November 13, 2025 • 16 mins
AI isn’t coming for your solopreneur job, but it will happily take your tasks. In this episode, Carly and Joe break down how to turn AI into the world’s most over-eager intern: fast, enthusiastic, occasionally clueless, and totally coachable. From using AI without losing your voice…to avoiding “hallucination traps”… to building a GPT that actually remembers what you told it, this episode shows solopreneurs exactly how to manage AI, not get managed by it.
FAQs From The Episode:
How do I actually ‘train’ AI for my business?”
Treat it like onboarding a new team member. Upload or paste your brand guidelines, audience description, business plan, examples of your writing, and list of do’s/don’ts into a custom GPT. Then, add instructions that reinforce your tone, values, target audience, and preferred outputs. Revisit the training regularly, because AI can “forget” if everything stays in one long chat thread.
What tasks should I delegate to AI, and which ones should stay 100% mine?
Delegate:
- Drafting (blogs, emails, social posts)
- Research summaries
- Brainstorming ideas
- Rewriting in different tones
- Organizing messy text
Never delegate:
- Strategic thinking
- Topic selection
- Opinions or point of view
- Final edits
- Any part of your brand voice that requires nuance
AI can assemble the pieces, but you must decide what the puzzle looks like.
How do I keep AI from drifting, forgetting instructions, or making weird mistakes?
Use a custom GPT (not just one long chat). Put your recurring instructions directly into the system prompt so they don’t fall out of the context window. Reinforce boundaries often (“never use profanity,” “don’t use dashes,” etc.), provide examples, and correct mistakes as they happen. Think of it as ongoing performance management. The more feedback and clarity you give, the better it performs.
🌟 Featured Resource: LifeStarr Intro for Solopreneurs
Are you building a business on your own and feeling like you’re going it alone? That stops today. LifeStarr Intro is a free, forever membership built especially for solopreneurs who want real support, real resources, and real community.
When you join LifeStarr Intro, you unlock:
- A vibrant community of like-minded solopreneurs for feedback, encouragement, and connection
- The LifeStarr productivity app (coming soon), built to support your workflow using GTD principles (that’s Tasks, Projects, Inbox that works)
- Live problem-solving meetups, expert sessions and strategies...and you don’t pay a thing
Total value: $65/month. Your cost? Zero.
👉 Ready to stop struggling solo and build a business that works for you?
Join LifeStarr Intro for Free
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Carly Ries (00:00):
AI isn't here to take your job. It's here to take
your tasks, but only if you knowhow to use it right. In this
episode of The AspiringSolopreneur, Joe and I break
down how solopreneurs can treatAI like an overeager intern,
fast, enthusiastic, and a littleclueless, and turn it into a
true teammate. We cover how toonboard your AI so it
understands your business andbrand, what not to delegate,
(00:21):
hint your thinking, why NeilPatel says human ideas still
outperform AI content, and thedanger of letting your intern
bot hallucinate on your behalf.If you've ever wondered how to
use AI without losing yourpersonal touch, this one's for
you.
So tune in and learn how tomanage AI, not be managed by it.
You're listening to the AspiringSolopreneur, the podcast for
(00:44):
anyone on the solo businessjourney, whether you're just
toying with the idea, takingyour first bold step, or have
been running your own show foryears and want to keep growing,
refining, and thriving. I'mCarly Ries, and along with my
cohost, Joe Rando, we're yourguides through the crazy but
awesome world of being a companyof one. As part of LifeStarr, a
(01:05):
digital hub dedicated to allthings solopreneurship, we help
people design businesses thatalign with their life's
ambitions so they can work tolive, not live to work. If
you're looking for a get richquick scheme, this is not the
place for you.
But if you want real worldinsights from industry experts,
lessons from the successes andstumbles of fellow solopreneurs,
and practical strategies forbuilding and sustaining a
(01:26):
business you love, you're in theright spot. Because flying solo
in business doesn't mean you'realone. No matter where you are
in your journey, we've got yourback. Joe, in our last episode
(02:19):
we talked about our experienceat Inbound, and obviously a big
topic for this year was AI, asis the topic for most things
this year, not just at thatconference. But I think the
biggest fear that people have isthat AI is here to take their
jobs.
And I would say, it's not hereto take your jobs, it's here to
take your tasks. And the onlyreason you would lose your job,
(02:43):
I think, is if you would lose itout to somebody that is using AI
for their tasks that has thesame position as you, and you
are not. Would you agree withthat?
Joe Rando (02:51):
Well, I think I mean, if we're talking about
solopreneurs, yes. If we'retalking about in general, I
mean, the news out today, we'reon the 10/29/2025, and major
companies are laying off tens ofthousands of white collar
employees because they'rebasically being pressured by
(03:13):
investors, and the c suite'sjust saying, we're gonna replace
these people with AI. I don'tpredict that's gonna go well. I
suspect that they're gonna be alittle surprised as to how that
doesn't live up to theirexpectations. Eventually, it
will because AI is gettingbetter all the time.
(03:34):
But yes, I think as asolopreneur where you're in
charge of your own destiny, youdon't have to lose your job
because AI starts doingsomething that you do. So I'll
go there.
Carly Ries (03:46):
And for solopreneur's sake, we think you
should be looking at AI as yourteammate. I think of AI as kind
of like an over enthusiasticintern. Like they're fast,
they're eager, but they arewrong, sometimes clueless. AI is
not perfect. And so I see it asa, like how good I can do, look
(04:07):
how good I can do, but thattraining still needs to be
there.
So I wanna talk about AI as yourteammate, especially as a
solopreneur, and how you cankind of coach that teammate
today, and to help youunderstand how to manage AI, not
be managed by AI. Does thatsound like a good direction?
Joe Rando (04:25):
It does. I wanna start with just kind of some
framing, which is, and I'mguilty of this as much as
anybody, is that we like tothink that AI thinks, but it's
not thinking. It really isn't.It just feels that way. It
predicts. It's a somebodydescribed it as a plausibility
(04:46):
engine, which I thought was abrilliant way to describe it.
It's predicting what the nextword should be based on the
inputs, and, it's surprisinglygood given that that's what it's
doing. You kind of think aboutit.
It's doing that, and you go,wow. It's pretty darn good. But
it is by no means, as you said,perfect or even close to perfect
(05:09):
and can really go off the rails.And if you wanna know, just how
weird it can get, I have a GPT Icreated called You're Wrong. And
You're Wrong basically has abunch of prompts to basically
think more, critically and to beless nice about critiquing.
(05:31):
And so I'll put something in it,and it'll kind of rip me apart.
You know? It really roasts me.And sometimes I'll take chat GPT
generated material and put itinto your wrong, which is also
chat GPT, and it will roast it.And so you just kinda look and
go, okay.
And the thing with you're wrongis it's actually better than
chat GPT at coming up with goodideas. It's much more critical
(05:54):
of its own thinking. But,anyway, the point being, you do
not want to treat this asanything other than a highly
eager, coachable, but prettypretty naive intern.
Carly Ries (06:11):
I'm so glad you said coachable because I think a
common misconception that peoplehave is that the AI knows their
business. Like if you typed yourwebsite in, that it would
automatically know the ins andouts and it just doesn't. you
really have to take time totrain AI so that it works the
best for you. So you can't justsay, let's say you're writing a
social media post for yourcompany, and it's like write a
(06:33):
social post for LifeStarr. Butit wouldn't really know what to
do.
So you have to say, write asocial post for LifeStarr that
targets solopreneurs and helpsthem with their productivity.
you need to train it. Andgranted over time it'll start
picking up on it, but if youwanna start getting it right
immediately, you need to put inthat effort just like you were
training another employee,another contractor, whatever. It
(06:57):
needs that training. Even thatonboarding.
We talk about onboarding a lot.
Joe Rando (07:02):
Yeah. There's a lot to it. But one of the problems
that I've seen, I don't know ifanybody else has experienced
this, is that I will train up aGPT, not necessarily, doing
anything, you know, under thehood, so to speak, but just
kinda go in and give a bunch ofinstructions. And over time, if
I'm using this thing for a lotof work and using the same feed,
(07:25):
it'll start to forget. And it'sgot to do with something called
the context window that can onlyhold so much information.
And so you start off with someinitial instructions. You get
deep down into it, it starts toforget the initial instructions.
So you need to if you reallywanna use it and train it up,
you've gotta go in and create aGPT and put in a bunch of
(07:45):
training materials so that itdoesn't ever lose that. Does
that make sense?
Carly Ries (07:50):
it does. And I mean, even if you have a business
plan, if you have like a brandguidelines document, those are
the kinds of things you shouldbe inputting and retraining. And
don't rely on it like you weresaying, to always remember.
Like, maybe have a Mondaymorning meeting with ChatGPT and
be like, hey, just a reminder,this is my business plan. Let's
(08:14):
focus on this for the rest ofthe week as we're putting
together the content and all ofthat.
Joe Rando (08:19):
Well, like I said, you should create a GPT for
that. So the business plan is inthere in the core training as
opposed to just trying to makeit remember in the base chat
GPT.
You don't want to do thatbecause it won't.
Carly Ries (08:34):
Yeah. But I kinda look at AI as like an executor,
a brainstormer, and aresearcher, whereas you are the
visionary, the decision maker,the editor, editor, editor. And
that's how I define the twodifferent roles. Again, kinda
with that intern mindset andframework.
(08:56):
But Joe, if people are treatingit like an employee, because, I
mean, AI really is a gamechanger for solopreneurs. It
brings up so much time. Whatwould you say you should
delegate, and what should younot delegate?
Joe Rando (09:10):
Well, at the core of it, do not delegate your
thinking. just as an example,write a blog post about the
three biggest mistakes thatsolopreneurs make without
telling it what those threemistakes are. Don't let AI think
(09:33):
through. I mean, you wanna goahead and brainstorm and say,
throw out, the biggest mistakesthat you think solopreneurs make
based on a search of the web,and then go through those and
go, oh, wow.
Yeah. I didn't think of thatone, and there's this one. And
then take that, but you need tofeed it your thinking. Right?
And you it's nice to feed ityour thinking, your writing
style, and a lot of context sothat you're getting something
(09:56):
that isn't just AI dribble. Andnobody wants to read AI drivel.
Neil Patel said that non AIgenerated content generates 4.7
times more views than AIgenerated content. And that
should tell you that, and I'mnot saying not to use AI, but if
you can use AI in a way thatit's your content, your ideas,
(10:16):
your thinking, people are gonnarespond to that better than this
kind of, kind of generic AIthinking average of the entire
inter interwebs, stuff that it'sgonna generate on its own.
Carly Ries (10:30):
Because it does hallucinate things.
Joe Rando (10:33):
Oh, that too. But even when it's not
hallucinating, on its own, it'spretty boring.
Carly Ries (10:38):
Yeah. Absolutely. But with the hallucination
thing, I think it's also reallyimportant to identify when AI is
leading you astray. When you'reworking with it as, I'm assuming
you keep saying intern forconsistency purposes.
Call it whatever you want. Butif you can identify the mistakes
it makes time and time again andtrain those mistakes out of them
(11:00):
like you would an intern,that'll also help with your
strategy, your content,everything that you're using AI
for. Joe, didn't you just do onethat replaced Emdashes?
Joe Rando (11:09):
It didn't work. I created a GPT, and the entire
prompt was never use Emdashes,period. Never use Emdash. I'd
put it in about it must havebeen 50 or 60 times. And then I
asked to write an EmilyDickinson poem, a poem in the
style of Emily Dickinson, and itused a bunch of em dashes.
It's nobody other than, yourEnglish professor uses em
(11:37):
dashes. It takes, keystrokesthat nobody does. How did it get
trained up on em dashes?
Carly Ries (11:45):
I know. it was almost like bring back the em
dash.
Joe Rando (11:50):
But nobody wants to use them now.
the woman that was editingSolopreneur Business for
Dummies, she was an Englishmajor and very, literary. And
she sent me some content. Isaid, oh, we can't use the em
dashes. It looks like AI. Shegoes, what? I always use em
(12:10):
dashes.
I heard semicolons are becomingthe same way, and I love
semicolons, been using them fordecades, and I'm gonna have to
give up semicolons.
Carly Ries (12:22):
so when I have used em dashes in my writing, I've
always had to copy and paste itfrom other copy or other content
because I couldn't figure outhow to do the em dash myself.
Which I suppose that's a quickAI search, but I just always put
them to different other content.Anyway, Joe, any parting words
of wisdom for having AI as youremploy and training it and
(12:44):
onboarding it that you thinksolopreneurs should know about?
Joe Rando (12:46):
Well, I'm gonna reiterate this idea of, there's
a difference between creating aGPT and putting training in the
GPT and just kinda going intoChatGPT and saying, do this and
do this and don't do thisbecause that context window and
I'm no expert. So you know? Butbasically, what it seems to me
is that context window thatcontains kinda what it's using
(13:09):
as a reference point, the oldstuff goes off eventually, and
it starts to drift. So, if youdo this, you're gonna wanna
build out a GPT trained to docertain things and put certain
documents in there and certaininstructions. At least that's
ChatGPT.
That's my go to. Not so sure on,things like perplexity and
(13:31):
anthropic. But, the main thingwith all of these is just check
the work. Make sure it's notcrazy. You know, it's just so
easy for these things to go offinto delusion.
And if you let that go out, it'snot gonna reflect on ChatGPT or
some other, large languagemodel. It's gonna reflect on
(13:52):
you.
Carly Ries (13:54):
And you need to train it, correct it. You know
what I've started doing, Joe?I've started and I don't know if
this does anything. I think itdoes. I started celebrating it.
So when ChatGPT does somethingreally well, I say, that's
awesome. That's exactly what Iwas looking for. And then I'll
(14:14):
iterate and be like, can youalso do something like this? And
it'll say, thank you so much.And then I find that everything
from that point on, the resultsare better because I gave it the
positive reinforcement.
I don't know. This might be inmy mind. Before an AI takes on
minds of their own, I want themto know that I was grateful.
Joe Rando (14:33):
Yeah. And it's true. And, yeah, it's good to give it
you know, there's a littlethumbs up. You can click on chat
GPT as well to let them know itdid a good job or a thumbs down.
But, but, yeah, and the otherthing I guess the one last thing
I wanna mention is that becausethey're updating the model all
the time, you know, it was four,then was four o. Now it's five,
(14:54):
and they got all the differentfive versions and, deep research
depending on which version ofChatGPT you're buying if you're
buying it. But it's weird, thebehavior changes, right, when
they make these changes to themodel. Like, I've got this
you're wrong one that I talkedabout that I use all the time,
(15:14):
and it's great. But all of asudden, it started using
profanity.
It never did before. And now allof a sudden, it's using and I
remember they made some changejust now to loosen the thing up
a little bit. And, it's not mystyle. I don't use profanity, so
I'm not really inclined to wantit to do that. So now I've got
to go in and change thetraining, say don't use
(15:35):
profanity. but just there's alot of weirdness. You always you
build these things, then youhave to keep an eye on them.
It's kind of like an internthat, develops a drinking
problem or something.
Carly Ries (15:47):
Or something. Well, listeners, hopefully you found
this episode useful. I knowthere's a lot of AI talk out
there, but not always as itrelates to solopreneurs
specifically. So hopefully youlearned something new. And as
always, leave us that five starreview.
We would so appreciate it. Sharethis episode with a friend.
Subscribe to our show on yourfavorite podcast platform,
including YouTube, and we'll seeyou next time on the Aspiring a
(16:09):
Solopreneur. You may be goingsolo in business, but that
doesn't mean you're alone. Infact, millions of people are in
your shoes, running a one personbusiness and figuring it out as
they go.
So why not connect with them andlearn from each other's
successes and failures? AtLifeStarr, we're creating a one
person business community whereyou can go to meet and get
(16:30):
advice from other solopreneurs.Be sure to join in on the
conversations atcommunity.lifestarr.com.
AI isn't here to take your job. It's here to take
your tasks, but only if you knowhow to use it right. In this
episode of The AspiringSolopreneur, Joe and I break
down how solopreneurs can treatAI like an overeager intern,
fast, enthusiastic, and a littleclueless, and turn it into a
true teammate. We cover how toonboard your AI so it
understands your business andbrand, what not to delegate,
(00:21):
hint your thinking, why NeilPatel says human ideas still
outperform AI content, and thedanger of letting your intern
bot hallucinate on your behalf.If you've ever wondered how to
use AI without losing yourpersonal touch, this one's for
you.
So tune in and learn how tomanage AI, not be managed by it.
You're listening to the AspiringSolopreneur, the podcast for
(00:44):
anyone on the solo businessjourney, whether you're just
toying with the idea, takingyour first bold step, or have
been running your own show foryears and want to keep growing,
refining, and thriving. I'mCarly Ries, and along with my
cohost, Joe Rando, we're yourguides through the crazy but
awesome world of being a companyof one. As part of LifeStarr, a
(01:05):
digital hub dedicated to allthings solopreneurship, we help
people design businesses thatalign with their life's
ambitions so they can work tolive, not live to work. If
you're looking for a get richquick scheme, this is not the
place for you.
But if you want real worldinsights from industry experts,
lessons from the successes andstumbles of fellow solopreneurs,
and practical strategies forbuilding and sustaining a
(01:26):
business you love, you're in theright spot. Because flying solo
in business doesn't mean you'realone. No matter where you are
in your journey, we've got yourback. Joe, in our last episode
(02:19):
we talked about our experienceat Inbound, and obviously a big
topic for this year was AI, asis the topic for most things
this year, not just at thatconference. But I think the
biggest fear that people have isthat AI is here to take their
jobs.
And I would say, it's not hereto take your jobs, it's here to
take your tasks. And the onlyreason you would lose your job,
(02:43):
I think, is if you would lose itout to somebody that is using AI
for their tasks that has thesame position as you, and you
are not. Would you agree withthat?
Joe Rando (02:51):
Well, I think I mean, if we're talking about
solopreneurs, yes. If we'retalking about in general, I
mean, the news out today, we'reon the 10/29/2025, and major
companies are laying off tens ofthousands of white collar
employees because they'rebasically being pressured by
(03:13):
investors, and the c suite'sjust saying, we're gonna replace
these people with AI. I don'tpredict that's gonna go well. I
suspect that they're gonna be alittle surprised as to how that
doesn't live up to theirexpectations. Eventually, it
will because AI is gettingbetter all the time.
(03:34):
But yes, I think as asolopreneur where you're in
charge of your own destiny, youdon't have to lose your job
because AI starts doingsomething that you do. So I'll
go there.
Carly Ries (03:46):
And for solopreneur's sake, we think you
should be looking at AI as yourteammate. I think of AI as kind
of like an over enthusiasticintern. Like they're fast,
they're eager, but they arewrong, sometimes clueless. AI is
not perfect. And so I see it asa, like how good I can do, look
(04:07):
how good I can do, but thattraining still needs to be
there.
So I wanna talk about AI as yourteammate, especially as a
solopreneur, and how you cankind of coach that teammate
today, and to help youunderstand how to manage AI, not
be managed by AI. Does thatsound like a good direction?
Joe Rando (04:25):
It does. I wanna start with just kind of some
framing, which is, and I'mguilty of this as much as
anybody, is that we like tothink that AI thinks, but it's
not thinking. It really isn't.It just feels that way. It
predicts. It's a somebodydescribed it as a plausibility
(04:46):
engine, which I thought was abrilliant way to describe it.
It's predicting what the nextword should be based on the
inputs, and, it's surprisinglygood given that that's what it's
doing. You kind of think aboutit.
It's doing that, and you go,wow. It's pretty darn good. But
it is by no means, as you said,perfect or even close to perfect
(05:09):
and can really go off the rails.And if you wanna know, just how
weird it can get, I have a GPT Icreated called You're Wrong. And
You're Wrong basically has abunch of prompts to basically
think more, critically and to beless nice about critiquing.
(05:31):
And so I'll put something in it,and it'll kind of rip me apart.
You know? It really roasts me.And sometimes I'll take chat GPT
generated material and put itinto your wrong, which is also
chat GPT, and it will roast it.And so you just kinda look and
go, okay.
And the thing with you're wrongis it's actually better than
chat GPT at coming up with goodideas. It's much more critical
(05:54):
of its own thinking. But,anyway, the point being, you do
not want to treat this asanything other than a highly
eager, coachable, but prettypretty naive intern.
Carly Ries (06:11):
I'm so glad you said coachable because I think a
common misconception that peoplehave is that the AI knows their
business. Like if you typed yourwebsite in, that it would
automatically know the ins andouts and it just doesn't. you
really have to take time totrain AI so that it works the
best for you. So you can't justsay, let's say you're writing a
social media post for yourcompany, and it's like write a
(06:33):
social post for LifeStarr. Butit wouldn't really know what to
do.
So you have to say, write asocial post for LifeStarr that
targets solopreneurs and helpsthem with their productivity.
you need to train it. Andgranted over time it'll start
picking up on it, but if youwanna start getting it right
immediately, you need to put inthat effort just like you were
training another employee,another contractor, whatever. It
(06:57):
needs that training. Even thatonboarding.
We talk about onboarding a lot.
Joe Rando (07:02):
Yeah. There's a lot to it. But one of the problems
that I've seen, I don't know ifanybody else has experienced
this, is that I will train up aGPT, not necessarily, doing
anything, you know, under thehood, so to speak, but just
kinda go in and give a bunch ofinstructions. And over time, if
I'm using this thing for a lotof work and using the same feed,
(07:25):
it'll start to forget. And it'sgot to do with something called
the context window that can onlyhold so much information.
And so you start off with someinitial instructions. You get
deep down into it, it starts toforget the initial instructions.
So you need to if you reallywanna use it and train it up,
you've gotta go in and create aGPT and put in a bunch of
(07:45):
training materials so that itdoesn't ever lose that. Does
that make sense?
Carly Ries (07:50):
it does. And I mean, even if you have a business
plan, if you have like a brandguidelines document, those are
the kinds of things you shouldbe inputting and retraining. And
don't rely on it like you weresaying, to always remember.
Like, maybe have a Mondaymorning meeting with ChatGPT and
be like, hey, just a reminder,this is my business plan. Let's
(08:14):
focus on this for the rest ofthe week as we're putting
together the content and all ofthat.
Joe Rando (08:19):
Well, like I said, you should create a GPT for
that. So the business plan is inthere in the core training as
opposed to just trying to makeit remember in the base chat
GPT.
You don't want to do thatbecause it won't.
Carly Ries (08:34):
Yeah. But I kinda look at AI as like an executor,
a brainstormer, and aresearcher, whereas you are the
visionary, the decision maker,the editor, editor, editor. And
that's how I define the twodifferent roles. Again, kinda
with that intern mindset andframework.
(08:56):
But Joe, if people are treatingit like an employee, because, I
mean, AI really is a gamechanger for solopreneurs. It
brings up so much time. Whatwould you say you should
delegate, and what should younot delegate?
Joe Rando (09:10):
Well, at the core of it, do not delegate your
thinking. just as an example,write a blog post about the
three biggest mistakes thatsolopreneurs make without
telling it what those threemistakes are. Don't let AI think
(09:33):
through. I mean, you wanna goahead and brainstorm and say,
throw out, the biggest mistakesthat you think solopreneurs make
based on a search of the web,and then go through those and
go, oh, wow.
Yeah. I didn't think of thatone, and there's this one. And
then take that, but you need tofeed it your thinking. Right?
And you it's nice to feed ityour thinking, your writing
style, and a lot of context sothat you're getting something
(09:56):
that isn't just AI dribble. Andnobody wants to read AI drivel.
Neil Patel said that non AIgenerated content generates 4.7
times more views than AIgenerated content. And that
should tell you that, and I'mnot saying not to use AI, but if
you can use AI in a way thatit's your content, your ideas,
(10:16):
your thinking, people are gonnarespond to that better than this
kind of, kind of generic AIthinking average of the entire
inter interwebs, stuff that it'sgonna generate on its own.
Carly Ries (10:30):
Because it does hallucinate things.
Joe Rando (10:33):
Oh, that too. But even when it's not
hallucinating, on its own, it'spretty boring.
Carly Ries (10:38):
Yeah. Absolutely. But with the hallucination
thing, I think it's also reallyimportant to identify when AI is
leading you astray. When you'reworking with it as, I'm assuming
you keep saying intern forconsistency purposes.
Call it whatever you want. Butif you can identify the mistakes
it makes time and time again andtrain those mistakes out of them
(11:00):
like you would an intern,that'll also help with your
strategy, your content,everything that you're using AI
for. Joe, didn't you just do onethat replaced Emdashes?
Joe Rando (11:09):
It didn't work. I created a GPT, and the entire
prompt was never use Emdashes,period. Never use Emdash. I'd
put it in about it must havebeen 50 or 60 times. And then I
asked to write an EmilyDickinson poem, a poem in the
style of Emily Dickinson, and itused a bunch of em dashes.
It's nobody other than, yourEnglish professor uses em
(11:37):
dashes. It takes, keystrokesthat nobody does. How did it get
trained up on em dashes?
Carly Ries (11:45):
I know. it was almost like bring back the em
dash.
Joe Rando (11:50):
But nobody wants to use them now.
the woman that was editingSolopreneur Business for
Dummies, she was an Englishmajor and very, literary. And
she sent me some content. Isaid, oh, we can't use the em
dashes. It looks like AI. Shegoes, what? I always use em
(12:10):
dashes.
I heard semicolons are becomingthe same way, and I love
semicolons, been using them fordecades, and I'm gonna have to
give up semicolons.
Carly Ries (12:22):
so when I have used em dashes in my writing, I've
always had to copy and paste itfrom other copy or other content
because I couldn't figure outhow to do the em dash myself.
Which I suppose that's a quickAI search, but I just always put
them to different other content.Anyway, Joe, any parting words
of wisdom for having AI as youremploy and training it and
(12:44):
onboarding it that you thinksolopreneurs should know about?
Joe Rando (12:46):
Well, I'm gonna reiterate this idea of, there's
a difference between creating aGPT and putting training in the
GPT and just kinda going intoChatGPT and saying, do this and
do this and don't do thisbecause that context window and
I'm no expert. So you know? Butbasically, what it seems to me
is that context window thatcontains kinda what it's using
(13:09):
as a reference point, the oldstuff goes off eventually, and
it starts to drift. So, if youdo this, you're gonna wanna
build out a GPT trained to docertain things and put certain
documents in there and certaininstructions. At least that's
ChatGPT.
That's my go to. Not so sure on,things like perplexity and
(13:31):
anthropic. But, the main thingwith all of these is just check
the work. Make sure it's notcrazy. You know, it's just so
easy for these things to go offinto delusion.
And if you let that go out, it'snot gonna reflect on ChatGPT or
some other, large languagemodel. It's gonna reflect on
(13:52):
you.
Carly Ries (13:54):
And you need to train it, correct it. You know
what I've started doing, Joe?I've started and I don't know if
this does anything. I think itdoes. I started celebrating it.
So when ChatGPT does somethingreally well, I say, that's
awesome. That's exactly what Iwas looking for. And then I'll
(14:14):
iterate and be like, can youalso do something like this? And
it'll say, thank you so much.And then I find that everything
from that point on, the resultsare better because I gave it the
positive reinforcement.
I don't know. This might be inmy mind. Before an AI takes on
minds of their own, I want themto know that I was grateful.
Joe Rando (14:33):
Yeah. And it's true. And, yeah, it's good to give it
you know, there's a littlethumbs up. You can click on chat
GPT as well to let them know itdid a good job or a thumbs down.
But, but, yeah, and the otherthing I guess the one last thing
I wanna mention is that becausethey're updating the model all
the time, you know, it was four,then was four o. Now it's five,
(14:54):
and they got all the differentfive versions and, deep research
depending on which version ofChatGPT you're buying if you're
buying it. But it's weird, thebehavior changes, right, when
they make these changes to themodel. Like, I've got this
you're wrong one that I talkedabout that I use all the time,
(15:14):
and it's great. But all of asudden, it started using
profanity.
It never did before. And now allof a sudden, it's using and I
remember they made some changejust now to loosen the thing up
a little bit. And, it's not mystyle. I don't use profanity, so
I'm not really inclined to wantit to do that. So now I've got
to go in and change thetraining, say don't use
(15:35):
profanity. but just there's alot of weirdness. You always you
build these things, then youhave to keep an eye on them.
It's kind of like an internthat, develops a drinking
problem or something.
Carly Ries (15:47):
Or something. Well, listeners, hopefully you found
this episode useful. I knowthere's a lot of AI talk out
there, but not always as itrelates to solopreneurs
specifically. So hopefully youlearned something new. And as
always, leave us that five starreview.
We would so appreciate it. Sharethis episode with a friend.
Subscribe to our show on yourfavorite podcast platform,
including YouTube, and we'll seeyou next time on the Aspiring a
(16:09):
Solopreneur. You may be goingsolo in business, but that
doesn't mean you're alone. Infact, millions of people are in
your shoes, running a one personbusiness and figuring it out as
they go.
So why not connect with them andlearn from each other's
successes and failures? AtLifeStarr, we're creating a one
person business community whereyou can go to meet and get
(16:30):
advice from other solopreneurs.Be sure to join in on the
conversations atcommunity.lifestarr.com.
Popular Podcasts
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
The Male Room with Dr. Jesse Mills
As Director of The Men’s Clinic at UCLA, Dr. Jesse Mills has spent his career helping men understand their bodies, their hormones, and their health. Now he’s bringing that expertise to The Male Room — a podcast where data-driven medicine meets common sense. Each episode separates fact from hype, science from snake oil, and gives men the tools to live longer, stronger, and happier lives. With candor, humor, and real-world experience from the exam room and the operating room, Dr. Mills breaks down the latest health headlines, dissects trends, and explains what actually works — and what doesn’t. Smart, straightforward, and entertaining, The Male Room is the show that helps men take charge of their health without the jargon.