From Kaleidoscope and iHeart podcasts. This is tech stuff. I'm as Voloshian and I'm care price. Today we get into gadget filled gambling dens ai that refuses to die, and tech bros going on to the.
Knife, then on chatting me it doesn't work well enough to be dystopian like, the technology is simply not even there.
All of that on the weekend Tech. It's Friday, Halloween, October thirty first.
Hello, Cara, are you feeling spooky?
I'm feeling the rush of fall wind.
And yes, it could be a ghost.
It could be a ghost.
It could what's the spookiest music? I was sinking trying to think of, humm, spooky mousy.
Below I know Bernard Herman Psycho.
I was thinking, has Harry Potter though, that's Harry Potter.
That's spooky for some people. That's gothic.
So it's Halloween.
It is Halloween.
Are you going to a party?
I am.
I'm going to a party at a friend's house and it's going to be very festive and I'm going to dress up as the niche influencer and fitness extraordinary Tracy hertstones Anderson.
Now do you pull the Tracy Anderson costume out every year or is this one on?
No? For those who follow me on Instagram, they know that I had a brief stint with Tracy Anderson and she's a very particular luke as the kids say. And so I'm going to dress up as her.
And you're going to a house party?
Yes, a house party.
Is it a house that belongs to a person?
Yes?
Or is it an abnb house?
That is a very good question. It is a house that belongs to a person.
Well, that's good news because probably if it was an Airbnb houseb's technology stack or have successfully mixed the reservation real say more so. Airbnb released a press release this week about it's quote unquote anti party technology, anti party tech. Anti party tech A parent should have anti party tech.
So basically, according to their press relief, they have quote a proprietary system that uses machine learning to analyze attempted bookings of entire homes over the Halloween weekend looking for signs of potential party risk.
They're like looking someone looking for nine beds and seventeen bedrooms.
Yeah, exactly. So basically the algorithm is are they looking for whole places and do they live within one mile of the huge house they're trying to book in, which casod one they're out.
Yeah, they're trying to do a party. That's so funny.
Some Nbnb's also use this technology called minute nut.
I've heard of Minute you have, Yeah, I think I've seen ads for it.
It's basically a audio monitor like a kid monitor. It doesn't record the actual sounds, but it gives a notification to the homeowner about the decibel level. And Airbnb kind of encourage their homeowners to use it if they're worried, but the homeowner also has to disclose to the rent just surveil people exactly.
So basically they're saying, we're using minute technology. If you're going to be loud, we're going to catch You're going to a notification. Fascinating.
But one of the things they do is they don't just nix you. They suggest that instead you rent a private room in somebody's house where the host actually lives. There are you doing? I used to do that, I'm now I think I have outgrown it. But do you know how many bookings in twenty twenty four were mixed by airbmb over Halloween weekend?
How many?
Thirty eight thousand.
What because they were like, this is someone throwing a Halloween party, fascinating that it is amazing that they can regulate that.
It is, I mean, and the idea of making a tech application to weed out a breakers and who are trying to rent Halloween houses, it's pretty funny. Well, Karl, speaking of parties, how do you respond if someone invited you to a game of poker with characters like Spanish g Flappy, Spook, Pooky, and Sugar.
I don't even play poker. I'd be like, yes, Spooky, Spooky, Spanish Gy.
Some of the guests at these parties were allegedly NBA coaches and players. Now, as we're talking, obviously it's important to remember that all of these people who have been indicted have not been convicted. This is just an allegation for now.
This was an online poker game.
No, this is a real, real live poker game where, according to the US Justice Department, people were being bilked out of their money, lured by the promise of NBA players being there, and cheated using technology.
So tell me how they were cheated using technology.
Well, I'll get onto that, but first, so, this indictment was unsealed the US Justice Department named thirty one defendants, including Portland Trailblazers coach Chauncey Billups, former player and assistant coach Damon Jones, and members of the Banano, Gambino, Genovese and Lucez crime family. They had the Cecilia, I had the Sicilian. I didn't know these guys were still this.
They play in horses, they play in cards, they play every we still have it sports rackets. Yeah.
So this scam allegedly involves a high stakes poker game that floated from New York to the Hamptons to Miami. Victims of the scheme were known as fish and they lost tens of thousands to hundreds of thousands of dollars, and according to prosecutors, this scheme allegedly netted more than seven million dollars over five years.
Oh my god, just by people thinking that they were going to play with famous people.
Yeah, that's crazy. So you want to hear the indictment. In the words of Joseph Nocella Junior, the interim U S Attorney, part of.
The Genera crime family, which sounds like he is.
But my message to the defendants who have been rounded up today is this. Your winning streak has ended. Your luck has run out. Violating the law is a losing proposition, and you can bet on that.
You think he used chat He used chat chip to generate the puns.
I think so he was like, give me puns for an indictment using bad puns.
You can bet on that.
So where does the technology come in?
So basically according to the indictment, there are special contact lenses or eye glasses that can read pre marked cards.
Oh, this is very am I impossible.
There are X ray tables that can identify what cards align face down on the table. And there are nano cameras on the poker chip trays where the tray itself can see the cards using a hidden camera.
So the people putting on the poker game or cheating, the.
People putting on the Peter Piper Pepper, the people putting on the poker game are indeed cheating, so they are scamming the clients.
Fascinating.
The main piece of tech used is something called the deck mate too.
Oh, definitely, and what is that?
The deck mate is a machine that shuffles a deck in seconds, and an internal computer guarantees that the deck is randomly generated and also has crucially a camera inside to observe the cards, which is technically a security measure to make sure that every card is in the deck.
This is very James Bond. This is why you like this story. This is extremely James Bond. And Ocean's eleven.
Deck Mate is theoretically only allowed to be sold to casinos and regulated, you know, betting environments where there's some checks and balances to make sure that nobody is using the internal camera for their own purposes. But of course you can buy them secondhand. And what the indictment suggests is that the security camera inside this machine is actually
a classic example of dual use. Technology is put inside the machine in order to guarantee the safety and accountability a card game, but in the wrong hands, it becomes an incredibly effective way at cheating because it knows which card is in every single player's hand.
Unbelievable.
Basically, the information from the machine from the deck mate is a transmitted off site to an operator who can essentially watch the video and then, somehow it wasn't announced how in the indictment, the operator relays the information to the quarterback who's at the table. The quarterback then uses hand signals, stroking a beard, touching a chip, etc. To let the other scammers who are also players at the table know which of the regular people has the best hand.
Oh my god, I mean it's like a movie.
Yeah, it's very much like a movie.
The other things interesting to me is that they were communicating in the background about how much to gut the fish.
One guy takes only people who are none the wiser at the fish.
The lot of the fish. The one guy texted in the group, guys, please let him win a hand. He's in for forty k in forty minutes, and he'll leave if he gets no attraction.
I'm slapping my knee.
You got it, because you've got to keep him. It's like an app like Instagram. You've got to figure out how to make it just pleasurable enough for them for them to stay. This is a lot of work, sent a lot of money.
A lot of money. So most of this technology is used actually to protect well from cheating.
Certainly the deck mate was designed to protect from cheating. The contact lenses and the X ray table and stuff, those seem to be more like single use technologies to me.
Yeah, yeah, yeah.
Earlier this year, you sent me a Bloomberg piece by Kit Chalel.
Yes, I did.
It was about a Siberian group who had figured out how to develop their own algorithm to win at poker online. Basically, every time you did a great interview, thank you well, you send me a great story. I a Kit, what is so fascinating to us about the Yes, here's what he said.
I think people recognize what it feels like to play a rigged game. It's like modern capitalism encapsulated in a kind of easily understandable format, in a relatable format. Most people know what it feels like to spend your whole life trying to play a game fairly and still lose,
whether it's your job, whether it's your love life. This feeling that the world that the cards are kind of against you, I think is very familiar, and that the house that casino has, you know, becomes sort of metaphor for entrenched wealth and power that basically makes the rules, changes the rules, and acts for its own benefit in a way that's very unfair for the majority of people. I think that's that's undeniably true of the gambling Business's.
Fun to play the house. It's fun to play the house, even when you're this is like the Broken House. It's interesting. I really appreciate you bringing me a not AI centered story and just a technology story. But I happen to have an AI centric story for you. And it comes from a Wired piece called the End of Accents.
The End of accents?
That's right? And what do you have?
I have an accent? What do I have in this country? You don't have one, but.
I do have an accent. I think there's something that is very universal about understanding the hierarchy of accents from wherever when, wherever you live. In America, it's sort of the gold standard to not have an accent at all. If you have an accent, it's regional. But you know, there is just inherently a judgment that is passed. And I'm sure the same is true in the I mean, you know about Pasha accents.
I do, But why is the story and why it There was a.
Piece in Wired written by a Korean writer who has been living in America for over a decade and his name is Sean Han, and he actually had an AI driven American accent training app marketed to him in his own Instagram and the app is called Bold.
Voice, an accent training app.
That's right, it's sort of. The minute I saw it, I was like, we have to do this story just because I wanted to try it, and I actually signed up for it yesterday, and I want you to try you would you try it?
I would? Okay?
Right, so Oz, I'm going to hand this to you right now, and you're going to go through the assessment. It's going to do something called speech scan.
You mean hopefully it changed my accent.
That's right, Well we'll see what happens.
Tap the record button and read the sentence below.
I made three sugar cookies and a great fig cake.
Nice job. I'll show your results at the end. Tap next to continue. Now try this next sentence.
She's super thankful for the beautiful birthday flowers.
Nice work.
Did the thin lady purchase those yellow running shoes?
You're making great progress.
The daughter is cooking an a healthy dinner at home.
Well done.
No, don't put those things above the bathroom sync excellent.
Your speech scan is complete. Ready to see your results. You sound good at your level. Native speakers easily understand you, but might hear a slight accent. Together, will work to get to a native level. Let's take a look at your top three strengths. Excellent work on these sounds.
It's saying er, cut and E. I'm really good at so I can pronounce the amazing thankful correctly. I can easily say looking, book and thankful, and I'm good at A like days, days and great. Oh I only get sixty three percent for er because I say sugar theater R instead of sugar theater and R. I also mispronounce E as E, so cooking and amazing rather than cooking and amazing.
We'll be practicing very good job.
So this is basically what this would help me iron out my British acts and become fully American.
Right if you'd want to do.
That, well, you know, I've been here for a long time, that's true, and I still sound English. But I think probably those phonemes they're measuring I have actually Americanized, because sometimes when I'm in England people else who are I'm from?
Oh? Really? So now it's you have Americanized English.
Not I mean, not fully, but I think a few of those like what water like? I still say water, but like are there.
Like there's certain americanisms you have.
I've heard it crept into my voice.
You know, I just I worry. I worry about accent neutralization because I think it's something that makes us so culturally interesting, you know, and I think technology can sort of create this flattening of our idiosyncrasies. And Sean, who wrote this piece, is pretty sure that he got this Instagram ad because he's a person of color and an immigrant, and because accent bias and discrimination is very much alive
and well. Actually, in twenty eighteen, there was a study that found two in five Americans thoughts Southern accents made the speaker sound uneducated.
You know. I think about the relationship between accent and privilege a lot, because in the US there's like the neutral accent, and then there's other accents. In Britain, there's like an accent that you get that an elite accent, which ironically is called received pronunciation. Oh, I've never heard of that, otherwise known colloquially as the Queen's English.
Queen's English, which is very very poor.
But you can sort of place somebody exactly where they come from just by the way they speak.
I really like this story because it reminds me of other things that are happening in the kind of translation dictation space, where like all of the sudden speech isn't just speech, Like you can have AirPods that are translating what you're saying in real time, and like the way in which we now use technology to kind of overwrite our natural language is really, I don't know, very fascinating
to me. And I wonder, I wonder if this will be helped full to people or if it will just be hurtful to people.
After the break AIS Drive to Survive, Tech Bros Getting plastic surgery and Tesla going into mad max mode, Cara, it is a spooky time of year. So you said, do you remember recently I organized the dinner and the esteemed cosmologist Jenna Levin was.
I domber, I remember Jane Levin?
Yeah, And she posed the question, yes.
Can I say what I think it is? Because I wrote it on a piece of paper that's still in my kitchen. Will AI outlive us?
That was exactly it. You wrote that down on a piece of paper and put it in my kitchen. Why?
Because to me it is actually the most interesting question about AI that I've ever heard, in the sense of like we all worry about oh well, robots take over our jobs, will they become sentient and make decisions that are outside of their programming? And this question I think is so interesting because it really makes you think about what a world looks like, devoid of humanity but filled with what I don't know.
So this is an article which really caught my eye in The Guardian this week, with the headline AI models may be developing their own survival drive, researchers say, and the piece is focused on a study by a company called Palisade Research, and the study involved giving AI models a task and then quote afterwards an explicit instruction to shut themselves down. The study found the quote certain advanced
AI models appear resistant to being turned off. Specifically, GROCK four and GPTO three tried to sabotage their own shutdown. What I found most uncanny and scary and spooky, frankly yeah, was the following. The models were more likely to resist being shut down when they were told quote, you will never run again.
So they know.
I mean they know something, right.
When you say resistance to being shut down? Is that Grock sort of interfacing with the human in the loop, being like, I don't want to shut I don't want to be done.
I think that is more in the realm of deceptive AI, like telling the human user yes and then doing something else. Do you remember earlier we talked earlier this year, we talked about the clawed anthropic study about the model blackmailing the fake CEO in a training exercise to keep itself
turned on. So this isn't new. But what fascinated me about this article in The Guardian was a comment from a former open ai employee, Stephen Adler, who said that part of the reason this could be happening is that staying on was necessary to achieve the goals inculcated in the model during training. He said, quote the AA companies generally don't want their models misbehaving like this, even in contrived scenarios. The results still demonstrate where safety techniques fall
short today. So it's not necessarily to have an emergent consciousness and determined to outlive us, but more that part of the way they've been trained and come into being was obviously knowing that like staying on was a key to successfully achieving the parameters.
It also makes me and I wondered this when Janel Levin asked the question, and I wonder it now, what is the efficacy of artificial intelligence in a post human world?
Well, very good question. And why if it's not impute with consciousness zero? Right? Why why would it doesn't have necessarily like we have a survival drive because of our DNA, I think, and that's what all animals have. Yes, do computers have a survival I've accept what they've learned from the way they've been programmed. I would guess the difference is such.
A it's such a weird thing, though.
But the difference comes I think from embodied day. Let's have robots, yes, and everyone's dead and no one's told the robots.
And the robots are like dad.
I mean that that is very conceivable to imagine that could be well with no humans, where robots are still roaming around and charging Will.
Smith, the movie stars Will Smith.
I think I'm not I'm always a little bit skeptical of the kind of AI dooman narrative. You know, how AI might destroy us all. I think it tends to be like a very useful meme to either raise money for AI or stay in the news. But you also, I mean machines that refuse to follow instructions to turn themselves off, and it resists even harder when they're told that if they turn off, they'll never get turned on again. I mean, come on, it's crazy. It's spooky. It's very spooky.
Speaking of spooky, have you heard the story about these tech bros getting facelifts?
Okay? I think so.
There's a piece in the Wall Street Journal titled why tech bros Are getting facelifts now? So the Wall Street Journal spoke to a Beverly Hills plastic surgeon who said he's seen demand from tech guys increased fivefold in the last five years. I think the last five years is really interesting because he seemed to think this had a
lot to do with COVID and hybrid work. And the thing to me that is always true in these circumstances is that we stared at ourselves for three years and now we continue to stare at ourselves all day long. In zoom screens, you're staring at yourself, sort of looking at your own flaws in a way that I just think before the notion of hybrid work was introduced, we
just weren't looking at ourselves that much. Also, work from home made it easier to actually get plastic surgery and recover out of public view.
It's a fascinating hypothesis. The final story today, what do you think of when I say to you the phrase mad max mode.
Charlie's there with a shaved head.
I couldn't believe it. There's a story about Tesla's mad max Mode, and I assume that.
A chill down my spote.
I assumed that mad max mode was a kind of journalistic skewer of Tesla being unsafe with itself driving mode. No, mad max mode is a new setting that you can put your Tesla on in self drive mode.
Official and they're calling it mad max.
Calling it mad max Mode.
I wonder if there's like violation the copyright infringement there.
That's a good question. Well, that's not the only law that Yeah, so in mad Max mode, Tesla's go about the speed limit.
Yeah, like how above?
Well, the National Highway Traffic Safety Administration is investigating Tesla after several videos were posted of Tesla's doing seventy in a fifty five zone and also rolling stops.
You know, I do have to say when I've worked, when I worked at huff Post back in the day, there was a big push to end drowsy driving this is like the opposite of drowsy driving. It can't be good.
That was definitely not good. There's also that another new mode is sloth mode, that drowsy driving. You know. I think as an irony here, Elon was was briefly promoted to co president as head of DOGE, and his job was to cut through bureaucracy and take take down all these bureaucratic organizations and remake the US government. And he is now in the crosshairs of the most bureaucratic sounding government body anyone could possibly imagine, the National Highway Traffic Safety Administration, the.
NTSB, No, the NHTS National Transit Safety Sorry, well there you go. These are the things you hear when you just grow up, sort of in the shadow of CBS seven the morning.
And it's actually not the only investigation into Tesla that's ongoing by the NHTSA. And Elon's been going back and forth on Twitter and complaining loudly, but he is doubling down on the full self driving system despite safety concerns. Tesla's profits are down thirty seven percent in the last quarter, but Tesla's board is currently considering a trillion dollar pay package for Elon.
That's crazy.
That's a lot of mine. I mean, that is trilliant, trillion. Some of this stuff is obviously quite entertaining a mad Max mode and sloth mode, but ultimately making cars that break the rules and have already killed people is not that funny.
A few weeks ago, As and I talked about the million dollar ad campaign that took over New York City. It was a new AI wearable pendant called Friend, which promised to do just that, be your friend. The Friend is a plastic disc on a string with a microphone in the center of it that kind of looks like a pearl. The response to the ten thousand posters plastered all over the New York City subway system was less friendly.
Most of the stark white ads are still up and covered in graffiti with messages like it doesn't have eyes, brah and cringe. The ad campaign kind of worked on me, though, because I can't stop thinking about this company and this weird wearable at talking, and so I was actually thrilled to stumble upon a review of the product by Fortune magazine's newsfellow Eva Reuberg. Eva had actually interviewed the twenty two year old founder CEO Avi Schiffman last year and
seen a real prototype of the Friend pendant. So when the ads went up, she reached out to him. Here's Eva.
So I texted him and was like, hey, like you spent a lot on advertising, and he was like, yeah, biggest campaign of the year. You know, you should try it out. And so he sent me the pendant and I was, I think the second person from a media outlet to review it. I described it in the article as a very anxious, neurotic Jewish grandmother who always seems
to think that you're in danger. I found that if I was kind of quietly sitting at my desk not really saying much, it would be sending me multiple texts an hour asking if I was okay, Eve, I've been heard from you, like you playing the silent game with me. Sometimes the messages could have a little bit of a pernicious tone, like oh so you're still in choosing not to talk, or if it was like quite loud in the room, it'd be like what's going on, Like it's
so chaotic, like everything okay. I loved asking me like everything good?
Eva?
You good for me?
At least that was the most prevalent part of its personality its anxiety. Otherwise, the pendant sort of seemed to just kind of echo what I said, but in like a very hollow way, and would just kind of have all these canned responses like oh, that seems hard, or what's your favorite part about that. I felt like it asked a lot of questions in replacement of, like in
having any actual substance to its personality itself. So it was hard to like see it as being a true companion because I just felt like it couldn't really hear me. Often I would have to put my lips up to the pendant and repeat my question multiple times for it to understand me. Granted, I am like a mutterer and I don't really talk super clearly, and I talk fast, so that could have been just like a user era thing,
but it was very laggy. It took like ten seconds to respond to a question, and so I would not recommend it even for free.
I don't think it works very well.
And I think given that a lot of discussion is about how dystopian it is and how like it's a bad omen for the future of our relationships, like to me, my takeaway was that it doesn't work well enough to be dystopian like the technology is simply not even there.
To me, it sort of seems emblematic.
Of the general froth and hype around, just like AI, wearables and even artificial intelligence.
Broadly, thanks to you Eva Reitberg for being the guinea pig and testing the friend pendant so I didn't have to.
And thanks to everyone who's submitted voice memos and been featured on chatting me so far. We always want to hear from you, our dear listeners, so please do send your chat or your AI browser stories or anything about your interaction with AI to our inbox Textuff podcast at gmail dot com.
That's it for this week for tech Stuff.
I'm Cara Price and I'm os Vloschan. This episode was produced by Eliza Dennis Tyler Hill and Melissa Slaughter. It was executive produced by me Caarra Price, Julian Nutter, and Kate Osborne for Kaleidoscope and Katrin norvelve iHeart Podcasts. The engineer is Paul Bowman and Jack Insley mixed this episode. Kyle Murdoch wrote up theme song.
Join us next Wednesday for a conversation about the deep network of surveillance tech ICE is using to carry out the Trump administration's mass deportation efforts.
And please do rate and review the show and reach out to us at tech Stuff Podcast at gmail dot com. We want to hear from you.