March 10, 2025 • 23 mins
What if you could create a personal collection of "cheat codes" that unlock the full power of AI? Vic Rogers, board member of AI Ready RVA, reveals exactly how prompt engineering transformed his relationship with artificial intelligence from frustrating to phenomenal.
Prompt engineering might sound technical, but as Vic explains, it's simply the art of talking to AI effectively. When he first attempted to use ChatGPT to write a business plan in early 2023, the results were disappointing - verbose documents with inappropriate language. Through trial and error, he discovered that by refining his approach and saving successful prompts, he could dramatically improve his results across countless applications.
"Think of it like a Rolodex or game cheat codes," Vic shares, describing his prompt library that's grown from basic requests to sophisticated instructions. We explore fascinating examples, including his "Eternal Ebony" prompt designed to generate authentic representations of Black individuals, addressing the persistent challenges of diversity in AI-generated images. His financial prompts showcase the evolution of his technique - from basic questions to detailed instructions that mimic the expertise of a financial advisor with 20 years of experience.
The most compelling revelation? Vic, who studied marketing rather than finance, credits prompt engineering with accelerating his investment learning "ten times faster" than traditional methods. By creating prompts based on financial experts like Ray Dalio and Michael Burr, he transformed complex market concepts into accessible knowledge. "I've gotten really strong," he admits while maintaining the humility of a lifelong learner.
Whether you're interested in investing, marketing, real estate, or parenting, Vic's approach demonstrates how systematic prompt engineering can serve as a powerful accelerator for learning and productivity. Connect with Vic through victorrogersai or his venture Sustainable Growth Creative to discover how developing your own prompt library might be the key to unlocking your AI potential.
Want to join a community of AI learners and enthusiasts? AI Ready RVA is leading the conversation and is rapidly rising as a hub for AI in the Richmond Region. Become a member and support our AI literacy initiatives.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:00):
Welcome RVA to Inspire AI, where we spotlight
companies and individuals in theregion who are pioneering the
development and use ofartificial intelligence.
I'm Jason McGinty from AI ReadyRVA.
At AI Ready RVA, our mission isto cultivate AI literacy in the
greater Richmond region throughawareness, community engagement
(00:24):
, education and advocacy.
Today's episode is madepossible by Modern Ancients
driving innovation with purpose.
Modern Ancients uses AI andstrategic insight to help
businesses create lasting,positive change with their
unique journey consultingpractice.
(00:44):
Find out more about how yourbusiness can grow at
modernagentscom, and thanks toour listeners for tuning in
today.
If you or your company wouldlike to be featured in the
Inspire AI Richmond episode,please drop us a message.
Don't forget to like, share orfollow our content and stay up
(01:07):
to date on the latest events forAI Ready RVA.
All right, Welcome back toInspire AI, a production by AI
Ready RVA, and this is a specialevent with Vic Rogers, board
member of AI Ready RVA,alongside with me.
(01:28):
Vic's been working with AIReady on a number of educational
opportunities and he has a tonof expertise that we'd like to
dig into today.
On prompt engineering, With therecent recording of prompt
engineering, we thought thatthis would be a great
opportunity to share some openinsights with the community at
(01:49):
large and just see where it goes.
So, Vic, welcome.
Speaker 2 (01:53):
Good to be here, appreciate you having me and I'm
looking forward to theconversation Awesome.
Speaker 1 (01:58):
Why don't you tell us a little bit about your
experience with promptengineering?
Where did it start?
What do you do with it thesedays, like, why is it so special
to you?
Speaker 2 (02:07):
yeah, I think that's really the catalyst to me, kind
of learning how to leverageartificial intelligence
effectively.
Um, it was like around februaryof 23 is when I really um, got
into the weeds of understandingai and initially one of the
things I wanted to do was, hey,write a business plan for me,
and and I and I told it, butthen it gave me this long book
and then the vernacular that itused was totally off base.
(02:31):
So I figured out eventually,like, oh, you have to, I guess,
iterate more.
So I guess that initial usewould have been zero shot
prompting and then few shotprompting over time, like that's
the actual terminology Ibelieve that is used.
But I just started talking toit more.
And once you started talking tothe machine more effectively, I
realized that, hey, if I saythis same thing over and over
(02:54):
again, I'll get here quicker.
So I created a prompt libraryand that prompt library ended up
growing and growing and it'sbeen one of the things that I
enjoy sharing with people and ithelps them really get around
that curve of prompt engineering.
So, like, if you find a goodprompt, copy and paste it, throw
it in a Google Doc and justkeep building over and over
again, because what's going tohappen over time is it's going
to allow for you to have abetter output and get to where
(03:17):
you want to look quicker.
Speaker 1 (03:19):
Okay, yeah, so help us understand.
What is.
What is it like to have aprompt library, is it?
It's a document that storesthese concepts of how to
interact with AI, right?
So can you break that down forus a little bit?
Imagine no one's ever workedwith this, with a prompt library
(03:39):
, before, and you're trying todescribe it to them.
What do you, what are youtelling them about?
Speaker 2 (03:45):
and you're trying to describe it to them.
What are you telling them about?
Old school people will feelthis it's like a Rolodex.
So what it is is just a placewhere all of your prompts are
stored.
I'm pretty basic with it, sothat's why I put it in a Google
Doc that I can share with folks.
But, notion, I believe you canalso put one, utilize a Notion
(04:06):
and have like a website whereyou can go to and you can do it
that way.
So I'm eventually gonna takeall the prompts that I have here
and put it there.
But pretty much what it is, it'sjust like another throwback
example.
Anybody who used to pay likeSega or like Super Nintendo,
game Genie that's a throwbackUsed to have a whole bunch of
(04:28):
cheat codes, right, but it'd bea book.
So what a prompt library is?
It's just that book that you goto.
You find the cheat code, youput it in and it's like the
Contra code or whatever you know.
It's like your God mode or Doomor whatnot, right?
I hope some of my gamers arefeeling me with these old school
references, like your God modeor Doom or whatnot, right?
I hope some of my gamers arefeeling me with these old school
references, but it's just a wayfor you to have all the prompts
in one place at one time.
(04:48):
So I shared my prompt librarywith you and I'm open to getting
your feedback, but, like one ofmy actual first prompts on here
a DEI prompt, so it's calledEternal Ebony, celebrating
Ageless Beauty and Resilience.
Why did I create that prompt?
Well, if you go into chat GPTand you ask it to create an
(05:10):
image of a person that you thinkis wealthy, a lot of times it
might not pop out what you want.
Or if you ask for it to giveyou an image of what you think I
look like, if I describe myself, it might not look like me.
This prompt in particular,though, it makes the machine or
(05:31):
the LLM that you use come backand give you an image that looks
like very, very good and theway I built it.
I just just started iterating,so like just kind of to read a
little bit of it, because it'skind of it's going to, it's
going to, it's going to soundfunny, but I create an image
that vividly embodies theconcept of ebony, along with the
(05:53):
timeless adage black don'tcrack.
Now, why did I say black don'tcrack?
In the black community.
We understand what that means.
If you look at me, I get a lotof times especially now, since
my hair is, you know, wrapped upI look a lot younger than I am.
But you know I'm pushing 40,you know, and it's one of those
things where people are like oh,black, don't crack, right?
So the image that you would getfrom a LLM if you put give me
(06:16):
an image of a black person withblack don't crack, put that in
if you're listening to this, andthen just give me it and then
go to another LLM and say giveme an image of a black person
Two totally separate, differentthings.
But sometimes you might forgetwhat the prompt was.
If you have a prompt library,though, you keep it all in one
place.
You can go back and rinse, wash, repeat, use it over and over
(06:36):
again.
A couple of other things inhere and of course it's like
it's long.
It talks about skin complexionIn the black community.
A lot of times, fair skinversus dark skin, hues can be
depicted differently.
So this one prompt inparticular, it just gives you
the ability to create an image,maybe of a woman or multiple
women that you want to depictmaybe a relative, or my mother
(07:01):
or my wife or my nieces oranything like that.
It gives you diversity in howthe image would come back to you
versus just asking a zero shot.
Create me an image of a blackfamily, because a lot of times
it doesn't give you what youwant.
You'd be surprised how often itcomes back and you know it's
not a positive image.
Speaker 1 (07:25):
And it's not a positive image.
Yeah, so you give it as muchdescription as possible to
depict what you're looking for.
So you're building a prompthere in a paragraph format so
that you can instruct the largelanguage model to depict exactly
what you're looking for.
And this one particularly isfor image development and you
(07:50):
can imagine the user of thisprompt library thinking about
whatever image that they'relooking for and you kind of lay
out how specific terms you'relooking for so that the
experience of that largelanguage model can determine
exactly what it is that you'rereferring to, because in quotes
(08:13):
you say black don't crack, andit knows exactly what that means
and therefore it can leveragethat knowledge to develop what
you're looking for here.
That sounds, that sounds reallygood yeah, 100 percent.
Speaker 2 (08:27):
Um llms understand colloquial speaking, um I can't
think about the exactterminology, but um, I always
shout out um.
There's a customized gpt onchat gpt called chat black gpt.
Just use that for anything thatyou want um and that's.
And if you want like a goodunderstanding of like how I
(08:48):
could be um more intentionalwith my communication with the
black community or anything likethat, that's a great, great GPT
.
I know the person who createdit and she's a rock star.
Her name is Erin in the AIspace.
But even if we want to talkabout something that me and you
both are really, reallyinterested in, I have one on
here called Teach Me Money andwhat it says is I want to assist
(09:11):
uh, I want assistance um by aqualified financial service
provider for 20 years,specializing in x, um and
enabled with experience onunderstanding charts using
technical analysis tools.
Why?
Interpreting macro economicenvironment prevailing across
world.
Consequently, assistingcustomer acquisition, long-term
(09:34):
advantages.
It's a lot of words in there,right, but I built that over
time with the chat GPT itself.
So, like, if you want a goodprompt, just you could tell chat
GPT to make a prompt for youand keep building it over and
over again, but in particularthis one, when I want to learn
about something, um, I mightlike right now.
Um, nvidia's earnings came outlast week.
(09:56):
Uh, they did well, but themarket didn't like it.
So now nvidia's looking badlike this we're going into
sunday.
What's the date of second right?
So, um, we're going into monday.
I don't know how the market'sgonna look, but if you want to
understand how to betterunderstand, like, have an idea,
like, well, why did the marketdip?
Why?
Why is this?
Why is that?
You can use this prompt andthen in chat, gpt, hit the
(10:20):
search button and it'll give youthe most up-to-date information
around how you want to betaught money, and then you can
make decisions from it.
Speaker 1 (10:28):
That's wild.
Okay, so this, this particularone, leads, leads up with give
me a qualified financial serviceprovider that has 20 years
experience specializing in.
You said X.
And if, if I were to look atNVIDIA, is the example you
(10:52):
provided?
Maybe I would say 20 yearsspecializing in market analysis,
or something like that, andthat would put this prompt, or
the AI with this prompt, intothe mindset that they
particularly have that kind ofexperience and leverage the
(11:14):
exact or the precise type ofinformation that a 20 year
experienced market analyst wouldhave when being asked specific
questions.
You know and so like you couldchange that by saying teach me
money, as if I were an eightyear old.
(11:34):
You could do that too, and thenyou would get a completely
different answer.
So one you're.
If you're willing and ready totalk with a financial service
provider that does have 20 yearsof experience, then this is the
prompt for you.
Yeah, I really like that.
And and I heard you say this acouple of times but you started
with you know, teach mesomething about this.
(11:55):
And then, as you learned howthe AI operated, you, you
updated, you modified this oneroutinely went back to it and
said I, you know, I want, I wanta little bit more in terms of
macroeconomic, environmental,environmental-like type
descriptions here, or I want toknow more about factors related
(12:18):
to inflation, and then you wouldjust plug in those types of
elements and, based on whatevergot you looking at this that day
, if it's NVIDIA, you mightchange the prompts so that
you're leveraging things aboutyou know, tech, industry, you
know, or hardware, or AI, evento get different, more specific
(12:45):
results.
Speaker 2 (12:46):
Yeah, 100%, and like what you're looking at again.
What we're talking about islike what you're looking at
again what we're talking aboutis like why a prompt library is
effective.
So you're at prompt number 10.
Scroll down to prompt number 58.
This is called the ultimatestock analysis trading prompt.
Now here I have technicalanalysis evaluating 200 day and
(13:08):
72 day moving averages,financial health, assets, year
over year, market position,market sentiment, risk
assessment, entry and exitstrategy, growth potential,
sector comparison.
And then I want you to give mea clear, concise, two to three
sentence output telling me whenI should get into a stock.
(13:29):
Is it a long-term play?
Is it a short-term play, if Iwant to do options or things
like that?
But the reason why I say scrolldown to number 58, because
you'll see the evolution of howI've been able to enhance my
prompting over time.
That prompt that I created atthe top I did that probably a
year and a half ago thisultimate stop analysis one I did
that probably about six monthsago and I'm just getting
(13:51):
stronger and stronger with it.
So, like, the more you playwith ChatGPT and the prompts and
if you have a use case, you'llget better, and I'm always open
to having these conversationswith people.
Victorrogersai, r-o-g-e-r-s.
Because we're not Aaron Rodgersfans, victorrogersai, come
holler at me but, um, yeah, likeit's one of those things where
(14:13):
it's just fun, because I'veworked with real estate people.
I've worked with people tryingto make milk preps.
I worked with parents trying tomake um, you know sleep
structures for their children.
Like you can do a lot ofdifferent things with ai, but
you just gotta um practice withit.
It's like playing a video game.
Like you know, if you're uh,I've been on this gamer thing
all day.
But if you know, if you'replaying Madden and you're
getting beat on all Madden, moveit down to maybe all pro and
(14:37):
you'll get a little better.
Then over time you can competein Madden.
You play online and when themkids from overseas are just
whipping you and talking smackto you in another language, then
you just hold your hand andshout at them.
It's a great opportunity tolearn, and it's free too.
You shouldn't necessarily haveto spend a lot of money to learn
, and it's free too.
Speaker 1 (14:51):
Um you know, you shouldn't necessarily um have to
spend a lot of money to learnhow to prompt yeah, yeah, I kind
of I try to emphasize that inthe podcast, that it's you know
it's never too too late to start, and the more you do this, the
better you'll get at it as wellas uh, the more ahead of of the
change that you're going to beright Like.
(15:13):
This sort of thing is going tocontinue to change over time.
Getting the foundationalunderstanding of how to leverage
these tools is going to makethings happen for you a lot
faster.
Yeah, I really love how likethe depth that you go into these
.
I see you have a lot ofinterest in investing.
(15:37):
So I would love to look at thisa little bit more, because
that's definitely up on my listof hobbies, for sure.
How successful would you sayyou've been with prompt
engineering and investingspecifically?
Not that you're a financialadvisor, so those listening to
this shouldn't take it for that,but for what it is right.
(15:59):
You're leveraging theintelligence of of all things
Internet and AI here.
So well, give it.
Give it a score, one to ten,like how do you feel like this
is done for you?
Speaker 2 (16:13):
Yeah for a guy.
You know I went, I went toschool for marketing, you know,
got a minor.
I think, well, actually I got aminor.
And I think, well, actually Igot a, yeah, minor in management
, right.
So like coming into, likeinvesting in things of that
nature, like I didn't reallyknow a lot, all I did was start
listening to like financialpodcasts and if you look on here
, michael Burr, ray Dalio, Iknow- the Kramer one Of all of
(16:45):
them.
there's a guy named Ian Dunlap,number 54.
What I did was I listened towhat they were talking about on
their podcast.
I took a transcript of whatthey would say and I said turn
what they said into a prompt andthen it a hundred percent
allowed me to be a lot morebetter, like what I, what I say.
If I had to scale myself on oneto ten I say at eight because
(17:05):
I'm not better than these people, right, I'm just able now to
catch up to like a learningcurve like that I would have.
It took me a lot longer to, youknow, learn like, I would say.
I learned this stuff 10 timesfaster than most people and I
take for granted how far alongthat I've come.
A combination of using AI andjust being a student of the news
constantly.
I've gotten really, reallystrong.
(17:27):
I think I am bullish, though inthe semiconductor space I need
to probably be a little bit morediverse.
Eli Lilly and healthcare issomething that I think I want to
diversify in and read a lotmore into.
But as it stands right now,look, I'm looking at an AMD and
TSCM and ASML and you know I canread.
I can rattle all those tickersymbols off.
(17:48):
So, like I'm understanding that, that semiconductor sector and
everything around it whetherit's Amazon, whether it's, you
know, meta, youa, all thosecompanies that have tentacles in
artificial intelligence I'mlooking at those companies and
finding out how to invest.
I'm mainly doing long-terminvesting.
I'm scared to do options.
A few options that I've donethey're always call options.
(18:11):
I'm never going to do a put.
I just don't feel comfortablebecause you can lose everything.
I had a buddy of mine lose hiswhole 401k because he didn't put
a stop.
Put, I think, is the term, andyeah, it just kept going down.
So you know you gotta be safewith that, but you know it
helped a lot.
I'll say an eight, though,because I mean, like I can't say
I'm not a professional likefinancial services provider, but
(18:35):
if you want to talk finance andnumbers and stuff, I'm, you
know, pretty good, and if youlook at how much I've been able
to accumulate over a shortamount of time, I think I'm
doing pretty average, you know.
I mean I'm confident that I'lldo better over time, but humble
about it because I know at anygiven time the market can dip.
Speaker 1 (18:54):
Yes, yes, indeed.
Yeah, I'm a long investor aswell.
Speaker 2 (18:57):
Do you have any long-term plays that you want to
recommend?
I always like having thoseconversations Long-term plays or
like companies to invest in.
Like when you do long-terminvesting, how are you doing it?
Is it in like Roths, usuallyETFs?
I do like the semiconductorindustry.
Speaker 1 (19:12):
I do like the semiconductor industry.
I like tech and healthcare.
I don't do anything in thecommodities and consumer goods.
I think it feels like I'mchasing something there and I
think that when I invest, Iinvest for growth.
(19:33):
They're not all consideredgrowth stocks or or anything
like that, but um, I do look forthe long-term wins, um not the.
I don't chase the short-termwins.
Um, sometimes if someone says,hey, palantir is doing really
well, uh, you need to get onthis train, I'll take a look at
(19:54):
it and and say, what, where doesthis fit into my long-term
approach?
And say, how much money would Ibe willing to kind of chase
this Because it's a chase, right, it's a risk, a bet on some
company that you don't reallyknow much about unless you do
your research.
It sounds like you do a lot ofresearch.
(20:17):
That is me.
Personally, I try to try to stayaway from too much of the the
risk, risky type moves in theshort term and and just stick
with that long-term stuff.
And and and I make bets on oncompanies that are, are
responsible.
I make bets on companies thatthat have good books in place
(20:38):
and, uh, they, they aren't youknow um disrespecting humanity
in any way.
Right, like I, I, I care aboutthose things and uh, you, you
vote with your wallet these days.
So that's that's kind of how Ido it.
I um try to max out my 401k,401k and it's barely risk averse
(21:00):
by putting money in 401k beforeyou put money into direct
equities, you know if you haveany money left over and you can.
You can put some in your directequities.
That's great, and you can playwith that and and you can.
You can do some other things.
I could talk all day about thisstuff, but this isn't a
financial service podcast, right, it's an AI podcast, and I
(21:22):
haven't really gotten the nerveto ask AI about my financial
strategy in any way.
But you've built my confidencehere and I say to myself I'm
going to take a deeper look atyour prompts and and and think
about how maybe I can, I can usethat for my Lawrence long-term
(21:42):
goals as well.
But hey, man, this has beenawesome.
I really appreciate your timetoday and I think I think we got
something good here.
So I'd really like to work withyou in the future on on maybe
some additional co-hostingpodcasts on various AI topics.
So yeah, man, let's make ithappen.
Speaker 2 (22:03):
Oh yeah, I'd love to do it, man.
I think it'd be, I think it'dbe a good little conversation,
man.
All right, yeah.
Speaker 1 (22:08):
And tell everybody again where they can find you.
Speaker 2 (22:11):
Yeah, so Sustainable Growth Creative that's the name
of my venture.
You can look it up atsustainablegrowthcreativecom or
org, but the easiest place isjust victorrodgersai and that's
V-I-C-T-O-R-R-O-G-E-R-Sai andthe company name Sustainable
Growth Creative.
I'm going to just do ashorthand now.
Sgc you can find that onLinkedIn.
(22:32):
We got Instagram.
Doesn't have a lot on there,but we made an AI agent on
Instagram.
That that's really what it'sfor.
So if you are interested in oh,if you're a federal worker
trying to figure out how tonavigate these bumpy times go to
our Instagram page.
We made an AI agent that helppeople through the job market.
(22:55):
Right now.
It's kind of spooky and likethat's the type of stuff that
we're doing over here atSustainable Growth Creative.
We're trying to help folks feelcomfortable with the technology
and then feel comfortable toget out of that, get out of any
kind of situation they're in.
But again, victorrodgersai isthe quickest place to find me.
I love to work with new clientsand hey, jason man, I
(23:20):
appreciate you sharing yourplatform with me.
Speaker 1 (23:21):
Um, I know you could be doing a lot of other things
besides listening to me rambleabout you know random stuff.
But thanks a lot, man.
It was a pleasure.
All right, talk to you later.
Later, and thanks to ourlisteners for tuning in today.
If you or your company wouldlike to be featured in the
inspire ai rich episode, pleasedrop us a message.
Don't forget to like, share orfollow our content and stay up
(23:42):
to date on the latest events forAI Ready RVA.
Thank you again and see younext time.
Welcome RVA to Inspire AI, where we spotlight
companies and individuals in theregion who are pioneering the
development and use ofartificial intelligence.
I'm Jason McGinty from AI ReadyRVA.
At AI Ready RVA, our mission isto cultivate AI literacy in the
greater Richmond region throughawareness, community engagement
(00:24):
, education and advocacy.
Today's episode is madepossible by Modern Ancients
driving innovation with purpose.
Modern Ancients uses AI andstrategic insight to help
businesses create lasting,positive change with their
unique journey consultingpractice.
(00:44):
Find out more about how yourbusiness can grow at
modernagentscom, and thanks toour listeners for tuning in
today.
If you or your company wouldlike to be featured in the
Inspire AI Richmond episode,please drop us a message.
Don't forget to like, share orfollow our content and stay up
(01:07):
to date on the latest events forAI Ready RVA.
All right, Welcome back toInspire AI, a production by AI
Ready RVA, and this is a specialevent with Vic Rogers, board
member of AI Ready RVA,alongside with me.
(01:28):
Vic's been working with AIReady on a number of educational
opportunities and he has a tonof expertise that we'd like to
dig into today.
On prompt engineering, With therecent recording of prompt
engineering, we thought thatthis would be a great
opportunity to share some openinsights with the community at
(01:49):
large and just see where it goes.
So, Vic, welcome.
Speaker 2 (01:53):
Good to be here, appreciate you having me and I'm
looking forward to theconversation Awesome.
Speaker 1 (01:58):
Why don't you tell us a little bit about your
experience with promptengineering?
Where did it start?
What do you do with it thesedays, like, why is it so special
to you?
Speaker 2 (02:07):
yeah, I think that's really the catalyst to me, kind
of learning how to leverageartificial intelligence
effectively.
Um, it was like around februaryof 23 is when I really um, got
into the weeds of understandingai and initially one of the
things I wanted to do was, hey,write a business plan for me,
and and I and I told it, butthen it gave me this long book
and then the vernacular that itused was totally off base.
(02:31):
So I figured out eventually,like, oh, you have to, I guess,
iterate more.
So I guess that initial usewould have been zero shot
prompting and then few shotprompting over time, like that's
the actual terminology Ibelieve that is used.
But I just started talking toit more.
And once you started talking tothe machine more effectively, I
realized that, hey, if I saythis same thing over and over
(02:54):
again, I'll get here quicker.
So I created a prompt libraryand that prompt library ended up
growing and growing and it'sbeen one of the things that I
enjoy sharing with people and ithelps them really get around
that curve of prompt engineering.
So, like, if you find a goodprompt, copy and paste it, throw
it in a Google Doc and justkeep building over and over
again, because what's going tohappen over time is it's going
to allow for you to have abetter output and get to where
(03:17):
you want to look quicker.
Speaker 1 (03:19):
Okay, yeah, so help us understand.
What is.
What is it like to have aprompt library, is it?
It's a document that storesthese concepts of how to
interact with AI, right?
So can you break that down forus a little bit?
Imagine no one's ever workedwith this, with a prompt library
(03:39):
, before, and you're trying todescribe it to them.
What do you, what are youtelling them about?
Speaker 2 (03:45):
and you're trying to describe it to them.
What are you telling them about?
Old school people will feelthis it's like a Rolodex.
So what it is is just a placewhere all of your prompts are
stored.
I'm pretty basic with it, sothat's why I put it in a Google
Doc that I can share with folks.
But, notion, I believe you canalso put one, utilize a Notion
(04:06):
and have like a website whereyou can go to and you can do it
that way.
So I'm eventually gonna takeall the prompts that I have here
and put it there.
But pretty much what it is, it'sjust like another throwback
example.
Anybody who used to pay likeSega or like Super Nintendo,
game Genie that's a throwbackUsed to have a whole bunch of
(04:28):
cheat codes, right, but it'd bea book.
So what a prompt library is?
It's just that book that you goto.
You find the cheat code, youput it in and it's like the
Contra code or whatever you know.
It's like your God mode or Doomor whatnot, right?
I hope some of my gamers arefeeling me with these old school
references, like your God modeor Doom or whatnot, right?
I hope some of my gamers arefeeling me with these old school
references, but it's just a wayfor you to have all the prompts
in one place at one time.
(04:48):
So I shared my prompt librarywith you and I'm open to getting
your feedback, but, like one ofmy actual first prompts on here
a DEI prompt, so it's calledEternal Ebony, celebrating
Ageless Beauty and Resilience.
Why did I create that prompt?
Well, if you go into chat GPTand you ask it to create an
(05:10):
image of a person that you thinkis wealthy, a lot of times it
might not pop out what you want.
Or if you ask for it to giveyou an image of what you think I
look like, if I describe myself, it might not look like me.
This prompt in particular,though, it makes the machine or
(05:31):
the LLM that you use come backand give you an image that looks
like very, very good and theway I built it.
I just just started iterating,so like just kind of to read a
little bit of it, because it'skind of it's going to, it's
going to, it's going to soundfunny, but I create an image
that vividly embodies theconcept of ebony, along with the
(05:53):
timeless adage black don'tcrack.
Now, why did I say black don'tcrack?
In the black community.
We understand what that means.
If you look at me, I get a lotof times especially now, since
my hair is, you know, wrapped upI look a lot younger than I am.
But you know I'm pushing 40,you know, and it's one of those
things where people are like oh,black, don't crack, right?
So the image that you would getfrom a LLM if you put give me
(06:16):
an image of a black person withblack don't crack, put that in
if you're listening to this, andthen just give me it and then
go to another LLM and say giveme an image of a black person
Two totally separate, differentthings.
But sometimes you might forgetwhat the prompt was.
If you have a prompt library,though, you keep it all in one
place.
You can go back and rinse, wash, repeat, use it over and over
(06:36):
again.
A couple of other things inhere and of course it's like
it's long.
It talks about skin complexionIn the black community.
A lot of times, fair skinversus dark skin, hues can be
depicted differently.
So this one prompt inparticular, it just gives you
the ability to create an image,maybe of a woman or multiple
women that you want to depictmaybe a relative, or my mother
(07:01):
or my wife or my nieces oranything like that.
It gives you diversity in howthe image would come back to you
versus just asking a zero shot.
Create me an image of a blackfamily, because a lot of times
it doesn't give you what youwant.
You'd be surprised how often itcomes back and you know it's
not a positive image.
Speaker 1 (07:25):
And it's not a positive image.
Yeah, so you give it as muchdescription as possible to
depict what you're looking for.
So you're building a prompthere in a paragraph format so
that you can instruct the largelanguage model to depict exactly
what you're looking for.
And this one particularly isfor image development and you
(07:50):
can imagine the user of thisprompt library thinking about
whatever image that they'relooking for and you kind of lay
out how specific terms you'relooking for so that the
experience of that largelanguage model can determine
exactly what it is that you'rereferring to, because in quotes
(08:13):
you say black don't crack, andit knows exactly what that means
and therefore it can leveragethat knowledge to develop what
you're looking for here.
That sounds, that sounds reallygood yeah, 100 percent.
Speaker 2 (08:27):
Um llms understand colloquial speaking, um I can't
think about the exactterminology, but um, I always
shout out um.
There's a customized gpt onchat gpt called chat black gpt.
Just use that for anything thatyou want um and that's.
And if you want like a goodunderstanding of like how I
(08:48):
could be um more intentionalwith my communication with the
black community or anything likethat, that's a great, great GPT
.
I know the person who createdit and she's a rock star.
Her name is Erin in the AIspace.
But even if we want to talkabout something that me and you
both are really, reallyinterested in, I have one on
here called Teach Me Money andwhat it says is I want to assist
(09:11):
uh, I want assistance um by aqualified financial service
provider for 20 years,specializing in x, um and
enabled with experience onunderstanding charts using
technical analysis tools.
Why?
Interpreting macro economicenvironment prevailing across
world.
Consequently, assistingcustomer acquisition, long-term
(09:34):
advantages.
It's a lot of words in there,right, but I built that over
time with the chat GPT itself.
So, like, if you want a goodprompt, just you could tell chat
GPT to make a prompt for youand keep building it over and
over again, but in particularthis one, when I want to learn
about something, um, I mightlike right now.
Um, nvidia's earnings came outlast week.
(09:56):
Uh, they did well, but themarket didn't like it.
So now nvidia's looking badlike this we're going into
sunday.
What's the date of second right?
So, um, we're going into monday.
I don't know how the market'sgonna look, but if you want to
understand how to betterunderstand, like, have an idea,
like, well, why did the marketdip?
Why?
Why is this?
Why is that?
You can use this prompt andthen in chat, gpt, hit the
(10:20):
search button and it'll give youthe most up-to-date information
around how you want to betaught money, and then you can
make decisions from it.
Speaker 1 (10:28):
That's wild.
Okay, so this, this particularone, leads, leads up with give
me a qualified financial serviceprovider that has 20 years
experience specializing in.
You said X.
And if, if I were to look atNVIDIA, is the example you
(10:52):
provided?
Maybe I would say 20 yearsspecializing in market analysis,
or something like that, andthat would put this prompt, or
the AI with this prompt, intothe mindset that they
particularly have that kind ofexperience and leverage the
(11:14):
exact or the precise type ofinformation that a 20 year
experienced market analyst wouldhave when being asked specific
questions.
You know and so like you couldchange that by saying teach me
money, as if I were an eightyear old.
(11:34):
You could do that too, and thenyou would get a completely
different answer.
So one you're.
If you're willing and ready totalk with a financial service
provider that does have 20 yearsof experience, then this is the
prompt for you.
Yeah, I really like that.
And and I heard you say this acouple of times but you started
with you know, teach mesomething about this.
(11:55):
And then, as you learned howthe AI operated, you, you
updated, you modified this oneroutinely went back to it and
said I, you know, I want, I wanta little bit more in terms of
macroeconomic, environmental,environmental-like type
descriptions here, or I want toknow more about factors related
(12:18):
to inflation, and then you wouldjust plug in those types of
elements and, based on whatevergot you looking at this that day
, if it's NVIDIA, you mightchange the prompts so that
you're leveraging things aboutyou know, tech, industry, you
know, or hardware, or AI, evento get different, more specific
(12:45):
results.
Speaker 2 (12:46):
Yeah, 100%, and like what you're looking at again.
What we're talking about islike what you're looking at
again what we're talking aboutis like why a prompt library is
effective.
So you're at prompt number 10.
Scroll down to prompt number 58.
This is called the ultimatestock analysis trading prompt.
Now here I have technicalanalysis evaluating 200 day and
(13:08):
72 day moving averages,financial health, assets, year
over year, market position,market sentiment, risk
assessment, entry and exitstrategy, growth potential,
sector comparison.
And then I want you to give mea clear, concise, two to three
sentence output telling me whenI should get into a stock.
(13:29):
Is it a long-term play?
Is it a short-term play, if Iwant to do options or things
like that?
But the reason why I say scrolldown to number 58, because
you'll see the evolution of howI've been able to enhance my
prompting over time.
That prompt that I created atthe top I did that probably a
year and a half ago thisultimate stop analysis one I did
that probably about six monthsago and I'm just getting
(13:51):
stronger and stronger with it.
So, like, the more you playwith ChatGPT and the prompts and
if you have a use case, you'llget better, and I'm always open
to having these conversationswith people.
Victorrogersai, r-o-g-e-r-s.
Because we're not Aaron Rodgersfans, victorrogersai, come
holler at me but, um, yeah, likeit's one of those things where
(14:13):
it's just fun, because I'veworked with real estate people.
I've worked with people tryingto make milk preps.
I worked with parents trying tomake um, you know sleep
structures for their children.
Like you can do a lot ofdifferent things with ai, but
you just gotta um practice withit.
It's like playing a video game.
Like you know, if you're uh,I've been on this gamer thing
all day.
But if you know, if you'replaying Madden and you're
getting beat on all Madden, moveit down to maybe all pro and
(14:37):
you'll get a little better.
Then over time you can competein Madden.
You play online and when themkids from overseas are just
whipping you and talking smackto you in another language, then
you just hold your hand andshout at them.
It's a great opportunity tolearn, and it's free too.
You shouldn't necessarily haveto spend a lot of money to learn
, and it's free too.
Speaker 1 (14:51):
Um you know, you shouldn't necessarily um have to
spend a lot of money to learnhow to prompt yeah, yeah, I kind
of I try to emphasize that inthe podcast, that it's you know
it's never too too late to start, and the more you do this, the
better you'll get at it as wellas uh, the more ahead of of the
change that you're going to beright Like.
(15:13):
This sort of thing is going tocontinue to change over time.
Getting the foundationalunderstanding of how to leverage
these tools is going to makethings happen for you a lot
faster.
Yeah, I really love how likethe depth that you go into these
.
I see you have a lot ofinterest in investing.
(15:37):
So I would love to look at thisa little bit more, because
that's definitely up on my listof hobbies, for sure.
How successful would you sayyou've been with prompt
engineering and investingspecifically?
Not that you're a financialadvisor, so those listening to
this shouldn't take it for that,but for what it is right.
(15:59):
You're leveraging theintelligence of of all things
Internet and AI here.
So well, give it.
Give it a score, one to ten,like how do you feel like this
is done for you?
Speaker 2 (16:13):
Yeah for a guy.
You know I went, I went toschool for marketing, you know,
got a minor.
I think, well, actually I got aminor.
And I think, well, actually Igot a, yeah, minor in management
, right.
So like coming into, likeinvesting in things of that
nature, like I didn't reallyknow a lot, all I did was start
listening to like financialpodcasts and if you look on here
, michael Burr, ray Dalio, Iknow- the Kramer one Of all of
(16:45):
them.
there's a guy named Ian Dunlap,number 54.
What I did was I listened towhat they were talking about on
their podcast.
I took a transcript of whatthey would say and I said turn
what they said into a prompt andthen it a hundred percent
allowed me to be a lot morebetter, like what I, what I say.
If I had to scale myself on oneto ten I say at eight because
(17:05):
I'm not better than these people, right, I'm just able now to
catch up to like a learningcurve like that I would have.
It took me a lot longer to, youknow, learn like, I would say.
I learned this stuff 10 timesfaster than most people and I
take for granted how far alongthat I've come.
A combination of using AI andjust being a student of the news
constantly.
I've gotten really, reallystrong.
(17:27):
I think I am bullish, though inthe semiconductor space I need
to probably be a little bit morediverse.
Eli Lilly and healthcare issomething that I think I want to
diversify in and read a lotmore into.
But as it stands right now,look, I'm looking at an AMD and
TSCM and ASML and you know I canread.
I can rattle all those tickersymbols off.
(17:48):
So, like I'm understanding that, that semiconductor sector and
everything around it whetherit's Amazon, whether it's, you
know, meta, youa, all thosecompanies that have tentacles in
artificial intelligence I'mlooking at those companies and
finding out how to invest.
I'm mainly doing long-terminvesting.
I'm scared to do options.
A few options that I've donethey're always call options.
(18:11):
I'm never going to do a put.
I just don't feel comfortablebecause you can lose everything.
I had a buddy of mine lose hiswhole 401k because he didn't put
a stop.
Put, I think, is the term, andyeah, it just kept going down.
So you know you gotta be safewith that, but you know it
helped a lot.
I'll say an eight, though,because I mean, like I can't say
I'm not a professional likefinancial services provider, but
(18:35):
if you want to talk finance andnumbers and stuff, I'm, you
know, pretty good, and if youlook at how much I've been able
to accumulate over a shortamount of time, I think I'm
doing pretty average, you know.
I mean I'm confident that I'lldo better over time, but humble
about it because I know at anygiven time the market can dip.
Speaker 1 (18:54):
Yes, yes, indeed.
Yeah, I'm a long investor aswell.
Speaker 2 (18:57):
Do you have any long-term plays that you want to
recommend?
I always like having thoseconversations Long-term plays or
like companies to invest in.
Like when you do long-terminvesting, how are you doing it?
Is it in like Roths, usuallyETFs?
I do like the semiconductorindustry.
Speaker 1 (19:12):
I do like the semiconductor industry.
I like tech and healthcare.
I don't do anything in thecommodities and consumer goods.
I think it feels like I'mchasing something there and I
think that when I invest, Iinvest for growth.
(19:33):
They're not all consideredgrowth stocks or or anything
like that, but um, I do look forthe long-term wins, um not the.
I don't chase the short-termwins.
Um, sometimes if someone says,hey, palantir is doing really
well, uh, you need to get onthis train, I'll take a look at
(19:54):
it and and say, what, where doesthis fit into my long-term
approach?
And say, how much money would Ibe willing to kind of chase
this Because it's a chase, right, it's a risk, a bet on some
company that you don't reallyknow much about unless you do
your research.
It sounds like you do a lot ofresearch.
(20:17):
That is me.
Personally, I try to try to stayaway from too much of the the
risk, risky type moves in theshort term and and just stick
with that long-term stuff.
And and and I make bets on oncompanies that are, are
responsible.
I make bets on companies thatthat have good books in place
(20:38):
and, uh, they, they aren't youknow um disrespecting humanity
in any way.
Right, like I, I, I care aboutthose things and uh, you, you
vote with your wallet these days.
So that's that's kind of how Ido it.
I um try to max out my 401k,401k and it's barely risk averse
(21:00):
by putting money in 401k beforeyou put money into direct
equities, you know if you haveany money left over and you can.
You can put some in your directequities.
That's great, and you can playwith that and and you can.
You can do some other things.
I could talk all day about thisstuff, but this isn't a
financial service podcast, right, it's an AI podcast, and I
(21:22):
haven't really gotten the nerveto ask AI about my financial
strategy in any way.
But you've built my confidencehere and I say to myself I'm
going to take a deeper look atyour prompts and and and think
about how maybe I can, I can usethat for my Lawrence long-term
(21:42):
goals as well.
But hey, man, this has beenawesome.
I really appreciate your timetoday and I think I think we got
something good here.
So I'd really like to work withyou in the future on on maybe
some additional co-hostingpodcasts on various AI topics.
So yeah, man, let's make ithappen.
Speaker 2 (22:03):
Oh yeah, I'd love to do it, man.
I think it'd be, I think it'dbe a good little conversation,
man.
All right, yeah.
Speaker 1 (22:08):
And tell everybody again where they can find you.
Speaker 2 (22:11):
Yeah, so Sustainable Growth Creative that's the name
of my venture.
You can look it up atsustainablegrowthcreativecom or
org, but the easiest place isjust victorrodgersai and that's
V-I-C-T-O-R-R-O-G-E-R-Sai andthe company name Sustainable
Growth Creative.
I'm going to just do ashorthand now.
Sgc you can find that onLinkedIn.
(22:32):
We got Instagram.
Doesn't have a lot on there,but we made an AI agent on
Instagram.
That that's really what it'sfor.
So if you are interested in oh,if you're a federal worker
trying to figure out how tonavigate these bumpy times go to
our Instagram page.
We made an AI agent that helppeople through the job market.
(22:55):
Right now.
It's kind of spooky and likethat's the type of stuff that
we're doing over here atSustainable Growth Creative.
We're trying to help folks feelcomfortable with the technology
and then feel comfortable toget out of that, get out of any
kind of situation they're in.
But again, victorrodgersai isthe quickest place to find me.
I love to work with new clientsand hey, jason man, I
(23:20):
appreciate you sharing yourplatform with me.
Speaker 1 (23:21):
Um, I know you could be doing a lot of other things
besides listening to me rambleabout you know random stuff.
But thanks a lot, man.
It was a pleasure.
All right, talk to you later.
Later, and thanks to ourlisteners for tuning in today.
If you or your company wouldlike to be featured in the
inspire ai rich episode, pleasedrop us a message.
Don't forget to like, share orfollow our content and stay up
(23:42):
to date on the latest events forAI Ready RVA.
Thank you again and see younext time.
Popular Podcasts
Amy Robach & T.J. Holmes present: Aubrey O’Day, Covering the Diddy Trial
Introducing… Aubrey O’Day Diddy’s former protege, television personality, platinum selling music artist, Danity Kane alum Aubrey O’Day joins veteran journalists Amy Robach and TJ Holmes to provide a unique perspective on the trial that has captivated the attention of the nation. Join them throughout the trial as they discuss, debate, and dissect every detail, every aspect of the proceedings. Aubrey will offer her opinions and expertise, as only she is qualified to do given her first-hand knowledge. From her days on Making the Band, as she emerged as the breakout star, the truth of the situation would be the opposite of the glitz and glamour. Listen throughout every minute of the trial, for this exclusive coverage. Amy Robach and TJ Holmes present Aubrey O’Day, Covering the Diddy Trial, an iHeartRadio podcast.
Betrayal: Season 4
Karoline Borega married a man of honor – a respected Colorado Springs Police officer. She knew there would be sacrifices to accommodate her husband’s career. But she had no idea that he was using his badge to fool everyone. This season, we expose a man who swore two sacred oaths—one to his badge, one to his bride—and broke them both. We follow Karoline as she questions everything she thought she knew about her partner of over 20 years. And make sure to check out Seasons 1-3 of Betrayal, along with Betrayal Weekly Season 1.
Crime Junkie
Does hearing about a true crime case always leave you scouring the internet for the truth behind the story? Dive into your next mystery with Crime Junkie. Every Monday, join your host Ashley Flowers as she unravels all the details of infamous and underreported true crime cases with her best friend Brit Prawat. From cold cases to missing persons and heroes in our community who seek justice, Crime Junkie is your destination for theories and stories you won’t hear anywhere else. Whether you're a seasoned true crime enthusiast or new to the genre, you'll find yourself on the edge of your seat awaiting a new episode every Monday. If you can never get enough true crime... Congratulations, you’ve found your people. Follow to join a community of Crime Junkies! Crime Junkie is presented by audiochuck Media Company.