Latest / Justice Team Podcast / Building Your Own Chatbot with Alec Lowi of Personal AI

Transcript

Building Your Own Chatbot with Alec Lowi of Personal AI · Justice Team Podcast

0:02
Bob: Welcome to this episode of the justice team podcast
0:05
on the justice team network.
0:06
And today we're talking about artificial intelligence and creating your own large
0:11
language model or your own chat pod.
0:13
Some use cases for it.
0:15
And I'm sitting with the person, Alec Lowi from personal AI that
0:19
actually built my chat bot.
0:22
So tell, tell everybody a little bit about yourself and how you got to build AI.
0:26
Alec: Yeah, sure.
0:27
Um, well, I think the answer is you.
0:29
I think, I think that's how I got here was you.
0:34
Um, when I started working for you, I think it was, it's been almost a year.
0:38
I did a little bit of work for you and.
0:41
You know, you were involved with personally I at the time and through
0:44
that process, I kind of, um, you know, being a math major and going through a
0:49
lot of computer science stuff at UCLA and I had a very good understanding
0:54
of how data works and how I worked.
0:56
And when I got involved in that project with you, it was kind of like a, uh, an
1:00
awesome opportunity with this company for them to bring me on and start.
1:05
Doing some more development work for them.
1:07
Bob: Yeah, and you know, just to give everybody a snapshot of what we're
1:10
going to be talking about here today is the use of essentially creating
1:14
your own internal chat GBT based on your mindset, the way that you work.
1:20
And one of the reasons I, you know, partner with personally, I had to build
1:22
my chat bot for this use case is to give what I think mentorship on scale,
1:27
but the ability for to have a bot be able to answer questions very quickly,
1:31
smoothly with your own intelligence, but built off of your own data set, right?
1:35
Your own, not everything on the Internet, not read it, not, you
1:39
know, Pornhub or whatever, but like I don't think you use Pornhub for mine.
1:43
Did you we could okay.
1:44
Well, maybe okay That's a little much maybe wiki feet So anyway, we're here
1:51
from Alex So whatever we went through this process and we'll talk about how
1:54
we built mine and how other people you you've helped other people build Or
1:57
theirs is you know, whether they're big lawyers that have a lot of Dad out there
2:01
on them or big people in the industry.
2:05
I know there's a lot of famous folks that are creating their owns to help their,
2:09
you know, help fans on scale some stuff.
2:11
So kind of walk us through how, how you built the AI chatbot.
2:16
Alec: Yeah, of course.
2:17
Um, so for you, I, I mean, we can talk about your use case among a lot of the
2:22
other legal use cases that we have.
2:24
Cause, um, we did started dipping into the enterprise space, I think a
2:28
little more about four months ago and we've had a lot of success there, but.
2:32
As far as building out the models for, uh, the legal industry, uh, we on our
2:38
platform, cause we have our own UI and everything we, we, I can say kind of has
2:43
successfully designed a way for people to create these things on their own.
2:49
And for people to, um, I guess maintain these models from
2:53
a user friendly perspective.
2:55
Cause when we talk about fine tuning and training AI's, um, It gets very confusing.
3:00
It's very hard.
3:01
There's a lot of developers that involves and we're kind of trying to
3:04
present a way for people to just be easily say, I have all these documents.
3:09
I have all these case files, emails, zoom transcripts, whatever it might be.
3:13
Um, upload to the model very easily as if you're uploading
3:16
to Google drive and everything kind of does the rest on its own.
3:20
Bob: Yeah.
3:20
And like one of the things, you know, your company is SOC 2 compliant, which is
3:24
the highest level to be able to have all your, your, your data, private things like
3:28
this, but whenever you have to be able to essentially get words onto text, to be
3:34
able to use it, text words to put into the
3:37
Alec: model.
3:37
Bob: Really?
3:38
Alec: Not anymore.
3:38
Bob: What do you do now?
3:39
Alec: Um, we do a lot of stuff with image recognition, image in image out.
3:44
Um, we also do natural language plus image with image out so we can Uh,
3:49
we're actually doing a lot of stuff for a sports retail business right now.
3:53
Um, creating product mock ups.
3:55
So you could think of, you have a 2023 shoe model or something.
4:00
And you want to create more product iterations based
4:03
off of that same shoe model.
4:05
You can upload a picture of it.
4:07
Um, a prompt describing what you want the model to look like.
4:10
And then develop as many iterations You can also do, um, there was a
4:16
marketing campaign they did for Chinese New Year with a new tennis
4:19
racket they just came out with.
4:20
And we built all these images with that tennis racket of all these different
4:24
people, um, holding it and, and like little teddy bears holding it in
4:29
like a Chinese New Year background.
4:31
It's like, it's, it's really cool.
4:33
Bob: Yeah, and I know you and the team, Suman, the, the, the CEO founder, are
4:37
going to be at La De Gra this year actually helping people, lawyers if
4:40
you're there or whoever's attending.
4:41
Yeah.
4:42
If they want to build their own, their own personal AI, they could do that at
4:47
Alec: the workshop at Lauderdale this year.
4:48
Yeah, exactly.
4:49
So we're, we're going to put on display a little bit of AI orchestration.
4:53
And what I mean by that is, um, you have senior partners that exist in a law firm.
4:59
You have paralegals, you have researchers, you have all these
5:01
people that work together.
5:02
Right?
5:03
Um, and we're going to put on display a way for these AIs
5:06
to be able to work together.
5:08
So that the paralegal has the expertise of not only just their own AI, but also
5:15
they can refer to Bob's AI, to another senior partner's AI, they can get
5:19
opinions from multiple people at once, take those responses and develop opinions
5:24
based off of other AI opinions as well.
5:26
Just like the
5:27
Bob: AIs are collaborating to try to get the best answer.
5:29
Yeah, with
5:29
Alec: all, with all, um, with all like a human in the loop, obviously, but,
5:34
um, We'll put it on display there.
5:36
It's going to be fun.
5:37
I love it.
5:37
Yeah.
5:37
And you
5:38
Bob: know, just to show some of the, if you're building something based
5:41
off of you, like I know when you build ours, we had to transcribe every
5:45
episode I've done a bourbon of proof of justice team podcast, um, you know,
5:50
books that I've written, um, published articles, all the trial transcripts,
5:54
deposition transcripts, and to sanitize all those to get them into the model.
5:58
How, how large of a lift is that for you?
6:00
Alec: So it's becoming less and less over time.
6:05
That's a big part of our development process is creating a lot of new training,
6:09
optimization methods and stuff like that.
6:12
Um, now I would say when we trained your model, I think the process took a couple
6:18
of months for us to get all of those files in there, um, and optimize them.
6:23
And I can happily say we've for the same kind of volume as what
6:27
you had given us, we've shrunk that time period down to about a week.
6:31
Um, and now we're able to kind of.
6:34
produce these models for these people, um, very, very quickly and even set
6:38
up real time training automation.
6:39
Bob: Yeah.
6:40
And one of the other things that's interesting with this is you can set,
6:44
um, like a credibility score, like a veracity score to see, will you allow
6:49
your thing to try to guess the answer or will you set a higher percentage to 15,
6:53
20, 50 percent to make sure that it's, it's grabbing it to get the right answer.
6:58
Alec: Yeah, yeah, exactly.
6:59
That's our, uh, our personal score threshold.
7:01
So we have Um, a feature on our platform because we we try our best to Fully
7:08
prioritize accuracy and put that on the forefront Um, so our personal score
7:13
threshold Is a way for us to kind of measure The amount of data that was
7:18
used to create the AI's response.
7:20
And if there wasn't enough of your data that was used to create the
7:22
response, then the message doesn't go through and it'll say, let me sync
7:25
up with Bob on that or something.
7:27
Let me ask Bob.
7:28
Bob: Yeah.
7:28
And it'll tell you, I could see when people were chatting it, if I, if Bob
7:32
doesn't know the answer, it's like, well, let me ask the real Bob Simon that one.
7:35
So, which is, which is good because you don't want it to guess.
7:37
Also one thing on there is you can, As a user go in and edit
7:42
the response to edit the memory.
7:45
Can you explain us what that is and how it works?
7:47
Alec: Yeah.
7:48
So, um, the way that, uh, I guess our real time messaging training works is if you're
7:54
having conversations with people or people are having conversations with your A.
7:57
I.
7:58
Um, we have this little plus button next to each, uh, message, uh, bubble.
8:05
And you can say, I like this message.
8:06
I want this message to be trained, or I like this message.
8:09
You can kind of go through the whole conversation thread and save them to the
8:13
AI's memory so that if that same question is asked before or asked in the past,
8:18
then you can have the same response.
8:20
And you can also make sure that response is what you want it to be in.
8:24
Bob: Yeah.
8:24
And it's an ongoing process because you still have to load more documents
8:27
into its data set as it grows.
8:30
So like every new show I do, we try to get in a cadence of putting it in.
8:33
So it continues to learn.
8:34
Yeah.
8:34
You know, my use case, I want people to not only be able to listen to our
8:37
podcasts and shows, be able to just to query the bot for some quick advice.
8:41
And we see it because I've said, Oh, you're monitoring ours.
8:43
I'm always very impressed at some of the answers it comes up with.
8:46
It's like, wow, that actually nailed it.
8:47
It did better than I would.
8:48
And yeah, somebody asked me who was a tech company and he's like, Hey, can
8:51
you write like a testimonial for me?
8:53
And I was like, just ask my bot.
8:54
Cause I want to know what it says.
8:55
And it nailed it.
8:56
I love this.
8:56
I was the one last night with nailed it.
8:58
I love it.
8:58
Like I just asked it.
8:59
Um, Like who was Morrow Fiore?
9:02
If you don't know Morrow, he's well, let's see what the answer it comes up with.
9:05
But we have my voice on it.
9:06
We also changed it to an avatar.
9:08
So we'll talk like, I mean, it's here.
9:09
I apologize, but I cannot reproduce.
9:11
Oh, we can't do that one.
9:13
Let's do that one.
9:14
Let's, we got to do a shorter one.
9:16
Who is, so we'll ask, what is your favorite whiskey?
9:20
It should know that one.
9:20
What is your favorite whiskey?
9:23
That should know.
9:25
Yeah.
9:25
But then the idea is if it gets it wrong, you can edit it, go back and get, by
9:28
the way, if anybody's listening, ask my chatbot, which my favorite whiskey is.
9:31
You can send it to me for Christmas.
9:33
I'll give my home address out to you at any time.
9:35
Um, it should be able to get the right one, but yeah, it doesn't, let's
9:38
Alec: see if It's a long one again.
9:41
You can just play the messages for a moment.
9:43
You can hear the voice avatar.
9:45
Bob: Yeah.
9:46
Alec: Let me see if I can
9:46
Bob: do that.
9:47
I'm just waiting for the voice activation to pop up.
9:49
Alec: Yeah, yeah.
9:50
Bob: Let's see.
9:50
Let's go.
9:52
See?
10:01
Summarizing key points discusses the author's love
10:03
for rye whiskey , particularly whistle
10:06
Bob: pig boss haw.
10:06
I think it's 'cause it's mine.
10:07
As well as their appreciation for good bourbons like Weller Booker . It
10:12
also mentions a legal talk show where the author enjoys sipping fine
10:17
whiskey while discussing legal topics.
10:22
So this is, this is my testing my own internal one.
10:26
So it's summarizing it for me.
10:27
But if a user's using, it's a different experience.
10:29
Right?
10:29
Right.
10:29
But you can see it has my voice.
10:30
Yeah.
10:31
And it got it right.
10:32
Um, but you know, the interesting thing with this is what are some of the use
10:36
cases that, that you're seeing people use to create their own personal ai?
10:39
We talked about law firms having that super user regardless of
10:43
your position at the firm, but how are other people doing it now?
10:46
Alec: Yeah, so that's a great question actually.
10:49
Um, so, uh, in the legal space, um, one of our customers,
10:57
uh, an advocate's ed at dia.
10:59
Yeah, I love that.
11:00
Yeah, yeah.
11:01
He, um, he's another good example of a legal use case right now.
11:05
He's, um, because he works in Hawaii and California, right?
11:09
So he has two completely different codes of evidence.
11:12
And he has a persona that's trained on, um, the California code of evidence as
11:18
well as the Hawaii code of evidence.
11:20
And he's able to kind of draw connections between those two codes of evidence
11:25
in the sense of, he always talks about how he knows California better.
11:29
So he'll ask his Hawaii one to say, Hey, are there any statutes in here that
11:34
are similar to what is in California that I can use for X, Y, and Z?
11:39
Um, so he's kind of able to draw comparisons for that.
11:43
And, and, uh, he does use it for a lot of like drafting emails.
11:47
So we can do.
11:48
Um, you know, live integrations with the email.
11:51
So if you receive emails, you can say, Oh, I want my AI to respond to this one.
11:54
You just hit the star button or a flag and then a draft really up in your inbox
11:58
with the, with the email response, you
11:59
Bob: can plug that in now.
12:01
Wow.
12:01
Alec: And then we also do he, a lot of, um, legal use cases do involve like the,
12:07
uh, zoom meeting transcripts as well.
12:10
So, um, We also have mechanisms where I know a lot of zoom meeting
12:15
transcripts are titled the same.
12:16
We can dump all those in there and you can recall them by date.
12:19
What was, what did I talk about in this meeting last week on September?
12:22
Whatever, what were the action items?
12:24
What were the summaries?
12:25
That's a good call.
12:26
You said what you can record all of your meetings and then
12:29
dump into the AI summaries.
12:31
Yeah, we have one company that's uses it for the same reason, but for
12:35
earnings call reports and QB ours.
12:37
And they're actually able to draw trends because they have so many of these
12:40
zoom transcripts from over the past from their business and they're able
12:44
to draw all these analytical trends from years worth of meeting transcripts
12:49
just from quarterly business reviews.
12:51
Wow.
12:52
And data.
12:52
Bob: Yeah, and then, you know, going back to the, a lot of our listeners are
12:55
lawyers or aspiring lawyers to people in the legal space, you know, one of
12:58
the visions we had is imagining having access to great strategy from great
13:03
trial lawyers or lawyers in their space.
13:05
Right.
13:05
Right.
13:05
And then putting them together in this lounge that you talked about.
13:08
So you have like this beehive mentality.
13:09
It's like, imagine asking like the 20 best trial lawyers a question about
13:13
strategy, letting them collaborate and come up with the answer.
13:16
Alec: Yeah.
13:16
We're going to show that a lot.
13:18
Oh really?
13:18
Bob: Oh, I love it.
13:19
Alec: Yeah.
13:19
Yeah.
13:20
We'll show that at Lottie Gras.
13:21
So we'll have, um, a couple of different AI personas we'll put on display for that.
13:25
And then.
13:26
We also have the, the Bob Simon avatar as well.
13:30
You got it ready.
13:31
Yeah.
13:31
Yeah.
13:31
Well, can you tell you the story about that?
13:33
No.
13:34
Okay.
13:35
So during the, so we set it up where, you know, you have to record like
13:38
the two minute long training video.
13:40
So, um, the responses, we can connect them to the avatar so that if you were
13:45
to ask it a question, the response from the AI can be the same response
13:49
that the avatar gives in the video.
13:51
Right.
13:51
So it would be you.
13:53
Um, And the, the, they didn't accept our training video.
13:58
The first one that, uh, that you sent them, they're like, it
14:01
has too much, what did they say?
14:03
Too much profanity.
14:05
Oh shit.
14:06
Bob: Well, I did.
14:07
They asked me to talk for five minutes.
14:08
So what the fuck am I going to say if I can't swear?
14:11
Alec: So I had to call the fricking CTO and they're like, Oh, it's fine.
14:15
I'm like, just push it through.
14:17
Like, it's fine.
14:17
This isn't going to come back through.
14:18
So we made it, it's done now.
14:20
Um, so we'll be able to show that at
14:23
Bob: the, at Laudigrass.
14:24
I'm excited.
14:24
You know, I always say one of my goals is to be able to do a podcast or an
14:29
interview and not actually be there.
14:31
And be in fricking Hawaii or something.
14:32
Be in the Maldives in my underwear.
14:35
I always say, you know, well, can you show it?
14:37
Cause I know you built a fun, like a funny Bob, like with my sarcasm, cause
14:42
personas, the ways that I answer things on social media, the way that I talk.
14:47
Do you have some examples?
14:48
You can open your computer.
14:49
Cause we, we had to, I have had some people testing it and
14:52
it was becoming so sarcastic.
14:55
It was a little mean.
14:55
I was like, we got to go back to the professional one for a little while,
14:57
but it was really funny and really good.
15:00
Like I know people were chatting.
15:01
It was like, I can't believe it's coming up with these answers on me.
15:05
I'll
15:05
Alec: ask it.
15:06
Uh, can you tell me about Brad Simon?
15:09
Brad Simon?
15:10
Oh, you mean my little brother?
15:11
Yeah.
15:12
I can tell you about him.
15:13
He's the co founder of our firm, the Simon law group.
15:15
He's also got his hands in justice HQ.
15:17
Smart kid I'll give him that Graduated from George Washington
15:21
University in Southern Law School.
15:22
He's got a knack for real estate litigation rarely loses emotion But
15:26
don't tell him I said that his ego is big enough already Brad's got
15:30
this whole tech thing going on too.
15:31
He's working on some virtual tabletop role playing game called Ravel
15:34
Wow, sounds like nerd stuff to me, but hey, whatever floats his boat
15:39
Bob: That's good.
15:40
I mean, that's how I would probably answer that question.
15:42
Yeah.
15:42
Yeah, we teach little memories tweak it a little He's technically my little
15:46
brother by six minutes, but we would put twin or womb mate things like this.
15:51
Yeah Oh, man, like we asked it about.
15:53
Um Maria monroy one time she does all the you know, law rank seo and I always
15:59
tease her that she's mean I think it's funny, but it gave a really mean response.
16:02
We were laughing because we were friends were testing it at the same
16:04
Alec: time Yeah, yeah we had the uh Because we have your sms number right
16:08
we're able to connect the phone numbers to these personas and You Yeah, so how do
16:12
people, how do people test the Bob bot?
16:15
It's bob.
16:15
persona.
16:16
Yeah, yeah, yeah.
16:17
So you can go to, um, bob.
16:19
personal.
16:19
ai and I actually just turned on your public chat page so people can
16:23
go on there um, and chat with your, uh, your AI bot uh, without having
16:29
to make an account on our platform.
16:30
Bob: Oh, awesome.
16:31
And then that's the one that actually has my voice on it, right?
16:33
Correct.
16:33
Yeah.
16:34
Alec: Yeah, yeah.
16:34
So you'll be able to get those, um, those voice transcripts.
16:37
Look, I'm
16:37
Bob: making it so easy to get deep faked.
16:39
Awesome.
16:39
I'm
16:40
Alec: fucked.
16:40
I'm fucked.
16:41
Did you see the deepfake I sent you?
16:43
Bob: Yeah, I used it at the Cala presentation.
16:46
Yeah, yeah.
16:46
He's gonna remove all
16:47
Alec: my
16:48
Bob: tattoos or something.
16:49
Now I'm a Cowboys fan and I'm gonna switch to the defense.
16:53
Yeah, deepfaking myself.
16:54
No, but I think this is like, the way the world is going is, imagine being
16:59
able to replicate yourself, your brain.
17:02
And one thing, the idea that we had, I think we talked about is
17:05
what I would love to be able to do.
17:06
Imagine Loading this up with all of the posts persona of like my dad, right.
17:12
And then, so when my, you know, he's not going to live forever, I hope he does,
17:17
but I would love to have my grandkids have the ability to ask pap, pap, a
17:21
question and have an answer as him.
17:24
Right.
17:24
Um, and have an avatar of him to be able to ask him those questions.
17:28
I mean, imagine how amazing would be able to talk to your, Your
17:31
grandpa for your grandma right now.
17:33
Yeah, you know,
17:33
Alec: yeah knowledge preservation.
17:35
That's kind of what our value proposition is, right?
17:38
I mean, you have a lot of senior partners that retire from law firms every day And
17:42
that's kind of the whole thing imagine having the ability to still Harvest
17:47
the knowledge of a senior partner that retires and being able to keep their
17:51
philosophies flowing by the law firm
17:54
Bob: Yeah.
17:54
And, but in order for you to do that, you have to have uncorrupted memories.
17:57
I always think about Harry Potter when they take the memories
17:59
out and distort them, right?
18:01
You got to be able to have somebody in there that's actually keeping true.
18:04
The, the archive of the memories and getting them in there.
18:07
But yeah, if you want to do with it for your, your parents or
18:09
grandparents, you would just need.
18:11
I'll want them to either talk a lot or type a lot or interview
18:15
a lot to be able to get that.
18:16
Yeah,
18:16
Alec: yeah.
18:17
I mean, you can, you can also, um, get, you know, whether it's emails,
18:21
just things that they've written.
18:22
Emails, books, um, posts, whatever it might be.
18:26
I mean, that's really all we need.
18:27
We, it's, it's getting to the point where we need less and less training
18:31
data to be able to talk like you.
18:32
Bob: So can it extract
18:33
Alec: all of my social media posts?
18:35
Yeah.
18:35
Bob: Oh,
18:35
Alec: that's,
18:36
Bob: we should add that to mine because it'd be We have, we have a lot of
18:38
things we've got to add to yours.
18:39
I'm excited.
18:41
I mean, I would love to create this for like my parents.
18:45
I think it'd be awesome.
18:45
Or you imagine being able to talk to your mom when she was 25 or 30, right?
18:51
If you're doing that, right.
18:52
It'd just be awesome.
18:53
Can I see mom at 40 years old and ask her a question?
18:56
You know, that'd be cool.
18:58
Alec: And then we, uh, we, we made you like the, we have like the
19:01
professional, um, Bob bot persona.
19:04
And then we have like the, The fun Bob, like alcoholic slash
19:08
unhinged persona that's unfiltered.
19:11
Yeah, yeah.
19:11
So we can, um, I was thinking like while I'm at Lautograph, you know, I
19:16
can have the computer set up and, you know, people come ask me questions.
19:19
I'll just type it into fun Bob and he can answer some of the questions.
19:22
I love it.
19:22
People are going to die, man.
19:24
People are going to be like, like this one, uh, I asked it who, who
19:27
your other brother was, Brandon Simon.
19:29
Yeah.
19:31
And he was like, oh you mean my little brother he thinks he's hot shit because
19:34
he's a partner at our firm He's a diss.
19:36
He's a decent lawyer, I guess and graduated from Thomas Jefferson with
19:40
some fancy honors, but it's not Harvard He's got a thing for bourbon too, but
19:44
I doubt he can hold his liquor like I can Spends his free time playing board
19:48
games with his life and losing from what I hear from it with his wife and losing
19:52
This is true actually Typical Brandon, at least he got good taste in dogs.
19:56
Those Bernese Mountain dogs are probably smarter than half our associates.
19:59
Bob: Oh man, Bob Bot.
20:01
Bad Bob Bot.
20:02
But that was pretty funny, that's how I would answer it to his face.
20:04
Bad Bob Bot.
20:05
Bad Bob Bot.
20:06
I've been screenshotting on my Instagram, if you go to
20:08
PlanetFunBob and see my stories.
20:10
I've been screenshotting some of the funny answers and when it nails it.
20:13
Yeah.
20:14
Mike, something about my wife, whether she likes snakes and
20:17
it gave a very funny answer.
20:18
You should look at it.
20:18
It was really funny.
20:20
Um, but yeah, so, you know, how do people find you, Alec?
20:22
If people want to, you know, are interested in building
20:24
their own internal personal AI
20:27
Alec: bot, what do they do?
20:28
Yeah.
20:28
Yeah.
20:28
So, um, anybody can go to personal.
20:31
ai.
20:32
That's our website.
20:33
Um, you can also reach out to us on LinkedIn.
20:35
We're on LinkedIn.
20:36
And, uh, you know, if you go to our website, there's personal.
20:39
ai.
20:39
There's a page where you can schedule a demo on there.
20:42
It's personal.
20:42
ai slash pricing.
20:44
Um, you can go on there and schedule a demo with us.
20:47
Uh, I do a lot of custom demos for people, so if you do schedule one
20:51
with us, I'll customize and kind of bring these things to life for them,
20:55
for them to really be able to see.
20:56
And, um, we're starting to see a lot of traction from a lot of different
21:01
types of enterprises and stuff, because, um, the use cases with this
21:06
thing are kind of endless, you know.
21:07
It's, it's
21:08
Bob: Yeah.
21:09
And what, and what do you think's in the hurdle?
21:10
Cause so much has changed since we built mine.
21:12
I mean, I'm just, I'm learning new stuff right here.
21:14
But where do you, where do you think the future stuff is going to go for this?
21:17
Alec: So personally, I will be running on device soon.
21:22
Um, we're currently working with a large chip company to make that happen.
21:25
What do you mean on device?
21:26
You won't need internet to talk to the AI really.
21:31
And it can train on all your local data, not your cloud data on device.
21:35
That'd be insane.
21:36
All private, all secure.
21:38
Um, and then we're also, um, working on, uh, a couple of other things
21:46
with some large, uh, networking companies, the sports retail business.
21:50
We're trying to, um, kind of scale this thing in businesses and in law firms
21:56
because everybody can have a persona.
21:58
Every team of every business can use a persona and have that knowledge and be
22:04
a part of the process in a sense of, Um, efficiency, ROI, all of that stuff.
22:11
Um, we're starting to see a lot of success with, uh, these larger businesses.
22:15
Education too.
22:16
We built a fully asynchronous tutoring classroom, no teachers,
22:21
first through eighth grade, um, doing a lot of cool stuff there.
22:25
So yeah, I mean, um, we're kind of just, Kind of just doing what we can with this.
22:30
Yeah.
22:30
I'd love
22:30
Bob: to see it where, you know, in professional sports, imagine being
22:33
able to use artificial intelligence to predict what the offensive
22:35
coordinator is going to play.
22:36
So you can run a defense on it.
22:38
It's got to be getting there.
22:39
I'm trying to train my bot right now on an answer.
22:42
Yeah, yeah.
22:43
Yeah.
22:43
We're going to teach you some information about you.
22:44
So if you're gonna reach out, if you have questions about Alec.
22:47
How much he can squat, what his dating life is, what he likes to
22:50
eat, look like such a huge, defined definition of a human being.
22:54
You used to play baseball, right?
22:55
I did, yeah.
22:55
I pitched in college.
22:57
And I got into powerlifting a few years later.
22:59
Powerlifting and pitching do not equate together.
23:01
Not really.
23:03
No, it does not, but if you want to reach out to Alec and go to justiceteamnetwork.
23:07
com to ping the ping us here and we'll be able to reach out to him
23:10
through there or go to personal.
23:12
ai to reach out to him.
23:14
But I think your email is just alec at personal.
23:16
ai.
23:16
com.
23:16
Yeah.
23:17
Alec: Yeah.
23:17
Uh, you can reach me at alec at personal.
23:19
ai.
23:19
Yeah.
23:19
Yeah.
23:20
Um, I'm open to any emails too.
23:22
I, I like to, um,
23:24
Bob: But will you be answering or will be your AI bot?
23:28
Yeah.
23:28
Alec: If my AI bot answers, I do have a signature that says, this is from Alec AI.
23:33
Oh, okay.
23:33
Yeah.
23:34
So at least people will know, like, like the message will all look the same and
23:38
you'll still probably read through the whole thing thinking it was from me, but
23:42
at the bottom it'll just say Alec AI.
23:44
Bob: I love that.
23:45
I mean, even if it's given somebody, yeah.
23:46
Alec: Wow.
23:47
So it's not like, oh, this is just some automated bullshit AI message.
23:50
Like, no, like it's legitimately from me because, um, it's modeled after
23:54
my previous emails, but it will say.
23:57
Bob: Yeah, I asked how much can Alec, Alec low our squad and it says not
24:00
enough that's the answer Maybe he'll get
24:04
Alec: 791 Are too freaking smart man.
24:08
There's this one time I built this sales chat bot for our website and
24:12
we're still kind of working on it because You know, we want it to be cool.
24:17
We want it to be robust This thing is like spitting out memes and
24:21
contents and context of his response.
24:23
Wow GIF memes.
24:24
It'll be like Oh yeah, personally, I, uh, you know, we, we do a real live data
24:30
upload and, and, and, and training, um, come visit our pricing page and it'll show
24:34
like, you know, but don't be like this guy and it'll show like a mean girls meme.
24:39
Oh my God.
24:39
Yeah.
24:40
Alec: That's awesome.
24:40
Or, uh, and then there was one time where, you know, like Rick being Rick rolled me.
24:44
Yeah, yeah, yeah.
24:46
So the AI was like, yeah, you can schedule a demo with us.
24:49
Um, You know, just visit this link and you clicked on it and
24:52
it frickin rickrolled I told it.
24:57
Yeah, I told it to troll people sometimes so she'll show she
25:00
might rickroll you a few times,
25:02
Bob: you know, that's I mean Here's the thing about the AI I know when somebody
25:06
uses AI to write emails or letters or things and it's always too many adjectives
25:11
and it sounds like You know, you know what I mean, but this is why I like this.
25:14
Cause it actually has your voice.
25:15
You can make it sarcastic.
25:16
You can make it fun, have a personality.
25:18
So that's cool.
25:20
Well, thanks for coming on this episode of the justice team network
25:22
on the justice team podcast.
25:24
Again, technology AI is all fascinating.
25:26
We're filming this in September of 2024.
25:28
It'll probably be out very shortly, but I mean, Alec, when you come
25:31
on the show six months from now, it might be completely different.
25:33
Alec: Yeah, I'm excited.
25:35
Bob: We might have our avatars do it.
25:37
Alec: We should we should we should we should do it with like
25:39
I'll be in San Diego We'll be filming the podcast up here.
25:42
Oh, that'd be sick.
25:44
And I'll be in the Maldives in my underwear.
25:45
Thank you for listening