📺 Develpreneur YouTube Episode

Video + transcript

Season 25 Recap – Lessons Learned from Our AI-Assisted Podcast Journey

2025-09-25 •Youtube

Detailed Notes

Season 25 of Building Better Developers with AI wraps up with a fully human conversation.

After more than thirty episodes experimenting with an AI-assisted podcast recap, hosts Rob Broadhead and Michael Meloche reflect on what they learned using AI to revisit past seasons, uncover new topics, and spark deeper discussions.

In this finale they share: * Key insights from months of AI collaboration * Where AI helped most—and where it fell short * Practical tips for creators considering their own AI-assisted workflow

Listen in as they review the surprises, successes, and lessons that will guide future seasons.

🎧 Full transcript and blog post: https://develpreneur.com/season-25-ai-assisted-podcast-recap/

#AI #Podcasting #Developers #SeasonRecap #ContentCreation

Transcript Text
[Music]
All right, I'm not even going to go to
AI for this last for our summary.
We're going to dive right into it and
just
riff a little bit about like what did we
what did we learn? uh what did we get
out of this season with AI? Probably
some like, you know, pros and cons and
things like that and be a little more
um probably conversational and things
like that, but I think it'll be
something that'll be hopefully it'll be
a good um
you know, have us give us give us an
excuse to sort of think back about like
what we've gotten out of AI and maybe
even talk a little bit about AI in
general. So that's my thoughts.
>> I like it. Um, we really only use chat
tpt and co-pilot, right? We didn't
really touch on or was it?
>> No, we used uh Gemini.
>> Okay.
>> We used that like a couple of times
mostly just to try it out. We did bounce
between chat GPT five and four. Um, I
don't know how often I actually
specified which was which because I
wasn't even sure sometimes because it
was using like best u whatever's the you
know most effective engine at the time.
I just keep it sort of left. I keep it
open and just do that kind of stuff. So,
um
>> yeah, I've had to play around with five
lately because I've been getting some
weird answers on the general one. Um
I've gone to like the thinking one and
it will actually give me a better
answer. Like it takes more time, but I
I'm not liking five. And I tried to go
back to 40 and 40 is now um you can use
it. It's limited. So, you can only use
40 a little bit unless you pay for the
professional version. And I'm like, "Oh,
that's crap." Because,
>> yeah, I went to the pro because I was
just using it so much. And I use the
thinking version a lot because I'm
usually doing it to say like a lot of
I've been doing a lot of it to
like migrate code and also to do like
design things and stuff like that where
I'll be like especially like that. Like
I said, the RB site, I got a lot of
stuff out of that where I'd be like,
take this
add these things to it, move this
around, do that thing. It's all the
stuff that like it's it's a little slow,
you know, it takes a couple, you know,
minute to think about it or whatever,
but it's so much faster than me like
going through and like, okay, can I
tweak this? Got to tweak this, got to
move that, got to move that. It's like
all those little things, it gets me
there faster. And so I'm like, yeah,
because and it's stuff that I'm like, I
have no desire to learn how to like
totally figure out this, you know, how
to do this in Bootstrap or how to do
that in Tailwind. And so it's been
>> really cool. It's allowed me to do
updates to interfaces really fast. It's
allowed me to even do some uh some
coding, some like swagger stuff and
things like that. It's like here, this
API, go in and just like give me a
better set of comments and stuff like
that. Now I've got more to work with. I
can go in, tweak it, boom, done. So
speed,
>> that's a lot of what I use it for. Um I
know you get on me sometimes because
you're like, "Oh, that's very AIish."
But sometimes when you're just dealing
with boilerplate stuff or you just need
a quick, hey, just give me a quick strut
or, you know, foundation for the
project. I'd rather do that and spend my
time working on the actual code and
yeah, I'll come back and tweak it later,
but if it works, it works. It's that
8020 thing. It's like, is it working?
Yeah. Okay, move on. Um
>> it is. It's just sometimes the code it
generates is oh my gosh. So like
>> and I do sometimes I get it but
sometimes it's speed. It's like
>> when when you're it depends where you
are in the project. If you're at the
point where results matter more than
quality you kind of got it's one of
those trade-offs. It it's a balance you
got to juggle. But um just teeny nitpick
and then we can jump in. Um, check your
um, what is it? Above the fold uh, your
image scroller on RB. One of your images
is jacking up your whole page. Like when
it scrolls it, the page is messed up
till it scrolls again. Um,
>> the RB site.
>> Yeah,
>> there aren't any. I don't think there's
any.
>> It may be on the blog because when I did
like the RB, it took me to the blog
page.
is it whatever page you have that has
like images that scroll the page got
jacked up from it and then it fixed
itself but it was weird.
>> Um that's interesting because there
shouldn't be thing left.
>> It might have been something cached but
I went to rbsns.com rblog. It does a
little shake and then it did like a
shift to an a new image and then the
whole top of the page was jacked for a
second till it switched back and then it
was fine. So you have something cached
in
um Cloud.
>> If you have something cached, there's
not much.
>> No, no. I mean, but if you're using
Cloudflare, you may need to go out there
and flush the cache and have it reach
your page because it was weird. Like I
said, it was very strange. Once it fix
itself, it was fine. But it the first
time I hit the page, it was very weird.
It it it was like, "Hey, it looks nice."
and all a sudden, whoop, you got this
big image of your icon of your logo,
then went back to the regular image.
>> Yeah, I think what it is is that Yeah.
Some because there because it's
a little bit behind the uh inside
baseball is basically what I do is I've
got like it's it was originally
has been forever a WordPress site and I
had a nice little theme and I like once
I started really messing with the theme,
I'm like no, I'm like I'm going to
override the theme. I'm just going to
break out of the theme. So now I've
basically I've done what I can to pull
RB back to be um so that everything runs
through now it's essentially my custom
pages, my custom theme, my
>> piece and then all I do is I use the I'm
trying to use WordPress as just a a
headless post producer and stuff like
that. Um, I'm half tempted to even yank
some of that stuff out. But there are
still ways you can get back once you're
back into like the actual WordPress
engine. Then there's some older stuff
that it's just like I'm not going to try
to like I'm trying to figure out how to
block all that so that it never goes
there. So everything comes back and it's
using even whatever image or whatever
post you're seeing and stuff like that.
So that's probably what it is is you can
get you like I just I was poking around
poking around and I was able to get back
to the old homepage. Yeah. And it's it's
not awesome. Um it doesn't still it
doesn't have rotating images anywhere.
So I'm not sure what it did, but um and
it's I I think that's the one I recently
had because it's not on Cloudflare. I
don't think Developer is, but uh RB I
yanked it off that years ago.
>> Okay. It's causing me all kinds of
issues. But good to know. I'll see if I
can find on my list. Um, if you have any
caching plugins, see if you can clear
the cache on them and have it reach
because that I had that issue with
Doctor Who. Uh, I had like the WP cache,
which was great because I didn't update
the site too often, but when they did, I
had to go clear that because it's like,
oh, I don't see your code changes. So,
anyway, I was not trying to nitpick.
It's just it was very strange how it
happened. And I'm like, I'll just point
it out because you were mentioning you
were working on I just didn't know if
you'd seen it.
>> Yeah, I need to go. That's still
something that's like now pretty low on
my uh priority is to go back and try to
figure out where anywhere that it goes
to um a WordPress article or page is to
make sure that it's got all of my
wrapped stuff. So, it's the new look and
feel. Um, I just haven't like chased all
that crap down because then it's
starting part of me is like I almost
want to just rip out the existing theme
completely and then build a custom theme
that does all this. It's just I haven't
gotten there yet. I that's actually what
I'm going to do I think with developor
is I think I'm just going to create a
custom theme and just use that and and
build it from there as opposed to um
what I've done with RB where I was
trying to sort of keep it up while I was
going because there's like I've made as
you probably noticed like if you go to
the main RB SNS page it's dramatically
different than it was um and a lot of
the stuff the links the information
that's in there all that kind of good
stuff um I've been going through and
putts with that. Um, yeah. So, cool
stuff. Good to know. And that leaves us
with I think it's time for us to dive
right in for this last potentially last
episode. We'll do a little three, two,
Oops. Let me get this up. So, I'm
looking at what I want to look at.
Uh, we do this. Let me move this over
here. Oops. I don't want you there.
Um, let me try this. If I do this and
move you here.
Dad, come. Uh, it doesn't work the same
when I've got multiple.
Let me take this and move this over
here.
There we go. Okay.
I tell you, when you got like multiple
virtual screens, it gets really confused
really fast. So all right, three, two,
hello and welcome back. We are
continuing and potentially wrapping up
yet another season with developer
building better developers. I am Rob
Broadhead, one of the founders of the
pre-mentioned developer and building
better developers. Also the founder of
RB Consulting where we are boutique
consulting. We are a fractional CIO.
Bottom line, we help businesses assess
and simplify their technology. We figure
out a way to walk through with you what
you've got and how to leverage it so
that there is a roadmap for success for
moving forward for growth for your
company. Bottom line, it really comes
back down to we assess where we're at.
Help you build a roadmap. Let's get you
to a better, brighter future.
Essentially, we do that through
simplification, integration, automation,
innovation. There's a lot of different
ways that we can utilize technology that
you can utilize technology, but also
that we can utilize it, help you do it
better. That's what we're here for. We
help you craft a specific recipe for you
custom to your business. We sit down and
we connect your business goals and where
you're at with where you want to be and
how to get you there in the best and
brightest future that you have ahead of
you. Good things and bad things. Oh,
actually, I guess I would be aiss if I
didn't mention rb-sns.com. You can check
out our website which has been we were
just talking in the pre-show about like
it has been evolving. We've been working
on it. We've been doing a lot of cool
stuff. Uh we like it. Give us feedback.
We'd love to hear how you like it. Uh
robbs.com.
Uh also check out our tool
matrix.rbs.com.
It's really a cool way for you to get
quickly to a road map of sorts. Uh it's
not quite as custom, but it's one of
those that definitely based on where
you're at can help you figure out what
your next steps are. And it's free. You
just go in there, sign up, answer a few
questions. I think it takes about 10
minutes, something like that, depending
on where you're at. It's a little bit
technical, but it will help your
business get to the brighter future or
at least give you the steps to do so.
Back into good thing, bad thing.
Good thing is uh we are wrapping up yet
another season. We are This is like It
really I can't tell you how much it is
just heartwarming. how much it is like,
you know, the endorphins and all that
cool stuff. Getting through another
season when you started way way back
episode one and you weren't sure you
were going to get through any episodes.
You weren't sure how far you were going
to go. You weren't how far this was
going to last. And the fact that we are
just like marching into now what I think
26 is going to be our next season. Uh
that's a lot of seasons. It's way beyond
what a lot of people do.
Sometimes you have to mute your mic when
you have a
sneeze or two. Apologies for that.
Uh the bad thing is that we are through
another season. Um it is it is always a
little bit of a challenge too to figure
out like what are we going to do next?
It's sort of funny that this has been a
challenge that we have now faced
multiple times like where do we go next?
What do we do? What's our next topic?
One of the things we may discuss is
actually going out to AI and saying,
"Hey, where's an area that we haven't
covered?" We've done that. We actually
got some pretty cool little uh
information back. If you check out the
YouTube channel, you'll be able to check
out part of that bonus material. But
first, I think I need my co-host to
introduce himself. Go for it. Hey
everyone, my name is Michael Malash. I'm
one of the co-founders and developer
building better developers. I'm also the
owner of Envision QA where we help
businesses take back control with their
customer with custom software that
builts around the needs uh not the other
way around. So our focus is simple,
great service, great solutions and a
rockolid quality. We build tools that
replace frustrating systems, streamline
operations, and are fully tested to work
right the first time. At Envision QA, we
combine development and quality
assurance to give you software that you
can trust and support you can count on.
Check us out at envisionqa.com.
Uh, good thing, bad thing. Uh, so good
thing, uh, I guess it's mixed, good and
bad. So, I'm another year older, another
year closer to the 50 mark. Um, not
quite there yet, almost. Um, and I'm
having to reflect on a lot of things and
update all my freaking policies and
things like that. So, you know, as you
get older, you have to worry about
things like mortgages, health insurance,
life insurance, and well, I just got
dinged by or pinged by my mortgage
broker. It's like, oh, interest rates
are going down again. You know, do you
want to refinance? And it's like, do I
uh how long do I have to retirement? it.
These are questions I don't want to ask
yet.
But anyway, um so that's kind of the
good and bad. Another year older, had a
wonderful birthday, but more crap to go
with it.
Mute.
Here's to one year older
and not realizing when you've actually
turned your little mic off. Apologies to
that. Um, yeah, I wish I was getting
closer to 50, but I'm getting closer to
150. So, that's just sort of how these
things go. But more importantly, we're
wrapping up this season. We have spent
another 30 plus episodes talking about
building better developers. This time,
we did it with AI. And what we want to
do in this uh this wrapup instead of and
we can I mean this is we'll see where
Michael wants to go but I I want to
spend a little more time like uh in a
meta retrospective a little bit of like
look at this is what we did when we came
into this was said hey
AI is a big thing right now everybody's
talking AI AI AI AI people that can't
spell AI are talking about AI I had a
conversation today and it's like with a
guy
they're in this area, they really need
AI and they've like all these people are
experts because they've done like three
things. There are very few people that
have spent more than I don't know 3 to
six months probably playing around with
AI. Most of them wrote a chatbot and
it's really about like okay great
everybody can spell it, we'll say, and
then thinks they're an expert, but let's
really talk about like how do we use it?
How do we utilize it? And during this
season and a little bit before, but
definitely during this season, I it it
really has been a journey on what does
AI provide us? Where can it help us? And
where do we need to still like make some
progress? And I would just like in this
uh I don't know this summary, this
little retrospective, just look back.
It's like it really has been um it's
been nice as being like a third host,
you know, another co-host in it that
it's really brought although it has
definitely touched on things that we
touched on which is probably for the
same kind of reasons because when you
have a certain topic in a well-known
field like this, there's there's like
there's it's a target-rich environment.
There are a lot of things that you can
talk about where you're like, "Oh, yeah,
that makes sense and that makes sense
and that makes sense and this is
probably shift mission." You know, it's
like uh when we started way way back,
there's things like we talk about the
software development life cycle, there's
certain things you're always going to
talk about with the software development
life cycle. If you talk about agile,
there's certain things you're going to
talk about. If you talk about scrum,
certain things you're going to talk
about. Software development in general,
there's like certain areas like, you
know, you're going to talk about code,
you're going to talk about databases,
you're going to talk about quality
assurance, you're all of these things.
And AI is really good about that. But
what we've seen is that it's really good
about touching on additional areas. It's
it really is. It's another set of eyes,
another set of ears to say, well, hey,
have you thought about that? And I think
that has been a a big boon going through
this season is that there have been some
areas where we didn't really connect it
and sometimes where it misunderstood,
we'll say, where it took it a little bit
different direction, but I think we got
some great uh conversations out of that.
So, I'll pause there and and get your
like, you know, initial thoughts.
>> Yeah. So, I I I I think I don't remember
which one was initially kicked off the
idea of, "Hey, let's like revisit a past
season with AI." Uh, but it became an
interesting journey. Initially, we're
like, "Oh, well, let's just see what it
can do." And, um, we'll just go with it.
And
as we went with it, it really
did a decent job of analyzing what we
talked about. In some cases, it was
completely different, but in a good way
where it's like, oh, we didn't even
think about that. And it gave us more
ideas
um to kind of expand upon past episodes.
Uh, one of the best things I can I guess
compare it to is it's like um throwing
ideas at a whiteboard, seeing what will
stick and AI was great for that based on
the way we used it. Now,
would it be great to actually flush out
the content for the full episodes? I
don't think so. I think we'd get into
that kind of false fake um or not fake
but just where it would just kind of
give us an answer but not really be an
answer uh for a lot of these solutions.
So for something a little higher level u
like summaries and outlines and things
like that I think it did a great job
this season.
>> I think so too. I think that's a really
good point is that it gives us um
yes, we can get some very good details
if we want to out of AI, but for
something like this, it's much better at
a at a high level, at a summary kind of
level. It was sort of like, hey, here's
an outline or something like that and
let us take it from there. Um there were
more than a couple times that I think it
came back with some stuff where it was
just like, huh, that's an interesting
way to go. We don't want to go there.
you know, like it would take the it
didn't have the right context of the
term or the topic or things like that.
So, it did um it could get lost, but
honestly, so can we. There are times
that we would put together a topic and
we would go in very different directions
because we were thinking different
things. So, I don't think that's a I
don't know that's necessarily a knock
against AI, but I think it is a uh a
caution against AI.
>> No, agreed. I mean, it it gives you a
good
it's good at giving you content, but
it's not necessarily good at giving you
the meat of what it is that you're
trying to convey.
>> Yeah. And I think that's this goes back
to like some of the other things I've
done with AI that are outside of the the
developer real world, which actually
we'll see some of this as we like part
of the things I'm going to be doing when
I'm revamping the website. It's
basically a lot of it is like take this
stuff, take this bucket of stuff and
reorganize it. It's like it's sometimes
it's not much different than like just
shuffle this around, but sometimes the
shuffling makes a big difference. It's
just like AB testing where you're like,
well, what if I put the button at the
top versus the bottom versus the left or
the right or things like that. Um,
that's some of what it is. It's
basically like say okay let's take this
and let's take honestly in some cases um
you know like best practices or
standards or things like that and let's
like apply that to this thing so that we
can get something done
um that
maintains the meat of it but also
dresses it up a little bit. And it's it
is sort of a um gosh it's so it's really
at the end of the day the things that
work best are the ones that are
processoriented are the things that are
like there's always a series of steps
that you want to get through. Um I will
share which is there's a lot more to go
into it but I will share that like one
of the things we've done that I found
has been really good is using it as a um
an advisor of sorts. like we we wanted
to plan trips and would throw questions
at it and it would be able to go like
gather a lot of information and say well
particularly in cases where you're
trying to figure out like you're going
into new areas of research. Uh it is a
great way to very quickly figure out
that like this is a good path or this
isn't a good path. Um, I've used it a
lot since we've started into this, I
think, since this season of things like
saying like if I want to build an app
from scratch
in this realm and this is sort of the
target audience and this is what I want
it to look like, what are the best
technologies for it? And it will give me
stuff like, well, here's here's an
example. here's the the popular
technology or here's the technology
that's going to take more time to learn
but it's actually going to be a better
long term. Uh those things are, you
know, it can get you there, but it
really does come down to it's people
talk about like I had a chat with chat
GPT. It really is, I think, uh where you
need to go is it has to be about
a chat. It has to be about you learning
how to use AI as much as AI giving you
that information.
>> Yeah. I mean, for those of us that have
been around for a while, it goes back to
like the old uh dictation software,
Dragon, Naturally Speak, you have to
spend time
teaching the tool that you're using how
to interact with you. You're not just
learning the tool, but the tool is
learning how to interact with you, how
to understand your sentence structure,
your grammar, uh your reflections. A lot
of times, it's interesting because when
I first started with Chat GPT, I'm a bad
speller.
It would more or less at early on just
correct my spelling and say, "Did you
mean this?"
Now it takes almost anything I throw at
it and it returns some type of message.
Now it may not be the correct response
but it is a response based on the
history of the interactions with the
tool. So if I were to log in anonymously
through chat GPT. So this is a good test
for those of you that have a chat GPT
account.
If you use chat GPT all the time, log
out, clear your browser cache or go
incognito, log into chat GPT or don't
log into chat GPT, but just go to chat
GPT and start using it. You're going to
get different responses and different
interactions. You're going to find that
either it's going to send you down a
different path or it's not going to give
you that kind of personal experience
that you're used to from being logged
in. So, these are just some of the
things to be cautious of as you continue
to learn and grow with the tools. It
takes time and you need to question it.
Even if you're just starting out, heck,
I would ask it almost uh when once I
started like building projects like Rob
was just talking about like with code, I
start out with, okay, I want to build a
web page. So, give me a web page. I'm
like, is this the best way to build the
web page? Yeah. Okay. Well, all right.
maybe we'll do this. And I'm like, all
right. And then it would prompt me,
well, who's the web page for? So, if you
are asking the right prompt, it will
prompt you back if it's not getting what
it needs. Uh, now with 50, I'm not sure
if it still does that. I would have to
go back and retest that, but I would
probably have to retest it in cognito
because I've already gone through that
learning process with Chat GPT. So,
as you're learning the tool, the tool is
learning you. And it just takes time. Be
patient with it, but definitely spend
time with it and work through it. If you
question it, Google it and call it out
if it's wrong.
And I think that's
that's really I think the context is so
critical. Um, and it it goes back to it
reminds me of Google food ability
people's ability to write searches in
Google to like get useful information
back and it AI is so much like that is
it really is and I I was thinking about
this today as I was like I was having a
chat with chat GPT and I was actually
getting it to do some work for me and I
knew I knew I knew I knew I was like I
really am gonna I like it was one of
these that I asked asked it to do
something and then I had to ask it for
something else and I wanted to go back
to the not the prior but two prior and I
was like if I don't ask this right it's
going to go to one prior and not two
prior and sure enough it did and it's
really is it's like it's
I like sometimes I like joke that it's
like talking with the child that like
has a very short attention span that you
have to like make sure you're very clear
on what you provide. I do think as
Michael's mentioned like the folders and
stuff like that, there are some things
that it does allow it now to do a better
job of keeping context, but
so often uh it still will like wander
off. And so it's things where I have to
and it's where it actually does become
worth it to have like the paid version.
So you can have a bigger question where
you can say, "Okay, based on this, I
want you to do this and make it look
like that." And it's like sometimes
that's a decent amount of stuff that you
need to work with. The cool thing in
building a better developer and then I'm
going to let you jump in on this is that
the best way to get that kind of
information is be dealing with small
chunks. And this goes back to something
we have often said is like try to break
your problem that you're solving down
into small chunks that are very easy
then to work with and maintain. And this
will also help you immensely when you
get into AI. You had a thought so I want
you to jump back.
>> I did. Um, so you you made a comment
that when working with check GPT, if
you're like two or three uh chats down
and you need to go back and it doesn't
go back to the right one, a small tip I
found with this is if you go copy the
selection you want to go back to,
repaste it, but start out with reset the
conversation to this uh chat, paste your
chat in. Sometimes it will reset
everything to where you need to be and
then you can continue your thread from
there. Um, I found that to be more
successful than just assuming it knows
where to go back to. That's I actually
had a conversation with a guy u not too
long ago that's a AI maven or whatever
but that was some that was one of the
things that he we talked about in our
conversation is how it's it has a very
limited memory and so there it's very
easy five or six requests we'll say into
it to suddenly lose stuff and it just
like it's sort of reset and he said that
was something that was he was struggling
with as he was building out longer term
conversations in that is to be able to
do it. And I think that's honestly, and
this is like a little pro tip or
whatever because this is something I've
been working with. Um, I think there's a
point where what you need to do is if
you're building like chat bots and stuff
like that for longer term conversations
is to have ways to actually freeze and
update the context. is very much this is
very a very much a Python thing but uh
very much when in Python where you if
you use pip if you use their library and
there's other things are like this but
there's a way to like say freeze like
use what I have right now give me a
script so that in the future I can go
back and then just and this is called
requirements basically but I can use
those requirements and I can suck all
those in and say I want exactly this
environment I want these libraries these
versions that the kind that is literally
the kind of stuff that we need with AI.
And if you're building something that is
an evolving AI,
I think you need to do that. But you
because AI has a it has a crap memory.
It's worse than mine. And so what you
need to do is you need to be able to do
something where if you really are
building this isn't like the chat tools.
If you're building a chat tool, you're
going to need to be able to do a
feedback loop into that to say, "Okay,
now we have knowledge that we want to
like maintain and we want to push that
back into the AI so that now the AI is
keeping that as part of it. It's like
this is what I know." It's just like if
you go to like notebook LM where it's
like load these documents in. It's like
well I need to have those documents
there. Those are the thing. It's like
marking knowledge that is key knowledge.
And honestly, it's funny because Michael
and I have had conversations in business
stuff outside of developer in recent
days, weeks, months where there are
things like that that I I realize I
recognize now that is very much a part
of the human conversation as well.
You'll be like, "Hey, this is a a
watershed moment or a milestone or
something a marker that we want to say
we have agreed on this. This is what
requirements documents are all about
really. We've agreed on this
and so this is what we're going to use
as our foundation moving forward. It's
literally no different when you're
dealing with AI other than AI is a
little more obnoxious than I know a lot
of obnoxious people. I'm not even going
to say it's more obnoxious than people.
But I think that's what we we didn't
embrace in this season is that we didn't
feed back into it. every time we asked
it about a a season about a topic for
and give us a couple of things to talk
about, we didn't actually give it
feedback on it. So that is I think why
we found over and over again we got
roughly the same response. It got I mean
we we asked a question a little bit
differently but generally speaking we
got the same response because we're
asking the same thing over and over.
>> Yeah. Uh so one of the things
as you went through that that kept
coming to my mind is
there are some tips and tricks you can
do with AI and this may be
more application desktop application
version of AI versus web but I have
found as I go through the process of
working with AI and resetting AI if it
gives me a response there is that little
check box that you can check under the
message. Hey, this is right. But what I
have found to be more useful is if it
gives me, hey, this is like exactly what
I want. I respond, save this into
memory. This is a good response.
And for those that are not, I say, okay,
this was a poor response.
Reject this, but do not follow this
path. And if I do that, I get better
results in the long run. But if I don't
do that and I just let it keep
regurgitating stuff,
you take kind of that long way to get
there. Like it it it takes longer to get
to the solution than where you tell
literally tell, hey, bad bad bad go
back. Here's a cookie. That's right.
Here's a cookie. That's good. But
>> I have to interrupt because this is you
and I have this conversation. I'm like,
"Okay, time out. Stop right there. Let's
Let's I don't say snapshot, but it's
basically, "Let's snapshot that. Can we
agree?" And we can move on. I know I've
done that with you. I've done that with
a lot of people. I will say because she
probably won't hear this. My wife gets
really annoyed when I do that sometimes
because I will cut her off in the middle
of a sentence and be like, "Stop right
there. That's a point. Let's move on
from there." But that is a I'm going to
let you go because that is really a very
important insight into how you find ways
to move AI forward instead of get into
those like loops or let it spin off into
space.
>> Exactly. And worst case scenario, if you
find yourself five or six messages into
a thread, even after trying to get it
corrected, stop. Create a new chat.
Delete. Do not archive. Delete the old
chat. Say before you delete it, say this
was a bad message thread. Delete it from
memory. Then delete it. Start a new
thread. Nine out of 10 times I find that
the new thread starts in a different
path. Usually closer to what I want and
it gets me there quicker.
These are not things that happen
overnight. Uh, a lot of times I can now
jump on the chat GPT probably within
about 5 10 minutes I get enough of what
I need from it to go do what I'm trying
to do or I get enough of a correction to
like a document, an email or something
that I can just jump in and go take it
from there and move on.
I use track GPT now more days as a good
virtual assistant and a quick
boilerplate like code generator like
here just throw this out here and I can
go from there.
Sometimes it works well for more complex
things
but I'm still struggling with most of
the chat bots to get something that will
build me an enterprise solution. And I I
only want to touch on this one other
thing cuz I read an article on this just
recently. It seems like more Seale
Fortune 500 companies are actually now
starting to shift away from AI a little
bit because they're finding that it's
costing more to get to that chatbot
level of maybe this is right to
something that is actually going to help
the customer.
And that's honestly that's the wave
we've seen in technology from forever is
it's like everybody like oh this is now
finally the silver bullet. This is the
thing that's going to solve all our
problems and then everybody throws a lot
of money at it and the next thing we
know it's like oh no it's not solving
our problems. I'm just going to say if
it's just throwing a lot of money at it
you're not you're not paying attention.
Throwing a lot of money is not it.
You've got to be there has to be wisdom
in that. You can throw good money after
bad all day long. Uh AI is no different
from all of the other silver bullets
that we've seen all the way back to like
I when I started out it was things like
UIs and object-oriented and things like
that actually AI I did a class I was
just talking again guya today I had a
class 35 years ago on AI it was
basically expert systems in artificial
intelligence and how to do that
way and things have evolved um massively
since then. But the interesting thing is
which is actually a really cool little
observation. This guy came out of the
gaming environ the gaming world and he
had dealt with a lot of stuff there.
There is a lot of AI built into games,
the gaming world of stuff. Like think
about it like if you're sitting there
and you're fighting. Now granted the the
MMO RPGs and stuff, all the massive
online stuff, it's just other people.
But when you're dealing with stuff and
there is a intelligence in the
application that is your opponent.
Uh a lot of times we know we've seen it
like you pick all of your games like the
Dark Souls series of stuff. There's
there's uh patterns that they do. The
things that they struggle with usually
is patterns with some sort of randomness
to it or things like that. But that's
honestly what we know. If you really
look at it, if you look at a a fighter,
if you look at uh a football team, if
you look at um I'm trying like a fencer
or things like there's certain moves u
the tai chi the uh
uh ultimate fighter and stuff like that.
Wrestlers, there are there's moves that
they use. There's certain things that
they do. If you look at dancers, you can
look at across the line of what humans
do. There are patterns of what we do.
The things that are different for those
that are the best is that we add
randomness to it. Is that we try not to
be predictable enough so that our our
opponent doesn't know which path or
which sequence we're taking at any given
moment.
That's not that much different from what
AI provides. What we're trying to do, of
course, is we want AI to be consistent.
However,
the bonus is that like AI is not
consistent partially because it doesn't
have the same set of information each
time we ask that question. Now,
sometimes we'll ask the same question
and it's close enough, but it's still
going to be like there's uh I think
there's percentages and stuff like that
behind the scenes, not getting too deep
into the eye and like and I'm trying to
simplify it for like not getting into
the deep of the deepness of what this
is, but honestly, at the bottom line, it
it does work down to like you're rolling
the dice. You're throwing a you're
asking a question. and you're rolling
dice and says, "What things am I going
to like most use to uh color my opinion
on this?" And we've seen that. We've
seen this in this season where we've
asked effectively the same question.
We've gotten slightly different results,
slightly different approach, and it's
based on time of day or whatever else is
going on. So, I think that's very key
for us to take. I think that's a a very
key takeaway is
AI is literally like another person is
like throwing out there I think if you
look at it that way but like saying hey
um and Michael mentioned u using as a
virtual assistant I really think before
like god this is such a rabbit trail I
could go down I really see uh AI as
replacing the VA I see so many things
that I do right now that I'm like I can
throw that to AI I AI I'll do that and I
could honestly this is your automation
stuff is like I could build a bot that
does that stuff for me and I talk to
people that are like yeah the the people
that are technical that are trying to
leverage AI that are not just throwing
random stuff at it say yeah I can spend
a little bit of time and I can build
some sort of an AI solution that gives
me this report this dashboard this look
this overview this summary this outline
things that are like all they do is just
get us to the solution a little bit
faster.
>> And I'm going to throw something to you
before I like get to the end of this of
this episode faster.
>> Yeah. So, the last thing I want to touch
on, so
as you were talking, spoilers for those
that have not seen Superman, the new
Superman,
the scene with Lex Luthther
where he's literally throwing out
numbers. He's basically controlling the
Ultra Man character in the movie through
the fight. So, it's a real time person
interacting with another person for a
battle. A lot of the best AI tools that
are out there are still the best
procedurally written applications.
Basically, if then do this, if then do
this. It's building upon a procedural
logic. It is not AI. It is a rules-based
engine that is driving
where your application is going and the
interaction with your customers.
I have seen more often than not,
especially with testing tools and since
Rob's been publishing all his
applications, I am probably going to get
mine out there again soon. I wrote a
testing application 10 years ago, a
testing framework. It needs to be
updated a little bit, but speaking of
legacy, I spun it up the other day, ran
it against a website, and it worked. So
the short
answer is
procedurally driven applications is
essentially the current form of AI. You
have to ask certain questions in a
certain way and AI is essentially
building you a procedural response to
those answers to give you a solution
based on your input.
everything I see for uh what is it uh
SAP and all these uh marketing tools and
uh business tracking tools, they are
literally just freaking integration
systems that are basically procedurally
driven based on rules, not necessarily
AI where based on customer rules, we're
going to give you this generated code or
this generated report. Yes, it's AIish,
but it's still procedural. It is not
really thinking outside the box. It's
thinking within this rule engine to
generate these responses, these reports,
these applications. So, be very careful
relying on AI as the be all end all
answer to your problems.
>> And that's I guess that's the bottom
line. It's just like it is it's an
adviser like anything else. It is not
going to always be correct. Um, it is
there. It is wrong at times. It makes
mistakes and things like that. Just get
used to that. But that doesn't mean that
it's not helpful. It's just like
everything else. It's like everybody
else you talk to, there's going to be
value in what they say and there's going
to be some stuff that is not very
valuable in what they say. There's a lot
of value in shooting us an email at
[email protected]
because we will use that. We will like
build that into this thing. you will
find the option, the opportunity to say
something to us and actually impact
season topics, episodes, uh stuff that
we do, if we do blog episodes, I mean
maybe even training and stuff like that
we do. There's a lot that you can do. If
you look back, we've done a lot over the
years. You go back especially to like
some of our mentor classes and some of
things those are all out on the YouTube
developer channel uh do YouTube.com
developer channel. um you'll find a lot
of stuff where there were discussions
that we had that ended up becoming uh
entire products and things like that. So
uh feedback is awesome. You can leave us
feedback wherever you listen to
podcasts. You can check us out on
YouTube. You can check us out at X. Uh
we are developer Facebook. There's a
developer page uh Facebook page. You can
leave us comments anywhere on the
developer.com site which is going to be
in the months ahead uh updating and
enhancing and we're going to do some
cool new stuff. Uh I I assume cool.
We'll see how cool it is when I get to
that. But I will just say I was very
happy with some of the things we changes
we made on the RB consulting site. I
very much expect to bring some of that
stuff forward and do even more on the
developer site plus some other side
projects I've got going that will sort
of feed into be like a little feedback
loop for these kinds of things. So, uh,
we're not done. We're not just giving
you content. We're going to find better
ways to bring you content and bring you,
uh, the stuff that you need, but it also
helps to give us feedback so that we
can, you know, know what we've done
correctly and where we need to do it
better. That being said, I just want to
say once again, as we are probably
wrapping up this season, I'm guessing
that our next episode, we will just dive
right into whatever our new ep or new
season is, which in recent seasons is
sort of what we do is we're like, I
don't know. We'll figure it out when we
get there. And uh it's turned out pretty
cool so far. We've gotten a lot of
stuff. We've learned a lot. Hopefully
shared a lot that has been valuable to
you. Appreciate you so much and the time
that you've given us. As always, go out
there and have yourself a great day, a
great way, great week, and we will come
back to you next time with season 26.
Oh my gosh, this is just insane. Have a
good one, folks. Talk to you later.
Oops, I didn't want to do that. bonus
material.
>> Well, do we need bonus for this one?
Because this was the end.
>> I don't know that we do. I think we like
we we talked a little bit beforehand.
So, I think we're in pretty good shape.
So, we can sort of wrap this one up. We
can go on to
>> our lives. Uh we will come back. Uh you
and I can discuss or maybe we'll discuss
at the start of the next episode what
that season's going to be. Um I will
I've got this stuff off in a folder so
we can take a look at it. Um
>> enabled screen reader.
>> Wow, somebody hit a screen reader
somewhere. Was that me?
>> No, I hit I really do not like this new
OS.
I hit a button, all of a sudden things
started popping up and uh
>> I hate when that happens.
>> The update it. This liquid glass thing
is weird.
>> It's going to take some getting used to.
Uh let's see. Oh, I'm sorry. I'm like my
This is why I put do not disturb. Stuff
starts popping up popping up on my
screen. So, it's like, "Dad, damn it." I
hate when that happens. Well,
>> that's what happened. Mine just ended.
So, things started popping up.
>> That's exactly what I'm getting. I'm
getting like all this stuff. It's like,
I don't need all of that. H. All right.
That being said, thank you all you guys
for yet another season. It
I cannot appreciate. It's like share
enough of my appreciation. Literally, if
you guys ever need any help, if there's
anything that we can do, if there's any
way we can help you, check us out. Uh,
shoot me an email [email protected].
Shoot me an email, robb-sns.com.
Uh, go out to the the matrix.rb-sns.com.
Feel free to check that out. It is it is
free. All it is is an email. We'll just
send you emails to say, hey, how you
doing? You can uh, you know, always just
say, I don't want to be a part of this
mailing list. You can jump back out.
It's it's literally free. And hopefully
it's helpful to you. I would love
feedback on all that. love feedback on
anything we have done because we are
going into a season. We're getting
towards the end of the year right now
going into the fourth quarter. By now
you probably know that fourth quarter is
when I really start like evaluating the
year behind and looking at what I want
to do in the year ahead. That is one of
the things that we do. It's one of the
things that I do personally.
I would love feedback of any sort,
suggestions, recommendations, all that
kind of stuff because this is going to
help us really do more for you in the
year ahead. Uh, we appreciate you much.
We want to do the most that we can for
you. Thank you. I'm going to let you
have the rest of your time off. Go have
yourself a good one and we will see you
next season.
[Music]
Transcript Segments
1.35

[Music]

27.439

All right, I'm not even going to go to

29.119

AI for this last for our summary.

33.68

We're going to dive right into it and

35.44

just

37.12

riff a little bit about like what did we

38.879

what did we learn? uh what did we get

40.96

out of this season with AI? Probably

43.28

some like, you know, pros and cons and

45.36

things like that and be a little more

48.96

um probably conversational and things

51.28

like that, but I think it'll be

52.559

something that'll be hopefully it'll be

53.92

a good um

56.399

you know, have us give us give us an

58.079

excuse to sort of think back about like

59.6

what we've gotten out of AI and maybe

61.44

even talk a little bit about AI in

64.32

general. So that's my thoughts.

67.36

>> I like it. Um, we really only use chat

70.799

tpt and co-pilot, right? We didn't

72.799

really touch on or was it?

74.4

>> No, we used uh Gemini.

76.32

>> Okay.

77.2

>> We used that like a couple of times

79.36

mostly just to try it out. We did bounce

81.439

between chat GPT five and four. Um, I

85.759

don't know how often I actually

87.52

specified which was which because I

89.2

wasn't even sure sometimes because it

90.56

was using like best u whatever's the you

93.759

know most effective engine at the time.

95.759

I just keep it sort of left. I keep it

97.36

open and just do that kind of stuff. So,

100.479

um

101.92

>> yeah, I've had to play around with five

103.439

lately because I've been getting some

105.52

weird answers on the general one. Um

109.36

I've gone to like the thinking one and

112.56

it will actually give me a better

113.92

answer. Like it takes more time, but I

117.84

I'm not liking five. And I tried to go

119.68

back to 40 and 40 is now um you can use

124.64

it. It's limited. So, you can only use

126.399

40 a little bit unless you pay for the

129.2

professional version. And I'm like, "Oh,

130.879

that's crap." Because,

132.239

>> yeah, I went to the pro because I was

133.84

just using it so much. And I use the

135.36

thinking version a lot because I'm

136.959

usually doing it to say like a lot of

139.2

I've been doing a lot of it to

142.239

like migrate code and also to do like

145.68

design things and stuff like that where

147.2

I'll be like especially like that. Like

148.8

I said, the RB site, I got a lot of

150.4

stuff out of that where I'd be like,

151.44

take this

153.599

add these things to it, move this

155.04

around, do that thing. It's all the

156.4

stuff that like it's it's a little slow,

159.68

you know, it takes a couple, you know,

160.959

minute to think about it or whatever,

162.319

but it's so much faster than me like

164

going through and like, okay, can I

165.28

tweak this? Got to tweak this, got to

166.48

move that, got to move that. It's like

167.599

all those little things, it gets me

169.519

there faster. And so I'm like, yeah,

171.68

because and it's stuff that I'm like, I

173.2

have no desire to learn how to like

175.36

totally figure out this, you know, how

177.599

to do this in Bootstrap or how to do

179.2

that in Tailwind. And so it's been

181.519

>> really cool. It's allowed me to do

182.959

updates to interfaces really fast. It's

185.04

allowed me to even do some uh some

186.959

coding, some like swagger stuff and

189.28

things like that. It's like here, this

190.48

API, go in and just like give me a

193.28

better set of comments and stuff like

195.12

that. Now I've got more to work with. I

197.2

can go in, tweak it, boom, done. So

200.319

speed,

200.72

>> that's a lot of what I use it for. Um I

204.239

know you get on me sometimes because

205.44

you're like, "Oh, that's very AIish."

206.959

But sometimes when you're just dealing

208.48

with boilerplate stuff or you just need

210.239

a quick, hey, just give me a quick strut

213.04

or, you know, foundation for the

214.959

project. I'd rather do that and spend my

217.519

time working on the actual code and

218.959

yeah, I'll come back and tweak it later,

220.159

but if it works, it works. It's that

221.68

8020 thing. It's like, is it working?

224.159

Yeah. Okay, move on. Um

226.4

>> it is. It's just sometimes the code it

228.159

generates is oh my gosh. So like

231.12

>> and I do sometimes I get it but

234.159

sometimes it's speed. It's like

236.64

>> when when you're it depends where you

238.64

are in the project. If you're at the

240

point where results matter more than

243.68

quality you kind of got it's one of

246

those trade-offs. It it's a balance you

248.319

got to juggle. But um just teeny nitpick

254.4

and then we can jump in. Um, check your

259.28

um, what is it? Above the fold uh, your

263.199

image scroller on RB. One of your images

265.759

is jacking up your whole page. Like when

267.68

it scrolls it, the page is messed up

270.96

till it scrolls again. Um,

273.04

>> the RB site.

274.16

>> Yeah,

274.88

>> there aren't any. I don't think there's

276.639

any.

277.04

>> It may be on the blog because when I did

279.12

like the RB, it took me to the blog

281.28

page.

283.6

is it whatever page you have that has

286.639

like images that scroll the page got

288.96

jacked up from it and then it fixed

290.56

itself but it was weird.

293.6

>> Um that's interesting because there

295.52

shouldn't be thing left.

300.4

>> It might have been something cached but

302.24

I went to rbsns.com rblog. It does a

306.32

little shake and then it did like a

309.28

shift to an a new image and then the

312.96

whole top of the page was jacked for a

314.8

second till it switched back and then it

316.32

was fine. So you have something cached

320

in

321.84

um Cloud.

323.039

>> If you have something cached, there's

324.16

not much.

325.039

>> No, no. I mean, but if you're using

326.639

Cloudflare, you may need to go out there

328.56

and flush the cache and have it reach

330.56

your page because it was weird. Like I

333.44

said, it was very strange. Once it fix

336.16

itself, it was fine. But it the first

339.12

time I hit the page, it was very weird.

341.12

It it it was like, "Hey, it looks nice."

343.199

and all a sudden, whoop, you got this

344.4

big image of your icon of your logo,

347.12

then went back to the regular image.

349.759

>> Yeah, I think what it is is that Yeah.

351.759

Some because there because it's

354.8

a little bit behind the uh inside

357.36

baseball is basically what I do is I've

359.12

got like it's it was originally

361.84

has been forever a WordPress site and I

364.16

had a nice little theme and I like once

366.16

I started really messing with the theme,

369.12

I'm like no, I'm like I'm going to

371.12

override the theme. I'm just going to

372.56

break out of the theme. So now I've

374

basically I've done what I can to pull

377.199

RB back to be um so that everything runs

381.039

through now it's essentially my custom

383.039

pages, my custom theme, my

385.52

>> piece and then all I do is I use the I'm

387.52

trying to use WordPress as just a a

389.759

headless post producer and stuff like

392.88

that. Um, I'm half tempted to even yank

395.52

some of that stuff out. But there are

397.36

still ways you can get back once you're

399.039

back into like the actual WordPress

401.199

engine. Then there's some older stuff

403.039

that it's just like I'm not going to try

404.56

to like I'm trying to figure out how to

406.16

block all that so that it never goes

407.919

there. So everything comes back and it's

409.52

using even whatever image or whatever

412.4

post you're seeing and stuff like that.

413.84

So that's probably what it is is you can

415.68

get you like I just I was poking around

418

poking around and I was able to get back

419.52

to the old homepage. Yeah. And it's it's

422.319

not awesome. Um it doesn't still it

426.16

doesn't have rotating images anywhere.

428.72

So I'm not sure what it did, but um and

431.84

it's I I think that's the one I recently

433.84

had because it's not on Cloudflare. I

435.68

don't think Developer is, but uh RB I

438.16

yanked it off that years ago.

439.919

>> Okay. It's causing me all kinds of

441.44

issues. But good to know. I'll see if I

443.759

can find on my list. Um, if you have any

447.68

caching plugins, see if you can clear

449.759

the cache on them and have it reach

452

because that I had that issue with

454.479

Doctor Who. Uh, I had like the WP cache,

458.319

which was great because I didn't update

460.16

the site too often, but when they did, I

462.88

had to go clear that because it's like,

464.8

oh, I don't see your code changes. So,

468.319

anyway, I was not trying to nitpick.

470.319

It's just it was very strange how it

472.16

happened. And I'm like, I'll just point

474.8

it out because you were mentioning you

475.919

were working on I just didn't know if

477.199

you'd seen it.

478.319

>> Yeah, I need to go. That's still

479.68

something that's like now pretty low on

481.44

my uh priority is to go back and try to

484.16

figure out where anywhere that it goes

486.96

to um a WordPress article or page is to

491.039

make sure that it's got all of my

492.639

wrapped stuff. So, it's the new look and

495.039

feel. Um, I just haven't like chased all

497.52

that crap down because then it's

498.639

starting part of me is like I almost

500.319

want to just rip out the existing theme

502.16

completely and then build a custom theme

505.039

that does all this. It's just I haven't

506.56

gotten there yet. I that's actually what

508.24

I'm going to do I think with developor

510.08

is I think I'm just going to create a

511.599

custom theme and just use that and and

514.56

build it from there as opposed to um

517.519

what I've done with RB where I was

519.279

trying to sort of keep it up while I was

520.8

going because there's like I've made as

523.279

you probably noticed like if you go to

524.64

the main RB SNS page it's dramatically

528

different than it was um and a lot of

530.56

the stuff the links the information

532.16

that's in there all that kind of good

534.24

stuff um I've been going through and

537.12

putts with that. Um, yeah. So, cool

540.64

stuff. Good to know. And that leaves us

543.12

with I think it's time for us to dive

544.88

right in for this last potentially last

549.12

episode. We'll do a little three, two,

552.48

Oops. Let me get this up. So, I'm

554.08

looking at what I want to look at.

558.32

Uh, we do this. Let me move this over

560.399

here. Oops. I don't want you there.

563.519

Um, let me try this. If I do this and

566.32

move you here.

568.24

Dad, come. Uh, it doesn't work the same

570.16

when I've got multiple.

572.32

Let me take this and move this over

574

here.

586

There we go. Okay.

588.48

I tell you, when you got like multiple

590.88

virtual screens, it gets really confused

593.12

really fast. So all right, three, two,

597.12

hello and welcome back. We are

599.519

continuing and potentially wrapping up

602.32

yet another season with developer

604.48

building better developers. I am Rob

607.12

Broadhead, one of the founders of the

609.04

pre-mentioned developer and building

611.44

better developers. Also the founder of

613.68

RB Consulting where we are boutique

616

consulting. We are a fractional CIO.

618.399

Bottom line, we help businesses assess

620.959

and simplify their technology. We figure

622.88

out a way to walk through with you what

626.24

you've got and how to leverage it so

628.399

that there is a roadmap for success for

630.56

moving forward for growth for your

632.16

company. Bottom line, it really comes

634.079

back down to we assess where we're at.

636.48

Help you build a roadmap. Let's get you

638.16

to a better, brighter future.

640.56

Essentially, we do that through

642

simplification, integration, automation,

644.16

innovation. There's a lot of different

646.32

ways that we can utilize technology that

648.48

you can utilize technology, but also

650.24

that we can utilize it, help you do it

652.399

better. That's what we're here for. We

654.64

help you craft a specific recipe for you

656.959

custom to your business. We sit down and

659.839

we connect your business goals and where

662.16

you're at with where you want to be and

664.56

how to get you there in the best and

666.56

brightest future that you have ahead of

668.32

you. Good things and bad things. Oh,

670.399

actually, I guess I would be aiss if I

672.48

didn't mention rb-sns.com. You can check

674.72

out our website which has been we were

676.399

just talking in the pre-show about like

678.079

it has been evolving. We've been working

679.44

on it. We've been doing a lot of cool

680.8

stuff. Uh we like it. Give us feedback.

683.36

We'd love to hear how you like it. Uh

685.12

robbs.com.

687.519

Uh also check out our tool

689.12

matrix.rbs.com.

691.12

It's really a cool way for you to get

692.72

quickly to a road map of sorts. Uh it's

696.079

not quite as custom, but it's one of

697.68

those that definitely based on where

699.68

you're at can help you figure out what

701.279

your next steps are. And it's free. You

702.8

just go in there, sign up, answer a few

705.839

questions. I think it takes about 10

707.2

minutes, something like that, depending

708.24

on where you're at. It's a little bit

709.68

technical, but it will help your

710.959

business get to the brighter future or

713.36

at least give you the steps to do so.

715.36

Back into good thing, bad thing.

718.56

Good thing is uh we are wrapping up yet

721.76

another season. We are This is like It

724.8

really I can't tell you how much it is

726.959

just heartwarming. how much it is like,

729.519

you know, the endorphins and all that

731.839

cool stuff. Getting through another

733.6

season when you started way way back

736.399

episode one and you weren't sure you

737.76

were going to get through any episodes.

739.12

You weren't sure how far you were going

740.16

to go. You weren't how far this was

741.6

going to last. And the fact that we are

743.36

just like marching into now what I think

745.44

26 is going to be our next season. Uh

748.8

that's a lot of seasons. It's way beyond

750.8

what a lot of people do.

755.68

Sometimes you have to mute your mic when

757.279

you have a

760.48

sneeze or two. Apologies for that.

763.68

Uh the bad thing is that we are through

766.24

another season. Um it is it is always a

769.279

little bit of a challenge too to figure

770.399

out like what are we going to do next?

771.839

It's sort of funny that this has been a

773.76

challenge that we have now faced

775.76

multiple times like where do we go next?

778

What do we do? What's our next topic?

780.8

One of the things we may discuss is

782.56

actually going out to AI and saying,

784.16

"Hey, where's an area that we haven't

785.76

covered?" We've done that. We actually

787.68

got some pretty cool little uh

789.44

information back. If you check out the

790.959

YouTube channel, you'll be able to check

792.48

out part of that bonus material. But

794.959

first, I think I need my co-host to

797.68

introduce himself. Go for it. Hey

799.44

everyone, my name is Michael Malash. I'm

801.12

one of the co-founders and developer

802.72

building better developers. I'm also the

804.72

owner of Envision QA where we help

806.72

businesses take back control with their

808.639

customer with custom software that

810.88

builts around the needs uh not the other

814.16

way around. So our focus is simple,

816.48

great service, great solutions and a

818.399

rockolid quality. We build tools that

820.72

replace frustrating systems, streamline

823.279

operations, and are fully tested to work

825.44

right the first time. At Envision QA, we

828.079

combine development and quality

829.44

assurance to give you software that you

831.279

can trust and support you can count on.

833.6

Check us out at envisionqa.com.

836.399

Uh, good thing, bad thing. Uh, so good

838.88

thing, uh, I guess it's mixed, good and

842.24

bad. So, I'm another year older, another

844.48

year closer to the 50 mark. Um, not

847.68

quite there yet, almost. Um, and I'm

851.44

having to reflect on a lot of things and

853.6

update all my freaking policies and

856.56

things like that. So, you know, as you

858.72

get older, you have to worry about

860

things like mortgages, health insurance,

862.959

life insurance, and well, I just got

866

dinged by or pinged by my mortgage

868.88

broker. It's like, oh, interest rates

870.24

are going down again. You know, do you

871.76

want to refinance? And it's like, do I

874.72

uh how long do I have to retirement? it.

877.519

These are questions I don't want to ask

879.44

yet.

880.959

But anyway, um so that's kind of the

883.519

good and bad. Another year older, had a

886.24

wonderful birthday, but more crap to go

888.72

with it.

898.88

Mute.

901.44

Here's to one year older

904.079

and not realizing when you've actually

906.56

turned your little mic off. Apologies to

908.8

that. Um, yeah, I wish I was getting

911.199

closer to 50, but I'm getting closer to

913.12

150. So, that's just sort of how these

914.72

things go. But more importantly, we're

919.6

wrapping up this season. We have spent

923.519

another 30 plus episodes talking about

926.48

building better developers. This time,

927.92

we did it with AI. And what we want to

929.839

do in this uh this wrapup instead of and

933.12

we can I mean this is we'll see where

934.88

Michael wants to go but I I want to

936.56

spend a little more time like uh in a

939.44

meta retrospective a little bit of like

941.6

look at this is what we did when we came

943.839

into this was said hey

946.88

AI is a big thing right now everybody's

948.88

talking AI AI AI AI people that can't

951.6

spell AI are talking about AI I had a

955.12

conversation today and it's like with a

957.36

guy

958.8

they're in this area, they really need

960.32

AI and they've like all these people are

962.24

experts because they've done like three

964.24

things. There are very few people that

966

have spent more than I don't know 3 to

968.079

six months probably playing around with

969.519

AI. Most of them wrote a chatbot and

972.32

it's really about like okay great

975.12

everybody can spell it, we'll say, and

978.16

then thinks they're an expert, but let's

979.519

really talk about like how do we use it?

981.279

How do we utilize it? And during this

984.959

season and a little bit before, but

988.72

definitely during this season, I it it

990.8

really has been a journey on what does

995.04

AI provide us? Where can it help us? And

998.399

where do we need to still like make some

1000.88

progress? And I would just like in this

1004

uh I don't know this summary, this

1005.44

little retrospective, just look back.

1006.88

It's like it really has been um it's

1010.48

been nice as being like a third host,

1013.519

you know, another co-host in it that

1015.279

it's really brought although it has

1018.079

definitely touched on things that we

1019.519

touched on which is probably for the

1021.759

same kind of reasons because when you

1023.12

have a certain topic in a well-known

1025.76

field like this, there's there's like

1028.319

there's it's a target-rich environment.

1030.079

There are a lot of things that you can

1031.36

talk about where you're like, "Oh, yeah,

1032.64

that makes sense and that makes sense

1033.76

and that makes sense and this is

1034.88

probably shift mission." You know, it's

1036.88

like uh when we started way way back,

1039.52

there's things like we talk about the

1040.959

software development life cycle, there's

1042.48

certain things you're always going to

1043.6

talk about with the software development

1045.039

life cycle. If you talk about agile,

1047.12

there's certain things you're going to

1048.079

talk about. If you talk about scrum,

1049.52

certain things you're going to talk

1050.4

about. Software development in general,

1052.48

there's like certain areas like, you

1053.52

know, you're going to talk about code,

1054.64

you're going to talk about databases,

1055.76

you're going to talk about quality

1056.64

assurance, you're all of these things.

1059.52

And AI is really good about that. But

1061.44

what we've seen is that it's really good

1063.44

about touching on additional areas. It's

1066.16

it really is. It's another set of eyes,

1068.24

another set of ears to say, well, hey,

1071.12

have you thought about that? And I think

1072.96

that has been a a big boon going through

1076.96

this season is that there have been some

1078.64

areas where we didn't really connect it

1080.96

and sometimes where it misunderstood,

1083.6

we'll say, where it took it a little bit

1084.96

different direction, but I think we got

1086.4

some great uh conversations out of that.

1088.799

So, I'll pause there and and get your

1090.559

like, you know, initial thoughts.

1092.48

>> Yeah. So, I I I I think I don't remember

1096.4

which one was initially kicked off the

1098.4

idea of, "Hey, let's like revisit a past

1100.48

season with AI." Uh, but it became an

1105.12

interesting journey. Initially, we're

1107.36

like, "Oh, well, let's just see what it

1108.559

can do." And, um, we'll just go with it.

1111.36

And

1112.88

as we went with it, it really

1117.76

did a decent job of analyzing what we

1121.919

talked about. In some cases, it was

1123.52

completely different, but in a good way

1126.24

where it's like, oh, we didn't even

1128

think about that. And it gave us more

1131.039

ideas

1133.36

um to kind of expand upon past episodes.

1136.32

Uh, one of the best things I can I guess

1140

compare it to is it's like um throwing

1142.96

ideas at a whiteboard, seeing what will

1146.4

stick and AI was great for that based on

1150.559

the way we used it. Now,

1154.16

would it be great to actually flush out

1156.4

the content for the full episodes? I

1158.559

don't think so. I think we'd get into

1160.08

that kind of false fake um or not fake

1164.559

but just where it would just kind of

1166.48

give us an answer but not really be an

1168.4

answer uh for a lot of these solutions.

1171.12

So for something a little higher level u

1175.36

like summaries and outlines and things

1177.36

like that I think it did a great job

1178.88

this season.

1180.4

>> I think so too. I think that's a really

1182

good point is that it gives us um

1185.76

yes, we can get some very good details

1188

if we want to out of AI, but for

1190.64

something like this, it's much better at

1192.4

a at a high level, at a summary kind of

1195.039

level. It was sort of like, hey, here's

1196.48

an outline or something like that and

1197.919

let us take it from there. Um there were

1201.2

more than a couple times that I think it

1202.72

came back with some stuff where it was

1204.16

just like, huh, that's an interesting

1205.76

way to go. We don't want to go there.

1207.2

you know, like it would take the it

1209.12

didn't have the right context of the

1211.12

term or the topic or things like that.

1213.36

So, it did um it could get lost, but

1217.2

honestly, so can we. There are times

1219.039

that we would put together a topic and

1220.64

we would go in very different directions

1222.4

because we were thinking different

1223.6

things. So, I don't think that's a I

1225.6

don't know that's necessarily a knock

1226.799

against AI, but I think it is a uh a

1230

caution against AI.

1231.6

>> No, agreed. I mean, it it gives you a

1234.08

good

1236

it's good at giving you content, but

1238.159

it's not necessarily good at giving you

1239.679

the meat of what it is that you're

1241.36

trying to convey.

1244.32

>> Yeah. And I think that's this goes back

1246.24

to like some of the other things I've

1247.52

done with AI that are outside of the the

1249.36

developer real world, which actually

1250.88

we'll see some of this as we like part

1252.96

of the things I'm going to be doing when

1254.32

I'm revamping the website. It's

1256.08

basically a lot of it is like take this

1258.48

stuff, take this bucket of stuff and

1261.679

reorganize it. It's like it's sometimes

1264.4

it's not much different than like just

1266.08

shuffle this around, but sometimes the

1269.2

shuffling makes a big difference. It's

1270.799

just like AB testing where you're like,

1272.24

well, what if I put the button at the

1273.52

top versus the bottom versus the left or

1275.52

the right or things like that. Um,

1277.679

that's some of what it is. It's

1279.2

basically like say okay let's take this

1282.4

and let's take honestly in some cases um

1286.72

you know like best practices or

1288.48

standards or things like that and let's

1290.08

like apply that to this thing so that we

1292.24

can get something done

1294.48

um that

1296.799

maintains the meat of it but also

1299.76

dresses it up a little bit. And it's it

1302.08

is sort of a um gosh it's so it's really

1305.679

at the end of the day the things that

1306.72

work best are the ones that are

1307.679

processoriented are the things that are

1309.52

like there's always a series of steps

1311.2

that you want to get through. Um I will

1313.44

share which is there's a lot more to go

1315.84

into it but I will share that like one

1317.12

of the things we've done that I found

1318.4

has been really good is using it as a um

1322.72

an advisor of sorts. like we we wanted

1325.6

to plan trips and would throw questions

1328.64

at it and it would be able to go like

1330.159

gather a lot of information and say well

1332.32

particularly in cases where you're

1333.76

trying to figure out like you're going

1335.039

into new areas of research. Uh it is a

1337.76

great way to very quickly figure out

1339.52

that like this is a good path or this

1341.36

isn't a good path. Um, I've used it a

1343.679

lot since we've started into this, I

1346.4

think, since this season of things like

1349.2

saying like if I want to build an app

1352.159

from scratch

1354.24

in this realm and this is sort of the

1356.72

target audience and this is what I want

1358.24

it to look like, what are the best

1360.48

technologies for it? And it will give me

1362.88

stuff like, well, here's here's an

1364.48

example. here's the the popular

1366.64

technology or here's the technology

1368.159

that's going to take more time to learn

1369.44

but it's actually going to be a better

1371.36

long term. Uh those things are, you

1373.919

know, it can get you there, but it

1375.44

really does come down to it's people

1377.679

talk about like I had a chat with chat

1379.44

GPT. It really is, I think, uh where you

1383.76

need to go is it has to be about

1387.12

a chat. It has to be about you learning

1390.32

how to use AI as much as AI giving you

1393.679

that information.

1396.96

>> Yeah. I mean, for those of us that have

1399.039

been around for a while, it goes back to

1401.6

like the old uh dictation software,

1404.159

Dragon, Naturally Speak, you have to

1407.28

spend time

1409.76

teaching the tool that you're using how

1413.36

to interact with you. You're not just

1416

learning the tool, but the tool is

1417.84

learning how to interact with you, how

1419.84

to understand your sentence structure,

1422.32

your grammar, uh your reflections. A lot

1426.799

of times, it's interesting because when

1429.44

I first started with Chat GPT, I'm a bad

1432.48

speller.

1434.08

It would more or less at early on just

1436.799

correct my spelling and say, "Did you

1438.08

mean this?"

1440.08

Now it takes almost anything I throw at

1443.2

it and it returns some type of message.

1445.84

Now it may not be the correct response

1448.559

but it is a response based on the

1451.6

history of the interactions with the

1453.919

tool. So if I were to log in anonymously

1458.559

through chat GPT. So this is a good test

1462

for those of you that have a chat GPT

1465.12

account.

1467.44

If you use chat GPT all the time, log

1471.919

out, clear your browser cache or go

1474.24

incognito, log into chat GPT or don't

1476.799

log into chat GPT, but just go to chat

1478.72

GPT and start using it. You're going to

1481.6

get different responses and different

1483.84

interactions. You're going to find that

1485.919

either it's going to send you down a

1487.919

different path or it's not going to give

1490.559

you that kind of personal experience

1492.32

that you're used to from being logged

1494.48

in. So, these are just some of the

1495.76

things to be cautious of as you continue

1498.4

to learn and grow with the tools. It

1500.799

takes time and you need to question it.

1505.36

Even if you're just starting out, heck,

1507.84

I would ask it almost uh when once I

1510.799

started like building projects like Rob

1512.48

was just talking about like with code, I

1514.88

start out with, okay, I want to build a

1518.48

web page. So, give me a web page. I'm

1520.159

like, is this the best way to build the

1521.76

web page? Yeah. Okay. Well, all right.

1524.32

maybe we'll do this. And I'm like, all

1525.44

right. And then it would prompt me,

1529.039

well, who's the web page for? So, if you

1531.679

are asking the right prompt, it will

1533.6

prompt you back if it's not getting what

1535.84

it needs. Uh, now with 50, I'm not sure

1539.6

if it still does that. I would have to

1540.88

go back and retest that, but I would

1542.96

probably have to retest it in cognito

1544.48

because I've already gone through that

1546.24

learning process with Chat GPT. So,

1550.32

as you're learning the tool, the tool is

1552.08

learning you. And it just takes time. Be

1554.64

patient with it, but definitely spend

1556.64

time with it and work through it. If you

1559.12

question it, Google it and call it out

1561.44

if it's wrong.

1564

And I think that's

1566.4

that's really I think the context is so

1569.84

critical. Um, and it it goes back to it

1572.4

reminds me of Google food ability

1574.64

people's ability to write searches in

1578.4

Google to like get useful information

1580.559

back and it AI is so much like that is

1583.44

it really is and I I was thinking about

1587.039

this today as I was like I was having a

1589.36

chat with chat GPT and I was actually

1591.279

getting it to do some work for me and I

1594.08

knew I knew I knew I knew I was like I

1597.2

really am gonna I like it was one of

1599.6

these that I asked asked it to do

1600.799

something and then I had to ask it for

1602.4

something else and I wanted to go back

1603.84

to the not the prior but two prior and I

1606.4

was like if I don't ask this right it's

1608

going to go to one prior and not two

1609.44

prior and sure enough it did and it's

1612.32

really is it's like it's

1614.88

I like sometimes I like joke that it's

1617.279

like talking with the child that like

1618.799

has a very short attention span that you

1620.72

have to like make sure you're very clear

1622.96

on what you provide. I do think as

1625.2

Michael's mentioned like the folders and

1626.96

stuff like that, there are some things

1628.159

that it does allow it now to do a better

1630.96

job of keeping context, but

1633.919

so often uh it still will like wander

1637.039

off. And so it's things where I have to

1639.279

and it's where it actually does become

1641.12

worth it to have like the paid version.

1642.799

So you can have a bigger question where

1645.44

you can say, "Okay, based on this, I

1647.12

want you to do this and make it look

1649.12

like that." And it's like sometimes

1650.799

that's a decent amount of stuff that you

1652.32

need to work with. The cool thing in

1654.4

building a better developer and then I'm

1655.679

going to let you jump in on this is that

1658.159

the best way to get that kind of

1660.24

information is be dealing with small

1661.84

chunks. And this goes back to something

1663.6

we have often said is like try to break

1667.039

your problem that you're solving down

1668.64

into small chunks that are very easy

1670.799

then to work with and maintain. And this

1673.36

will also help you immensely when you

1675.12

get into AI. You had a thought so I want

1676.64

you to jump back.

1677.44

>> I did. Um, so you you made a comment

1679.919

that when working with check GPT, if

1683.039

you're like two or three uh chats down

1686.399

and you need to go back and it doesn't

1688.96

go back to the right one, a small tip I

1691.84

found with this is if you go copy the

1693.919

selection you want to go back to,

1696

repaste it, but start out with reset the

1698.559

conversation to this uh chat, paste your

1702.32

chat in. Sometimes it will reset

1705.679

everything to where you need to be and

1707.12

then you can continue your thread from

1708.64

there. Um, I found that to be more

1711.039

successful than just assuming it knows

1713.039

where to go back to. That's I actually

1715.6

had a conversation with a guy u not too

1717.84

long ago that's a AI maven or whatever

1720.64

but that was some that was one of the

1721.919

things that he we talked about in our

1723.6

conversation is how it's it has a very

1726.799

limited memory and so there it's very

1730.24

easy five or six requests we'll say into

1733.919

it to suddenly lose stuff and it just

1736.559

like it's sort of reset and he said that

1738.799

was something that was he was struggling

1740.72

with as he was building out longer term

1743.76

conversations in that is to be able to

1745.52

do it. And I think that's honestly, and

1748.32

this is like a little pro tip or

1749.84

whatever because this is something I've

1751.12

been working with. Um, I think there's a

1754.24

point where what you need to do is if

1757.52

you're building like chat bots and stuff

1759.36

like that for longer term conversations

1761.2

is to have ways to actually freeze and

1764.72

update the context. is very much this is

1768.08

very a very much a Python thing but uh

1770.799

very much when in Python where you if

1773.2

you use pip if you use their library and

1775.2

there's other things are like this but

1776.64

there's a way to like say freeze like

1778.559

use what I have right now give me a

1781.84

script so that in the future I can go

1784.159

back and then just and this is called

1786.08

requirements basically but I can use

1787.52

those requirements and I can suck all

1788.96

those in and say I want exactly this

1791.679

environment I want these libraries these

1793.6

versions that the kind that is literally

1796.72

the kind of stuff that we need with AI.

1799.279

And if you're building something that is

1800.72

an evolving AI,

1803.6

I think you need to do that. But you

1804.88

because AI has a it has a crap memory.

1808.08

It's worse than mine. And so what you

1810.08

need to do is you need to be able to do

1811.679

something where if you really are

1813.44

building this isn't like the chat tools.

1816.799

If you're building a chat tool, you're

1818.72

going to need to be able to do a

1820.08

feedback loop into that to say, "Okay,

1822.64

now we have knowledge that we want to

1824.799

like maintain and we want to push that

1827.36

back into the AI so that now the AI is

1830.159

keeping that as part of it. It's like

1832

this is what I know." It's just like if

1833.52

you go to like notebook LM where it's

1836.08

like load these documents in. It's like

1837.919

well I need to have those documents

1839.76

there. Those are the thing. It's like

1842.72

marking knowledge that is key knowledge.

1845.6

And honestly, it's funny because Michael

1847.52

and I have had conversations in business

1850.159

stuff outside of developer in recent

1853.12

days, weeks, months where there are

1855.12

things like that that I I realize I

1857.039

recognize now that is very much a part

1858.72

of the human conversation as well.

1860.64

You'll be like, "Hey, this is a a

1863.36

watershed moment or a milestone or

1865.52

something a marker that we want to say

1867.2

we have agreed on this. This is what

1870.48

requirements documents are all about

1871.919

really. We've agreed on this

1874.799

and so this is what we're going to use

1876.64

as our foundation moving forward. It's

1879.039

literally no different when you're

1881.039

dealing with AI other than AI is a

1882.799

little more obnoxious than I know a lot

1885.76

of obnoxious people. I'm not even going

1887.039

to say it's more obnoxious than people.

1888.96

But I think that's what we we didn't

1892.48

embrace in this season is that we didn't

1896

feed back into it. every time we asked

1898.399

it about a a season about a topic for

1901.039

and give us a couple of things to talk

1902.799

about, we didn't actually give it

1904.64

feedback on it. So that is I think why

1908.08

we found over and over again we got

1910.08

roughly the same response. It got I mean

1912.96

we we asked a question a little bit

1914.88

differently but generally speaking we

1917.44

got the same response because we're

1918.799

asking the same thing over and over.

1923.919

>> Yeah. Uh so one of the things

1927.279

as you went through that that kept

1928.96

coming to my mind is

1931.84

there are some tips and tricks you can

1933.84

do with AI and this may be

1937.919

more application desktop application

1940.48

version of AI versus web but I have

1943.519

found as I go through the process of

1947.12

working with AI and resetting AI if it

1950.159

gives me a response there is that little

1953.039

check box that you can check under the

1955.679

message. Hey, this is right. But what I

1957.679

have found to be more useful is if it

1961.279

gives me, hey, this is like exactly what

1963.44

I want. I respond, save this into

1965.84

memory. This is a good response.

1970.48

And for those that are not, I say, okay,

1973.2

this was a poor response.

1976.24

Reject this, but do not follow this

1978.96

path. And if I do that, I get better

1983.36

results in the long run. But if I don't

1985.919

do that and I just let it keep

1987.36

regurgitating stuff,

1989.679

you take kind of that long way to get

1991.76

there. Like it it it takes longer to get

1994.72

to the solution than where you tell

1997.6

literally tell, hey, bad bad bad go

2000.559

back. Here's a cookie. That's right.

2002.48

Here's a cookie. That's good. But

2005.44

>> I have to interrupt because this is you

2007.36

and I have this conversation. I'm like,

2008.88

"Okay, time out. Stop right there. Let's

2011.76

Let's I don't say snapshot, but it's

2013.84

basically, "Let's snapshot that. Can we

2015.6

agree?" And we can move on. I know I've

2018

done that with you. I've done that with

2019.2

a lot of people. I will say because she

2021.519

probably won't hear this. My wife gets

2023.2

really annoyed when I do that sometimes

2025.2

because I will cut her off in the middle

2026.64

of a sentence and be like, "Stop right

2028.48

there. That's a point. Let's move on

2031.039

from there." But that is a I'm going to

2034

let you go because that is really a very

2036.08

important insight into how you find ways

2039.279

to move AI forward instead of get into

2041.6

those like loops or let it spin off into

2044.08

space.

2045.2

>> Exactly. And worst case scenario, if you

2048.879

find yourself five or six messages into

2050.96

a thread, even after trying to get it

2053.599

corrected, stop. Create a new chat.

2058.159

Delete. Do not archive. Delete the old

2060.8

chat. Say before you delete it, say this

2063.599

was a bad message thread. Delete it from

2065.52

memory. Then delete it. Start a new

2068

thread. Nine out of 10 times I find that

2071.2

the new thread starts in a different

2074

path. Usually closer to what I want and

2076.96

it gets me there quicker.

2079.28

These are not things that happen

2080.72

overnight. Uh, a lot of times I can now

2083.04

jump on the chat GPT probably within

2084.879

about 5 10 minutes I get enough of what

2087.679

I need from it to go do what I'm trying

2090

to do or I get enough of a correction to

2094.32

like a document, an email or something

2095.839

that I can just jump in and go take it

2098.079

from there and move on.

2100.4

I use track GPT now more days as a good

2103.68

virtual assistant and a quick

2106

boilerplate like code generator like

2108.48

here just throw this out here and I can

2110.32

go from there.

2112.8

Sometimes it works well for more complex

2115.599

things

2117.359

but I'm still struggling with most of

2119.92

the chat bots to get something that will

2122.8

build me an enterprise solution. And I I

2126.72

only want to touch on this one other

2128.16

thing cuz I read an article on this just

2129.92

recently. It seems like more Seale

2132.56

Fortune 500 companies are actually now

2134.56

starting to shift away from AI a little

2137.119

bit because they're finding that it's

2139.2

costing more to get to that chatbot

2142.72

level of maybe this is right to

2146.56

something that is actually going to help

2147.92

the customer.

2149.839

And that's honestly that's the wave

2152.4

we've seen in technology from forever is

2155.2

it's like everybody like oh this is now

2157.119

finally the silver bullet. This is the

2158.72

thing that's going to solve all our

2160

problems and then everybody throws a lot

2162.16

of money at it and the next thing we

2163.28

know it's like oh no it's not solving

2164.88

our problems. I'm just going to say if

2166.64

it's just throwing a lot of money at it

2168.24

you're not you're not paying attention.

2170.48

Throwing a lot of money is not it.

2171.76

You've got to be there has to be wisdom

2173.28

in that. You can throw good money after

2174.8

bad all day long. Uh AI is no different

2178.4

from all of the other silver bullets

2180.8

that we've seen all the way back to like

2182.32

I when I started out it was things like

2184.8

UIs and object-oriented and things like

2188.88

that actually AI I did a class I was

2191.68

just talking again guya today I had a

2194.16

class 35 years ago on AI it was

2198.4

basically expert systems in artificial

2200.64

intelligence and how to do that

2203.92

way and things have evolved um massively

2207.2

since then. But the interesting thing is

2209.68

which is actually a really cool little

2211.92

observation. This guy came out of the

2213.52

gaming environ the gaming world and he

2216.4

had dealt with a lot of stuff there.

2218

There is a lot of AI built into games,

2222

the gaming world of stuff. Like think

2224.24

about it like if you're sitting there

2225.28

and you're fighting. Now granted the the

2228

MMO RPGs and stuff, all the massive

2230.24

online stuff, it's just other people.

2232.96

But when you're dealing with stuff and

2236.8

there is a intelligence in the

2239.04

application that is your opponent.

2241.76

Uh a lot of times we know we've seen it

2244.079

like you pick all of your games like the

2246.88

Dark Souls series of stuff. There's

2249.599

there's uh patterns that they do. The

2253.76

things that they struggle with usually

2255.359

is patterns with some sort of randomness

2258

to it or things like that. But that's

2259.76

honestly what we know. If you really

2262.88

look at it, if you look at a a fighter,

2265.28

if you look at uh a football team, if

2267.92

you look at um I'm trying like a fencer

2271.04

or things like there's certain moves u

2273.68

the tai chi the uh

2277.2

uh ultimate fighter and stuff like that.

2279.68

Wrestlers, there are there's moves that

2282.4

they use. There's certain things that

2283.76

they do. If you look at dancers, you can

2285.52

look at across the line of what humans

2289.359

do. There are patterns of what we do.

2293.119

The things that are different for those

2295.44

that are the best is that we add

2298.4

randomness to it. Is that we try not to

2300.88

be predictable enough so that our our

2302.96

opponent doesn't know which path or

2306.4

which sequence we're taking at any given

2308.32

moment.

2310

That's not that much different from what

2312

AI provides. What we're trying to do, of

2314.48

course, is we want AI to be consistent.

2317.839

However,

2319.359

the bonus is that like AI is not

2321.68

consistent partially because it doesn't

2324.64

have the same set of information each

2326.88

time we ask that question. Now,

2328.56

sometimes we'll ask the same question

2330.56

and it's close enough, but it's still

2332.8

going to be like there's uh I think

2335.52

there's percentages and stuff like that

2337.119

behind the scenes, not getting too deep

2338.88

into the eye and like and I'm trying to

2340.56

simplify it for like not getting into

2343.28

the deep of the deepness of what this

2345.68

is, but honestly, at the bottom line, it

2348.079

it does work down to like you're rolling

2350.32

the dice. You're throwing a you're

2351.839

asking a question. and you're rolling

2352.88

dice and says, "What things am I going

2354.88

to like most use to uh color my opinion

2359.28

on this?" And we've seen that. We've

2361.359

seen this in this season where we've

2362.64

asked effectively the same question.

2364.079

We've gotten slightly different results,

2365.599

slightly different approach, and it's

2367.52

based on time of day or whatever else is

2370.24

going on. So, I think that's very key

2372.64

for us to take. I think that's a a very

2375.04

key takeaway is

2378.079

AI is literally like another person is

2381.52

like throwing out there I think if you

2383.2

look at it that way but like saying hey

2386.4

um and Michael mentioned u using as a

2388.96

virtual assistant I really think before

2391.76

like god this is such a rabbit trail I

2394.16

could go down I really see uh AI as

2397.76

replacing the VA I see so many things

2400.48

that I do right now that I'm like I can

2402.4

throw that to AI I AI I'll do that and I

2404.72

could honestly this is your automation

2407.04

stuff is like I could build a bot that

2409.52

does that stuff for me and I talk to

2411.359

people that are like yeah the the people

2413.68

that are technical that are trying to

2415.599

leverage AI that are not just throwing

2417.359

random stuff at it say yeah I can spend

2419.2

a little bit of time and I can build

2421.92

some sort of an AI solution that gives

2424.079

me this report this dashboard this look

2427.28

this overview this summary this outline

2429.92

things that are like all they do is just

2432.16

get us to the solution a little bit

2433.92

faster.

2434.96

>> And I'm going to throw something to you

2436.16

before I like get to the end of this of

2438.72

this episode faster.

2440.24

>> Yeah. So, the last thing I want to touch

2442.16

on, so

2444.32

as you were talking, spoilers for those

2447.52

that have not seen Superman, the new

2450.079

Superman,

2452.16

the scene with Lex Luthther

2454.96

where he's literally throwing out

2457.359

numbers. He's basically controlling the

2460.72

Ultra Man character in the movie through

2464

the fight. So, it's a real time person

2467.04

interacting with another person for a

2469.04

battle. A lot of the best AI tools that

2473.52

are out there are still the best

2475.76

procedurally written applications.

2478.64

Basically, if then do this, if then do

2481.44

this. It's building upon a procedural

2484.24

logic. It is not AI. It is a rules-based

2489.2

engine that is driving

2492.16

where your application is going and the

2494.079

interaction with your customers.

2496.96

I have seen more often than not,

2498.88

especially with testing tools and since

2501.76

Rob's been publishing all his

2503.2

applications, I am probably going to get

2504.8

mine out there again soon. I wrote a

2507.76

testing application 10 years ago, a

2510.24

testing framework. It needs to be

2511.52

updated a little bit, but speaking of

2513.68

legacy, I spun it up the other day, ran

2516.56

it against a website, and it worked. So

2522.079

the short

2524.24

answer is

2527.119

procedurally driven applications is

2529.92

essentially the current form of AI. You

2532.24

have to ask certain questions in a

2534

certain way and AI is essentially

2536.4

building you a procedural response to

2539.04

those answers to give you a solution

2541.68

based on your input.

2544.24

everything I see for uh what is it uh

2547.04

SAP and all these uh marketing tools and

2551.04

uh business tracking tools, they are

2553.119

literally just freaking integration

2555.28

systems that are basically procedurally

2557.359

driven based on rules, not necessarily

2561.119

AI where based on customer rules, we're

2565.119

going to give you this generated code or

2568.64

this generated report. Yes, it's AIish,

2572.16

but it's still procedural. It is not

2574.079

really thinking outside the box. It's

2575.68

thinking within this rule engine to

2578.079

generate these responses, these reports,

2582

these applications. So, be very careful

2585.44

relying on AI as the be all end all

2588.48

answer to your problems.

2590.56

>> And that's I guess that's the bottom

2592.319

line. It's just like it is it's an

2593.839

adviser like anything else. It is not

2596.24

going to always be correct. Um, it is

2598.88

there. It is wrong at times. It makes

2601.2

mistakes and things like that. Just get

2604.16

used to that. But that doesn't mean that

2606.48

it's not helpful. It's just like

2607.76

everything else. It's like everybody

2609.04

else you talk to, there's going to be

2610.48

value in what they say and there's going

2612

to be some stuff that is not very

2613.68

valuable in what they say. There's a lot

2616.48

of value in shooting us an email at

2619.92

because we will use that. We will like

2622.8

build that into this thing. you will

2624.4

find the option, the opportunity to say

2627.119

something to us and actually impact

2630.319

season topics, episodes, uh stuff that

2633.68

we do, if we do blog episodes, I mean

2636.16

maybe even training and stuff like that

2637.52

we do. There's a lot that you can do. If

2639.52

you look back, we've done a lot over the

2640.96

years. You go back especially to like

2643.2

some of our mentor classes and some of

2644.72

things those are all out on the YouTube

2646.4

developer channel uh do YouTube.com

2649.52

developer channel. um you'll find a lot

2653.359

of stuff where there were discussions

2655.2

that we had that ended up becoming uh

2658.4

entire products and things like that. So

2661.2

uh feedback is awesome. You can leave us

2663.52

feedback wherever you listen to

2664.8

podcasts. You can check us out on

2666.72

YouTube. You can check us out at X. Uh

2669.76

we are developer Facebook. There's a

2672.72

developer page uh Facebook page. You can

2675.52

leave us comments anywhere on the

2676.8

developer.com site which is going to be

2680.4

in the months ahead uh updating and

2682.48

enhancing and we're going to do some

2684.319

cool new stuff. Uh I I assume cool.

2686.72

We'll see how cool it is when I get to

2688.079

that. But I will just say I was very

2690.56

happy with some of the things we changes

2692

we made on the RB consulting site. I

2693.92

very much expect to bring some of that

2695.359

stuff forward and do even more on the

2697.44

developer site plus some other side

2699.359

projects I've got going that will sort

2701.119

of feed into be like a little feedback

2703.119

loop for these kinds of things. So, uh,

2705.04

we're not done. We're not just giving

2707.04

you content. We're going to find better

2708.319

ways to bring you content and bring you,

2710.72

uh, the stuff that you need, but it also

2712.56

helps to give us feedback so that we

2714.16

can, you know, know what we've done

2716.72

correctly and where we need to do it

2718.319

better. That being said, I just want to

2720.48

say once again, as we are probably

2723.04

wrapping up this season, I'm guessing

2724.64

that our next episode, we will just dive

2726.4

right into whatever our new ep or new

2728.4

season is, which in recent seasons is

2731.28

sort of what we do is we're like, I

2732.88

don't know. We'll figure it out when we

2734

get there. And uh it's turned out pretty

2736.079

cool so far. We've gotten a lot of

2737.839

stuff. We've learned a lot. Hopefully

2739.68

shared a lot that has been valuable to

2741.04

you. Appreciate you so much and the time

2743.119

that you've given us. As always, go out

2745.52

there and have yourself a great day, a

2747.119

great way, great week, and we will come

2749.599

back to you next time with season 26.

2754.16

Oh my gosh, this is just insane. Have a

2756.16

good one, folks. Talk to you later.

2760.48

Oops, I didn't want to do that. bonus

2762.319

material.

2764

>> Well, do we need bonus for this one?

2765.359

Because this was the end.

2766.88

>> I don't know that we do. I think we like

2768.56

we we talked a little bit beforehand.

2770.4

So, I think we're in pretty good shape.

2771.68

So, we can sort of wrap this one up. We

2773.2

can go on to

2774.56

>> our lives. Uh we will come back. Uh you

2776.96

and I can discuss or maybe we'll discuss

2778.88

at the start of the next episode what

2780.48

that season's going to be. Um I will

2782.72

I've got this stuff off in a folder so

2784.4

we can take a look at it. Um

2785.839

>> enabled screen reader.

2788.24

>> Wow, somebody hit a screen reader

2789.92

somewhere. Was that me?

2792.16

>> No, I hit I really do not like this new

2795.28

OS.

2796.96

I hit a button, all of a sudden things

2798.48

started popping up and uh

2801.119

>> I hate when that happens.

2802.16

>> The update it. This liquid glass thing

2804.72

is weird.

2807.28

>> It's going to take some getting used to.

2812.4

Uh let's see. Oh, I'm sorry. I'm like my

2815.599

This is why I put do not disturb. Stuff

2817.599

starts popping up popping up on my

2819.44

screen. So, it's like, "Dad, damn it." I

2821.68

hate when that happens. Well,

2822.56

>> that's what happened. Mine just ended.

2824

So, things started popping up.

2825.52

>> That's exactly what I'm getting. I'm

2826.8

getting like all this stuff. It's like,

2828.24

I don't need all of that. H. All right.

2832.56

That being said, thank you all you guys

2834.8

for yet another season. It

2837.44

I cannot appreciate. It's like share

2839.76

enough of my appreciation. Literally, if

2842.56

you guys ever need any help, if there's

2844.079

anything that we can do, if there's any

2845.359

way we can help you, check us out. Uh,

2848.319

shoot me an email [email protected].

2850.64

Shoot me an email, robb-sns.com.

2854.079

Uh, go out to the the matrix.rb-sns.com.

2857.28

Feel free to check that out. It is it is

2859.119

free. All it is is an email. We'll just

2860.96

send you emails to say, hey, how you

2863.28

doing? You can uh, you know, always just

2865.76

say, I don't want to be a part of this

2867.04

mailing list. You can jump back out.

2868.64

It's it's literally free. And hopefully

2871.119

it's helpful to you. I would love

2872.48

feedback on all that. love feedback on

2874.56

anything we have done because we are

2876.64

going into a season. We're getting

2878

towards the end of the year right now

2879.28

going into the fourth quarter. By now

2881.2

you probably know that fourth quarter is

2882.56

when I really start like evaluating the

2885.359

year behind and looking at what I want

2886.96

to do in the year ahead. That is one of

2889.28

the things that we do. It's one of the

2890.56

things that I do personally.

2892.8

I would love feedback of any sort,

2895.68

suggestions, recommendations, all that

2897.44

kind of stuff because this is going to

2898.64

help us really do more for you in the

2901.44

year ahead. Uh, we appreciate you much.

2904

We want to do the most that we can for

2905.599

you. Thank you. I'm going to let you

2908.079

have the rest of your time off. Go have

2909.76

yourself a good one and we will see you

2911.839

next season.

2916.63

[Music]