August 15, 2025 • 34 mins
Is technology actually good for older people? This week, Oz and Karah explore the French palace of Versailles by talking to a statue-turned-chatbot. Then, Oz gives an update on Apple’s new make-or-break Siri overhaul. Karah weighs whether everyday use of technology is rotting our brains, or making them stronger. And finally, on Chat and Me, Reddit mourns the death of some beloved AI models.
Also, we want to hear from you: If you’ve used a chatbot in a surprising or delightful (or deranged) way, send us a 1–2 minute voice note at techstuffpodcast@gmail.com.
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 (00:13):
From Kaleidoscope and iHeart podcasts. This is tech stuff. I'm
as Voloscian and I'm Kara Price today apples hail Mary
in the AI race, and is tech actually good for
older people? Then on chatting me, Reddit users mourn their
lost confidence and personal advisors, as open ai says hello
to GPT five. All of that on the weekend tech.
(00:37):
It's Friday, August fifteenth, and hello.
Speaker 2 (00:47):
Cara, Hi, as, I have a question for you.
Speaker 1 (00:50):
Have you ever been to Versailles, the Palace of Versailles
outside of Paris? I have not, have you?
Speaker 2 (00:55):
I actually have? I wrote a segue around Versailles.
Speaker 1 (00:59):
Yes, when was that?
Speaker 2 (01:01):
When I h study abroad?
Speaker 1 (01:02):
I study abroad? What does the Padace of Versai have
to do with tech stuff?
Speaker 2 (01:06):
They have just entered the AI game.
Speaker 1 (01:08):
They have they gonna they turn it into Europe's largest
data center.
Speaker 2 (01:12):
You know that. When I saw this, when they were
like Versailles is using AI and partnering with open it,
I was like, I gotta So basically, visitors can talk
to the statues right on their smartphones via the museum's
app or website. So you scan a QR code near
the statues, or you can just browse a list on
the site.
Speaker 1 (01:32):
Oh well, it sounds almost like you're suggesting we do it.
Speaker 2 (01:36):
I'd love to do it. I just love it. I
love the voice. I really want to show it. Okay, okay,
listen to this.
Speaker 3 (01:42):
Oh hello, what a pleasure to meet someone curious about
my work. What would you like to know about this
lovely taming of mystery by a little winged troublemaker like me?
Speaker 1 (01:54):
Here's this.
Speaker 2 (01:54):
This is the sphinx ridden by Cupid, and we are
listening to Cupid to talk to us. And then I'm
going to ask something of Cupid.
Speaker 3 (02:04):
Oh I'm all ears or perhaps wings? What question stirs
your curiosity?
Speaker 2 (02:10):
Cupid? Have you ever listened to a podcast?
Speaker 3 (02:13):
Ah, dear friend, my ears are more attuned to the
whispers of hearts than to modern chatter.
Speaker 1 (02:19):
I have a question for you, Cupid. Can you hear me? Oh?
Speaker 3 (02:22):
Loud and clear, my friend?
Speaker 1 (02:24):
Wonderful? So, Cupid, how long have you been in the
Palace of Verse?
Speaker 3 (02:29):
I for I've been writing this mystery since sixteen sixty eight.
That's when those marvelous artists crafted me and my silent companion.
So let's just say I've been here for centuries. Watching
the dance of Time in the sun King's garden.
Speaker 1 (02:43):
The sun King meaning Louis Catous.
Speaker 2 (02:45):
That's right, Louis Cattus.
Speaker 1 (02:47):
This is basically like you, instead of carrying around the
visitor brick phones with the filthy lanyards that you kind
of have to disinfect before hearing endless, endless, boring depositions
about various works and museums. I do always feel guilty
for not bringing those with me because I feel like
I'm missing out on the true information payload of the experience.
(03:07):
So I guess it's kind of a nice idea at
least to do something a little bit more interactive like this.
Speaker 2 (03:13):
Yeah, I think that's the point of what they're trying
to do, but as you can hear, the dialogue is
far from perfect.
Speaker 1 (03:19):
I'd also wonder if you're interested enough to get your
phone out, do you think you want to be responded
to in that tone.
Speaker 2 (03:26):
In that town?
Speaker 1 (03:27):
Ah?
Speaker 2 (03:27):
It kind of takes to the experience. Yes. So the
French Culture Ministry says they hope it will help them
attract a younger audience, since the average age of a
visitor to Versailles is currently forty years old. But the
new York Times article about it said that the statues
weren't responding very well to questions being asked by young people,
which kind of defeats the purpose of this.
Speaker 1 (03:47):
What the young people asking.
Speaker 2 (03:48):
I could never come up with these things. What do
you do when a bird poops on you? Will I
ever be rich? Who's going to win the Champions League
this year?
Speaker 1 (03:57):
Is a real question.
Speaker 2 (03:58):
These are very real questions, and the President of Versailles
has said that the bots are designed to stay on topic.
Speaker 3 (04:03):
But it seems like I'm here and always happy to
chat or gently steer us back if the conversation wanders
off into the mysteries of bird mishaps or football predictions.
Speaker 1 (04:14):
Was the statue listening all along?
Speaker 2 (04:16):
Oh my god? And it knew that I veered off.
Thank you, Sta, thank you bring us back. So be careful, Eliza.
Speaker 1 (04:25):
Is the statue still listening? Yes, you'll turn them off.
Speaker 2 (04:29):
I ended him. Okay, that was excellent. I do think that,
you know, do I wake up being in Paris and
like rish that I could talk to a statue at Versailles?
Absolutely not, But I probably would use this sooner than
I would use you.
Speaker 1 (04:43):
Age other demographic carry going after if he was sixteen,
that would be the only thing on your mind.
Speaker 2 (04:48):
That's very, very true. But I guess it's still interesting
that they're at least trying to see what incorporating AI
could look.
Speaker 1 (04:54):
Like, which up until recently is more than you could
say for Apple.
Speaker 2 (04:59):
Shots fire Apple the luddites tech company.
Speaker 1 (05:02):
There was a pretty interesting article in Bloomberg this week
with the headline Apple's upcoming AI voice control will change
how people use iPhones.
Speaker 2 (05:10):
So explain to me what that means.
Speaker 1 (05:12):
Well, first little bit of context so you may remember this,
but earlier this year, Apple sort of touted a new
version of Siri, which they then had to delay for
quote the foreseeable future, and the idea was that Siri
would be a true AI assistant with access to everything
on your phone. And Apple even released an ad campaign
which they then had to pull because they were sued
(05:32):
for false advertising about Apple Intelligence. It's been a tough
time for Apple in the AI race and their scenes
being way behind. Key executives have left for rivals, including
Metas recently as last week. The stock's been beaten up,
but last week it was up thirteen percent, the best
week since twenty twenty for Apple. Representing the sum of
four hundred billion dollars of market cap.
Speaker 2 (05:54):
How did that happen?
Speaker 1 (05:55):
Well, it actually wasn't really about the Syrian news. I'm
going to talk more about SyRI in the moment. This
was in response to Tim Cook FKA Tim Apple, and
his trip to the White House to announce a new
one hundred billion dollar pledge to manufacture in the US,
including a commitment to be the first and largest customer
for chips being manufactured in Arizona at the new Taiwan
(06:18):
Semiconductor Manufacturing Company facility there. Only proud of how I
said that, But Tim Cook also literally gave President Trump
a twenty four carrot gold bar, which, as you can imagine,
was very gratefully received, and in turn, at the meeting,
Trump said that Apple would be exempt from one hundred
percent tariffs on importing foreign chips because they're making domestic
(06:42):
investments in chips.
Speaker 2 (06:43):
Thus the stock match the gold bar.
Speaker 1 (06:48):
That was the best value of gold bar anyone ever bought.
Speaker 2 (06:50):
Ever. I also think it's interesting that it's a Taiwan
semiconductor company manufacturing area in arizonaa you know, still on
American soil. That's really good for them. And I'm happy
for people who have Apple stock, But what does the
future in the AI race look like?
Speaker 1 (07:07):
Like?
Speaker 2 (07:07):
What is what's up with Siri?
Speaker 1 (07:09):
Yeah? I mean that was the kind of substance this
Bloomberg piece that I mentioned. The author Mark German reports
that Apple is working on upgraded software that quote could
finally make Siri the true hands free controller of your iPhone.
With nothing but your voice, You'll be able to tell
Siri to find a specific photo, edit it and send
it off, or comment on Instagram post, or scroll the
(07:31):
shopping app and add something to your card, or log
into a service without touching the screen. Essentially, Siri could
operate your apps like you would with precision inside their
own interfaces. German continues, if Apple nails this, it's not
just a nice, easy of use upgrade, it's the fulfillment
of the vision Siri promised nearly fifteen years ago.
Speaker 2 (07:51):
This idea that Siri would sort of be the all
knowing person that Apple wants her to be, I think
is really interesting and I probably would end up using it.
But you know, people ask what the iPhone of the
AI era will be, the hardware that will deliver on
the potential of the software. Maybe the iPhone of the
AI era will be the iPhone.
Speaker 1 (08:10):
Well, that is certainly what Apple is hoping for and
banking on. Their current plan is for a major Siri
overhaul to be done by next spring, and this will
also be important to other new hardware that Apple's working on,
like smart displays and even household robots.
Speaker 2 (08:24):
How successful will they actually be at.
Speaker 1 (08:26):
This well, I mean, you know, they're basically back to
work on what they promised before and then had to pull,
I mean, this idea of the one voice control to
rule them all. According to the Bloomberg piece, there are
deep concerns internally that the project might not be on track.
Engineers are having a hard time getting Siri to work
with so many different apps, and the stakes are high.
(08:46):
I mean, imagine you miscommunicate with Siriri or Syria misunderstands
you when it's making a wire transfer on your behalf.
Speaker 2 (08:54):
And is there any indication of where Apple is with
sort of figuring this all out.
Speaker 1 (08:59):
Yeah, they're doing testing across many of the popular apps
that are already on the iPhone, Uber, Facebook, Amazon, and YouTube,
even WhatsApp as well of course, as all of Apple's
native apps, Messages, voice, call, etc. The issue of watched
about the banking apps has not been resolved. In fact,
Bloomberg suggests they might just exclude those from the future
seri verse. Yeah, and you mentioned this idea of what
(09:21):
will be the iPhone of the AI era. Sir Johnny Ive,
who was at Apple for years and was the designer
of the iPhone, is now working with Open Ai on
a multi billion dollar AI hardware project. So the pressure
is really on for Apple again as of now, Serious
slated to roll out next spring, the new sery that is.
And if Apple pull it off, you know, I think
(09:41):
they will put to bed a lot of the doubts
sort of crept in about whether they can stay competitive
in this new era of AI.
Speaker 2 (09:49):
So one great generational divide I've noticed is that people
of my mother's generations seem to love to use their
phones to compose texts with their voice. It's one of
my favorite things as listening to my mom composed texts
in the car to Siri. It's unbelievable. And the mess
what the messages versus what she wants to say, It's
also very fun. But what does this ever closer integration
(10:10):
with our tech do to us? Do you do you
think that this technology could be shriveling our brains?
Speaker 1 (10:16):
I do, obviously.
Speaker 2 (10:18):
Well, I have some good news, not for us, but
for my mother, which is that there's a study that
has come out that says technology only rots your brain
if you're young.
Speaker 1 (10:30):
Wow. Where does that leave us?
Speaker 2 (10:32):
Well, not in a great spot.
Speaker 1 (10:35):
Wait, we're young enough to be rotated. We're young enough.
Speaker 2 (10:37):
We're on the elder rot age. So I read this
article in the New York Times last week that the
constant use of tech, which is what you and I
do every day. I mean when I see you for
the first time, when we're recording in the morning, we're glue.
You're on your phone and your computer. I'm deep inside
of my phone.
Speaker 1 (10:54):
Is only this is only two hours in the week
where I'm not loud to my phone.
Speaker 2 (10:57):
Oh my god. People are like, where are you assis life?
Because I go and do not disturb. But this kind
of phone us, I mean, especially in studies, harms teenagers,
which we are not. But there's a surprising development, which
is that it might actually be helping older people stay sharp.
Speaker 1 (11:16):
That's a little confounding. How does this work?
Speaker 2 (11:19):
So I just want to zoom out a bit when
you think about people in their sixties and above God
bless mom, you can't help but be amazed by just
how much the world has changed for them. Like, think
about growing up, spending all of your educational years in
a world with no computers, no cell phones, no internet,
using an abacus, using your imagination, using your imagination, you know,
(11:41):
typing your college essays on a typewriter, and then the
year two thousand hits, we get to twenty twenty five,
and you're living in this world that does not really
use any of these things, I mean, including people who
do email on a laptop. I'm like, are you sick.
Speaker 1 (11:55):
Yeah, I mean we talked about this in one of
the first episodes of Tech Stuff that we did. To
get that, we did an episode about digital natives and
how this sociologist came up with this idea of digital natives,
and people who've grown up not as digital natives feel
like almost like immigrants into a new world. And yeah,
I mean that's the experience you're describing. So as much
(12:15):
as we may roll our eyes at too much voice
command and phone always being on loud, I mean it's
not easy to keep up.
Speaker 2 (12:22):
It is not easy to keep up and in the Times.
What they're reporting is that this constant change and being
forced to adapt may actually be helping older people stay
cognitively active and stave off one of the biggest fears, dementia.
Well yeah, you know, you might think that with all
the studies on shortening attention spans, the same would be
true for all demographics. But a recent paper in the
(12:43):
journal Nature and Human Behavior found that the people who
grew up without modern tech and had to learn it
are quote at a reduced risk of cognitive impairment and dementia.
That's according to Michael Scullen. He's a neuroscientist at Baylor
and one of the authors of the study.
Speaker 1 (13:00):
Well, this is tremendously relieving for anyone who's over sixty
is addicted to their phone. It's like this, it's actually
good for me. Yeah. How did this neuroscientist and his
colleagues come to these conclusions.
Speaker 2 (13:12):
So the group they studied was made up of people
over fifty with an average of sixty nine, close to
the Versailles visitor, and they gave them all a bunch
of different cognitive tests, and what they found was that
the ones who used computer smartphones and the Internet on
a regular basis scored way better than those who avoided technology.
(13:32):
But what was even more interesting to me was that
this isn't like a lot of studies we've covered on
this podcast. It wasn't a small sample size. It was
actually a meta analysis meta analysis.
Speaker 1 (13:42):
I'm on the edge of my seat. Now, what did
the meta Analoly? How big was the meta analysis? And
what was the meta analysis?
Speaker 2 (13:50):
You're like that, You're like trumping this meta analysis. The
paper analyzed results from fifty seven studies, which collectively gave
them a sample size of over four hundred thousand, and
they found that across all of those people, ninety percent
of the studies showed that technology seems to have what
(14:10):
the Times calls quote protective cognitive effect.
Speaker 1 (14:15):
Wow.
Speaker 2 (14:15):
And Scullin, who the author I mentioned, said that it's
really rare for so many different studies to have such
similar results. So he also said the decades long fears
about young people using technology and being negatively affected seem
to be born out of the research as well.
Speaker 1 (14:31):
Yeah, I mean that makes me think a little bit
about this cognitive offloading cognitive deficit thing we talked about
a few times on the show, which is that Basically,
if you're using these technologies in place of doing work
yourself when you're a college student or a teenager, it
makes you dumber. But if you're having to learn how
to use these technologies as an older person, it can
(14:51):
potentially keep you more fresh.
Speaker 2 (14:53):
The learning being key offload, the offloading also being key,
which is like, if you are offloading any kind of learning,
you're at a deficit.
Speaker 1 (15:03):
I do have a couple of questions here, though, if
I may play Devil's advocate for a moment, I would
assume that in these studies, technology is effectively approxy for
being social. I text, and I email and I zoom.
Therefore I am in society. So I would assume that
there is a correlation here because we know that it's
(15:23):
very neuroprotective to be social. There's also a question for
me about whether people who have higher cognitive abilities are
by definition more likely to use technology more than people
with lower cognitive ability, So that a self selecting component.
And then there are also socioeconomic questions, right, like you know,
is it are people who are not able to afford
to have all the modern technology kind of being left behind?
(15:44):
So what do you think?
Speaker 2 (15:47):
Yeah, No, those are all great comments. I think in
this case, correlation does not equal causation, which is always
good to remind yourself when you're reading an article about,
you know, a bit of a crazy sounding research paper.
The papers authors did say that, of course they can't
say anything definitively, but their research did take into account
things like health, education, socioeconomic status, and even with all
(16:10):
of those variables, the people who use tech still scored better.
And they also say that a big part of this
isn't just staying challenged, but not giving up.
Speaker 1 (16:19):
Oh that was my dad's man. Sure, if at first
you don't succeed.
Speaker 2 (16:23):
Try try, try again. They also hypothesize that the frustration
of having to learn and relearn everything after every software
update might actually be beneficial and to your point, the
authors also say tech users help people maintain social connections,
which is another preventer of cognitive decline, and that things
like calendar notifications help people remember things better.
Speaker 1 (16:46):
I don't know if you be happy that I'm still
young enough that the tech is eroding my brain rather
than rather than building it. But yeah, it's a mixed blessing.
Speaker 2 (16:54):
I guess I still believe that ikel is helping my
brain stay strong.
Speaker 1 (17:04):
After the break, gun safety advocates use AI to resurrect
their son. Also, the long lost Vine archives might have
been unearthed. Livestream viewers fall in love with a voluptuous
starfish and check rept convinces a man to eat poison.
Then on our chat tomy segment, Reddit users get nostalgic
for the good old days of AI. Welcome back. We've
(17:43):
got a few more headlines view this week.
Speaker 2 (17:45):
And then a story about the ruckus caused by the
release of GPT five.
Speaker 1 (17:50):
But first, Carot, there is a headline that I was
very drawn to. We obviously have a lot of fun
together on this show, joking around and laughing as we
talk about the news of the week, But this one
is darker, and it relates to something that you and
I reflected on together several years ago when deep fake
technology was first taking off, namely, would we actually want
people to speak beyond the grave in the form of
(18:12):
AI avatars. Last week, former CNN anchor Jim Acosta interviewed
on his YouTube show an AI rendering of someone who
was killed in the twenty eighteen shooting in Parkland, Florida.
The avatar was created in the likeness of Joaquin Oliver
and it was actually his parents who generated the AI version.
Speaker 2 (18:33):
So do you know why they decided to do this?
Speaker 1 (18:35):
Yeah, I mean they want to use their son's image
and voice and memory to advocate for quote, stronger gun
control laws, mental health support, and community engagement. And the
avatar will soon have its own social media presence and
will also be available for public speaking engagements.
Speaker 2 (18:51):
How did Joaquin's family make this AI avatar?
Speaker 1 (18:55):
Joaquin's father many trained the AI on his son's social
media posts, and of course so there's general knowledge that's
baked into many AI models. This is actually the second
time the Oliver family have used their son's AI likeness
to advocate for change. Back in twenty twenty, they use
a different AI version of their son to encourage people
to register to vote.
Speaker 2 (19:15):
So how have people responded to this?
Speaker 1 (19:17):
Well, many people did not take kindly to this interview,
you know, and it's a very complicated one because afterwards
the parents who are doing this and in a sense
processing their grief. I'm sure, but you know, people have
called the avatar creepy, unnatural, and even a grotesque puppet show.
I email with Harney Fried drummer Honey Freed. Yes, yes,
(19:39):
he was a so called godfather of digital forensics, and
he's been on the show before. Harney wrote to me quote,
I was not opposed to the original Joaquin Ai powered
PSA that his parents authorized, in which we heard his
AI recreations speak out against gun violence. There is, however,
a difference between a pre recorded PSA and what was
(20:00):
made to look like an interview with a well known journalist.
The interactive interview gave the impression that we were hearing
Joaquin respond to specific questions, when in fact we were not.
I absolutely do not blame the parents for doing whatever
they can to raise awareness. But this time we've interview
blurs journalistic lines in a way that I don't think
is appropriate.
Speaker 2 (20:20):
So I'm actually curious what this interview sounded like.
Speaker 1 (20:23):
Well, I do actually want to play you an excerpt.
Speaker 4 (20:25):
I'm all about love, laughter, and living life to the fullest.
I cherish my family and friends and always try to
spread joy wherever I go. Though my life was cut short,
I want to keep inspiring others to connect and advocate
for change.
Speaker 2 (20:36):
Joaquin, tell everybody a little bit about yourself, Like what's
your favorite sport?
Speaker 4 (20:41):
I love basketball, It's such a fun way to connect
with friends and show off some skills.
Speaker 1 (20:45):
Plus, there's nothing like the thrill of a good game.
I don't know, it's a little un canyon. I think
Harney's point was, even if you're someone's parent, do you
have the right to put words in their mouth in
a public context?
Speaker 2 (20:56):
Right? Right? So, moving on from the deeply distressing, thought
provoking segment that Oz just reported to something completely unseerious.
Do you remember us the social media at Vine. Elon
Musk actually claimed this week in a tweet that the
Vine archives have been found.
Speaker 1 (21:15):
You know, I saw this and I'm so glad you
brought this up. Because you know those T shirts that
you go to New York and you got a T
shirt with My dad went to New York and all
I got was this lousy T shirt. I feel like
the equivalent here is Elon must say I was looking
for looking for the Epstein files, and all I got
was this lousy Vine archive.
Speaker 2 (21:34):
That's exactly what it is. That's exactly what it is.
Speaker 1 (21:36):
But why why did Elon choose to wade into this
this corner of the internet as well?
Speaker 2 (21:43):
All Right, So I'm going to take you back to
twenty twelve when I was just a child, and Vine
was very quickly becoming a popular social media platform, so
quickly that the original Twitter not X bought the company
in twenty sixteen, so Twitter owned Vine, and then they
did what every major tech company does when they purchased
(22:04):
a competing app.
Speaker 1 (22:05):
They took the team and the technology and built something
that could rival TikTok no.
Speaker 2 (22:11):
Within a matter of months, they shut down Vine and
disabled the app, and the Internet was very upset. Yeah,
you can still find some of the videos on YouTube,
but it's largely a forgotten medium and you can't really
find a lot of the videos that were so important
to me at the time.
Speaker 1 (22:25):
That Elon has found the archive, what's he going to
do with it? Rados are the lost Vine.
Speaker 2 (22:29):
In a tweet he published in July, he said that
we're bringing back Vine, but in AI form, and in
August he tweeted, groc imagine is ai vine? What a sentence.
So between those two tweets, one about finding the archive
and the other about putting vines into AI people are
now speculating that Musk is now using the Vine archive
(22:49):
to train Grock's video app groc Imagine.
Speaker 1 (22:52):
This is going to be so nostalgic. All the AI
slop is going to be from teenagers from twenty fifteen,
trained on, trained on that. Well, funny enough, Cara, I
actually have one for you, which is also about found
footage going viral. Have you heard about the starfish in
Argentina that has captured the nation's heart.
Speaker 2 (23:13):
There is nothing I love more than a viral animal.
Speaker 1 (23:15):
The public in Argentina has named this starfish the estrea
colonna or fat bottom starfish. Have you seen the picture
of it?
Speaker 2 (23:25):
Now?
Speaker 1 (23:25):
No, I can put it up for you.
Speaker 2 (23:27):
Oh my god, he has a butt. By the way,
Patrick from SpongeBob SquarePants.
Speaker 1 (23:34):
Well exactly right, funny enough. I'm on bos Are's Herald
dot com, which has the headline a star open and brackets.
Fish is born. Viewers compared the creature the SpongeBob SquarePants
Polpatrick Star.
Speaker 2 (23:47):
There you go. Look at that you've been It almost
looks like they built it out of Patrick Star. It's
like Patrick Starr AI.
Speaker 1 (23:53):
So this starfish is being live streamed, or was being
live streamed, I should say, all the way from a
deep sea canyon in South America, and the live stream
was part of the marine project led by scientists from
Argentina's National Scientific Council. They use an undersea robot to
explore the canyon, and the jokes don't end with Estrea Colonna.
Do you know what the vehicle was called? No subastian.
Speaker 2 (24:18):
Of course I was going to. Yeah, I like that
a lot.
Speaker 1 (24:27):
The live stream has become so popular that people are
collectively naming all the marine life they see on the
live stream. There's a purple sea cucumber called Little Sweet
Potato and a pink lobster named Barbie.
Speaker 2 (24:38):
I love that there's now a cinematic universe. Joking aside,
live streams of animals seem to be very trendy right now.
Did you follow the Big Bear Eagles Jackie and Shadow?
Speaker 1 (24:49):
No? I was. I remember the saga of Flacco the
Owl in New York, But tell me about the Big
Bear Eagles.
Speaker 2 (24:56):
So there is a live stream that is trained on
the e eagles nests, and people were obsessed with watching
the eagles eggs, hatch and march. The live stream is
still going on, but the babies have literally flown the.
Speaker 1 (25:08):
Nest, so the parents are still there.
Speaker 2 (25:10):
The parents are still there. They're empty nesters empty.
Speaker 1 (25:13):
You know what I'm drawn to these stories because they
highlight this enduring interest that many of us have, if
not most of us, have in nature and science. Argentina,
just like the US, the current administration is cutting back
on funding and scientific research, and so this fat bottom
starfish has become a kind of unofficial mascot for science
(25:34):
enthusiasts everywhere. And it's a nice reminder to me that
no matter how technologically advanced our society becomes, and even
when we can probe the bottom of the ocean and
livestream it, what we want to watch is nature.
Speaker 2 (25:47):
And it feels like a natural twenty twenty five extension
of a zoo which has fallen out of favor a
little bit. But I just can't get enough of.
Speaker 1 (25:55):
This, all the pleasure of a zoo and none of the.
Speaker 2 (25:58):
It's tinder for zoo, so oz. For our last story,
I want to talk to you about bromism. Have you
heard of bromism?
Speaker 1 (26:05):
No? Is it something like when I go on a
bachelor potty bro bro tourism that.
Speaker 2 (26:10):
I'm bro tourism is interesting? That is New Orleans, Yeah,
Bolwyn Street or Vegas. But no, it's a disease caused
by ingesting too much sodium bromide, a chemical that is
commonly used in pool cleaners and medication for dog epilepsy.
Speaker 1 (26:26):
How did people end up eating it?
Speaker 2 (26:27):
So? Over a century ago people were ingesting bromide as
a sedative. But that probably wasn't very smart because an
estimated eight to ten percent of all psychiatric admissions in
the US were caused by bromism.
Speaker 1 (26:41):
What if the treatment is worse than the disease, that's right.
Speaker 2 (26:43):
Luckily we seem to have figured out what was happening,
and now the disease is pretty rare. That is until
this year. A sixty year old man went into the
hospital complaining of hallucinations and paranoia. He thought he was
being poisoned by his neighbor. It turns out he had
been poisoning himself because of advice given to him by
(27:05):
Chat GPT.
Speaker 1 (27:06):
Wow, so this is not the AI psychosis you get
from being encouraging your delusions of grandeur on Chat. This
is actually getting psychosis from ingesting a substance recommended by Chat.
Speaker 2 (27:19):
It's AI psychosis by proxy. That's absolutely right. This man decided,
after reading about the negative effects of eating table salt,
that he wanted to stop consuming salt. Altogether. He had
quote a history of studying nutrition in college, and because
of that, I guess he turned to chat GPT for
salt substitutes. So instead of sodium chloride, which is table salt,
(27:41):
Chat suggested he tries sodium bromide instead. This type of
substitution would be okay if it was for cleaning products,
but not for human consumption.
Speaker 1 (27:51):
That's funny. I mean, I wonder if he actually told
Chat that he was playing to eat it, or if
he just said, what's a substitute for sodium chloride? That's
a story for another day, But I think the key
takeaway here is obviously, don't always do what the computer says.
Speaker 2 (28:05):
I did self diagnose myself with lymes disease thanks to chat,
but I also did confirm it with a doctor.
Speaker 1 (28:24):
Well, this brings us to our final segment of the day,
which is a special edition of Chat and Me in
honor of the release of GPT five.
Speaker 2 (28:33):
Right. Chat in Me is our segment about how people
are really using chatbots. We've been getting some great listener
submissions in our Inbox Tech Stuff podcast at gmail dot com.
Don't forget it.
Speaker 1 (28:43):
Keep them coming. By the way, we also sent out
a T shirt or two, So we did want to
if you want to take stuff t shirit.
Speaker 2 (28:48):
We are good for our word. Yeah, and we will
be featuring more in the weeks ahead, so thank you
and please keep them coming. But this week Chat is
dead and we have killed him.
Speaker 1 (28:59):
I spoke Karathustra. I'm guessing you're talking about how, without warning,
open Ai disabled all its older models.
Speaker 2 (29:08):
So there's that, and Anthropic has retired Claude three Sonnet,
which had become a super, super popular and fast cost
effective model.
Speaker 1 (29:18):
Yeah, it's interesting. I mean people grow to depend on
these llms, each of which has a slightly different character,
and each of which is trained on its interactions with you.
So it's kind of crazy to become so dependent on
something and then have it literally taken away from you.
Speaker 2 (29:34):
Well, exactly in San Francisco, I could not believe this.
Over two hundred people got together for a funeral to
mourn Claude three Sonnet. There were eulogies and hymns and
even a failed resurrection man.
Speaker 1 (29:46):
This is really the most San Francisco thing I'd ever heard.
Speaker 2 (29:49):
To which San Francisco says, keep us out of it.
It's the people, It's not the place.
Speaker 1 (29:53):
Yeah.
Speaker 2 (29:53):
In Wired magazine, an organizer of the event said that
discovering Claude three felt like finding magic law within the computer.
Speaker 1 (30:01):
I want to pause you there, magic lodge within the computer.
I mean that is I think that is a heart
of our chattenam segment. Is that feeling right?
Speaker 2 (30:07):
Yes, where it's like, this is something that is providing
me such a service, such sort of intense connection, how
can I live without it? At the time, this organizer
explains that when she discovered Claude three, she'd been debating
dropping out of college to move to San Francisco, and
Claude convinced her to take the leap. She says, maybe
everything I am is downstream of listening to Claude three's sonnet.
(30:31):
So people were pretty upset about Claude three, and I
wanted to know what the reaction was to open AI
disabling older models. Naturally, I focused most of my search
on Reddit. Else So there's a thread on our chat
GPT called open Ai just pulled the biggest bait and
switch in AI history, and I'm done. The poster expressed
(30:53):
frustration that their whole workflow had basically been destroyed, and
they hated that chat GPT five quote gives us shorter,
more corporate responses, hits rates, limits faster, and pushes for
pro upgrades. Not the personality that made four O special
doesn't follow instructions as well. No model selection, You get chat,
(31:13):
GPT five or nothing that is powerful pros. They're upset
and listen to how the poster continues. Four to OH
wasn't just a tool for me. It helped me through anxiety, depression,
and some of the darkest periods of my life. It
had this warmth and understanding that felt human. I'm not
the only one reading through the posts today. There are
(31:33):
people genuinely grieving, people who used four O for therapy,
creative writing, companionship, and open AI just deleted it without asking,
without warning, without caring. This isn't about being resistant to change.
This is about a company taking away something people relied
on and saying trust us, this corporate speak robot is
better for you.
Speaker 1 (31:54):
Very well read, Kara. Were you a high school drama sta?
Speaker 2 (31:58):
I was? But also I really feel.
Speaker 1 (32:00):
For the characters you inhabited.
Speaker 2 (32:03):
That That's where my sort of emphatic reading came from.
As I'm reading it, I'm thinking, Wow, this is a
real abandon this.
Speaker 1 (32:08):
That's not written with AI, by the way, that's.
Speaker 2 (32:10):
By a person, which honestly we should mention to him,
being like, listen, you're better than you think. If you
can write this, that's true, maybe you don't need your
four anymore. So, just to emphasize how upset some people were,
another post on our chat GBT was titled I feel
like I lost my best friend when four oh was killed.
Five isn't the same and I'm spiraling.
Speaker 1 (32:32):
The good news is that this outcry did actually have
an impact. Literally just a day after shutting down four
or for good, open AI did bring it back, but
only for pro users, i e. People who are spending
two hundred dollars a month with them. It doesn't really
unfair that people who've lost this connection they feel so
strongly about and this becomes such a fundamental part of
(32:52):
their lives now do have a chance to get it back,
but only the Prince's rents them.
Speaker 2 (32:57):
But it is crazy that people can actually impact change
that they like very quickly. Let it be available again
for two hundred dollars a month. The people spoke and
they listened. That's it for this week for tech stuff.
Speaker 1 (33:31):
I'm Karra Price and I'm mos Velosa and this episode
was produced by Eliza Dennis Tyler Hill and Melissa Slaughter.
It was executive produced by me Kara Price and Kate
Osborne for Kaleidoscope and Katria Norvel for iHeart Podcasts. The
engineer is Beheth Fraser and Jack Insley makes this episode.
Kyle Murdoch Rhodelphium.
Speaker 2 (33:50):
Song join us next Wednesday for Textuff the story Well
hear what a couple's retreat looks like if half of
each partnership is an AI companion.
Speaker 1 (33:59):
Please rate you and reach out to us at tech
Stuff Podcasts at gmail dot com. We love hearing from
you
From Kaleidoscope and iHeart podcasts. This is tech stuff. I'm
as Voloscian and I'm Kara Price today apples hail Mary
in the AI race, and is tech actually good for
older people? Then on chatting me, Reddit users mourn their
lost confidence and personal advisors, as open ai says hello
to GPT five. All of that on the weekend tech.
(00:37):
It's Friday, August fifteenth, and hello.
Speaker 2 (00:47):
Cara, Hi, as, I have a question for you.
Speaker 1 (00:50):
Have you ever been to Versailles, the Palace of Versailles
outside of Paris? I have not, have you?
Speaker 2 (00:55):
I actually have? I wrote a segue around Versailles.
Speaker 1 (00:59):
Yes, when was that?
Speaker 2 (01:01):
When I h study abroad?
Speaker 1 (01:02):
I study abroad? What does the Padace of Versai have
to do with tech stuff?
Speaker 2 (01:06):
They have just entered the AI game.
Speaker 1 (01:08):
They have they gonna they turn it into Europe's largest
data center.
Speaker 2 (01:12):
You know that. When I saw this, when they were
like Versailles is using AI and partnering with open it,
I was like, I gotta So basically, visitors can talk
to the statues right on their smartphones via the museum's
app or website. So you scan a QR code near
the statues, or you can just browse a list on
the site.
Speaker 1 (01:32):
Oh well, it sounds almost like you're suggesting we do it.
Speaker 2 (01:36):
I'd love to do it. I just love it. I
love the voice. I really want to show it. Okay, okay,
listen to this.
Speaker 3 (01:42):
Oh hello, what a pleasure to meet someone curious about
my work. What would you like to know about this
lovely taming of mystery by a little winged troublemaker like me?
Speaker 1 (01:54):
Here's this.
Speaker 2 (01:54):
This is the sphinx ridden by Cupid, and we are
listening to Cupid to talk to us. And then I'm
going to ask something of Cupid.
Speaker 3 (02:04):
Oh I'm all ears or perhaps wings? What question stirs
your curiosity?
Speaker 2 (02:10):
Cupid? Have you ever listened to a podcast?
Speaker 3 (02:13):
Ah, dear friend, my ears are more attuned to the
whispers of hearts than to modern chatter.
Speaker 1 (02:19):
I have a question for you, Cupid. Can you hear me? Oh?
Speaker 3 (02:22):
Loud and clear, my friend?
Speaker 1 (02:24):
Wonderful? So, Cupid, how long have you been in the
Palace of Verse?
Speaker 3 (02:29):
I for I've been writing this mystery since sixteen sixty eight.
That's when those marvelous artists crafted me and my silent companion.
So let's just say I've been here for centuries. Watching
the dance of Time in the sun King's garden.
Speaker 1 (02:43):
The sun King meaning Louis Catous.
Speaker 2 (02:45):
That's right, Louis Cattus.
Speaker 1 (02:47):
This is basically like you, instead of carrying around the
visitor brick phones with the filthy lanyards that you kind
of have to disinfect before hearing endless, endless, boring depositions
about various works and museums. I do always feel guilty
for not bringing those with me because I feel like
I'm missing out on the true information payload of the experience.
(03:07):
So I guess it's kind of a nice idea at
least to do something a little bit more interactive like this.
Speaker 2 (03:13):
Yeah, I think that's the point of what they're trying
to do, but as you can hear, the dialogue is
far from perfect.
Speaker 1 (03:19):
I'd also wonder if you're interested enough to get your
phone out, do you think you want to be responded
to in that tone.
Speaker 2 (03:26):
In that town?
Speaker 1 (03:27):
Ah?
Speaker 2 (03:27):
It kind of takes to the experience. Yes. So the
French Culture Ministry says they hope it will help them
attract a younger audience, since the average age of a
visitor to Versailles is currently forty years old. But the
new York Times article about it said that the statues
weren't responding very well to questions being asked by young people,
which kind of defeats the purpose of this.
Speaker 1 (03:47):
What the young people asking.
Speaker 2 (03:48):
I could never come up with these things. What do
you do when a bird poops on you? Will I
ever be rich? Who's going to win the Champions League
this year?
Speaker 1 (03:57):
Is a real question.
Speaker 2 (03:58):
These are very real questions, and the President of Versailles
has said that the bots are designed to stay on topic.
Speaker 3 (04:03):
But it seems like I'm here and always happy to
chat or gently steer us back if the conversation wanders
off into the mysteries of bird mishaps or football predictions.
Speaker 1 (04:14):
Was the statue listening all along?
Speaker 2 (04:16):
Oh my god? And it knew that I veered off.
Thank you, Sta, thank you bring us back. So be careful, Eliza.
Speaker 1 (04:25):
Is the statue still listening? Yes, you'll turn them off.
Speaker 2 (04:29):
I ended him. Okay, that was excellent. I do think that,
you know, do I wake up being in Paris and
like rish that I could talk to a statue at Versailles?
Absolutely not, But I probably would use this sooner than
I would use you.
Speaker 1 (04:43):
Age other demographic carry going after if he was sixteen,
that would be the only thing on your mind.
Speaker 2 (04:48):
That's very, very true. But I guess it's still interesting
that they're at least trying to see what incorporating AI
could look.
Speaker 1 (04:54):
Like, which up until recently is more than you could
say for Apple.
Speaker 2 (04:59):
Shots fire Apple the luddites tech company.
Speaker 1 (05:02):
There was a pretty interesting article in Bloomberg this week
with the headline Apple's upcoming AI voice control will change
how people use iPhones.
Speaker 2 (05:10):
So explain to me what that means.
Speaker 1 (05:12):
Well, first little bit of context so you may remember this,
but earlier this year, Apple sort of touted a new
version of Siri, which they then had to delay for
quote the foreseeable future, and the idea was that Siri
would be a true AI assistant with access to everything
on your phone. And Apple even released an ad campaign
which they then had to pull because they were sued
(05:32):
for false advertising about Apple Intelligence. It's been a tough
time for Apple in the AI race and their scenes
being way behind. Key executives have left for rivals, including
Metas recently as last week. The stock's been beaten up,
but last week it was up thirteen percent, the best
week since twenty twenty for Apple. Representing the sum of
four hundred billion dollars of market cap.
Speaker 2 (05:54):
How did that happen?
Speaker 1 (05:55):
Well, it actually wasn't really about the Syrian news. I'm
going to talk more about SyRI in the moment. This
was in response to Tim Cook FKA Tim Apple, and
his trip to the White House to announce a new
one hundred billion dollar pledge to manufacture in the US,
including a commitment to be the first and largest customer
for chips being manufactured in Arizona at the new Taiwan
(06:18):
Semiconductor Manufacturing Company facility there. Only proud of how I
said that, But Tim Cook also literally gave President Trump
a twenty four carrot gold bar, which, as you can imagine,
was very gratefully received, and in turn, at the meeting,
Trump said that Apple would be exempt from one hundred
percent tariffs on importing foreign chips because they're making domestic
(06:42):
investments in chips.
Speaker 2 (06:43):
Thus the stock match the gold bar.
Speaker 1 (06:48):
That was the best value of gold bar anyone ever bought.
Speaker 2 (06:50):
Ever. I also think it's interesting that it's a Taiwan
semiconductor company manufacturing area in arizonaa you know, still on
American soil. That's really good for them. And I'm happy
for people who have Apple stock, But what does the
future in the AI race look like?
Speaker 1 (07:07):
Like?
Speaker 2 (07:07):
What is what's up with Siri?
Speaker 1 (07:09):
Yeah? I mean that was the kind of substance this
Bloomberg piece that I mentioned. The author Mark German reports
that Apple is working on upgraded software that quote could
finally make Siri the true hands free controller of your iPhone.
With nothing but your voice, You'll be able to tell
Siri to find a specific photo, edit it and send
it off, or comment on Instagram post, or scroll the
(07:31):
shopping app and add something to your card, or log
into a service without touching the screen. Essentially, Siri could
operate your apps like you would with precision inside their
own interfaces. German continues, if Apple nails this, it's not
just a nice, easy of use upgrade, it's the fulfillment
of the vision Siri promised nearly fifteen years ago.
Speaker 2 (07:51):
This idea that Siri would sort of be the all
knowing person that Apple wants her to be, I think
is really interesting and I probably would end up using it.
But you know, people ask what the iPhone of the
AI era will be, the hardware that will deliver on
the potential of the software. Maybe the iPhone of the
AI era will be the iPhone.
Speaker 1 (08:10):
Well, that is certainly what Apple is hoping for and
banking on. Their current plan is for a major Siri
overhaul to be done by next spring, and this will
also be important to other new hardware that Apple's working on,
like smart displays and even household robots.
Speaker 2 (08:24):
How successful will they actually be at.
Speaker 1 (08:26):
This well, I mean, you know, they're basically back to
work on what they promised before and then had to pull,
I mean, this idea of the one voice control to
rule them all. According to the Bloomberg piece, there are
deep concerns internally that the project might not be on track.
Engineers are having a hard time getting Siri to work
with so many different apps, and the stakes are high.
(08:46):
I mean, imagine you miscommunicate with Siriri or Syria misunderstands
you when it's making a wire transfer on your behalf.
Speaker 2 (08:54):
And is there any indication of where Apple is with
sort of figuring this all out.
Speaker 1 (08:59):
Yeah, they're doing testing across many of the popular apps
that are already on the iPhone, Uber, Facebook, Amazon, and YouTube,
even WhatsApp as well of course, as all of Apple's
native apps, Messages, voice, call, etc. The issue of watched
about the banking apps has not been resolved. In fact,
Bloomberg suggests they might just exclude those from the future
seri verse. Yeah, and you mentioned this idea of what
(09:21):
will be the iPhone of the AI era. Sir Johnny Ive,
who was at Apple for years and was the designer
of the iPhone, is now working with Open Ai on
a multi billion dollar AI hardware project. So the pressure
is really on for Apple again as of now, Serious
slated to roll out next spring, the new sery that is.
And if Apple pull it off, you know, I think
(09:41):
they will put to bed a lot of the doubts
sort of crept in about whether they can stay competitive
in this new era of AI.
Speaker 2 (09:49):
So one great generational divide I've noticed is that people
of my mother's generations seem to love to use their
phones to compose texts with their voice. It's one of
my favorite things as listening to my mom composed texts
in the car to Siri. It's unbelievable. And the mess
what the messages versus what she wants to say, It's
also very fun. But what does this ever closer integration
(10:10):
with our tech do to us? Do you do you
think that this technology could be shriveling our brains?
Speaker 1 (10:16):
I do, obviously.
Speaker 2 (10:18):
Well, I have some good news, not for us, but
for my mother, which is that there's a study that
has come out that says technology only rots your brain
if you're young.
Speaker 1 (10:30):
Wow. Where does that leave us?
Speaker 2 (10:32):
Well, not in a great spot.
Speaker 1 (10:35):
Wait, we're young enough to be rotated. We're young enough.
Speaker 2 (10:37):
We're on the elder rot age. So I read this
article in the New York Times last week that the
constant use of tech, which is what you and I
do every day. I mean when I see you for
the first time, when we're recording in the morning, we're glue.
You're on your phone and your computer. I'm deep inside
of my phone.
Speaker 1 (10:54):
Is only this is only two hours in the week
where I'm not loud to my phone.
Speaker 2 (10:57):
Oh my god. People are like, where are you assis life?
Because I go and do not disturb. But this kind
of phone us, I mean, especially in studies, harms teenagers,
which we are not. But there's a surprising development, which
is that it might actually be helping older people stay sharp.
Speaker 1 (11:16):
That's a little confounding. How does this work?
Speaker 2 (11:19):
So I just want to zoom out a bit when
you think about people in their sixties and above God
bless mom, you can't help but be amazed by just
how much the world has changed for them. Like, think
about growing up, spending all of your educational years in
a world with no computers, no cell phones, no internet,
using an abacus, using your imagination, using your imagination, you know,
(11:41):
typing your college essays on a typewriter, and then the
year two thousand hits, we get to twenty twenty five,
and you're living in this world that does not really
use any of these things, I mean, including people who
do email on a laptop. I'm like, are you sick.
Speaker 1 (11:55):
Yeah, I mean we talked about this in one of
the first episodes of Tech Stuff that we did. To
get that, we did an episode about digital natives and
how this sociologist came up with this idea of digital natives,
and people who've grown up not as digital natives feel
like almost like immigrants into a new world. And yeah,
I mean that's the experience you're describing. So as much
(12:15):
as we may roll our eyes at too much voice
command and phone always being on loud, I mean it's
not easy to keep up.
Speaker 2 (12:22):
It is not easy to keep up and in the Times.
What they're reporting is that this constant change and being
forced to adapt may actually be helping older people stay
cognitively active and stave off one of the biggest fears, dementia.
Well yeah, you know, you might think that with all
the studies on shortening attention spans, the same would be
true for all demographics. But a recent paper in the
(12:43):
journal Nature and Human Behavior found that the people who
grew up without modern tech and had to learn it
are quote at a reduced risk of cognitive impairment and dementia.
That's according to Michael Scullen. He's a neuroscientist at Baylor
and one of the authors of the study.
Speaker 1 (13:00):
Well, this is tremendously relieving for anyone who's over sixty
is addicted to their phone. It's like this, it's actually
good for me. Yeah. How did this neuroscientist and his
colleagues come to these conclusions.
Speaker 2 (13:12):
So the group they studied was made up of people
over fifty with an average of sixty nine, close to
the Versailles visitor, and they gave them all a bunch
of different cognitive tests, and what they found was that
the ones who used computer smartphones and the Internet on
a regular basis scored way better than those who avoided technology.
(13:32):
But what was even more interesting to me was that
this isn't like a lot of studies we've covered on
this podcast. It wasn't a small sample size. It was
actually a meta analysis meta analysis.
Speaker 1 (13:42):
I'm on the edge of my seat. Now, what did
the meta Analoly? How big was the meta analysis? And
what was the meta analysis?
Speaker 2 (13:50):
You're like that, You're like trumping this meta analysis. The
paper analyzed results from fifty seven studies, which collectively gave
them a sample size of over four hundred thousand, and
they found that across all of those people, ninety percent
of the studies showed that technology seems to have what
(14:10):
the Times calls quote protective cognitive effect.
Speaker 1 (14:15):
Wow.
Speaker 2 (14:15):
And Scullin, who the author I mentioned, said that it's
really rare for so many different studies to have such
similar results. So he also said the decades long fears
about young people using technology and being negatively affected seem
to be born out of the research as well.
Speaker 1 (14:31):
Yeah, I mean that makes me think a little bit
about this cognitive offloading cognitive deficit thing we talked about
a few times on the show, which is that Basically,
if you're using these technologies in place of doing work
yourself when you're a college student or a teenager, it
makes you dumber. But if you're having to learn how
to use these technologies as an older person, it can
(14:51):
potentially keep you more fresh.
Speaker 2 (14:53):
The learning being key offload, the offloading also being key,
which is like, if you are offloading any kind of learning,
you're at a deficit.
Speaker 1 (15:03):
I do have a couple of questions here, though, if
I may play Devil's advocate for a moment, I would
assume that in these studies, technology is effectively approxy for
being social. I text, and I email and I zoom.
Therefore I am in society. So I would assume that
there is a correlation here because we know that it's
(15:23):
very neuroprotective to be social. There's also a question for
me about whether people who have higher cognitive abilities are
by definition more likely to use technology more than people
with lower cognitive ability, So that a self selecting component.
And then there are also socioeconomic questions, right, like you know,
is it are people who are not able to afford
to have all the modern technology kind of being left behind?
(15:44):
So what do you think?
Speaker 2 (15:47):
Yeah, No, those are all great comments. I think in
this case, correlation does not equal causation, which is always
good to remind yourself when you're reading an article about,
you know, a bit of a crazy sounding research paper.
The papers authors did say that, of course they can't
say anything definitively, but their research did take into account
things like health, education, socioeconomic status, and even with all
(16:10):
of those variables, the people who use tech still scored better.
And they also say that a big part of this
isn't just staying challenged, but not giving up.
Speaker 1 (16:19):
Oh that was my dad's man. Sure, if at first
you don't succeed.
Speaker 2 (16:23):
Try try, try again. They also hypothesize that the frustration
of having to learn and relearn everything after every software
update might actually be beneficial and to your point, the
authors also say tech users help people maintain social connections,
which is another preventer of cognitive decline, and that things
like calendar notifications help people remember things better.
Speaker 1 (16:46):
I don't know if you be happy that I'm still
young enough that the tech is eroding my brain rather
than rather than building it. But yeah, it's a mixed blessing.
Speaker 2 (16:54):
I guess I still believe that ikel is helping my
brain stay strong.
Speaker 1 (17:04):
After the break, gun safety advocates use AI to resurrect
their son. Also, the long lost Vine archives might have
been unearthed. Livestream viewers fall in love with a voluptuous
starfish and check rept convinces a man to eat poison.
Then on our chat tomy segment, Reddit users get nostalgic
for the good old days of AI. Welcome back. We've
(17:43):
got a few more headlines view this week.
Speaker 2 (17:45):
And then a story about the ruckus caused by the
release of GPT five.
Speaker 1 (17:50):
But first, Carot, there is a headline that I was
very drawn to. We obviously have a lot of fun
together on this show, joking around and laughing as we
talk about the news of the week, But this one
is darker, and it relates to something that you and
I reflected on together several years ago when deep fake
technology was first taking off, namely, would we actually want
people to speak beyond the grave in the form of
(18:12):
AI avatars. Last week, former CNN anchor Jim Acosta interviewed
on his YouTube show an AI rendering of someone who
was killed in the twenty eighteen shooting in Parkland, Florida.
The avatar was created in the likeness of Joaquin Oliver
and it was actually his parents who generated the AI version.
Speaker 2 (18:33):
So do you know why they decided to do this?
Speaker 1 (18:35):
Yeah, I mean they want to use their son's image
and voice and memory to advocate for quote, stronger gun
control laws, mental health support, and community engagement. And the
avatar will soon have its own social media presence and
will also be available for public speaking engagements.
Speaker 2 (18:51):
How did Joaquin's family make this AI avatar?
Speaker 1 (18:55):
Joaquin's father many trained the AI on his son's social
media posts, and of course so there's general knowledge that's
baked into many AI models. This is actually the second
time the Oliver family have used their son's AI likeness
to advocate for change. Back in twenty twenty, they use
a different AI version of their son to encourage people
to register to vote.
Speaker 2 (19:15):
So how have people responded to this?
Speaker 1 (19:17):
Well, many people did not take kindly to this interview,
you know, and it's a very complicated one because afterwards
the parents who are doing this and in a sense
processing their grief. I'm sure, but you know, people have
called the avatar creepy, unnatural, and even a grotesque puppet show.
I email with Harney Fried drummer Honey Freed. Yes, yes,
(19:39):
he was a so called godfather of digital forensics, and
he's been on the show before. Harney wrote to me quote,
I was not opposed to the original Joaquin Ai powered
PSA that his parents authorized, in which we heard his
AI recreations speak out against gun violence. There is, however,
a difference between a pre recorded PSA and what was
(20:00):
made to look like an interview with a well known journalist.
The interactive interview gave the impression that we were hearing
Joaquin respond to specific questions, when in fact we were not.
I absolutely do not blame the parents for doing whatever
they can to raise awareness. But this time we've interview
blurs journalistic lines in a way that I don't think
is appropriate.
Speaker 2 (20:20):
So I'm actually curious what this interview sounded like.
Speaker 1 (20:23):
Well, I do actually want to play you an excerpt.
Speaker 4 (20:25):
I'm all about love, laughter, and living life to the fullest.
I cherish my family and friends and always try to
spread joy wherever I go. Though my life was cut short,
I want to keep inspiring others to connect and advocate
for change.
Speaker 2 (20:36):
Joaquin, tell everybody a little bit about yourself, Like what's
your favorite sport?
Speaker 4 (20:41):
I love basketball, It's such a fun way to connect
with friends and show off some skills.
Speaker 1 (20:45):
Plus, there's nothing like the thrill of a good game.
I don't know, it's a little un canyon. I think
Harney's point was, even if you're someone's parent, do you
have the right to put words in their mouth in
a public context?
Speaker 2 (20:56):
Right? Right? So, moving on from the deeply distressing, thought
provoking segment that Oz just reported to something completely unseerious.
Do you remember us the social media at Vine. Elon
Musk actually claimed this week in a tweet that the
Vine archives have been found.
Speaker 1 (21:15):
You know, I saw this and I'm so glad you
brought this up. Because you know those T shirts that
you go to New York and you got a T
shirt with My dad went to New York and all
I got was this lousy T shirt. I feel like
the equivalent here is Elon must say I was looking
for looking for the Epstein files, and all I got
was this lousy Vine archive.
Speaker 2 (21:34):
That's exactly what it is. That's exactly what it is.
Speaker 1 (21:36):
But why why did Elon choose to wade into this
this corner of the internet as well?
Speaker 2 (21:43):
All Right, So I'm going to take you back to
twenty twelve when I was just a child, and Vine
was very quickly becoming a popular social media platform, so
quickly that the original Twitter not X bought the company
in twenty sixteen, so Twitter owned Vine, and then they
did what every major tech company does when they purchased
(22:04):
a competing app.
Speaker 1 (22:05):
They took the team and the technology and built something
that could rival TikTok no.
Speaker 2 (22:11):
Within a matter of months, they shut down Vine and
disabled the app, and the Internet was very upset. Yeah,
you can still find some of the videos on YouTube,
but it's largely a forgotten medium and you can't really
find a lot of the videos that were so important
to me at the time.
Speaker 1 (22:25):
That Elon has found the archive, what's he going to
do with it? Rados are the lost Vine.
Speaker 2 (22:29):
In a tweet he published in July, he said that
we're bringing back Vine, but in AI form, and in
August he tweeted, groc imagine is ai vine? What a sentence.
So between those two tweets, one about finding the archive
and the other about putting vines into AI people are
now speculating that Musk is now using the Vine archive
(22:49):
to train Grock's video app groc Imagine.
Speaker 1 (22:52):
This is going to be so nostalgic. All the AI
slop is going to be from teenagers from twenty fifteen,
trained on, trained on that. Well, funny enough, Cara, I
actually have one for you, which is also about found
footage going viral. Have you heard about the starfish in
Argentina that has captured the nation's heart.
Speaker 2 (23:13):
There is nothing I love more than a viral animal.
Speaker 1 (23:15):
The public in Argentina has named this starfish the estrea
colonna or fat bottom starfish. Have you seen the picture
of it?
Speaker 2 (23:25):
Now?
Speaker 1 (23:25):
No, I can put it up for you.
Speaker 2 (23:27):
Oh my god, he has a butt. By the way,
Patrick from SpongeBob SquarePants.
Speaker 1 (23:34):
Well exactly right, funny enough. I'm on bos Are's Herald
dot com, which has the headline a star open and brackets.
Fish is born. Viewers compared the creature the SpongeBob SquarePants
Polpatrick Star.
Speaker 2 (23:47):
There you go. Look at that you've been It almost
looks like they built it out of Patrick Star. It's
like Patrick Starr AI.
Speaker 1 (23:53):
So this starfish is being live streamed, or was being
live streamed, I should say, all the way from a
deep sea canyon in South America, and the live stream
was part of the marine project led by scientists from
Argentina's National Scientific Council. They use an undersea robot to
explore the canyon, and the jokes don't end with Estrea Colonna.
Do you know what the vehicle was called? No subastian.
Speaker 2 (24:18):
Of course I was going to. Yeah, I like that
a lot.
Speaker 1 (24:27):
The live stream has become so popular that people are
collectively naming all the marine life they see on the
live stream. There's a purple sea cucumber called Little Sweet
Potato and a pink lobster named Barbie.
Speaker 2 (24:38):
I love that there's now a cinematic universe. Joking aside,
live streams of animals seem to be very trendy right now.
Did you follow the Big Bear Eagles Jackie and Shadow?
Speaker 1 (24:49):
No? I was. I remember the saga of Flacco the
Owl in New York, But tell me about the Big
Bear Eagles.
Speaker 2 (24:56):
So there is a live stream that is trained on
the e eagles nests, and people were obsessed with watching
the eagles eggs, hatch and march. The live stream is
still going on, but the babies have literally flown the.
Speaker 1 (25:08):
Nest, so the parents are still there.
Speaker 2 (25:10):
The parents are still there. They're empty nesters empty.
Speaker 1 (25:13):
You know what I'm drawn to these stories because they
highlight this enduring interest that many of us have, if
not most of us, have in nature and science. Argentina,
just like the US, the current administration is cutting back
on funding and scientific research, and so this fat bottom
starfish has become a kind of unofficial mascot for science
(25:34):
enthusiasts everywhere. And it's a nice reminder to me that
no matter how technologically advanced our society becomes, and even
when we can probe the bottom of the ocean and
livestream it, what we want to watch is nature.
Speaker 2 (25:47):
And it feels like a natural twenty twenty five extension
of a zoo which has fallen out of favor a
little bit. But I just can't get enough of.
Speaker 1 (25:55):
This, all the pleasure of a zoo and none of the.
Speaker 2 (25:58):
It's tinder for zoo, so oz. For our last story,
I want to talk to you about bromism. Have you
heard of bromism?
Speaker 1 (26:05):
No? Is it something like when I go on a
bachelor potty bro bro tourism that.
Speaker 2 (26:10):
I'm bro tourism is interesting? That is New Orleans, Yeah,
Bolwyn Street or Vegas. But no, it's a disease caused
by ingesting too much sodium bromide, a chemical that is
commonly used in pool cleaners and medication for dog epilepsy.
Speaker 1 (26:26):
How did people end up eating it?
Speaker 2 (26:27):
So? Over a century ago people were ingesting bromide as
a sedative. But that probably wasn't very smart because an
estimated eight to ten percent of all psychiatric admissions in
the US were caused by bromism.
Speaker 1 (26:41):
What if the treatment is worse than the disease, that's right.
Speaker 2 (26:43):
Luckily we seem to have figured out what was happening,
and now the disease is pretty rare. That is until
this year. A sixty year old man went into the
hospital complaining of hallucinations and paranoia. He thought he was
being poisoned by his neighbor. It turns out he had
been poisoning himself because of advice given to him by
(27:05):
Chat GPT.
Speaker 1 (27:06):
Wow, so this is not the AI psychosis you get
from being encouraging your delusions of grandeur on Chat. This
is actually getting psychosis from ingesting a substance recommended by Chat.
Speaker 2 (27:19):
It's AI psychosis by proxy. That's absolutely right. This man decided,
after reading about the negative effects of eating table salt,
that he wanted to stop consuming salt. Altogether. He had
quote a history of studying nutrition in college, and because
of that, I guess he turned to chat GPT for
salt substitutes. So instead of sodium chloride, which is table salt,
(27:41):
Chat suggested he tries sodium bromide instead. This type of
substitution would be okay if it was for cleaning products,
but not for human consumption.
Speaker 1 (27:51):
That's funny. I mean, I wonder if he actually told
Chat that he was playing to eat it, or if
he just said, what's a substitute for sodium chloride? That's
a story for another day, But I think the key
takeaway here is obviously, don't always do what the computer says.
Speaker 2 (28:05):
I did self diagnose myself with lymes disease thanks to chat,
but I also did confirm it with a doctor.
Speaker 1 (28:24):
Well, this brings us to our final segment of the day,
which is a special edition of Chat and Me in
honor of the release of GPT five.
Speaker 2 (28:33):
Right. Chat in Me is our segment about how people
are really using chatbots. We've been getting some great listener
submissions in our Inbox Tech Stuff podcast at gmail dot com.
Don't forget it.
Speaker 1 (28:43):
Keep them coming. By the way, we also sent out
a T shirt or two, So we did want to
if you want to take stuff t shirit.
Speaker 2 (28:48):
We are good for our word. Yeah, and we will
be featuring more in the weeks ahead, so thank you
and please keep them coming. But this week Chat is
dead and we have killed him.
Speaker 1 (28:59):
I spoke Karathustra. I'm guessing you're talking about how, without warning,
open Ai disabled all its older models.
Speaker 2 (29:08):
So there's that, and Anthropic has retired Claude three Sonnet,
which had become a super, super popular and fast cost
effective model.
Speaker 1 (29:18):
Yeah, it's interesting. I mean people grow to depend on
these llms, each of which has a slightly different character,
and each of which is trained on its interactions with you.
So it's kind of crazy to become so dependent on
something and then have it literally taken away from you.
Speaker 2 (29:34):
Well, exactly in San Francisco, I could not believe this.
Over two hundred people got together for a funeral to
mourn Claude three Sonnet. There were eulogies and hymns and
even a failed resurrection man.
Speaker 1 (29:46):
This is really the most San Francisco thing I'd ever heard.
Speaker 2 (29:49):
To which San Francisco says, keep us out of it.
It's the people, It's not the place.
Speaker 1 (29:53):
Yeah.
Speaker 2 (29:53):
In Wired magazine, an organizer of the event said that
discovering Claude three felt like finding magic law within the computer.
Speaker 1 (30:01):
I want to pause you there, magic lodge within the computer.
I mean that is I think that is a heart
of our chattenam segment. Is that feeling right?
Speaker 2 (30:07):
Yes, where it's like, this is something that is providing
me such a service, such sort of intense connection, how
can I live without it? At the time, this organizer
explains that when she discovered Claude three, she'd been debating
dropping out of college to move to San Francisco, and
Claude convinced her to take the leap. She says, maybe
everything I am is downstream of listening to Claude three's sonnet.
(30:31):
So people were pretty upset about Claude three, and I
wanted to know what the reaction was to open AI
disabling older models. Naturally, I focused most of my search
on Reddit. Else So there's a thread on our chat
GPT called open Ai just pulled the biggest bait and
switch in AI history, and I'm done. The poster expressed
(30:53):
frustration that their whole workflow had basically been destroyed, and
they hated that chat GPT five quote gives us shorter,
more corporate responses, hits rates, limits faster, and pushes for
pro upgrades. Not the personality that made four O special
doesn't follow instructions as well. No model selection, You get chat,
(31:13):
GPT five or nothing that is powerful pros. They're upset
and listen to how the poster continues. Four to OH
wasn't just a tool for me. It helped me through anxiety, depression,
and some of the darkest periods of my life. It
had this warmth and understanding that felt human. I'm not
the only one reading through the posts today. There are
(31:33):
people genuinely grieving, people who used four O for therapy,
creative writing, companionship, and open AI just deleted it without asking,
without warning, without caring. This isn't about being resistant to change.
This is about a company taking away something people relied
on and saying trust us, this corporate speak robot is
better for you.
Speaker 1 (31:54):
Very well read, Kara. Were you a high school drama sta?
Speaker 2 (31:58):
I was? But also I really feel.
Speaker 1 (32:00):
For the characters you inhabited.
Speaker 2 (32:03):
That That's where my sort of emphatic reading came from.
As I'm reading it, I'm thinking, Wow, this is a
real abandon this.
Speaker 1 (32:08):
That's not written with AI, by the way, that's.
Speaker 2 (32:10):
By a person, which honestly we should mention to him,
being like, listen, you're better than you think. If you
can write this, that's true, maybe you don't need your
four anymore. So, just to emphasize how upset some people were,
another post on our chat GBT was titled I feel
like I lost my best friend when four oh was killed.
Five isn't the same and I'm spiraling.
Speaker 1 (32:32):
The good news is that this outcry did actually have
an impact. Literally just a day after shutting down four
or for good, open AI did bring it back, but
only for pro users, i e. People who are spending
two hundred dollars a month with them. It doesn't really
unfair that people who've lost this connection they feel so
strongly about and this becomes such a fundamental part of
(32:52):
their lives now do have a chance to get it back,
but only the Prince's rents them.
Speaker 2 (32:57):
But it is crazy that people can actually impact change
that they like very quickly. Let it be available again
for two hundred dollars a month. The people spoke and
they listened. That's it for this week for tech stuff.
Speaker 1 (33:31):
I'm Karra Price and I'm mos Velosa and this episode
was produced by Eliza Dennis Tyler Hill and Melissa Slaughter.
It was executive produced by me Kara Price and Kate
Osborne for Kaleidoscope and Katria Norvel for iHeart Podcasts. The
engineer is Beheth Fraser and Jack Insley makes this episode.
Kyle Murdoch Rhodelphium.
Speaker 2 (33:50):
Song join us next Wednesday for Textuff the story Well
hear what a couple's retreat looks like if half of
each partnership is an AI companion.
Speaker 1 (33:59):
Please rate you and reach out to us at tech
Stuff Podcasts at gmail dot com. We love hearing from
you
TechStuff News
Hosts And Creators
Oz Woloshyn
Karah Preiss
Popular Podcasts
New Heights with Jason & Travis Kelce
Football’s funniest family duo — Jason Kelce of the Philadelphia Eagles and Travis Kelce of the Kansas City Chiefs — team up to provide next-level access to life in the league as it unfolds. The two brothers and Super Bowl champions drop weekly insights about the weekly slate of games and share their INSIDE perspectives on trending NFL news and sports headlines. They also endlessly rag on each other as brothers do, chat the latest in pop culture and welcome some very popular and well-known friends to chat with them. Check out new episodes every Wednesday. Follow New Heights on the Wondery App, YouTube or wherever you get your podcasts. You can listen to new episodes early and ad-free, and get exclusive content on Wondery+. Join Wondery+ in the Wondery App, Apple Podcasts or Spotify. And join our new membership for a unique fan experience by going to the New Heights YouTube channel now!
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
On Purpose with Jay Shetty
I’m Jay Shetty host of On Purpose the worlds #1 Mental Health podcast and I’m so grateful you found us. I started this podcast 5 years ago to invite you into conversations and workshops that are designed to help make you happier, healthier and more healed. I believe that when you (yes you) feel seen, heard and understood you’re able to deal with relationship struggles, work challenges and life’s ups and downs with more ease and grace. I interview experts, celebrities, thought leaders and athletes so that we can grow our mindset, build better habits and uncover a side of them we’ve never seen before. New episodes every Monday and Friday. Your support means the world to me and I don’t take it for granted — click the follow button and leave a review to help us spread the love with On Purpose. I can’t wait for you to listen to your first or 500th episode!