October 8, 2024 • 25 mins
Have you ever wanted a customized chatbot to answer your emails for you? Now, that might be possible! In this episode of the Justice Team Podcast, the host welcomes Alec Lowi from Personal AI to discuss the possibilities of creating personalized large language models and AI chatbots. They delve into the benefits and use cases, highlighting how AI can be tailored for different industries, especially legal, to provide quick, intelligent responses based on personal data.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Bob (00:02):
Welcome to this episode of the justice team podcast
on the justice team network.
And today we're talking about artificialintelligence and creating your own large
language model or your own chat pod.
Some use cases for it.
And I'm sitting with the person,Alec Lowi from personal AI that
actually built my chat bot.
So tell, tell everybody a little bit aboutyourself and how you got to build AI.
Alec (00:26):
Yeah, sure.
Um, well, I think the answer is you.
I think, I think that'show I got here was you.
Um, when I started working for you, Ithink it was, it's been almost a year.
I did a little bit of work for you and.
You know, you were involved withpersonally I at the time and through
that process, I kind of, um, you know,being a math major and going through a
(00:49):
lot of computer science stuff at UCLAand I had a very good understanding
of how data works and how I worked.
And when I got involved in that projectwith you, it was kind of like a, uh, an
awesome opportunity with this companyfor them to bring me on and start.
Doing some more development work for them.
Bob (01:07):
Yeah, and you know, just to give everybody a snapshot of what we're
going to be talking about here todayis the use of essentially creating
your own internal chat GBT based onyour mindset, the way that you work.
And one of the reasons I, you know,partner with personally, I had to build
my chat bot for this use case is togive what I think mentorship on scale,
(01:27):
but the ability for to have a bot beable to answer questions very quickly,
smoothly with your own intelligence, butbuilt off of your own data set, right?
Your own, not everything on theInternet, not read it, not, you
know, Pornhub or whatever, but like Idon't think you use Pornhub for mine.
Did you we could okay.
Well, maybe okay That's a little muchmaybe wiki feet So anyway, we're here
(01:51):
from Alex So whatever we went throughthis process and we'll talk about how
we built mine and how other people youyou've helped other people build Or
theirs is you know, whether they're biglawyers that have a lot of Dad out there
on them or big people in the industry.
I know there's a lot of famous folks thatare creating their owns to help their,
you know, help fans on scale some stuff.
(02:11):
So kind of walk us through how,how you built the AI chatbot.
Alec (02:16):
Yeah, of course.
Um, so for you, I, I mean, we can talkabout your use case among a lot of the
other legal use cases that we have.
Cause, um, we did started dippinginto the enterprise space, I think a
little more about four months ago andwe've had a lot of success there, but.
As far as building out the models for,uh, the legal industry, uh, we on our
(02:38):
platform, cause we have our own UI andeverything we, we, I can say kind of has
successfully designed a way for peopleto create these things on their own.
And for people to, um, I guessmaintain these models from
a user friendly perspective.
Cause when we talk about fine tuning andtraining AI's, um, It gets very confusing.
(03:00):
It's very hard.
There's a lot of developers thatinvolves and we're kind of trying to
present a way for people to just beeasily say, I have all these documents.
I have all these case files, emails,zoom transcripts, whatever it might be.
Um, upload to the model veryeasily as if you're uploading
to Google drive and everythingkind of does the rest on its own.
Bob (03:20):
Yeah.
And like one of the things, you know,your company is SOC 2 compliant, which is
the highest level to be able to have allyour, your, your data, private things like
this, but whenever you have to be ableto essentially get words onto text, to be
able to use it, text words to put into the
Alec (03:37):
model.
Bob (03:37):
Really?
Alec (03:38):
Not anymore.
Bob (03:38):
What do you do now?
Alec (03:39):
Um, we do a lot of stuff with image recognition, image in image out.
Um, we also do natural language plusimage with image out so we can Uh,
we're actually doing a lot of stufffor a sports retail business right now.
Um, creating product mock ups.
So you could think of, you havea 2023 shoe model or something.
(04:00):
And you want to create moreproduct iterations based
off of that same shoe model.
You can upload a picture of it.
Um, a prompt describing whatyou want the model to look like.
And then develop as many iterationsYou can also do, um, there was a
marketing campaign they did forChinese New Year with a new tennis
racket they just came out with.
(04:20):
And we built all these images with thattennis racket of all these different
people, um, holding it and, and likelittle teddy bears holding it in
like a Chinese New Year background.
It's like, it's, it's really cool.
Bob (04:33):
Yeah, and I know you and the team, Suman, the, the, the CEO founder, are
going to be at La De Gra this yearactually helping people, lawyers if
you're there or whoever's attending.
Yeah.
If they want to build their own, theirown personal AI, they could do that at
Alec (04:47):
the workshop at Lauderdale this year.
Yeah, exactly.
So we're, we're going to put on displaya little bit of AI orchestration.
And what I mean by that is, um, you havesenior partners that exist in a law firm.
You have paralegals, you haveresearchers, you have all these
people that work together.
Right?
Um, and we're going to put ondisplay a way for these AIs
to be able to work together.
(05:08):
So that the paralegal has the expertiseof not only just their own AI, but also
they can refer to Bob's AI, to anothersenior partner's AI, they can get
opinions from multiple people at once,take those responses and develop opinions
based off of other AI opinions as well.
Just like the
Bob (05:27):
AIs are collaborating to try to get the best answer.
Yeah, with
Alec (05:29):
all, with all, um, with all like a human in the loop, obviously, but,
um, We'll put it on display there.
It's going to be fun.
I love it.
Yeah.
And you
Bob (05:38):
know, just to show some of the, if you're building something based
off of you, like I know when youbuild ours, we had to transcribe every
episode I've done a bourbon of proofof justice team podcast, um, you know,
books that I've written, um, publishedarticles, all the trial transcripts,
deposition transcripts, and to sanitizeall those to get them into the model.
(05:58):
How, how large of a lift is that for you?
Alec (06:00):
So it's becoming less and less over time.
That's a big part of our developmentprocess is creating a lot of new training,
optimization methods and stuff like that.
Um, now I would say when we trained yourmodel, I think the process took a couple
of months for us to get all of thosefiles in there, um, and optimize them.
(06:23):
And I can happily say we've forthe same kind of volume as what
you had given us, we've shrunk thattime period down to about a week.
Um, and now we're able to kind of.
produce these models for these people,um, very, very quickly and even set
up real time training automation.
Bob (06:39):
Yeah.
And one of the other things that'sinteresting with this is you can set,
um, like a credibility score, like averacity score to see, will you allow
your thing to try to guess the answer orwill you set a higher percentage to 15,
20, 50 percent to make sure that it's,it's grabbing it to get the right answer.
Alec (06:58):
Yeah, yeah, exactly.
That's our, uh, ourpersonal score threshold.
So we have Um, a feature on our platformbecause we we try our best to Fully
prioritize accuracy and put that onthe forefront Um, so our personal score
threshold Is a way for us to kind ofmeasure The amount of data that was
used to create the AI's response.
(07:20):
And if there wasn't enough of yourdata that was used to create the
response, then the message doesn'tgo through and it'll say, let me sync
up with Bob on that or something.
Let me ask Bob.
Bob (07:28):
Yeah.
And it'll tell you, I could see whenpeople were chatting it, if I, if Bob
doesn't know the answer, it's like, well,let me ask the real Bob Simon that one.
So, which is, which is goodbecause you don't want it to guess.
Also one thing on there is youcan, As a user go in and edit
the response to edit the memory.
Can you explain us whatthat is and how it works?
Alec (07:47):
Yeah.
So, um, the way that, uh, I guess our realtime messaging training works is if you're
having conversations with people or peopleare having conversations with your A.
I.
Um, we have this little plus buttonnext to each, uh, message, uh, bubble.
And you can say, I like this message.
I want this message to betrained, or I like this message.
(08:09):
You can kind of go through the wholeconversation thread and save them to the
AI's memory so that if that same questionis asked before or asked in the past,
then you can have the same response.
And you can also make sure thatresponse is what you want it to be in.
Bob (08:24):
Yeah.
And it's an ongoing process becauseyou still have to load more documents
into its data set as it grows.
So like every new show I do, we tryto get in a cadence of putting it in.
So it continues to learn.
Yeah.
You know, my use case, I want peopleto not only be able to listen to our
podcasts and shows, be able to just toquery the bot for some quick advice.
And we see it because I've said,Oh, you're monitoring ours.
I'm always very impressed at someof the answers it comes up with.
(08:46):
It's like, wow, that actually nailed it.
It did better than I would.
And yeah, somebody asked me who was atech company and he's like, Hey, can
you write like a testimonial for me?
And I was like, just ask my bot.
Cause I want to know what it says.
And it nailed it.
I love this.
I was the one last night with nailed it.
I love it.
Like I just asked it.
Um, Like who was Morrow Fiore?
If you don't know Morrow, he's well, let'ssee what the answer it comes up with.
But we have my voice on it.
We also changed it to an avatar.
(09:08):
So we'll talk like, I mean, it's here.
I apologize, but I cannot reproduce.
Oh, we can't do that one.
Let's do that one.
Let's, we got to do a shorter one.
Who is, so we'll ask, whatis your favorite whiskey?
It should know that one.
What is your favorite whiskey?
That should know.
Yeah.
But then the idea is if it gets it wrong,you can edit it, go back and get, by
(09:28):
the way, if anybody's listening, ask mychatbot, which my favorite whiskey is.
You can send it to me for Christmas.
I'll give my home addressout to you at any time.
Um, it should be able to get theright one, but yeah, it doesn't, let's
Alec (09:38):
see if It's a long one again.
You can just play themessages for a moment.
You can hear the voice avatar.
Bob (09:45):
Yeah.
Alec (09:46):
Let me see if I can
Bob (09:46):
do that.
I'm just waiting for thevoice activation to pop up.
Alec (09:49):
Yeah, yeah.
Bob (09:50):
Let's see.
Let's go.
See?
Summarizing key pointsdiscusses the author's love
for rye whiskey , particularly whistle
pig boss haw.
I think it's 'cause it's mine.
As well as their appreciation forgood bourbons like Weller Booker . It
(10:12):
also mentions a legal talk showwhere the author enjoys sipping fine
whiskey while discussing legal topics.
So this is, this is mytesting my own internal one.
So it's summarizing it for me.
But if a user's using, it'sa different experience.
Right?
Right.
But you can see it has my voice.
Yeah.
And it got it right.
Um, but you know, the interesting thingwith this is what are some of the use
(10:36):
cases that, that you're seeing peopleuse to create their own personal ai?
We talked about law firms havingthat super user regardless of
your position at the firm, buthow are other people doing it now?
Alec (10:46):
Yeah, so that's a great question actually.
Um, so, uh, in the legal space,um, one of our customers,
uh, an advocate's ed at dia.
Yeah, I love that.
Yeah, yeah.
He, um, he's another good exampleof a legal use case right now.
He's, um, because he works inHawaii and California, right?
(11:09):
So he has two completelydifferent codes of evidence.
And he has a persona that's trained on,um, the California code of evidence as
well as the Hawaii code of evidence.
And he's able to kind of draw connectionsbetween those two codes of evidence
in the sense of, he always talksabout how he knows California better.
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 Californiathat I can use for X, Y, and Z?
Um, so he's kind of able todraw comparisons for that.
And, and, uh, he does use it fora lot of like drafting emails.
So we can do.
Um, you know, liveintegrations with the email.
So if you receive emails, you can say,Oh, I want my AI to respond to this one.
You just hit the star button or a flagand then a draft really up in your inbox
(11:58):
with the, with the email response, you
Bob (11:59):
can plug that in now.
Wow.
Alec (12:01):
And then we also do he, a lot of, um, legal use cases do involve like the,
uh, zoom meeting transcripts as well.
So, um, We also have mechanismswhere I know a lot of zoom meeting
transcripts are titled the same.
We can dump all those in thereand you can recall them by date.
What was, what did I talk about inthis meeting last week on September?
(12:22):
Whatever, what were the action items?
What were the summaries?
That's a good call.
You said what you can recordall of your meetings and then
dump into the AI summaries.
Yeah, we have one company that'suses it for the same reason, but for
earnings call reports and QB ours.
And they're actually able to draw trendsbecause they have so many of these
zoom transcripts from over the pastfrom their business and they're able
(12:44):
to draw all these analytical trendsfrom years worth of meeting transcripts
just from quarterly business reviews.
Wow.
And data.
Bob (12:52):
Yeah, and then, you know, going back to the, a lot of our listeners are
lawyers or aspiring lawyers to peoplein the legal space, you know, one of
the visions we had is imagining havingaccess to great strategy from great
trial lawyers or lawyers in their space.
Right.
Right.
And then putting them together inthis lounge that you talked about.
So you have like this beehive mentality.
It's like, imagine asking like the 20best trial lawyers a question about
(13:13):
strategy, letting them collaborateand come up with the answer.
Alec (13:16):
Yeah.
We're going to show that a lot.
Oh really?
Bob (13:18):
Oh, I love it.
Alec (13:19):
Yeah.
Yeah.
We'll show that at Lottie Gras.
So we'll have, um, a couple of differentAI personas we'll put on display for that.
And then.
We also have the, theBob Simon avatar as well.
You got it ready.
Yeah.
Yeah.
Well, can you tell youthe story about that?
No.
Okay.
So during the, so we set it up where,you know, you have to record like
the two minute long training video.
(13:40):
So, um, the responses, we can connectthem to the avatar so that if you were
to ask it a question, the responsefrom the AI can be the same response
that the avatar gives in the video.
Right.
So it would be you.
Um, And the, the, they didn'taccept our training video.
The first one that, uh, thatyou sent them, they're like, it
(14:01):
has too much, what did they say?
Too much profanity.
Oh shit.
Bob (14:06):
Well, I did.
They asked me to talk for five minutes.
So what the fuck am I goingto say if I can't swear?
Alec (14:11):
So I had to call the fricking CTO and they're like, Oh, it's fine.
I'm like, just push it through.
Like, it's fine.
This isn't going to come back through.
So we made it, it's done now.
Um, so we'll be able to show that at
Bob (14:23):
the, at Laudigrass.
I'm excited.
You know, I always say one of my goalsis to be able to do a podcast or an
interview and not actually be there.
And be in fricking Hawaii or something.
Be in the Maldives in my underwear.
I always say, you know,well, can you show it?
Cause I know you built a fun, like afunny Bob, like with my sarcasm, cause
personas, the ways that I answer thingson social media, the way that I talk.
(14:47):
Do you have some examples?
You can open your computer.
Cause we, we had to, I havehad some people testing it and
it was becoming so sarcastic.
It was a little mean.
I was like, we got to go back to theprofessional one for a little while,
but it was really funny and really good.
Like I know people were chatting.
It was like, I can't believe it'scoming up with these answers on me.
I'll
Alec (15:05):
ask it.
Uh, can you tell me about Brad Simon?
Brad Simon?
Oh, you mean my little brother?
Yeah.
I can tell you about him.
He's the co founder of ourfirm, the Simon law group.
He's also got his hands in justice HQ.
Smart kid I'll give him thatGraduated from George Washington
University in Southern Law School.
He's got a knack for real estatelitigation rarely loses emotion But
(15:26):
don't tell him I said that his egois big enough already Brad's got
this whole tech thing going on too.
He's working on some virtual tabletoprole playing game called Ravel
Wow, sounds like nerd stuff to me,but hey, whatever floats his boat
Bob (15:39):
That's good.
I mean, that's how I wouldprobably answer that question.
Yeah.
Yeah, we teach little memories tweakit a little He's technically my little
brother by six minutes, but we wouldput twin or womb mate things like this.
Yeah Oh, man, like we asked it about.
Um Maria monroy one time she does allthe you know, law rank seo and I always
tease her that she's mean I think it'sfunny, but it gave a really mean response.
(16:02):
We were laughing because we werefriends were testing it at the same
Alec (16:04):
time Yeah, yeah we had the uh Because we have your sms number right
we're able to connect the phone numbersto these personas and You Yeah, so how do
people, how do people test the Bob bot?
It's bob.
persona.
Yeah, yeah, yeah.
So you can go to, um, bob.
personal.
ai and I actually just turned onyour public chat page so people can
go on there um, and chat with your,uh, your AI bot uh, without having
(16:29):
to make an account on our platform.
Bob (16:30):
Oh, awesome.
And then that's the one thatactually has my voice on it, right?
Correct.
Yeah.
Alec (16:34):
Yeah, yeah.
So you'll be able to get those,um, those voice transcripts.
Look, I'm
Bob (16:37):
making it so easy to get deep faked.
Awesome.
I'm
Alec (16:40):
fucked.
I'm fucked.
Did you see the deepfake I sent you?
Bob (16:43):
Yeah, I used it at the Cala presentation.
Yeah, yeah.
He's gonna remove all
Alec (16:47):
my
Bob (16:48):
tattoos or something.
Now I'm a Cowboys fan and I'mgonna switch to the defense.
Yeah, deepfaking myself.
No, but I think this is like, the waythe world is going is, imagine being
able to replicate yourself, your brain.
And one thing, the idea that wehad, I think we talked about is
what I would love to be able to do.
Imagine Loading this up with all of theposts persona of like my dad, right.
(17:12):
And then, so when my, you know, he's notgoing to live forever, I hope he does,
but I would love to have my grandkidshave the ability to ask pap, pap, a
question and have an answer as him.
Right.
Um, and have an avatar of him tobe able to ask him those questions.
I mean, imagine how amazing wouldbe able to talk to your, Your
grandpa for your grandma right now.
(17:33):
Yeah, you know,
Alec (17:33):
yeah knowledge preservation.
That's kind of what ourvalue proposition is, right?
I mean, you have a lot of senior partnersthat retire from law firms every day And
that's kind of the whole thing imaginehaving the ability to still Harvest
the knowledge of a senior partner thatretires and being able to keep their
philosophies flowing by the law firm
Bob (17:54):
Yeah.
And, but in order for you to do that,you have to have uncorrupted memories.
I always think about Harry Potterwhen they take the memories
out and distort them, right?
You got to be able to have somebodyin there that's actually keeping true.
The, the archive of the memoriesand getting them in there.
But yeah, if you want to do withit for your, your parents or
grandparents, you would just need.
I'll want them to either talk alot or type a lot or interview
(18:15):
a lot to be able to get that.
Yeah,
Alec (18:16):
yeah.
I mean, you can, you can also, um,get, you know, whether it's emails,
just things that they've written.
Emails, books, um, posts,whatever it might be.
I mean, that's really all we need.
We, it's, it's getting to the pointwhere we need less and less training
data to be able to talk like you.
Bob (18:32):
So can it extract
Alec (18:33):
all of my social media posts?
Yeah.
Bob (18:35):
Oh,
Alec (18:35):
that's,
Bob (18:36):
we should add that to mine because it'd be We have, we have a lot of
things we've got to add to yours.
I'm excited.
I mean, I would love to createthis for like my parents.
I think it'd be awesome.
Or you imagine being able to talk toyour mom when she was 25 or 30, right?
If you're doing that, right.
It'd just be awesome.
Can I see mom at 40 yearsold and ask her a question?
(18:56):
You know, that'd be cool.
Alec (18:58):
And then we, uh, we, we made you like the, we have like the
professional, um, Bob bot persona.
And then we have like the, Thefun Bob, like alcoholic slash
unhinged persona that's unfiltered.
Yeah, yeah.
So we can, um, I was thinking likewhile I'm at Lautograph, you know, I
can have the computer set up and, youknow, people come ask me questions.
(19:19):
I'll just type it into fun Bob andhe can answer some of the questions.
I love it.
People are going to die, man.
People are going to be like, likethis one, uh, I asked it who, who
your other brother was, Brandon Simon.
Yeah.
And he was like, oh you mean my littlebrother he thinks he's hot shit because
he's a partner at our firm He's a diss.
He's a decent lawyer, I guess andgraduated from Thomas Jefferson with
(19:40):
some fancy honors, but it's not HarvardHe's got a thing for bourbon too, but
I doubt he can hold his liquor like Ican Spends his free time playing board
games with his life and losing from whatI hear from it with his wife and losing
This is true actually Typical Brandon,at least he got good taste in dogs.
Those Bernese Mountain dogs are probablysmarter than half our associates.
Bob (19:59):
Oh man, Bob Bot.
Bad Bob Bot.
But that was pretty funny, that'show I would answer it to his face.
Bad Bob Bot.
Bad Bob Bot.
I've been screenshotting onmy Instagram, if you go to
PlanetFunBob and see my stories.
I've been screenshotting some of thefunny answers and when it nails it.
Yeah.
Mike, something about my wife,whether she likes snakes and
it gave a very funny answer.
You should look at it.
It was really funny.
(20:20):
Um, but yeah, so, you know,how do people find you, Alec?
If people want to, you know,are interested in building
their own internal personal AI
Alec (20:27):
bot, what do they do?
Yeah.
Yeah.
So, um, anybody can go to personal.
ai.
That's our website.
Um, you can also reachout to us on LinkedIn.
We're on LinkedIn.
And, uh, you know, if you go toour website, there's personal.
ai.
There's a page where you canschedule a demo on there.
It's personal.
ai slash pricing.
Um, you can go on there andschedule a demo with us.
(20:47):
Uh, I do a lot of custom demos forpeople, so if you do schedule one
with us, I'll customize and kind ofbring these things to life for them,
for them to really be able to see.
And, um, we're starting to see a lotof traction from a lot of different
types of enterprises and stuff,because, um, the use cases with this
thing are kind of endless, you know.
(21:07):
It's, it's
Bob (21:08):
Yeah.
And what, and what do youthink's in the hurdle?
Cause so much has changedsince we built mine.
I mean, I'm just, I'mlearning new stuff right here.
But where do you, where do you think thefuture stuff is going to go for this?
Alec (21:17):
So personally, I will be running on device soon.
Um, we're currently working with alarge chip company to make that happen.
What do you mean on device?
You won't need internetto talk to the AI really.
And it can train on all your localdata, not your cloud data on device.
That'd be insane.
All private, all secure.
(21:38):
Um, and then we're also, um, workingon, uh, a couple of other things
with some large, uh, networkingcompanies, the sports retail business.
We're trying to, um, kind of scale thisthing in businesses and in law firms
because everybody can have a persona.
Every team of every business can use apersona and have that knowledge and be
(22:04):
a part of the process in a sense of,Um, efficiency, ROI, all of that stuff.
Um, we're starting to see a lot ofsuccess with, uh, these larger businesses.
Education too.
We built a fully asynchronoustutoring classroom, no teachers,
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.
Yeah.
I'd love
Bob (22:30):
to see it where, you know, in professional sports, imagine being
able to use artificial intelligenceto predict what the offensive
coordinator is going to play.
So you can run a defense on it.
It's got to be getting there.
I'm trying to train my botright now on an answer.
Yeah, yeah.
Yeah.
We're going to teach yousome information about you.
So if you're gonna reach out, ifyou have questions about Alec.
How much he can squat, what hisdating life is, what he likes to
(22:50):
eat, look like such a huge, defineddefinition of a human being.
You used to play baseball, right?
I did, yeah.
I pitched in college.
And I got into powerliftinga few years later.
Powerlifting and pitchingdo not equate together.
Not really.
No, it does not, but if you want to reachout to Alec and go to justiceteamnetwork.
com to ping the ping us here andwe'll be able to reach out to him
through there or go to personal.
(23:12):
ai to reach out to him.
But I think your emailis just alec at personal.
ai.
com.
Yeah.
Alec (23:17):
Yeah.
Uh, you can reach me at alec at personal.
ai.
Yeah.
Yeah.
Um, I'm open to any emails too.
I, I like to, um,
Bob (23:24):
But will you be answering or will be your AI bot?
Yeah.
Alec (23:28):
If my AI bot answers, I do have a signature that says, this is from Alec AI.
Oh, okay.
Yeah.
So at least people will know, like, likethe message will all look the same and
you'll still probably read through thewhole thing thinking it was from me, but
at the bottom it'll just say Alec AI.
Bob (23:44):
I love that.
I mean, even if it's given somebody, yeah.
Alec (23:46):
Wow.
So it's not like, oh, this is justsome automated bullshit AI message.
Like, no, like it's legitimately fromme because, um, it's modeled after
my previous emails, but it will say.
Bob (23:57):
Yeah, I asked how much can Alec, Alec low our squad and it says not
enough that's the answer Maybe he'll get
Alec (24:04):
791 Are too freaking smart man.
There's this one time I built thissales chat bot for our website and
we're still kind of working on itbecause You know, we want it to be cool.
We want it to be robust This thingis like spitting out memes and
contents and context of his response.
Wow GIF memes.
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
like, you know, but don't be like thisguy and it'll show like a mean girls meme.
Oh my God.
Yeah.
That's awesome.
Or, uh, and then there was one time where,you know, like Rick being Rick rolled me.
Yeah, yeah, yeah.
So the AI was like, yeah, youcan schedule a demo with us.
Um, You know, just visit thislink and you clicked on it and
(24:52):
it frickin rickrolled I told it.
Yeah, I told it to troll peoplesometimes so she'll show she
might rickroll you a few times,
Bob (25:02):
you know, that's I mean Here's the thing about the AI I know when somebody
uses AI to write emails or letters orthings and it's always too many adjectives
and it sounds like You know, you knowwhat I mean, but this is why I like this.
Cause it actually has your voice.
You can make it sarcastic.
You can make it fun, have a personality.
So that's cool.
Well, thanks for coming on thisepisode of the justice team network
(25:22):
on the justice team podcast.
Again, technology AI is all fascinating.
We're filming this in September of 2024.
It'll probably be out very shortly,but I mean, Alec, when you come
on the show six months from now,it might be completely different.
Alec (25:33):
Yeah, I'm excited.
Bob (25:35):
We might have our avatars do it.
Alec (25:37):
We should we should we should we should do it with like
I'll be in San Diego We'll befilming the podcast up here.
Oh, that'd be sick.
And I'll be in theMaldives in my underwear.
Thank you for listening
Welcome to this episode of the justice team podcast
on the justice team network.
And today we're talking about artificialintelligence and creating your own large
language model or your own chat pod.
Some use cases for it.
And I'm sitting with the person,Alec Lowi from personal AI that
actually built my chat bot.
So tell, tell everybody a little bit aboutyourself and how you got to build AI.
Alec (00:26):
Yeah, sure.
Um, well, I think the answer is you.
I think, I think that'show I got here was you.
Um, when I started working for you, Ithink it was, it's been almost a year.
I did a little bit of work for you and.
You know, you were involved withpersonally I at the time and through
that process, I kind of, um, you know,being a math major and going through a
(00:49):
lot of computer science stuff at UCLAand I had a very good understanding
of how data works and how I worked.
And when I got involved in that projectwith you, it was kind of like a, uh, an
awesome opportunity with this companyfor them to bring me on and start.
Doing some more development work for them.
Bob (01:07):
Yeah, and you know, just to give everybody a snapshot of what we're
going to be talking about here todayis the use of essentially creating
your own internal chat GBT based onyour mindset, the way that you work.
And one of the reasons I, you know,partner with personally, I had to build
my chat bot for this use case is togive what I think mentorship on scale,
(01:27):
but the ability for to have a bot beable to answer questions very quickly,
smoothly with your own intelligence, butbuilt off of your own data set, right?
Your own, not everything on theInternet, not read it, not, you
know, Pornhub or whatever, but like Idon't think you use Pornhub for mine.
Did you we could okay.
Well, maybe okay That's a little muchmaybe wiki feet So anyway, we're here
(01:51):
from Alex So whatever we went throughthis process and we'll talk about how
we built mine and how other people youyou've helped other people build Or
theirs is you know, whether they're biglawyers that have a lot of Dad out there
on them or big people in the industry.
I know there's a lot of famous folks thatare creating their owns to help their,
you know, help fans on scale some stuff.
(02:11):
So kind of walk us through how,how you built the AI chatbot.
Alec (02:16):
Yeah, of course.
Um, so for you, I, I mean, we can talkabout your use case among a lot of the
other legal use cases that we have.
Cause, um, we did started dippinginto the enterprise space, I think a
little more about four months ago andwe've had a lot of success there, but.
As far as building out the models for,uh, the legal industry, uh, we on our
(02:38):
platform, cause we have our own UI andeverything we, we, I can say kind of has
successfully designed a way for peopleto create these things on their own.
And for people to, um, I guessmaintain these models from
a user friendly perspective.
Cause when we talk about fine tuning andtraining AI's, um, It gets very confusing.
(03:00):
It's very hard.
There's a lot of developers thatinvolves and we're kind of trying to
present a way for people to just beeasily say, I have all these documents.
I have all these case files, emails,zoom transcripts, whatever it might be.
Um, upload to the model veryeasily as if you're uploading
to Google drive and everythingkind of does the rest on its own.
Bob (03:20):
Yeah.
And like one of the things, you know,your company is SOC 2 compliant, which is
the highest level to be able to have allyour, your, your data, private things like
this, but whenever you have to be ableto essentially get words onto text, to be
able to use it, text words to put into the
Alec (03:37):
model.
Bob (03:37):
Really?
Alec (03:38):
Not anymore.
Bob (03:38):
What do you do now?
Alec (03:39):
Um, we do a lot of stuff with image recognition, image in image out.
Um, we also do natural language plusimage with image out so we can Uh,
we're actually doing a lot of stufffor a sports retail business right now.
Um, creating product mock ups.
So you could think of, you havea 2023 shoe model or something.
(04:00):
And you want to create moreproduct iterations based
off of that same shoe model.
You can upload a picture of it.
Um, a prompt describing whatyou want the model to look like.
And then develop as many iterationsYou can also do, um, there was a
marketing campaign they did forChinese New Year with a new tennis
racket they just came out with.
(04:20):
And we built all these images with thattennis racket of all these different
people, um, holding it and, and likelittle teddy bears holding it in
like a Chinese New Year background.
It's like, it's, it's really cool.
Bob (04:33):
Yeah, and I know you and the team, Suman, the, the, the CEO founder, are
going to be at La De Gra this yearactually helping people, lawyers if
you're there or whoever's attending.
Yeah.
If they want to build their own, theirown personal AI, they could do that at
Alec (04:47):
the workshop at Lauderdale this year.
Yeah, exactly.
So we're, we're going to put on displaya little bit of AI orchestration.
And what I mean by that is, um, you havesenior partners that exist in a law firm.
You have paralegals, you haveresearchers, you have all these
people that work together.
Right?
Um, and we're going to put ondisplay a way for these AIs
to be able to work together.
(05:08):
So that the paralegal has the expertiseof not only just their own AI, but also
they can refer to Bob's AI, to anothersenior partner's AI, they can get
opinions from multiple people at once,take those responses and develop opinions
based off of other AI opinions as well.
Just like the
Bob (05:27):
AIs are collaborating to try to get the best answer.
Yeah, with
Alec (05:29):
all, with all, um, with all like a human in the loop, obviously, but,
um, We'll put it on display there.
It's going to be fun.
I love it.
Yeah.
And you
Bob (05:38):
know, just to show some of the, if you're building something based
off of you, like I know when youbuild ours, we had to transcribe every
episode I've done a bourbon of proofof justice team podcast, um, you know,
books that I've written, um, publishedarticles, all the trial transcripts,
deposition transcripts, and to sanitizeall those to get them into the model.
(05:58):
How, how large of a lift is that for you?
Alec (06:00):
So it's becoming less and less over time.
That's a big part of our developmentprocess is creating a lot of new training,
optimization methods and stuff like that.
Um, now I would say when we trained yourmodel, I think the process took a couple
of months for us to get all of thosefiles in there, um, and optimize them.
(06:23):
And I can happily say we've forthe same kind of volume as what
you had given us, we've shrunk thattime period down to about a week.
Um, and now we're able to kind of.
produce these models for these people,um, very, very quickly and even set
up real time training automation.
Bob (06:39):
Yeah.
And one of the other things that'sinteresting with this is you can set,
um, like a credibility score, like averacity score to see, will you allow
your thing to try to guess the answer orwill you set a higher percentage to 15,
20, 50 percent to make sure that it's,it's grabbing it to get the right answer.
Alec (06:58):
Yeah, yeah, exactly.
That's our, uh, ourpersonal score threshold.
So we have Um, a feature on our platformbecause we we try our best to Fully
prioritize accuracy and put that onthe forefront Um, so our personal score
threshold Is a way for us to kind ofmeasure The amount of data that was
used to create the AI's response.
(07:20):
And if there wasn't enough of yourdata that was used to create the
response, then the message doesn'tgo through and it'll say, let me sync
up with Bob on that or something.
Let me ask Bob.
Bob (07:28):
Yeah.
And it'll tell you, I could see whenpeople were chatting it, if I, if Bob
doesn't know the answer, it's like, well,let me ask the real Bob Simon that one.
So, which is, which is goodbecause you don't want it to guess.
Also one thing on there is youcan, As a user go in and edit
the response to edit the memory.
Can you explain us whatthat is and how it works?
Alec (07:47):
Yeah.
So, um, the way that, uh, I guess our realtime messaging training works is if you're
having conversations with people or peopleare having conversations with your A.
I.
Um, we have this little plus buttonnext to each, uh, message, uh, bubble.
And you can say, I like this message.
I want this message to betrained, or I like this message.
(08:09):
You can kind of go through the wholeconversation thread and save them to the
AI's memory so that if that same questionis asked before or asked in the past,
then you can have the same response.
And you can also make sure thatresponse is what you want it to be in.
Bob (08:24):
Yeah.
And it's an ongoing process becauseyou still have to load more documents
into its data set as it grows.
So like every new show I do, we tryto get in a cadence of putting it in.
So it continues to learn.
Yeah.
You know, my use case, I want peopleto not only be able to listen to our
podcasts and shows, be able to just toquery the bot for some quick advice.
And we see it because I've said,Oh, you're monitoring ours.
I'm always very impressed at someof the answers it comes up with.
(08:46):
It's like, wow, that actually nailed it.
It did better than I would.
And yeah, somebody asked me who was atech company and he's like, Hey, can
you write like a testimonial for me?
And I was like, just ask my bot.
Cause I want to know what it says.
And it nailed it.
I love this.
I was the one last night with nailed it.
I love it.
Like I just asked it.
Um, Like who was Morrow Fiore?
If you don't know Morrow, he's well, let'ssee what the answer it comes up with.
But we have my voice on it.
We also changed it to an avatar.
(09:08):
So we'll talk like, I mean, it's here.
I apologize, but I cannot reproduce.
Oh, we can't do that one.
Let's do that one.
Let's, we got to do a shorter one.
Who is, so we'll ask, whatis your favorite whiskey?
It should know that one.
What is your favorite whiskey?
That should know.
Yeah.
But then the idea is if it gets it wrong,you can edit it, go back and get, by
(09:28):
the way, if anybody's listening, ask mychatbot, which my favorite whiskey is.
You can send it to me for Christmas.
I'll give my home addressout to you at any time.
Um, it should be able to get theright one, but yeah, it doesn't, let's
Alec (09:38):
see if It's a long one again.
You can just play themessages for a moment.
You can hear the voice avatar.
Bob (09:45):
Yeah.
Alec (09:46):
Let me see if I can
Bob (09:46):
do that.
I'm just waiting for thevoice activation to pop up.
Alec (09:49):
Yeah, yeah.
Bob (09:50):
Let's see.
Let's go.
See?
Summarizing key pointsdiscusses the author's love
for rye whiskey , particularly whistle
pig boss haw.
I think it's 'cause it's mine.
As well as their appreciation forgood bourbons like Weller Booker . It
(10:12):
also mentions a legal talk showwhere the author enjoys sipping fine
whiskey while discussing legal topics.
So this is, this is mytesting my own internal one.
So it's summarizing it for me.
But if a user's using, it'sa different experience.
Right?
Right.
But you can see it has my voice.
Yeah.
And it got it right.
Um, but you know, the interesting thingwith this is what are some of the use
(10:36):
cases that, that you're seeing peopleuse to create their own personal ai?
We talked about law firms havingthat super user regardless of
your position at the firm, buthow are other people doing it now?
Alec (10:46):
Yeah, so that's a great question actually.
Um, so, uh, in the legal space,um, one of our customers,
uh, an advocate's ed at dia.
Yeah, I love that.
Yeah, yeah.
He, um, he's another good exampleof a legal use case right now.
He's, um, because he works inHawaii and California, right?
(11:09):
So he has two completelydifferent codes of evidence.
And he has a persona that's trained on,um, the California code of evidence as
well as the Hawaii code of evidence.
And he's able to kind of draw connectionsbetween those two codes of evidence
in the sense of, he always talksabout how he knows California better.
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 Californiathat I can use for X, Y, and Z?
Um, so he's kind of able todraw comparisons for that.
And, and, uh, he does use it fora lot of like drafting emails.
So we can do.
Um, you know, liveintegrations with the email.
So if you receive emails, you can say,Oh, I want my AI to respond to this one.
You just hit the star button or a flagand then a draft really up in your inbox
(11:58):
with the, with the email response, you
Bob (11:59):
can plug that in now.
Wow.
Alec (12:01):
And then we also do he, a lot of, um, legal use cases do involve like the,
uh, zoom meeting transcripts as well.
So, um, We also have mechanismswhere I know a lot of zoom meeting
transcripts are titled the same.
We can dump all those in thereand you can recall them by date.
What was, what did I talk about inthis meeting last week on September?
(12:22):
Whatever, what were the action items?
What were the summaries?
That's a good call.
You said what you can recordall of your meetings and then
dump into the AI summaries.
Yeah, we have one company that'suses it for the same reason, but for
earnings call reports and QB ours.
And they're actually able to draw trendsbecause they have so many of these
zoom transcripts from over the pastfrom their business and they're able
(12:44):
to draw all these analytical trendsfrom years worth of meeting transcripts
just from quarterly business reviews.
Wow.
And data.
Bob (12:52):
Yeah, and then, you know, going back to the, a lot of our listeners are
lawyers or aspiring lawyers to peoplein the legal space, you know, one of
the visions we had is imagining havingaccess to great strategy from great
trial lawyers or lawyers in their space.
Right.
Right.
And then putting them together inthis lounge that you talked about.
So you have like this beehive mentality.
It's like, imagine asking like the 20best trial lawyers a question about
(13:13):
strategy, letting them collaborateand come up with the answer.
Alec (13:16):
Yeah.
We're going to show that a lot.
Oh really?
Bob (13:18):
Oh, I love it.
Alec (13:19):
Yeah.
Yeah.
We'll show that at Lottie Gras.
So we'll have, um, a couple of differentAI personas we'll put on display for that.
And then.
We also have the, theBob Simon avatar as well.
You got it ready.
Yeah.
Yeah.
Well, can you tell youthe story about that?
No.
Okay.
So during the, so we set it up where,you know, you have to record like
the two minute long training video.
(13:40):
So, um, the responses, we can connectthem to the avatar so that if you were
to ask it a question, the responsefrom the AI can be the same response
that the avatar gives in the video.
Right.
So it would be you.
Um, And the, the, they didn'taccept our training video.
The first one that, uh, thatyou sent them, they're like, it
(14:01):
has too much, what did they say?
Too much profanity.
Oh shit.
Bob (14:06):
Well, I did.
They asked me to talk for five minutes.
So what the fuck am I goingto say if I can't swear?
Alec (14:11):
So I had to call the fricking CTO and they're like, Oh, it's fine.
I'm like, just push it through.
Like, it's fine.
This isn't going to come back through.
So we made it, it's done now.
Um, so we'll be able to show that at
Bob (14:23):
the, at Laudigrass.
I'm excited.
You know, I always say one of my goalsis to be able to do a podcast or an
interview and not actually be there.
And be in fricking Hawaii or something.
Be in the Maldives in my underwear.
I always say, you know,well, can you show it?
Cause I know you built a fun, like afunny Bob, like with my sarcasm, cause
personas, the ways that I answer thingson social media, the way that I talk.
(14:47):
Do you have some examples?
You can open your computer.
Cause we, we had to, I havehad some people testing it and
it was becoming so sarcastic.
It was a little mean.
I was like, we got to go back to theprofessional one for a little while,
but it was really funny and really good.
Like I know people were chatting.
It was like, I can't believe it'scoming up with these answers on me.
I'll
Alec (15:05):
ask it.
Uh, can you tell me about Brad Simon?
Brad Simon?
Oh, you mean my little brother?
Yeah.
I can tell you about him.
He's the co founder of ourfirm, the Simon law group.
He's also got his hands in justice HQ.
Smart kid I'll give him thatGraduated from George Washington
University in Southern Law School.
He's got a knack for real estatelitigation rarely loses emotion But
(15:26):
don't tell him I said that his egois big enough already Brad's got
this whole tech thing going on too.
He's working on some virtual tabletoprole playing game called Ravel
Wow, sounds like nerd stuff to me,but hey, whatever floats his boat
Bob (15:39):
That's good.
I mean, that's how I wouldprobably answer that question.
Yeah.
Yeah, we teach little memories tweakit a little He's technically my little
brother by six minutes, but we wouldput twin or womb mate things like this.
Yeah Oh, man, like we asked it about.
Um Maria monroy one time she does allthe you know, law rank seo and I always
tease her that she's mean I think it'sfunny, but it gave a really mean response.
(16:02):
We were laughing because we werefriends were testing it at the same
Alec (16:04):
time Yeah, yeah we had the uh Because we have your sms number right
we're able to connect the phone numbersto these personas and You Yeah, so how do
people, how do people test the Bob bot?
It's bob.
persona.
Yeah, yeah, yeah.
So you can go to, um, bob.
personal.
ai and I actually just turned onyour public chat page so people can
go on there um, and chat with your,uh, your AI bot uh, without having
(16:29):
to make an account on our platform.
Bob (16:30):
Oh, awesome.
And then that's the one thatactually has my voice on it, right?
Correct.
Yeah.
Alec (16:34):
Yeah, yeah.
So you'll be able to get those,um, those voice transcripts.
Look, I'm
Bob (16:37):
making it so easy to get deep faked.
Awesome.
I'm
Alec (16:40):
fucked.
I'm fucked.
Did you see the deepfake I sent you?
Bob (16:43):
Yeah, I used it at the Cala presentation.
Yeah, yeah.
He's gonna remove all
Alec (16:47):
my
Bob (16:48):
tattoos or something.
Now I'm a Cowboys fan and I'mgonna switch to the defense.
Yeah, deepfaking myself.
No, but I think this is like, the waythe world is going is, imagine being
able to replicate yourself, your brain.
And one thing, the idea that wehad, I think we talked about is
what I would love to be able to do.
Imagine Loading this up with all of theposts persona of like my dad, right.
(17:12):
And then, so when my, you know, he's notgoing to live forever, I hope he does,
but I would love to have my grandkidshave the ability to ask pap, pap, a
question and have an answer as him.
Right.
Um, and have an avatar of him tobe able to ask him those questions.
I mean, imagine how amazing wouldbe able to talk to your, Your
grandpa for your grandma right now.
(17:33):
Yeah, you know,
Alec (17:33):
yeah knowledge preservation.
That's kind of what ourvalue proposition is, right?
I mean, you have a lot of senior partnersthat retire from law firms every day And
that's kind of the whole thing imaginehaving the ability to still Harvest
the knowledge of a senior partner thatretires and being able to keep their
philosophies flowing by the law firm
Bob (17:54):
Yeah.
And, but in order for you to do that,you have to have uncorrupted memories.
I always think about Harry Potterwhen they take the memories
out and distort them, right?
You got to be able to have somebodyin there that's actually keeping true.
The, the archive of the memoriesand getting them in there.
But yeah, if you want to do withit for your, your parents or
grandparents, you would just need.
I'll want them to either talk alot or type a lot or interview
(18:15):
a lot to be able to get that.
Yeah,
Alec (18:16):
yeah.
I mean, you can, you can also, um,get, you know, whether it's emails,
just things that they've written.
Emails, books, um, posts,whatever it might be.
I mean, that's really all we need.
We, it's, it's getting to the pointwhere we need less and less training
data to be able to talk like you.
Bob (18:32):
So can it extract
Alec (18:33):
all of my social media posts?
Yeah.
Bob (18:35):
Oh,
Alec (18:35):
that's,
Bob (18:36):
we should add that to mine because it'd be We have, we have a lot of
things we've got to add to yours.
I'm excited.
I mean, I would love to createthis for like my parents.
I think it'd be awesome.
Or you imagine being able to talk toyour mom when she was 25 or 30, right?
If you're doing that, right.
It'd just be awesome.
Can I see mom at 40 yearsold and ask her a question?
(18:56):
You know, that'd be cool.
Alec (18:58):
And then we, uh, we, we made you like the, we have like the
professional, um, Bob bot persona.
And then we have like the, Thefun Bob, like alcoholic slash
unhinged persona that's unfiltered.
Yeah, yeah.
So we can, um, I was thinking likewhile I'm at Lautograph, you know, I
can have the computer set up and, youknow, people come ask me questions.
(19:19):
I'll just type it into fun Bob andhe can answer some of the questions.
I love it.
People are going to die, man.
People are going to be like, likethis one, uh, I asked it who, who
your other brother was, Brandon Simon.
Yeah.
And he was like, oh you mean my littlebrother he thinks he's hot shit because
he's a partner at our firm He's a diss.
He's a decent lawyer, I guess andgraduated from Thomas Jefferson with
(19:40):
some fancy honors, but it's not HarvardHe's got a thing for bourbon too, but
I doubt he can hold his liquor like Ican Spends his free time playing board
games with his life and losing from whatI hear from it with his wife and losing
This is true actually Typical Brandon,at least he got good taste in dogs.
Those Bernese Mountain dogs are probablysmarter than half our associates.
Bob (19:59):
Oh man, Bob Bot.
Bad Bob Bot.
But that was pretty funny, that'show I would answer it to his face.
Bad Bob Bot.
Bad Bob Bot.
I've been screenshotting onmy Instagram, if you go to
PlanetFunBob and see my stories.
I've been screenshotting some of thefunny answers and when it nails it.
Yeah.
Mike, something about my wife,whether she likes snakes and
it gave a very funny answer.
You should look at it.
It was really funny.
(20:20):
Um, but yeah, so, you know,how do people find you, Alec?
If people want to, you know,are interested in building
their own internal personal AI
Alec (20:27):
bot, what do they do?
Yeah.
Yeah.
So, um, anybody can go to personal.
ai.
That's our website.
Um, you can also reachout to us on LinkedIn.
We're on LinkedIn.
And, uh, you know, if you go toour website, there's personal.
ai.
There's a page where you canschedule a demo on there.
It's personal.
ai slash pricing.
Um, you can go on there andschedule a demo with us.
(20:47):
Uh, I do a lot of custom demos forpeople, so if you do schedule one
with us, I'll customize and kind ofbring these things to life for them,
for them to really be able to see.
And, um, we're starting to see a lotof traction from a lot of different
types of enterprises and stuff,because, um, the use cases with this
thing are kind of endless, you know.
(21:07):
It's, it's
Bob (21:08):
Yeah.
And what, and what do youthink's in the hurdle?
Cause so much has changedsince we built mine.
I mean, I'm just, I'mlearning new stuff right here.
But where do you, where do you think thefuture stuff is going to go for this?
Alec (21:17):
So personally, I will be running on device soon.
Um, we're currently working with alarge chip company to make that happen.
What do you mean on device?
You won't need internetto talk to the AI really.
And it can train on all your localdata, not your cloud data on device.
That'd be insane.
All private, all secure.
(21:38):
Um, and then we're also, um, workingon, uh, a couple of other things
with some large, uh, networkingcompanies, the sports retail business.
We're trying to, um, kind of scale thisthing in businesses and in law firms
because everybody can have a persona.
Every team of every business can use apersona and have that knowledge and be
(22:04):
a part of the process in a sense of,Um, efficiency, ROI, all of that stuff.
Um, we're starting to see a lot ofsuccess with, uh, these larger businesses.
Education too.
We built a fully asynchronoustutoring classroom, no teachers,
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.
Yeah.
I'd love
Bob (22:30):
to see it where, you know, in professional sports, imagine being
able to use artificial intelligenceto predict what the offensive
coordinator is going to play.
So you can run a defense on it.
It's got to be getting there.
I'm trying to train my botright now on an answer.
Yeah, yeah.
Yeah.
We're going to teach yousome information about you.
So if you're gonna reach out, ifyou have questions about Alec.
How much he can squat, what hisdating life is, what he likes to
(22:50):
eat, look like such a huge, defineddefinition of a human being.
You used to play baseball, right?
I did, yeah.
I pitched in college.
And I got into powerliftinga few years later.
Powerlifting and pitchingdo not equate together.
Not really.
No, it does not, but if you want to reachout to Alec and go to justiceteamnetwork.
com to ping the ping us here andwe'll be able to reach out to him
through there or go to personal.
(23:12):
ai to reach out to him.
But I think your emailis just alec at personal.
ai.
com.
Yeah.
Alec (23:17):
Yeah.
Uh, you can reach me at alec at personal.
ai.
Yeah.
Yeah.
Um, I'm open to any emails too.
I, I like to, um,
Bob (23:24):
But will you be answering or will be your AI bot?
Yeah.
Alec (23:28):
If my AI bot answers, I do have a signature that says, this is from Alec AI.
Oh, okay.
Yeah.
So at least people will know, like, likethe message will all look the same and
you'll still probably read through thewhole thing thinking it was from me, but
at the bottom it'll just say Alec AI.
Bob (23:44):
I love that.
I mean, even if it's given somebody, yeah.
Alec (23:46):
Wow.
So it's not like, oh, this is justsome automated bullshit AI message.
Like, no, like it's legitimately fromme because, um, it's modeled after
my previous emails, but it will say.
Bob (23:57):
Yeah, I asked how much can Alec, Alec low our squad and it says not
enough that's the answer Maybe he'll get
Alec (24:04):
791 Are too freaking smart man.
There's this one time I built thissales chat bot for our website and
we're still kind of working on itbecause You know, we want it to be cool.
We want it to be robust This thingis like spitting out memes and
contents and context of his response.
Wow GIF memes.
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
like, you know, but don't be like thisguy and it'll show like a mean girls meme.
Oh my God.
Yeah.
That's awesome.
Or, uh, and then there was one time where,you know, like Rick being Rick rolled me.
Yeah, yeah, yeah.
So the AI was like, yeah, youcan schedule a demo with us.
Um, You know, just visit thislink and you clicked on it and
(24:52):
it frickin rickrolled I told it.
Yeah, I told it to troll peoplesometimes so she'll show she
might rickroll you a few times,
Bob (25:02):
you know, that's I mean Here's the thing about the AI I know when somebody
uses AI to write emails or letters orthings and it's always too many adjectives
and it sounds like You know, you knowwhat I mean, but this is why I like this.
Cause it actually has your voice.
You can make it sarcastic.
You can make it fun, have a personality.
So that's cool.
Well, thanks for coming on thisepisode of the justice team network
(25:22):
on the justice team podcast.
Again, technology AI is all fascinating.
We're filming this in September of 2024.
It'll probably be out very shortly,but I mean, Alec, when you come
on the show six months from now,it might be completely different.
Alec (25:33):
Yeah, I'm excited.
Bob (25:35):
We might have our avatars do it.
Alec (25:37):
We should we should we should we should do it with like
I'll be in San Diego We'll befilming the podcast up here.
Oh, that'd be sick.
And I'll be in theMaldives in my underwear.
Thank you for listening
Popular Podcasts
United States of Kennedy
United States of Kennedy is a podcast about our cultural fascination with the Kennedy dynasty. Every week, hosts Lyra Smith and George Civeris go into one aspect of the Kennedy story.
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com