again, just check down below

in the description. Check out Maker

School, my 90-day accountability

program. We'll guarantee your first

customer selling systems like this.

Catch you all tomorrow.