Arvid Kahl talks about starting and bootstrapping businesses, how to build an audience, and how to build in public.
Unknown: Hello, everyone and
welcome to the bootstrapped
founder. My name is Arvid Kahl,
and I talk about bootstrapping,
entrepreneurship and building in
public. Today I will share with
you how I write with a writing
buddy that never sleeps. It
really leveled up my writing,
and I think it will be
incredibly useful for your work,
too. Before we get started, let
me quickly thank the sponsor of
today's episode, a question. Do
you have enough operating cash
in your business to make it
through to the next month? Are
you sure about that? Well enter
Pinto financial, they streamline
your bookkeeping, the
forecasting and cash flow, but
they don't stop there. Pinto
takes it to the next level by
providing custom video based
monthly reports for you so that
you always know where you stand.
Think of them as your financial
lifeline, your CFO guiding you
through the choppy waters of
business financial management.
So if you're ready to navigate
these waters with confidence,
visit www that use
pinto.com/learn. To learn more
about how Pinto financial can
help you build profitably, don't
let your cash flow drift away.
Choose Pinto financial well, and
let's make waves together. All
right, let's get to our main
topic today.
Are you getting tired of jet
TPTs endless regurgitation of
SEO optimized articles and
social media posts, I am well on
even Chechi Beatty is getting
tired of that. At this point.
Too many people use to train the
AI as a text generator. And too
few people use it as a highly
capable writing partner that
never sleeps. When I first ran
into Chet GPT, it was amazing.
But I swore that I would never
use its output verbatim between
it being easily detected and
occasionally completely
fabricated. It just doesn't get
my style and tone just right.
But it can certainly help me
write better, the trick will
treat it like an editor, a
proofreader and disgruntled
reader at the same time, I make
it an enemy of my text and let
it attack it as vigorously as
possible. And then I incorporate
that feedback into my next draft
that I write. So here's how I
use conversational AI to
strengthen my argument by making
chat up at argue against my
writing. The most impactful way
of using chat up at mid process
as a writer has been using it as
a skeptic. After I've written my
first draft of anything I write,
I paste the whole thing into a
Genchi party session. And then I
prompt the AI to act like
someone who disagrees vehemently
with anything that I'm writing
about, and making the AI into my
personal devil's advocate. One
of the benefits of chat GPT is
that it's trained on millions of
think pieces and opinions. And
that includes the polar
opposites of my personal
thoughts and my feelings as
well. So instead of having to
step outside of my own
perspective all the time, I can
use chance up to to play that
part. Most of the time, I asked
the AI to list the top three
arguments that someone opposed
to my kind of thinking would
disagree with, and then why they
would disagree with that. The
response to this single prompt
alone often gives me food for
thought that can lead to
complete rewrite of the article
because they see something that
I completely forgot when I first
drafted it. Usually, I'm so
trapped in my own ocean of bias.
And just the mention of a color
argument allows me to burst that
bubble. What would an opponent
of my school of thought claim?
How would they attack even a
well reasoned article? That's
what jet UBT can do? So I then
asked to give a few examples of
answers to those points of
criticism. They're usually not
very good. They're very generic
and unspecific, but they do
point me in a direction that I
can explore with my own
arguments. I run this prompt for
every long form article that I
write sometimes even tweets, if
the points of contention are
strong enough, I immediately
tried to defuse them right there
and then by expanding my article
to address these concerns, and
this usually doesn't take more
than 10 minutes for an article,
but it's time incredibly well
spent, because it makes it much
more defensible, and just more
approachable. GPT is good at a
few more things that I
occasionally ask it to do with
my writing not just being a
devil's advocate. Sometimes I
write something that feels
unfinished. The thoughts are
there, but they're not really
clear. I've asked jet UBT about
what is missing from this to
make it more cohesive of an
argument, which tends to
highlight the missing pieces of
the puzzle and I can go in and
fix them. The AI is also
surprised
reasonably good at detecting the
emotional subtext of any given
passage, I often ask it, which
emotional arcs exist in the
article. And where do they
clash, which regularly
highlights a way to abrupt
change of tone that I can then
smooth out in the article as I
write the next draft. And none
of these questions as of the
text are in any way novel or
magical, but the speed at which
set up can allow you to reflect
on them. That's the awesome part
of this experience. The other
area that Chad should be at can
help with is the quality and
accuracy of examples in my
writing, I highlight real world
businesses, examples and founder
journeys a lot, but I write from
within my own echo chamber. And
that makes a whole lot of sense
to me, but it doesn't
necessarily connect with all my
readers who come from outside of
that echo chamber. So for this,
I have found it helpful to ask
Chet GPT to find unexplained any
confusing examples for an
audience of x if it finds such
examples. Then I asked him to
come up with better examples,
which tends to surface names and
ideas that I may have missed in
my own research and exploration.
It broadens both my own mind and
the compatibility surface of the
text. But there's one big
problem here. Church CPT is
tendency to make things up. Any
claim related to the real world
should be thoroughly fact
checked outside of church CPT,
even frameworks and concepts
that it suggests need to be
researched. They might not exist
outside of the church UBT
session, I was asked to find
studies on mental health topics
and the AI gave me 10 scientific
paper titles, of which only
three actually existed. And that
brings me to another editorial
job that GPT can be used for
fact checking. Wait, what did I
just say that Judge up
hallucinates things all the
time? Well, yes, which is why
that I never trust the examples
it gives. But that doesn't mean
that I can treat Changi PT as a
writing truther. In a way, I
asked the AI to be extremely
skeptical, and surface the five
parts of the article that really
need to be fact checked, I make
chat up to look for anything
that sounds particularly
unbelievable and search for
misleading phrases. And since
Chechi beauty is pretty much a
gaslighting engine at scale.
After all, its primary purpose
is to come up with believable
and convincing text. I have
found that it's pretty good at
finding this kind of tension in
my written content to it knows
what it's doing, and it knows
how to find it in your work too.
I often ask the AI to point out
any logical fallacies and my
text, it has so far found a lot
of confirmation bias. If you
have No True Scotsman arguments,
and a surprisingly high amount
of loaded questions, it's really
useful to have a logical
reasoning system. Take a look at
my drafts. And I want my
articles to be inclusive and
appeal not to just a tiny niche
audience, but a lot of people
and for that one final thing
that I use mid writing is the
perspective shift. I asked GPT
two questions. From a beginner's
perspective, what is confusing
and what is complicated, and
from an expert's perspective,
what is over simplified or
misleading. The resulting list
of paragraphs and sections gives
me ample opportunity to make the
article more comprehensible to
either audience if I want. If
it's meant to be for a specific
audience, I can skip this step.
But any topic that touches the
lives of all kinds of peoples
and all sorts of journeys, like
whenever I write about mental
health, I want to leave no
reader behind. Well, there you
have it, adversarial writing
with generative AI. That's my
way of rounding out an article.
When you use chat up t as your
part time writing nemesis,
you'll end up with a piece of
writing that is both completely
written in your own voice
because you write it but it's
also more accessible for readers
inside and outside of your
existing readership. Because the
AI gave you an opportunity to
look at it from somebody else's
view. And that's it for today.
Thank you for listening to the
Bucha founder. You can find me
on Twitter at Arvid Kahl
arvidkahl. You'll find my books
and my Twitter course there as
well. If you want to support me
and to show please subscribe to
my YouTube channel, get the
podcast in your podcast player
of choice and leave a rating and
review by going to rate this
podcast.com/founder. Any of this
will truly help the show. So
thank you so much for listening,
and have a wonderful day. Bye
bye