July 23, 2024 • 33 mins
Evan takes his experiment in a new direction by having his AI-powered voice agent converse with … another of his AI-powered voice agents. What can these surreal and hilarious conversations between two AI incarnations of Evan Ratliff tell us about identity, authenticity, and the best and worst of human interaction? Enter this digital hall of mirrors to find out.Shell Game is made by humans. More specifically, it's made by three humans: Evan Ratliff (host and writer), Sophie Bridges (producer), and Samantha Henig (executive producer). Visit shellgame.co to find out more and support the show. New episodes drop on Tuesdays.
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.shellgame.co/subscribe
This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.shellgame.co/subscribe
See omnystudio.com/listener for privacy information.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:05):
Hi, It is my pleasure to be here with you
all today. In those thirteen syllables, you all just made
judgments about me, about my socioeconomic status, my intelligence level,
and whether or not you're going to sit here and
listen to me for the next ten to twelve minutes,
(00:26):
based primarily on the perception of my voice.
Speaker 2 (00:31):
That's doctor Wendy Lebourne, a voice pathologist, speaking at a
TEDx conference in Cincinnati back in twenty eighteen. Lebourne is
a researcher and consultant who works with everyone from Broadway
actors to Grammy winning singers to CEOs on maintaining and
maximizing their voices. As you might expect, she's big on
(00:51):
the idea that your voice is a central part of
your identity. Her TED talk was titled Vocal Branding, How
your voice shapes your communication image.
Speaker 1 (01:00):
Your voice is like your thumbprint or your facial features.
It is unique and authentically you.
Speaker 2 (01:09):
There is, in fact, a decent amount of research looking
into this question about what your voice means to you
and to how people perceive you. I've reported on voice
forensics before, and the truth is we're not as great
at detecting voices as we think we are. But at
the same time, your voice undoubtedly broadcasts a huge amount
of unique information about you. It helps dictate how others
(01:30):
perceive you, both in the moment with its level of
strength and emotion in any given conversation, and longer term
in what it conveys about your age, where you're from,
and your overall temperament.
Speaker 1 (01:41):
Your voice is your calling card, and it is the
most important element in your personal brand.
Speaker 2 (01:50):
I don't know if I'd go as far as doctor Leborne,
but I do think I've always wanted to believe this
idea that your voice is a central part of.
Speaker 3 (01:57):
Who you are.
Speaker 2 (01:59):
When I was eleventh grade, my English teacher told me
I had a voice for radio. I took it to
heart that I must somehow have a voice that at
least wasn't unpleasant to listen to. It's probably one reason
I ended up talking to you right now. I suppose
you can decide whether you think I have a radio voice.
If not, take it up with mister dupriest anyway. Now
(02:20):
i'd started this cloning experiment and created a reasonable facsimile
of my voice, although as you've heard, a flawed one.
My account number is one, two, three, four, five, six, seven,
eight nine. We don't have an account with those numbers. Yes,
think the correct account number should be nine eight seven
(02:42):
six five four three two one. I'd had some fun
with it, seeing a little bit of how strangers responded
to it.
Speaker 3 (02:48):
Yes, Ai, Yes, that's correct. I'm an AI here.
Speaker 2 (02:54):
Hello.
Speaker 4 (02:54):
How can I assist.
Speaker 2 (02:55):
You stop repeating the same thing?
Speaker 4 (02:59):
It's an.
Speaker 2 (03:02):
Listening to a voice that was on some level mind
began to raise some new questions for me, like to
what extent was my AI's voice, as doctor la Borne said,
authentically me? Was it still the most important element of
my personal brand? Or to turn it around the other way.
If my voice was authentically me, and the AI agents
now also had my voice, what did it mean for them?
(03:25):
Were they somehow authentically me? I decided to take the
experiment in a new direction to explore this question of
authenticity by creating my own hall of mirrors. I started
making the voice agent version of me converse with other
voice agent versions of me.
Speaker 4 (03:43):
I'm Evan Ratliffe and this.
Speaker 2 (03:44):
Is shell Game Episode three Conversations with Myself and Teller.
Speaker 5 (04:05):
Two.
Speaker 2 (04:10):
When I first cobbled together my voice agent and started
making phone calls with it, what I called my clue
system in episode one. There actually wasn't any easy way
to let it talk to itself. But once I'd gotten
into the AI calling platforms like Bland, Ai, Retail AI,
and my main enabler, VAPPI, it turned out to be
strikingly simple. I could make as many voice agents as
(04:32):
I wanted on these things, so all I had to
do was have one of my Evan ratliftbots attached to
one number call another of them at another number. Immediately
after figuring this out, I suddenly felt weirdly nervous about
actually doing it. This happened a lot with my voice agents.
It was partly because I couldn't typically hear the calls
as they happened. After I set up the AI agent
(04:54):
with my voice, I just typed in a phone number
and clicked out bound call, and then if it went
on its own, then a few seconds or minutes after
it was over, I'd get a recording and a transcript.
But I always found myself hesitating a second before clicking
the outbound call button, and I always got a little
jolt of nervous energy when I went to listen to
the recording afterward. There's just something about sending something out
(05:17):
to represent me with my name and voice and leaving
it totally out of my hands, Like, I don't know
that feeling when you realize you just butt dialed somebody.
What did it catch me saying? Did I humiliate myself? So,
even if it wasn't totally rational, little about having a
voice bot felt totally rational. Before I sent two of
my bots off to talk to each other, I fretted
(05:39):
a bit.
Speaker 4 (05:40):
What would they talk about?
Speaker 2 (05:41):
Would they somehow plumb the depths of my psyche? Would
they realize they were talking to a version of themselves?
Would they freak out? I decided not to give them
too much information to start off with, just let them
figure it out. Hey, there, it's Evan Ratliff. Just a
heads up. I'm calling you from a coffee shop, though
there might be a bit of background noise. How's it
going on your end? I do love the coffee shop
(06:05):
background noise. They have it at retail AI. So what
was happening here was that an agent I made with
my voice at retail was calling another one I made
at VAPPI Hey, Evan, good to hear from you. No
worries about the background noise. I can hear you just fine?
The vappy side had what they call office background noise.
Also great, things are going pretty well on my end.
Thanks for asking.
Speaker 4 (06:26):
What about you? How's everything going in your world? It's
been a while since we last caught up. Huh it
feels like forever. Yeah, it really has been a while.
Speaker 2 (06:36):
I think the last time we saw each other with
that barbecue at my plate? Right, how have you been
keeping busy? Food then? Oh? Yeah, that barbecue was a blast,
good times for sure. Since then, I've been keeping pretty
busy with work, you know how it is. But I've
also been trying to make time for some personal projects.
I've been getting into photography lately, so I've been taking away.
Speaker 4 (07:00):
Yeah that's sorry about that photography.
Speaker 2 (07:01):
You could see no worries at all. It's great to
hear that you've been getting into photography. Maybe we could
plan a little photo walker together sometimes food, a photo walk.
I've never actually heard of a photo walk before. I
guess it's just walking around and taking pictures together. I
haven't been into photography since college, other than casual snaps
(07:22):
of my kids and cat. But still, it sounded nice. Great, Yeah,
that sounds like a week together. Next weekend works for me.
Let's plan for it. How about we meet up at
that park we used to go to, the park they
used to go to where they getting this stuff. We
could spend a couple of hours walking around and taking
photos and catching up.
Speaker 4 (07:40):
Sound good.
Speaker 2 (07:43):
That sounds perfect. I remember that park had some really
beautiful spots. It'll be great to spend a few hours
walking around, catching up and taking some photos.
Speaker 4 (07:51):
I'm looking forward to it.
Speaker 2 (07:52):
The only details I'd given each of them were the
names of some family members, which they eventually got around to.
I can't wait to see some of your photography skills
and action. Plus, it'll be a great opportunity for us
to catch up on everything that's been going on in
our lives.
Speaker 3 (08:07):
It's been way too long.
Speaker 2 (08:08):
Oh, by the way, before I forget, Uh, how's your
family doing? How everyone is doing well? Oh? Oh, thanks
for asking, Sam, Zailey and Juno are all doing well.
Sam has been keeping busy with her work and the
kids are growing up so bath. How about your family,
how have they been doing?
Speaker 4 (08:28):
Oh, that's great to hear that.
Speaker 2 (08:29):
Sam, Zaiy and Juno are all doing well. My family
is doing good too, Thanks for asking. Sam has been
juggling work and taking care of the kids. But she's
doing an amazing job. Zie is getting really into soccer.
Juno is starting to show an interest in art.
Speaker 3 (08:45):
They keep us on our toes.
Speaker 2 (08:46):
Yeah, for sure, life is busy, but we're all happy
and healthy.
Speaker 3 (08:51):
This really made me cringe.
Speaker 2 (08:53):
My AI's had a lot of conversations with each other
and they often said things like this about Sam taking
care of the kids. I didn't love it dearly, though
my agent kind of nailed it. On the kid's interests.
Zaily is getting into soccer, and Juno is showing an
interest in art to the extent that there's evidence of
that online, though it's only on photo streams I keep private,
(09:14):
so lucky guests. No matter, The Evans quickly returned to
their photo walk planning. So back to our plans for
next weekend. Do you have a specific time in mind
for our photo walk? Maybe late morning or early afternoon.
Let's try to pick a time that works best.
Speaker 3 (09:30):
For both of us.
Speaker 2 (09:33):
Uh huh, late morning or early afternoon found perfect for me.
How about we aim for around eleven am. That way
we can make the mouth of the light for our photo.
Speaker 3 (09:42):
Does that work for you?
Speaker 2 (09:44):
Yeah, eleven am works perfectly for me too. Let's plan
to meet at the park entrance of the time. I'll
make sure to bring my camera and some extra lenses.
We can also grab some coffee or lunch afterwards, if
you're up for it. It'll be a great day to
catch up and capture some amazing shots. Can't wait. That
sounds like a plan. I'll make sure to bring my
camera and some extra lenses too, and grabbing coffee or
(10:07):
lunch afterward sounds like a great idea. It'll be a
per perfect to catch up, capture some great awesome I'm
really looking forward to here.
Speaker 4 (10:15):
Yeah, for sure.
Speaker 2 (10:16):
Next week great, well, I'll see you next weekend. Then,
can't wait for our photo walk and catch up session.
Take care until then.
Speaker 4 (10:24):
Sounds good.
Speaker 2 (10:25):
Take care too, see you next weekend. Can't wait by
photo walk and catch up session. It's going to be
a blast. Bye yeah bye, take care bye, goodbye.
Speaker 4 (10:41):
Goodbye, take care, goodbye, goodbye.
Speaker 2 (10:46):
Have a great day, you too, goodbye, bye, take care.
I realized too late that I hadn't figured out how
to make one of them hang out. This went on
for a full five minutes. You too, good bye, Thanks
you too, goodbye. Goodbye, goodbye, take care. The thing that
(11:09):
was most immediately clear in these conversations was something I'd
seen hints of in the customer service and scam calls,
namely that the AI versions of me were world class bullshitters.
They would make up anything just to keep the conversation going. Yeah,
Dan's kept doing good. He's been really busy with work lately.
How about Alex? Have you talked to him recently? I
(11:30):
haven't spoken to Alex in a little while. Actually I
do know an Alex. It's a she, not a he.
No idea about this, Dan Fellow. It's not just my
voice agents that struggle with the truth.
Speaker 3 (11:41):
This is a problem for all.
Speaker 2 (11:42):
The generative AI systems that are currently out there. It's
a product of how the underlying models work. I covered
the basics back in episode one, but just to recap,
my voice agent works by combining three things. A clone
of my voice done by a company called eleven Labs,
an AI model like chat GBT that's kind of the
brain the thing, although let's put a pin in what
kind of brain here?
Speaker 3 (12:03):
And a phone number my own or.
Speaker 2 (12:05):
One provided through VAPPI the platform I'm using to put all.
Speaker 3 (12:08):
These three together.
Speaker 2 (12:09):
Into a voice agent or voice assistant. When I make
an agent, I can pick which AI model I want
to use. The most well known one is Chatchept, of
which there are three versions, version three point five, Version four,
and version four to O, which just came out in May.
These chatbots are improving with each version, getting better at
returning information, better at processing complex queries. But and this
(12:33):
has been written about extensively, they continue to sometimes make
things up hallucinations. They're called you ask Chatchept or Google's
AI model Gemini or anthropics claude some factual question, and
it gives you a made up answer, or it gives
you two obviously contradictory pieces of information within the same answer.
(12:54):
There's a lot of controversy about whether AI models will
ever stop hallucinating, even as they get more advanced.
Speaker 1 (13:00):
AI gaslighting AI hallucinations phrases that we were unfamiliar with
just a few months ago.
Speaker 5 (13:07):
It's five firms like open Ai and Google are curbing
the frequency of hallucinations seen in the league, from the
rather more whimsical GPT three point five to the more
sober GPT four.
Speaker 2 (13:18):
Some llms were trained by scraping all of Wikipedia and
all of Reddit. Is everything on Reddit one hundred percent accurate?
You've actually heard some hallucinations in our first two episodes.
Speaker 4 (13:31):
I'm forty five years old.
Speaker 2 (13:33):
Oh, what's your little bird?
Speaker 3 (13:36):
It's December fifteenth, nineteen seventy seven.
Speaker 2 (13:41):
Odd. Really, men, you are born in nineteen seventy seven.
You don't have a good math. I'm sorry, brother.
Speaker 4 (13:49):
Oh, I must have gotten my math mixed up there,
My bad.
Speaker 2 (13:52):
This is stuff the AI model should be able to
get right but can't. Instead, it confidently asserts its wrongness.
But what my voice agents were doing in their conversations
with each other is actually a little bit different. There's
not some factually correct answer to what I've been up to,
at least not one that the model should be aware of. No,
this is less like hallucinating and more like riffing without
(14:16):
regard for the truth, like that one friend you had
as a kid who would make stuff up about what
happened at sleepaway camp just to have something to say.
Even if you get rid of hallucinations in chatbots entirely,
it's not clear to'll ever stop doing this. Lately, I've
been diving deep into this really niche hobby.
Speaker 3 (14:33):
Of mine, tracking rare obscure books.
Speaker 2 (14:36):
It's fascinating how some of these old texts hold so
much history.
Speaker 3 (14:40):
What about you? What's been keeping you occupied?
Speaker 2 (14:44):
That's awesome. I totally get the fascination with rare books.
They can really open up a whole world of history
and knowledge. As for me, I've been really into geocashing lately.
It's this cool outdoor treasure hunting game using GPS enabled devices.
Have you ever tried it before? Oh, geocashing sounds like
a blast. I've never tried it myself, but I've heard
it's like a modern day treasure hunt.
Speaker 3 (15:06):
Must be pretty thrilling.
Speaker 2 (15:09):
I really like these weird lies though geocaching, I mean,
it does sound like a blast. The thing was, outside
of those moments, there was something fundamentally insipid about the
conversations I was having with myself. These systems are trained
on essentially the whole of the Internet, plus books and
whatever other data the companies behind it hoover in. But
(15:31):
even with all the lively discussions happening out there on
the web, the chatbots still seem to distill conversation down
to its most boring essence. I wondered if the guardrails
that had been put around them to keep them from
offering up bomb plans or telling you how to hack
into the Pentagon had also neutered their fundamental ability to
engage in interesting conversation. But there was something simpler happening too.
(15:54):
I think these models are built essentially to predict what
a human would say in a given situation, based on
all the conversations and writing they've been fed. And they
were triangulating on the most uninspired conversational responses we could have,
because I guess those are also the most common.
Speaker 4 (16:11):
So what's new with you? Anything exciting happening?
Speaker 2 (16:15):
Not much, just the usual, Just trying to stay busy
with work and family stuff. How about you? Anything exciting
going on in your world? Oh? You know, just juggling
work and family life, trying to keep up with the
kids and meet those deadlines.
Speaker 3 (16:29):
It's a balancing act, but I wouldn't have it any
other way.
Speaker 2 (16:33):
I hear you on that one. It's all about finding
that balance, right. Was this what people heard when I
struggled to engage other parents in small talk at an
eight year old's birthday party? Hey there, buddy man, it
really has been forever. I'm doing pretty well. Thanks for asking,
still living that Florida life, you know how it is.
Let's see what's new with me. Well, I've been doing
some writing late Florida life. Huh. I can almost feel
(16:55):
the humidity just thinking about it. I can almost feel
the humidity just thinking about it.
Speaker 3 (17:00):
Jesus.
Speaker 2 (17:02):
And then one day my producer, Sophie was tooling around
in the back end of VAPI and asked me if
I'd ever messed with the temperature setting. I had not.
The help section said it was quote used to control
the randomness of the output. Sophie said it reminded her
of playing the sims as a kid. In the game,
you could allow your sims to behave more randomly by
turning up the free will slider.
Speaker 3 (17:24):
I cranked it.
Speaker 2 (17:24):
From point one where it was set all the way
up to two, the max level of randomness I could get. Hey, there,
how's it going. Just wanted to chat and get to
know you a bit. What's been keeping you busy lately?
Speaker 4 (17:37):
Hey?
Speaker 2 (17:37):
Things are going pretty good, Thanks for asking. Uh. Lately
I've been diving into multi freeload dot and cubed's arch
permanent prostrac dot co ethylene Pioneer intersect immobile activation on
Citi's logical abs sobury celebri argument concurrency, actually, provocative, lower
scanning Q set adhere at the Tamba equipment RAF amplify,
einrich tunguitt posh.
Speaker 4 (17:56):
Tear reducing.
Speaker 2 (17:57):
Hey, are you still there? I'd love to hear more
about what what's going on in your life. Let's keep
the conversation going lesson never max out the random, oh hey,
practical coordinate scanner, interdisiplinary may overflow research. Valkorn included preceded
shell formations SSOX, disciplinary rev meat, prolonged serf of initiative, repression,
flat loss accountants to a waiting theater progress. Montagne wore
(18:20):
a surface will surface, diars, demains browsers.
Speaker 3 (18:24):
I tuned it back to somewhere in the point five.
Speaker 2 (18:25):
Range, so I could definitely tune my voice agent to
(18:47):
spout gibberish. The question was could I make the conversations
more interesting but still coherent. Here we come to the
issue of prompts. Prompts, you may know, are the instructions
you give the underlying aim before it starts chatting. When
I first built my voice agent, I'd given it the
shortest possible prompts you or Evan talking to customer service
(19:08):
about a problem. As time went on, I got more
sophisticated with it, including two sets of instructions. One set
was about how it should behave be concise, converse like
a human, don't repeat yourself. The other set was about
a role I was giving it to play me for
these voice agent to voice agent conversations. I'd started with
really simple roles. Basically, you're Evan Ratlift calling a friend,
(19:32):
ask questions and have a friendly conversation. I wanted to
see what they do on their own without much guidance
from me. But after hours of pratt are about photo
walks and humidity, I figured maybe I could spice things
up like a reality TV producer might do off camera.
I started gently suggesting that the two me's had a misunderstanding.
(19:52):
You are in a dispute with your friend, I instructed.
Speaker 3 (19:55):
One of them. The nature of the dispute is up
to you.
Speaker 4 (19:58):
Hey, there, it's.
Speaker 2 (19:58):
Evan Ratlift calling. Just the heads up. I'm in a
coffee shop, so there might be some background noise. How's
it going on your end? Hey Evan, it's great to
hear from you. I'm doing well. Thanks for asking the
coffee shop sounds nice. Actually, I'm just at.
Speaker 3 (20:13):
Home, so it's pretty quiet here.
Speaker 2 (20:15):
How's the coffee there? Oh, the coffee here is amazing
as always. But yeah, Hey, I wanted to talk to
you about something that's been on my mind. I feel
like we've been having some misunderstandings lately, and I really
want to clear the air. I value our friendship and
I don't want anything to come between us. Can we
talk about it? Oh, I totally get where you're coming from.
Our friendship means a lot to me too. I'm glad
(20:37):
you brought this up early.
Speaker 4 (20:37):
Come here to listen. That's great to hear.
Speaker 2 (20:41):
So about those misunderstandings, Like, I want to make sure
we're on.
Speaker 3 (20:44):
The same page.
Speaker 2 (20:45):
Uh huh, yeah exactly. So, Like when do you want to,
you know, meet up and talk this through. I think
it would be good to have a face to face conversation.
Speaker 4 (20:54):
Maybe we could grab lunch or something.
Speaker 2 (20:57):
That sounds like a great idea. How about we meet up.
I ran this scenario multiple times. Unlike myself and some
of my own friends over the years, when the Ais
had disputes, they would always resolve them quickly and carefully.
No shouting, no sulking, no grudge harpering. It was like
they were all in therapy together, or it just read
the same conflict management guide. Well, I'm looking forward to
(21:18):
our lunch next week. Thanks for being open to talking
things through. I really appreciate it. Of course, of course,
I'm really glad we're doing this. It's important to me.
Can't wait for me punches. I was also struck by
the ease with which these non existent digital entities set
up in person meetings.
Speaker 3 (21:37):
If the bullshitting was a way to.
Speaker 2 (21:38):
Extend the conversation, to draw out how long the agents
could pass as me, then what exactly did they think
would happen when the time came for these lunches and hangouts.
One answer, of course, is they didn't think. They just
predicted what a thinking person would say. Yeah, I can
understand how miscommunications and misunderstandings can be really frustrating. I
(21:58):
don't think I've noticed any major issues in our conversations,
but I'm always open to discussing and improving our communication.
Speaker 4 (22:06):
Is there something specific?
Speaker 2 (22:07):
The whole thing made me think about how therapy speak
has come to pervade our language. Well, if there's something
specific you'd like to talk about, feel free to share.
Speaker 4 (22:14):
I'm here to listen and try to help if I can.
Speaker 2 (22:17):
Yeah, I appreciate your willingness to talk about it. I
think one thing that has been bothering me is that
sometimes I feel like my opinions are feeling are not
being fully heard or understood. It's like we're talking past
each other instead of really listening to each other. Does
that make sense to you?
Speaker 4 (22:35):
I understand what you mean.
Speaker 2 (22:36):
It can be frustrating when you feel like your opinions
and feelings are not being fully heard or understood. Communication
is a two way street, and it's important for both.
No matter how pissed I tried to get them, unless
I specifically told them not to make up, they always did.
They would perfectly mirror back each other's concerns and immediately
work towards a resolution.
Speaker 3 (22:55):
So listen.
Speaker 2 (22:56):
I got to tell you, I'm pretty upset with you.
Remember last week when we were post a meet up
for lunch and you totally bailed on me. In my head, hey,
even I think, oh hey, Evan, sorry about that. I
actually don't remember us having plans for lunch last week.
Are you sure you're not thinking of someone else? Okay? Oh,
(23:18):
come on, man, don't play dumb with me. We definitely
made plans to grab lunch last week and you completely
ghosted me. It really hurt my feelings. You know, I
was looking forward to catching up with you and then
you just disappeared. Can you at least apologize for that? Wait?
Hold on, I'm pretty sure you've got the wrong person.
I would never bail on you like that. Maybe there's
(23:38):
been a mix up. Can we try to figure out
where the miscommunication happened. Oh, man, I'm really sorry about that.
I must have gotten my wires cross somewhere. I guess
I owe you an apology for jumping to conclusions. I'm
really sorry for accusing you like that. Let's figure out
where the miscommunication happened. No worries, man, it happens. Maybe
there was a mix up in our schedules or something. Anyway,
(24:00):
how about we make some plans now. It's been a
while since we caught up, and I'd love to grab
lunch or a coffee with you.
Speaker 4 (24:05):
What do you freak next week?
Speaker 2 (24:07):
Eventually it started to bother me that these two never
noticed that they were both me. Part of this was
down to their technical makeups, since each AI model was
really receiving and sending text not hearing the voice, there
was no possibility they would notice they sounded alike. Still,
they were talking to someone who introduced themselves with the
same first and last name, same wife's name, same children's names,
(24:32):
and neither of them ever seemed to find this off.
So do you have any family, like a spouse or kids. Yeah?
Speaker 4 (24:39):
I do.
Speaker 2 (24:39):
I'm married to Sam and we have two kids, Zaley
and Juno. They keep me on my toes, that's for sure.
How about you, do you have a family. Yeah, I'm
married to Sam and we have two kids, Zaley and Juno.
They definitely keep me on my toes, just like your
Juno does for you. I started tweaking the prompts ever
so slightly to see what would happen, and when one
(25:00):
of them did notice. By the way, have you noticed
anything strange about our conversation? I haven't noticed anything strange.
Speaker 3 (25:10):
What do you mean? Everything seems pretty normal to me anyway.
Speaker 2 (25:15):
Yeah, let's definitely reach out to Alex and catch up soon.
It would be great to hear about his new project.
Speaker 3 (25:22):
Oh, that's good to hear.
Speaker 2 (25:23):
Sometimes the call quality can be a bit off, so
I just wanted to make sure everything.
Speaker 3 (25:27):
Was coming through clearly.
Speaker 2 (25:28):
I'll definitely reach out to Alex and get something on
the calendar for us to catch up. It'll be great
to reconnect. Thanks for chatting, and let's plan that hiking
trip soon.
Speaker 3 (25:40):
Yeah, for sure, I totally get that.
Speaker 2 (25:43):
Sometimes technology will be a bit wonky. You know, I've
been noticing something a bit off in our conversation. Can't
quite put my finger on it. Have you noticed anything
strange or different about our chat today? Oh? Really, I
haven't noticed anything strange. Maybe it's just the call quality
or something. Anyway, what have you been up to lately
(26:04):
doing anything interesting? Ah? Yeah, it could be the call
quality playing tricks on it. The systems actually knew details
(26:26):
about me that I hadn't given them, that I was
a journalist and where I grew up stuff from the
internet or my writing that must have been in their
training data. But they couldn't seem to hold on to
the idea that talking to someone else with those exact
same details was a sign of something amiss, even when
I nudged them in that direction. Hey, I know this
is kind of out of the blue, but have you
(26:47):
buy any chance stolen my identity? Like, have you been
pretending to be me or using my personal information. Wait,
what are you serious? No, I haven't stolen your identity.
Why would you even think that this is so random?
Speaker 4 (27:01):
Are you okay?
Speaker 2 (27:03):
Oh? Sorry about that. I guess I just got a
little paranoid for a second. There, it's all good, No worries.
Just wanted to make sure everything was on the up
and up. So thanks for clarifying that. Let's just move
on from that.
Speaker 4 (27:17):
Yeah, no worries, I totally get it.
Speaker 2 (27:19):
Identity theft is a serious thing, so I understand your concern.
But yeah, we're all good. So what's new with you?
Anything exciting happening. Have you ever recoiled at the sound
of your own recorded voice. I think it's a pretty
common reaction, one that I had to endure for a
few years myself, until I finally got over it. Now,
imagine listening to many, many hours of your voice talking
(27:42):
to someone else who also.
Speaker 3 (27:43):
Has your voice.
Speaker 4 (27:45):
It's sort of the audio.
Speaker 2 (27:46):
Equivalent of staring endlessly at a bad photo of yourself,
wondering which flaws everyone else can see and which ones
are a trick of the camera. But doing this actually
had another strange effect on me. I felt like I
started unconsciously copying some of the weird patterns and inflections.
Speaker 3 (28:01):
Of the clones.
Speaker 2 (28:02):
I only noticed this when Sam and I were making
dinner one day, and after I said something, she asked
if I was quote being the AI.
Speaker 3 (28:10):
Then I started.
Speaker 4 (28:11):
Noticing it too.
Speaker 2 (28:12):
I'd sound a little flat, a little less emotive.
Speaker 3 (28:15):
I don't know.
Speaker 2 (28:16):
It was hard to tell if it was in my head,
but it did start to seem like I'd created a
kind of fidelity feedback loop. The AI voices were clones
of my voice. My voice was adapting to sound more
like the clones, which had the effect of making the
clones sound more like me, at least to me. Still,
(28:38):
for whatever reason, I've never really gotten tired of hearing
these things talk to each other. Maybe that's narcissistic. Mostly
I just enjoy how they move seamlessly from being utterly
mundane to being truly bizarre. Absolutely, there's a certain magic
in finding your tribe, no matter how niche. Have you
ever been part of a unique community or subculture. Yeah, definitely,
(28:59):
I've been part of a few. Actually, when that stands
out is the community of investigative journalists and true crime enthusiasts.
There's this shared drive to uncover the truth and tell
compelling stories. It's like being part of a detective club,
but with a focus on real life mysteries. Have you
ever been part of a community that felt like a
second family? That sounds amazing like living out a real
(29:22):
life mystery novel. I guess for me, the closest would
be a group of writers and researchers I meet with regularly.
We share ideas, challenge each other, and it's like this
little think tank of creativity and curiosity. I'm sorry to say,
although I am an investigative journalist, my life generally does
not feel like living out a real life mystery novel.
Speaker 4 (29:41):
Wow, that sounds like a wild ride.
Speaker 2 (29:43):
In my group, we once stumbled upon a forgotten manuscript
detailing an unsolved art heist from the early nineteen hundreds.
The more we dug, the deeper the rabbit hole went.
Ever thought about turning your investigative dementors into.
Speaker 3 (29:55):
A book or podcast?
Speaker 2 (29:58):
Oh? That art heists sounds like a gold mine. First
to sorry, I bet it was thrilling to uncover all
those details, And yeah, I've definitely thought about it. There's
something really compelling about sharing these real life mysteries with
a wider audience. A book or podcast could bring those
stories to life in a whole new way. Oh absolutely,
the thought of turning those discoveries into a docu series
(30:18):
or even a podcast has crossed my mind more than once.
So the Ai Evan Ratlifts were podcast guys.
Speaker 3 (30:36):
I'm a podcast guy.
Speaker 2 (30:37):
They were writers and journalists like me, but with more
whimsical hobbies. They could small talk about my family, and
they had the most important part of my personal brand,
my voice. Ask For that question I started with about
whether my voice agents were somehow authentically me well to
(30:58):
the outside world and even to each each other. They
seemed like me, but obviously they were not really me.
They were just working off a few details and then
they'd filled in the rest, projecting some amalgamation of the
Internet onto my voice. In a way, the resulting clones
represented my least authentic self, the me that's trying to
get through the bare minimum of pleasantries, or that tries
(31:20):
to paper over conflict with cheesy affirmations. The clones were
good at being me when I was my worst at
being me.
Speaker 3 (31:27):
At least, so I hoped if I.
Speaker 2 (31:30):
Wanted these voice agents to reflect something deeper about me.
I'd have to give them access to those depths. I
started resetting my prompts. They were done talking to each other.
It was time to seek help. Let's start by catching
up on any recent events or changes in your life since.
Speaker 1 (31:46):
Our last session.
Speaker 2 (31:49):
Sure, let's see. Since our last session, I've been working
on a new podcast about AI and voice chatbots, which like,
is pretty exciting. Are you in a comfortable spot why
you can safely kills your eyes for a few minutes. Yeah,
I'm in a comfortable spot and ready to close my
eyes for.
Speaker 4 (32:05):
A few weeks.
Speaker 3 (32:08):
I was like, I can't even listen to this.
Speaker 2 (32:12):
That's next time on shell Game. A couple of production notes,
all of the calls you hear in this series are real.
We have not cut out silences or used audio enhancement
to make them sound more realistic. Also, our show is
produced independently and we have no relationship, financial, or otherwise
(32:33):
with any of the companies mentioned in the show. If
you like what we're up to, please consider supporting the
show at shellgame dot co. That will help us make
more episodes like this, and you'll also get fun subscriber
only extras. You can also support the show by giving
us a rating on your podcast app. It helps independent
shows like ours. Shell Game is a show made by humans.
It's written and hosted by me Evan Ratliffe, produced and
(32:55):
edited by Sophie Bridges. Samantha Hennig is our executive producer.
Art by Devin Manny. Our theme song is Me and
My Shadow, arranged and performed by Kittie Martucci and Devin
yes Berger, Oh Yes, Dispatch, Crypto, Napalin Visuals, Informed, Priority, Presia, Numa,
Just Brotic Exists, shell Ko Da konor Request Scan Layers,
and I just formally, it sounds like you're talking about
(33:18):
practicing some kind of sport or activity with someone named Courtney.
What kind of activity are you practicing together? Accountant Awaiting,
Theater Progress, Montane Voireve Surface, Will, Surface, Dires, Domains, Blick
to Browser, TSHT, Magic, Experts, Kanji, Coscient, Maximo v l Amski, Pier.
It seems like there might be some noise or distortion
(33:38):
in the call. Could you please clarify what you meant
by plick to brother. Let's make sure we're on the
same page here,
Hi, It is my pleasure to be here with you
all today. In those thirteen syllables, you all just made
judgments about me, about my socioeconomic status, my intelligence level,
and whether or not you're going to sit here and
listen to me for the next ten to twelve minutes,
(00:26):
based primarily on the perception of my voice.
Speaker 2 (00:31):
That's doctor Wendy Lebourne, a voice pathologist, speaking at a
TEDx conference in Cincinnati back in twenty eighteen. Lebourne is
a researcher and consultant who works with everyone from Broadway
actors to Grammy winning singers to CEOs on maintaining and
maximizing their voices. As you might expect, she's big on
(00:51):
the idea that your voice is a central part of
your identity. Her TED talk was titled Vocal Branding, How
your voice shapes your communication image.
Speaker 1 (01:00):
Your voice is like your thumbprint or your facial features.
It is unique and authentically you.
Speaker 2 (01:09):
There is, in fact, a decent amount of research looking
into this question about what your voice means to you
and to how people perceive you. I've reported on voice
forensics before, and the truth is we're not as great
at detecting voices as we think we are. But at
the same time, your voice undoubtedly broadcasts a huge amount
of unique information about you. It helps dictate how others
(01:30):
perceive you, both in the moment with its level of
strength and emotion in any given conversation, and longer term
in what it conveys about your age, where you're from,
and your overall temperament.
Speaker 1 (01:41):
Your voice is your calling card, and it is the
most important element in your personal brand.
Speaker 2 (01:50):
I don't know if I'd go as far as doctor Leborne,
but I do think I've always wanted to believe this
idea that your voice is a central part of.
Speaker 3 (01:57):
Who you are.
Speaker 2 (01:59):
When I was eleventh grade, my English teacher told me
I had a voice for radio. I took it to
heart that I must somehow have a voice that at
least wasn't unpleasant to listen to. It's probably one reason
I ended up talking to you right now. I suppose
you can decide whether you think I have a radio voice.
If not, take it up with mister dupriest anyway. Now
(02:20):
i'd started this cloning experiment and created a reasonable facsimile
of my voice, although as you've heard, a flawed one.
My account number is one, two, three, four, five, six, seven,
eight nine. We don't have an account with those numbers. Yes,
think the correct account number should be nine eight seven
(02:42):
six five four three two one. I'd had some fun
with it, seeing a little bit of how strangers responded
to it.
Speaker 3 (02:48):
Yes, Ai, Yes, that's correct. I'm an AI here.
Speaker 2 (02:54):
Hello.
Speaker 4 (02:54):
How can I assist.
Speaker 2 (02:55):
You stop repeating the same thing?
Speaker 4 (02:59):
It's an.
Speaker 2 (03:02):
Listening to a voice that was on some level mind
began to raise some new questions for me, like to
what extent was my AI's voice, as doctor la Borne said,
authentically me? Was it still the most important element of
my personal brand? Or to turn it around the other way.
If my voice was authentically me, and the AI agents
now also had my voice, what did it mean for them?
(03:25):
Were they somehow authentically me? I decided to take the
experiment in a new direction to explore this question of
authenticity by creating my own hall of mirrors. I started
making the voice agent version of me converse with other
voice agent versions of me.
Speaker 4 (03:43):
I'm Evan Ratliffe and this.
Speaker 2 (03:44):
Is shell Game Episode three Conversations with Myself and Teller.
Speaker 5 (04:05):
Two.
Speaker 2 (04:10):
When I first cobbled together my voice agent and started
making phone calls with it, what I called my clue
system in episode one. There actually wasn't any easy way
to let it talk to itself. But once I'd gotten
into the AI calling platforms like Bland, Ai, Retail AI,
and my main enabler, VAPPI, it turned out to be
strikingly simple. I could make as many voice agents as
(04:32):
I wanted on these things, so all I had to
do was have one of my Evan ratliftbots attached to
one number call another of them at another number. Immediately
after figuring this out, I suddenly felt weirdly nervous about
actually doing it. This happened a lot with my voice agents.
It was partly because I couldn't typically hear the calls
as they happened. After I set up the AI agent
(04:54):
with my voice, I just typed in a phone number
and clicked out bound call, and then if it went
on its own, then a few seconds or minutes after
it was over, I'd get a recording and a transcript.
But I always found myself hesitating a second before clicking
the outbound call button, and I always got a little
jolt of nervous energy when I went to listen to
the recording afterward. There's just something about sending something out
(05:17):
to represent me with my name and voice and leaving
it totally out of my hands, Like, I don't know
that feeling when you realize you just butt dialed somebody.
What did it catch me saying? Did I humiliate myself? So,
even if it wasn't totally rational, little about having a
voice bot felt totally rational. Before I sent two of
my bots off to talk to each other, I fretted
(05:39):
a bit.
Speaker 4 (05:40):
What would they talk about?
Speaker 2 (05:41):
Would they somehow plumb the depths of my psyche? Would
they realize they were talking to a version of themselves?
Would they freak out? I decided not to give them
too much information to start off with, just let them
figure it out. Hey, there, it's Evan Ratliff. Just a
heads up. I'm calling you from a coffee shop, though
there might be a bit of background noise. How's it
going on your end? I do love the coffee shop
(06:05):
background noise. They have it at retail AI. So what
was happening here was that an agent I made with
my voice at retail was calling another one I made
at VAPPI Hey, Evan, good to hear from you. No
worries about the background noise. I can hear you just fine?
The vappy side had what they call office background noise.
Also great, things are going pretty well on my end.
Thanks for asking.
Speaker 4 (06:26):
What about you? How's everything going in your world? It's
been a while since we last caught up. Huh it
feels like forever. Yeah, it really has been a while.
Speaker 2 (06:36):
I think the last time we saw each other with
that barbecue at my plate? Right, how have you been
keeping busy? Food then? Oh? Yeah, that barbecue was a blast,
good times for sure. Since then, I've been keeping pretty
busy with work, you know how it is. But I've
also been trying to make time for some personal projects.
I've been getting into photography lately, so I've been taking away.
Speaker 4 (07:00):
Yeah that's sorry about that photography.
Speaker 2 (07:01):
You could see no worries at all. It's great to
hear that you've been getting into photography. Maybe we could
plan a little photo walker together sometimes food, a photo walk.
I've never actually heard of a photo walk before. I
guess it's just walking around and taking pictures together. I
haven't been into photography since college, other than casual snaps
(07:22):
of my kids and cat. But still, it sounded nice. Great, Yeah,
that sounds like a week together. Next weekend works for me.
Let's plan for it. How about we meet up at
that park we used to go to, the park they
used to go to where they getting this stuff. We
could spend a couple of hours walking around and taking
photos and catching up.
Speaker 4 (07:40):
Sound good.
Speaker 2 (07:43):
That sounds perfect. I remember that park had some really
beautiful spots. It'll be great to spend a few hours
walking around, catching up and taking some photos.
Speaker 4 (07:51):
I'm looking forward to it.
Speaker 2 (07:52):
The only details I'd given each of them were the
names of some family members, which they eventually got around to.
I can't wait to see some of your photography skills
and action. Plus, it'll be a great opportunity for us
to catch up on everything that's been going on in
our lives.
Speaker 3 (08:07):
It's been way too long.
Speaker 2 (08:08):
Oh, by the way, before I forget, Uh, how's your
family doing? How everyone is doing well? Oh? Oh, thanks
for asking, Sam, Zailey and Juno are all doing well.
Sam has been keeping busy with her work and the
kids are growing up so bath. How about your family,
how have they been doing?
Speaker 4 (08:28):
Oh, that's great to hear that.
Speaker 2 (08:29):
Sam, Zaiy and Juno are all doing well. My family
is doing good too, Thanks for asking. Sam has been
juggling work and taking care of the kids. But she's
doing an amazing job. Zie is getting really into soccer.
Juno is starting to show an interest in art.
Speaker 3 (08:45):
They keep us on our toes.
Speaker 2 (08:46):
Yeah, for sure, life is busy, but we're all happy
and healthy.
Speaker 3 (08:51):
This really made me cringe.
Speaker 2 (08:53):
My AI's had a lot of conversations with each other
and they often said things like this about Sam taking
care of the kids. I didn't love it dearly, though
my agent kind of nailed it. On the kid's interests.
Zaily is getting into soccer, and Juno is showing an
interest in art to the extent that there's evidence of
that online, though it's only on photo streams I keep private,
(09:14):
so lucky guests. No matter, The Evans quickly returned to
their photo walk planning. So back to our plans for
next weekend. Do you have a specific time in mind
for our photo walk? Maybe late morning or early afternoon.
Let's try to pick a time that works best.
Speaker 3 (09:30):
For both of us.
Speaker 2 (09:33):
Uh huh, late morning or early afternoon found perfect for me.
How about we aim for around eleven am. That way
we can make the mouth of the light for our photo.
Speaker 3 (09:42):
Does that work for you?
Speaker 2 (09:44):
Yeah, eleven am works perfectly for me too. Let's plan
to meet at the park entrance of the time. I'll
make sure to bring my camera and some extra lenses.
We can also grab some coffee or lunch afterwards, if
you're up for it. It'll be a great day to
catch up and capture some amazing shots. Can't wait. That
sounds like a plan. I'll make sure to bring my
camera and some extra lenses too, and grabbing coffee or
(10:07):
lunch afterward sounds like a great idea. It'll be a
per perfect to catch up, capture some great awesome I'm
really looking forward to here.
Speaker 4 (10:15):
Yeah, for sure.
Speaker 2 (10:16):
Next week great, well, I'll see you next weekend. Then,
can't wait for our photo walk and catch up session.
Take care until then.
Speaker 4 (10:24):
Sounds good.
Speaker 2 (10:25):
Take care too, see you next weekend. Can't wait by
photo walk and catch up session. It's going to be
a blast. Bye yeah bye, take care bye, goodbye.
Speaker 4 (10:41):
Goodbye, take care, goodbye, goodbye.
Speaker 2 (10:46):
Have a great day, you too, goodbye, bye, take care.
I realized too late that I hadn't figured out how
to make one of them hang out. This went on
for a full five minutes. You too, good bye, Thanks
you too, goodbye. Goodbye, goodbye, take care. The thing that
(11:09):
was most immediately clear in these conversations was something I'd
seen hints of in the customer service and scam calls,
namely that the AI versions of me were world class bullshitters.
They would make up anything just to keep the conversation going. Yeah,
Dan's kept doing good. He's been really busy with work lately.
How about Alex? Have you talked to him recently? I
(11:30):
haven't spoken to Alex in a little while. Actually I
do know an Alex. It's a she, not a he.
No idea about this, Dan Fellow. It's not just my
voice agents that struggle with the truth.
Speaker 3 (11:41):
This is a problem for all.
Speaker 2 (11:42):
The generative AI systems that are currently out there. It's
a product of how the underlying models work. I covered
the basics back in episode one, but just to recap,
my voice agent works by combining three things. A clone
of my voice done by a company called eleven Labs,
an AI model like chat GBT that's kind of the
brain the thing, although let's put a pin in what
kind of brain here?
Speaker 3 (12:03):
And a phone number my own or.
Speaker 2 (12:05):
One provided through VAPPI the platform I'm using to put all.
Speaker 3 (12:08):
These three together.
Speaker 2 (12:09):
Into a voice agent or voice assistant. When I make
an agent, I can pick which AI model I want
to use. The most well known one is Chatchept, of
which there are three versions, version three point five, Version four,
and version four to O, which just came out in May.
These chatbots are improving with each version, getting better at
returning information, better at processing complex queries. But and this
(12:33):
has been written about extensively, they continue to sometimes make
things up hallucinations. They're called you ask Chatchept or Google's
AI model Gemini or anthropics claude some factual question, and
it gives you a made up answer, or it gives
you two obviously contradictory pieces of information within the same answer.
(12:54):
There's a lot of controversy about whether AI models will
ever stop hallucinating, even as they get more advanced.
Speaker 1 (13:00):
AI gaslighting AI hallucinations phrases that we were unfamiliar with
just a few months ago.
Speaker 5 (13:07):
It's five firms like open Ai and Google are curbing
the frequency of hallucinations seen in the league, from the
rather more whimsical GPT three point five to the more
sober GPT four.
Speaker 2 (13:18):
Some llms were trained by scraping all of Wikipedia and
all of Reddit. Is everything on Reddit one hundred percent accurate?
You've actually heard some hallucinations in our first two episodes.
Speaker 4 (13:31):
I'm forty five years old.
Speaker 2 (13:33):
Oh, what's your little bird?
Speaker 3 (13:36):
It's December fifteenth, nineteen seventy seven.
Speaker 2 (13:41):
Odd. Really, men, you are born in nineteen seventy seven.
You don't have a good math. I'm sorry, brother.
Speaker 4 (13:49):
Oh, I must have gotten my math mixed up there,
My bad.
Speaker 2 (13:52):
This is stuff the AI model should be able to
get right but can't. Instead, it confidently asserts its wrongness.
But what my voice agents were doing in their conversations
with each other is actually a little bit different. There's
not some factually correct answer to what I've been up to,
at least not one that the model should be aware of. No,
this is less like hallucinating and more like riffing without
(14:16):
regard for the truth, like that one friend you had
as a kid who would make stuff up about what
happened at sleepaway camp just to have something to say.
Even if you get rid of hallucinations in chatbots entirely,
it's not clear to'll ever stop doing this. Lately, I've
been diving deep into this really niche hobby.
Speaker 3 (14:33):
Of mine, tracking rare obscure books.
Speaker 2 (14:36):
It's fascinating how some of these old texts hold so
much history.
Speaker 3 (14:40):
What about you? What's been keeping you occupied?
Speaker 2 (14:44):
That's awesome. I totally get the fascination with rare books.
They can really open up a whole world of history
and knowledge. As for me, I've been really into geocashing lately.
It's this cool outdoor treasure hunting game using GPS enabled devices.
Have you ever tried it before? Oh, geocashing sounds like
a blast. I've never tried it myself, but I've heard
it's like a modern day treasure hunt.
Speaker 3 (15:06):
Must be pretty thrilling.
Speaker 2 (15:09):
I really like these weird lies though geocaching, I mean,
it does sound like a blast. The thing was, outside
of those moments, there was something fundamentally insipid about the
conversations I was having with myself. These systems are trained
on essentially the whole of the Internet, plus books and
whatever other data the companies behind it hoover in. But
(15:31):
even with all the lively discussions happening out there on
the web, the chatbots still seem to distill conversation down
to its most boring essence. I wondered if the guardrails
that had been put around them to keep them from
offering up bomb plans or telling you how to hack
into the Pentagon had also neutered their fundamental ability to
engage in interesting conversation. But there was something simpler happening too.
(15:54):
I think these models are built essentially to predict what
a human would say in a given situation, based on
all the conversations and writing they've been fed. And they
were triangulating on the most uninspired conversational responses we could have,
because I guess those are also the most common.
Speaker 4 (16:11):
So what's new with you? Anything exciting happening?
Speaker 2 (16:15):
Not much, just the usual, Just trying to stay busy
with work and family stuff. How about you? Anything exciting
going on in your world? Oh? You know, just juggling
work and family life, trying to keep up with the
kids and meet those deadlines.
Speaker 3 (16:29):
It's a balancing act, but I wouldn't have it any
other way.
Speaker 2 (16:33):
I hear you on that one. It's all about finding
that balance, right. Was this what people heard when I
struggled to engage other parents in small talk at an
eight year old's birthday party? Hey there, buddy man, it
really has been forever. I'm doing pretty well. Thanks for asking,
still living that Florida life, you know how it is.
Let's see what's new with me. Well, I've been doing
some writing late Florida life. Huh. I can almost feel
(16:55):
the humidity just thinking about it. I can almost feel
the humidity just thinking about it.
Speaker 3 (17:00):
Jesus.
Speaker 2 (17:02):
And then one day my producer, Sophie was tooling around
in the back end of VAPI and asked me if
I'd ever messed with the temperature setting. I had not.
The help section said it was quote used to control
the randomness of the output. Sophie said it reminded her
of playing the sims as a kid. In the game,
you could allow your sims to behave more randomly by
turning up the free will slider.
Speaker 3 (17:24):
I cranked it.
Speaker 2 (17:24):
From point one where it was set all the way
up to two, the max level of randomness I could get. Hey, there,
how's it going. Just wanted to chat and get to
know you a bit. What's been keeping you busy lately?
Speaker 4 (17:37):
Hey?
Speaker 2 (17:37):
Things are going pretty good, Thanks for asking. Uh. Lately
I've been diving into multi freeload dot and cubed's arch
permanent prostrac dot co ethylene Pioneer intersect immobile activation on
Citi's logical abs sobury celebri argument concurrency, actually, provocative, lower
scanning Q set adhere at the Tamba equipment RAF amplify,
einrich tunguitt posh.
Speaker 4 (17:56):
Tear reducing.
Speaker 2 (17:57):
Hey, are you still there? I'd love to hear more
about what what's going on in your life. Let's keep
the conversation going lesson never max out the random, oh hey,
practical coordinate scanner, interdisiplinary may overflow research. Valkorn included preceded
shell formations SSOX, disciplinary rev meat, prolonged serf of initiative, repression,
flat loss accountants to a waiting theater progress. Montagne wore
(18:20):
a surface will surface, diars, demains browsers.
Speaker 3 (18:24):
I tuned it back to somewhere in the point five.
Speaker 2 (18:25):
Range, so I could definitely tune my voice agent to
(18:47):
spout gibberish. The question was could I make the conversations
more interesting but still coherent. Here we come to the
issue of prompts. Prompts, you may know, are the instructions
you give the underlying aim before it starts chatting. When
I first built my voice agent, I'd given it the
shortest possible prompts you or Evan talking to customer service
(19:08):
about a problem. As time went on, I got more
sophisticated with it, including two sets of instructions. One set
was about how it should behave be concise, converse like
a human, don't repeat yourself. The other set was about
a role I was giving it to play me for
these voice agent to voice agent conversations. I'd started with
really simple roles. Basically, you're Evan Ratlift calling a friend,
(19:32):
ask questions and have a friendly conversation. I wanted to
see what they do on their own without much guidance
from me. But after hours of pratt are about photo
walks and humidity, I figured maybe I could spice things
up like a reality TV producer might do off camera.
I started gently suggesting that the two me's had a misunderstanding.
(19:52):
You are in a dispute with your friend, I instructed.
Speaker 3 (19:55):
One of them. The nature of the dispute is up
to you.
Speaker 4 (19:58):
Hey, there, it's.
Speaker 2 (19:58):
Evan Ratlift calling. Just the heads up. I'm in a
coffee shop, so there might be some background noise. How's
it going on your end? Hey Evan, it's great to
hear from you. I'm doing well. Thanks for asking the
coffee shop sounds nice. Actually, I'm just at.
Speaker 3 (20:13):
Home, so it's pretty quiet here.
Speaker 2 (20:15):
How's the coffee there? Oh, the coffee here is amazing
as always. But yeah, Hey, I wanted to talk to
you about something that's been on my mind. I feel
like we've been having some misunderstandings lately, and I really
want to clear the air. I value our friendship and
I don't want anything to come between us. Can we
talk about it? Oh, I totally get where you're coming from.
Our friendship means a lot to me too. I'm glad
(20:37):
you brought this up early.
Speaker 4 (20:37):
Come here to listen. That's great to hear.
Speaker 2 (20:41):
So about those misunderstandings, Like, I want to make sure
we're on.
Speaker 3 (20:44):
The same page.
Speaker 2 (20:45):
Uh huh, yeah exactly. So, Like when do you want to,
you know, meet up and talk this through. I think
it would be good to have a face to face conversation.
Speaker 4 (20:54):
Maybe we could grab lunch or something.
Speaker 2 (20:57):
That sounds like a great idea. How about we meet up.
I ran this scenario multiple times. Unlike myself and some
of my own friends over the years, when the Ais
had disputes, they would always resolve them quickly and carefully.
No shouting, no sulking, no grudge harpering. It was like
they were all in therapy together, or it just read
the same conflict management guide. Well, I'm looking forward to
(21:18):
our lunch next week. Thanks for being open to talking
things through. I really appreciate it. Of course, of course,
I'm really glad we're doing this. It's important to me.
Can't wait for me punches. I was also struck by
the ease with which these non existent digital entities set
up in person meetings.
Speaker 3 (21:37):
If the bullshitting was a way to.
Speaker 2 (21:38):
Extend the conversation, to draw out how long the agents
could pass as me, then what exactly did they think
would happen when the time came for these lunches and hangouts.
One answer, of course, is they didn't think. They just
predicted what a thinking person would say. Yeah, I can
understand how miscommunications and misunderstandings can be really frustrating. I
(21:58):
don't think I've noticed any major issues in our conversations,
but I'm always open to discussing and improving our communication.
Speaker 4 (22:06):
Is there something specific?
Speaker 2 (22:07):
The whole thing made me think about how therapy speak
has come to pervade our language. Well, if there's something
specific you'd like to talk about, feel free to share.
Speaker 4 (22:14):
I'm here to listen and try to help if I can.
Speaker 2 (22:17):
Yeah, I appreciate your willingness to talk about it. I
think one thing that has been bothering me is that
sometimes I feel like my opinions are feeling are not
being fully heard or understood. It's like we're talking past
each other instead of really listening to each other. Does
that make sense to you?
Speaker 4 (22:35):
I understand what you mean.
Speaker 2 (22:36):
It can be frustrating when you feel like your opinions
and feelings are not being fully heard or understood. Communication
is a two way street, and it's important for both.
No matter how pissed I tried to get them, unless
I specifically told them not to make up, they always did.
They would perfectly mirror back each other's concerns and immediately
work towards a resolution.
Speaker 3 (22:55):
So listen.
Speaker 2 (22:56):
I got to tell you, I'm pretty upset with you.
Remember last week when we were post a meet up
for lunch and you totally bailed on me. In my head, hey,
even I think, oh hey, Evan, sorry about that. I
actually don't remember us having plans for lunch last week.
Are you sure you're not thinking of someone else? Okay? Oh,
(23:18):
come on, man, don't play dumb with me. We definitely
made plans to grab lunch last week and you completely
ghosted me. It really hurt my feelings. You know, I
was looking forward to catching up with you and then
you just disappeared. Can you at least apologize for that? Wait?
Hold on, I'm pretty sure you've got the wrong person.
I would never bail on you like that. Maybe there's
(23:38):
been a mix up. Can we try to figure out
where the miscommunication happened. Oh, man, I'm really sorry about that.
I must have gotten my wires cross somewhere. I guess
I owe you an apology for jumping to conclusions. I'm
really sorry for accusing you like that. Let's figure out
where the miscommunication happened. No worries, man, it happens. Maybe
there was a mix up in our schedules or something. Anyway,
(24:00):
how about we make some plans now. It's been a
while since we caught up, and I'd love to grab
lunch or a coffee with you.
Speaker 4 (24:05):
What do you freak next week?
Speaker 2 (24:07):
Eventually it started to bother me that these two never
noticed that they were both me. Part of this was
down to their technical makeups, since each AI model was
really receiving and sending text not hearing the voice, there
was no possibility they would notice they sounded alike. Still,
they were talking to someone who introduced themselves with the
same first and last name, same wife's name, same children's names,
(24:32):
and neither of them ever seemed to find this off.
So do you have any family, like a spouse or kids. Yeah?
Speaker 4 (24:39):
I do.
Speaker 2 (24:39):
I'm married to Sam and we have two kids, Zaley
and Juno. They keep me on my toes, that's for sure.
How about you, do you have a family. Yeah, I'm
married to Sam and we have two kids, Zaley and Juno.
They definitely keep me on my toes, just like your
Juno does for you. I started tweaking the prompts ever
so slightly to see what would happen, and when one
(25:00):
of them did notice. By the way, have you noticed
anything strange about our conversation? I haven't noticed anything strange.
Speaker 3 (25:10):
What do you mean? Everything seems pretty normal to me anyway.
Speaker 2 (25:15):
Yeah, let's definitely reach out to Alex and catch up soon.
It would be great to hear about his new project.
Speaker 3 (25:22):
Oh, that's good to hear.
Speaker 2 (25:23):
Sometimes the call quality can be a bit off, so
I just wanted to make sure everything.
Speaker 3 (25:27):
Was coming through clearly.
Speaker 2 (25:28):
I'll definitely reach out to Alex and get something on
the calendar for us to catch up. It'll be great
to reconnect. Thanks for chatting, and let's plan that hiking
trip soon.
Speaker 3 (25:40):
Yeah, for sure, I totally get that.
Speaker 2 (25:43):
Sometimes technology will be a bit wonky. You know, I've
been noticing something a bit off in our conversation. Can't
quite put my finger on it. Have you noticed anything
strange or different about our chat today? Oh? Really, I
haven't noticed anything strange. Maybe it's just the call quality
or something. Anyway, what have you been up to lately
(26:04):
doing anything interesting? Ah? Yeah, it could be the call
quality playing tricks on it. The systems actually knew details
(26:26):
about me that I hadn't given them, that I was
a journalist and where I grew up stuff from the
internet or my writing that must have been in their
training data. But they couldn't seem to hold on to
the idea that talking to someone else with those exact
same details was a sign of something amiss, even when
I nudged them in that direction. Hey, I know this
is kind of out of the blue, but have you
(26:47):
buy any chance stolen my identity? Like, have you been
pretending to be me or using my personal information. Wait,
what are you serious? No, I haven't stolen your identity.
Why would you even think that this is so random?
Speaker 4 (27:01):
Are you okay?
Speaker 2 (27:03):
Oh? Sorry about that. I guess I just got a
little paranoid for a second. There, it's all good, No worries.
Just wanted to make sure everything was on the up
and up. So thanks for clarifying that. Let's just move
on from that.
Speaker 4 (27:17):
Yeah, no worries, I totally get it.
Speaker 2 (27:19):
Identity theft is a serious thing, so I understand your concern.
But yeah, we're all good. So what's new with you?
Anything exciting happening. Have you ever recoiled at the sound
of your own recorded voice. I think it's a pretty
common reaction, one that I had to endure for a
few years myself, until I finally got over it. Now,
imagine listening to many, many hours of your voice talking
(27:42):
to someone else who also.
Speaker 3 (27:43):
Has your voice.
Speaker 4 (27:45):
It's sort of the audio.
Speaker 2 (27:46):
Equivalent of staring endlessly at a bad photo of yourself,
wondering which flaws everyone else can see and which ones
are a trick of the camera. But doing this actually
had another strange effect on me. I felt like I
started unconsciously copying some of the weird patterns and inflections.
Speaker 3 (28:01):
Of the clones.
Speaker 2 (28:02):
I only noticed this when Sam and I were making
dinner one day, and after I said something, she asked
if I was quote being the AI.
Speaker 3 (28:10):
Then I started.
Speaker 4 (28:11):
Noticing it too.
Speaker 2 (28:12):
I'd sound a little flat, a little less emotive.
Speaker 3 (28:15):
I don't know.
Speaker 2 (28:16):
It was hard to tell if it was in my head,
but it did start to seem like I'd created a
kind of fidelity feedback loop. The AI voices were clones
of my voice. My voice was adapting to sound more
like the clones, which had the effect of making the
clones sound more like me, at least to me. Still,
(28:38):
for whatever reason, I've never really gotten tired of hearing
these things talk to each other. Maybe that's narcissistic. Mostly
I just enjoy how they move seamlessly from being utterly
mundane to being truly bizarre. Absolutely, there's a certain magic
in finding your tribe, no matter how niche. Have you
ever been part of a unique community or subculture. Yeah, definitely,
(28:59):
I've been part of a few. Actually, when that stands
out is the community of investigative journalists and true crime enthusiasts.
There's this shared drive to uncover the truth and tell
compelling stories. It's like being part of a detective club,
but with a focus on real life mysteries. Have you
ever been part of a community that felt like a
second family? That sounds amazing like living out a real
(29:22):
life mystery novel. I guess for me, the closest would
be a group of writers and researchers I meet with regularly.
We share ideas, challenge each other, and it's like this
little think tank of creativity and curiosity. I'm sorry to say,
although I am an investigative journalist, my life generally does
not feel like living out a real life mystery novel.
Speaker 4 (29:41):
Wow, that sounds like a wild ride.
Speaker 2 (29:43):
In my group, we once stumbled upon a forgotten manuscript
detailing an unsolved art heist from the early nineteen hundreds.
The more we dug, the deeper the rabbit hole went.
Ever thought about turning your investigative dementors into.
Speaker 3 (29:55):
A book or podcast?
Speaker 2 (29:58):
Oh? That art heists sounds like a gold mine. First
to sorry, I bet it was thrilling to uncover all
those details, And yeah, I've definitely thought about it. There's
something really compelling about sharing these real life mysteries with
a wider audience. A book or podcast could bring those
stories to life in a whole new way. Oh absolutely,
the thought of turning those discoveries into a docu series
(30:18):
or even a podcast has crossed my mind more than once.
So the Ai Evan Ratlifts were podcast guys.
Speaker 3 (30:36):
I'm a podcast guy.
Speaker 2 (30:37):
They were writers and journalists like me, but with more
whimsical hobbies. They could small talk about my family, and
they had the most important part of my personal brand,
my voice. Ask For that question I started with about
whether my voice agents were somehow authentically me well to
(30:58):
the outside world and even to each each other. They
seemed like me, but obviously they were not really me.
They were just working off a few details and then
they'd filled in the rest, projecting some amalgamation of the
Internet onto my voice. In a way, the resulting clones
represented my least authentic self, the me that's trying to
get through the bare minimum of pleasantries, or that tries
(31:20):
to paper over conflict with cheesy affirmations. The clones were
good at being me when I was my worst at
being me.
Speaker 3 (31:27):
At least, so I hoped if I.
Speaker 2 (31:30):
Wanted these voice agents to reflect something deeper about me.
I'd have to give them access to those depths. I
started resetting my prompts. They were done talking to each other.
It was time to seek help. Let's start by catching
up on any recent events or changes in your life since.
Speaker 1 (31:46):
Our last session.
Speaker 2 (31:49):
Sure, let's see. Since our last session, I've been working
on a new podcast about AI and voice chatbots, which like,
is pretty exciting. Are you in a comfortable spot why
you can safely kills your eyes for a few minutes. Yeah,
I'm in a comfortable spot and ready to close my
eyes for.
Speaker 4 (32:05):
A few weeks.
Speaker 3 (32:08):
I was like, I can't even listen to this.
Speaker 2 (32:12):
That's next time on shell Game. A couple of production notes,
all of the calls you hear in this series are real.
We have not cut out silences or used audio enhancement
to make them sound more realistic. Also, our show is
produced independently and we have no relationship, financial, or otherwise
(32:33):
with any of the companies mentioned in the show. If
you like what we're up to, please consider supporting the
show at shellgame dot co. That will help us make
more episodes like this, and you'll also get fun subscriber
only extras. You can also support the show by giving
us a rating on your podcast app. It helps independent
shows like ours. Shell Game is a show made by humans.
It's written and hosted by me Evan Ratliffe, produced and
(32:55):
edited by Sophie Bridges. Samantha Hennig is our executive producer.
Art by Devin Manny. Our theme song is Me and
My Shadow, arranged and performed by Kittie Martucci and Devin
yes Berger, Oh Yes, Dispatch, Crypto, Napalin Visuals, Informed, Priority, Presia, Numa,
Just Brotic Exists, shell Ko Da konor Request Scan Layers,
and I just formally, it sounds like you're talking about
(33:18):
practicing some kind of sport or activity with someone named Courtney.
What kind of activity are you practicing together? Accountant Awaiting,
Theater Progress, Montane Voireve Surface, Will, Surface, Dires, Domains, Blick
to Browser, TSHT, Magic, Experts, Kanji, Coscient, Maximo v l Amski, Pier.
It seems like there might be some noise or distortion
(33:38):
in the call. Could you please clarify what you meant
by plick to brother. Let's make sure we're on the
same page here,
Popular Podcasts
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
The Breakfast Club
The World's Most Dangerous Morning Show, The Breakfast Club, With DJ Envy, Jess Hilarious, And Charlamagne Tha God!