This transcript was created using speech recognition software. While it has been reviewed by human transcribers, it may contain errors. Please review the episode audio before quoting from this transcript and email transcripts@nytimes.com with any questions.

My biggest news of the week is that I am in a war with a car wash. Really?

Yes. Last week — or I guess, two weeks ago now, I took my car into a car wash to get it washed, and it’s one of these places where they will not only wash the outside of your car, but also vacuum out the inside and clean the floor mats and get all the crusty food out —

A full service car wash.

We love a full service car wash. This one, unfortunately — so I dropped my car off. I go get a coffee. I come back half an hour later, and they have lost my key. And so I can’t drive my car away because the key is gone, and I have to call my wife who brings the spare.

And at first, they try to blame it on me. They’re like, well, was the key here when you dropped it off. I’m like, yes, because you had to drive it through the car wash and to the place where they, you know, vacuum it out, so clearly, they had just lost it. They looked in the vacuum cleaner, and couldn’t find it there, and so now I am out a key. And, Casey, I want you to guess how much it costs to replace a key on a Toyota SUV.

(LAUGHING) I know too much about this because of the following story. My friend got a new apartment, and he was like, I want you to have a spare key. And I said, of course, I would love to be able to do that for you, dear friend. And he gave me the key, and I lost it the very same night. I went home, and I reached into my pocket, and it was gone. And he’s never trusted me again.

This same friend got a car, and he wanted to, again, consider letting me have a spare key. And so he went to get a key for his car, which is a 20-year-old car, and the replacement key was $1,000. And so the key exists, but it has an air tag on it because he doesn’t even trust himself with it, and certainly, I wouldn’t either.

Yeah, so mine was not quite that expensive, but I did get quoted $575 for a single key.

Does this key have a large language model running inside it?

(LAUGHING) Yes. (SPEAKING NORMALLY) Yes, it is actually connected to a neural interface in my brain. No, it is just a key, but because it’s proprietary, and they have to program it, and it has to be specially matched to your Vehicle Identification Number, they are able to jack up the price.

We need to bring back hot wiring.

Yes.

You need to learn how to just be able to reach right into that steering wheel and —

See, I was looking for regulatory solutions, and I would like for the federal government to take this on. Maybe the FTC could take a look at some FTKeys.

You like that one?

No, absolutely not. We’re moving on.

[MUSIC PLAYING]

I’m Kevin Roose, a tech columnist at “The New York Times.”

I’m Casey Newton from Platformer.

And this is “Hard Fork.”

This week, OpenAI has a brand new AI model, and it won’t stop flirting. Then I go to Google IO and report back on how the company’s plans could end the web as we know it. And finally, pass the hat. It’s time once again for Hat GPT.

So, Casey, it has been a big week in AI news. So much happening. OpenAI made some announcements. Google made some announcements. We’re going to talk about all of it, but I would just start by saying today that this has been a big week for what you have called, and I have shamelessly stolen and used as my own term, AI vertigo.

Yes. AI vertigo, of course, is that sort of feeling of wooziness when you see something that makes you feel like you’ve sort of just been dragged five years into the future instantly, and you’re not exactly sure what we’re all going to do about it.

Yes, so I’ve had AI vertigo at least twice this week. We’ll talk about that. One of them more maybe optimistic, and one of them might be more pessimistic. But let’s just start with OpenAI because, on Monday, OpenAI announced their newest model, which is called GPT 4O. The O stands for Omni.

This is a new model that has native multimodal support. It can work with images and video and audio. It also appears to be better at a number of reasoning and coding tasks, but the part of the announcement that got all of the attention was the voice. This is a new voice mode for ChatGPT that is going to be rolling out in the coming weeks, and it is uncanny. I’ll just say it. It’s a lot. It’s a lot to take in.

Yeah, it is uncanny. I would say, at the top, that we have not used this. I have asked to use it and have not gotten it yet, and so everything that we’re going to talk about is a tech demo. And in the demos that we saw, or at least in the big event, they had the phone plugged into internet to ensure that they had a very fast connection.

So I just point those things out at the beginning because we just sort of learned, in our years as tech reporters, you never want to trust the demo 100 percent.

Totally. So OpenAI sort of framed this as being the real life Samantha from “Her.” “Her” is the 2013 Spike Jones movie, of course, in which a lonely man named Theodore falls for his lifelike AI assistant. The AI assistant is voiced by Scarlett Johansson. Joaquin Phoenix plays Theodore. Great movie.

And they basically said, yeah, we built that. Sam Altman himself even tweeted “Her” on Monday. Another OpenAI employee posted, you are all going to fall in love with it. So let’s just play a little clip of this voice because I think listeners should just. If they haven’t heard the demo, they should just hear what this thing sounds like.

Yes.

[AUDIO PLAYBACK] - Hey, how’s it going?

- Hey, Rocky. I’m doing great. How about you?

- I’m awesome. Listen, I got some huge news.

- Oh, do tell. I’m all ears.

- Well, in a few minutes, I’m going to be interviewing at OpenAI. Have you heard of them?

- OpenAI? Huh? Sounds vaguely familiar.

Kidding, of course. That’s incredible, Rocky. What kind of interview?

- Well, it’s for a software engineering role, but I just need to know. Do I look presentable? Professional?

- Well, Rocky, you definitely have the, I’ve been coding all night look down, which could actually work in your favor. Maybe just run a hand through your hair or lean into the mad genius vibe. Your enthusiasm is what’s really going to shine through.

- I don’t have a lot of time, so I’m just going to throw this on. What do you think?

Oh, Rocky, that’s quite a statement piece. I mean, you’ll definitely stand out, though maybe not in the way you’re hoping for an interview.

- I got it.

[PLAYBACK ENDS]

So that was an OpenAI employee, Rocky Smith, doing a demo of the new ChatGPT voice mode. And there at the end, he put on a bucket hat. And because GPT 4O can see through the camera on your phone, it was able to see the hat and tell him that it looked silly.

Yeah, and so look, we have played a fair number of clips of voices on this show that have been made with AI audio. Very little of what we’ve shown you so far has been generated in real time in this way.

Yeah, so just last week, on this show, you had a conversation with my AI friend Turing, in which you guys talked about lots of things, orphanages, fundraisers for my neighbors, and that experience, I would say, was a far cry from what we saw at the OpenAI demo. What do you — how do you think those things compare?

Well, I mean, last week’s conversation really could not have teed up OpenAI’s announcement better in the sense that the conversation with Turing last week was the state of the art last week and pales in comparison to what we just heard.

The conversation that we had last week was with something that could not process audio and video and text at the same time, and that meant that the model had a really difficult time understanding emotion, understanding sarcasm, responding appropriately to the way that I was interacting with it.

Telling the difference between your voice and my voice.

That’s right. And so then you fast forward to this demo that we see this week, and it’s like, here is the leap forward. Here is something that can understand tonality, that can respond with something that approximates a human emotion. And assuming all of this stuff works just as well when we get it into our hands, I think that’s very powerful.

Yeah, I mean, the biggest difference for me between the Turing demo last week and the OpenAI demo this week is the latency. Because when we were talking with Turing, there was sort of like a three to five second lag between when you would say something and finish talking and when —

Every single time.

— Turing would process and respond. And we edited those gaps down because we didn’t want to give listeners the experience of having to sit there and wait.

We didn’t want your experience to be as bad as ours was actually doing it.

Right. But we should say, the OpenAI ChatGPT voice assistant at least appears to be very fast, very low latency. You barely have to wait at all between when you stop speaking and when it starts. And in part, I think that’s because it is not doing what Turing did.

It is not transcribing the audio from you or me and then feeding the text into a model, getting a response back, and then resynthesizing the voice. It is natively accepting the audio input and working with it directly as audio without that middle step.

One thing I would say stands out is the way that they have tried to make it feel more human by, for example, making it seem sort of halting and uncertain, by varying the pace of the speech, by sort of having the voice talk at various parts of a register. There’s a moment where she’s kind of squealing, like oh, Rocky, sort of getting way up in the voice. So we are very far away from your sort of monotone himbo friend.

In defense of my monotone himbo friend, there was a little variation in Turing’s voice, but I would say that the ChatGPT voice assistant that we saw this week, it’s just much more dynamic. They even showed off a demo where it can sing, which is something that other AI voice assistants have not been able to do.

And I just was sort of amazed by how much variety there was, and with also the things that OpenAI did to make it feel more human. It will insert little filler words like um or let’s see or good question. It sort of feels more like you’re talking with a real person, and less like you’re getting answers from an AI model.

Well, I’m glad that now the AI will start getting emails about all the filler words it uses because, previously, only podcasters have had that experience.

It’s true.

But I think it’s important to say that everything you just described is true, and it does not make ChatGPT more useful as an assistant. Filler words aren’t making it more useful as an assistant. The dynamic range of its voice is not making it more useful. What it is doing, it is making it feel more emotional. It is feeling you more drawn to it. This is an engagement hack. This is designed to get you to use this product because there is now something that is tricking you into making you believe that it likes you.

I actually think it could be an engagement hack, but I do think it opens up new use cases as well because part of why we haven’t seen a lot of AI voice assistants doing things like customer service is that they’re sort of in the uncanny valley. When you’re talking with an AI assistant, you know you’re talking with a robot. It’s got a little delay on it, and it just is sort of an off putting experience.

Yeah, so assuming that this stuff works, Kevin, and that you get it into your hands soon, how do you imagine that you are going to be interacting with it? And does it change things for you?

I mean, the first thought was that this is what Siri should be. And in fact, there’s some reports out there that OpenAI and Apple are in talks to build OpenAI’s technology into the iPhone. There’s also been some reporting by my colleagues at “The Times” that Apple is doing a sort of overhaul of Siri to make it more like these generative AI assistants.

But that was sort of my first immediate thought. It was like, as soon as this becomes available, I am going to program the action button on my iPhone so that it goes immediately to this voice assistant instead of to Siri because this is the kind of assistant that I want on my phone.

Yeah, and what do you want to do with that kind of assistant?

I mean, you can imagine lots of queries that you might want to do in the course of a day. Can I — how long can something stay in the fridge?

Because one thing about Kevin is he’s always pushing it with those expiration dates.

I really am. I’ve become sort of a truther about expiration dates on things in the fridge. I think they’re designed by big food to just make you shuffle your inventory more frequently.

Remind me to order takeout the next time I come over for dinner at your place.

But that’s the kind of thing, or just any number of daily queries that you might want to ask to ChatGPT. I also think it’s going to be very useful for things like tutoring. There was an interesting demo included in OpenAI’s announcement where Sal Khan, who runs the Khan Academy, was essentially using this new voice assistant to help his son with a math problem.

And we should say, it is not just through the phone that this thing works. They also announced that ChatGPT has a native Mac app for desktop, and so you can do things like have it analyze what’s on the screen and then talk to you about it.

So yeah, I think all of that sounds pretty useful, but I think the most important thing about this story, Kevin, is the way that it goes beyond utility. This company has said, we want to make something that is emotional, that you feel emotions about. And I think this stands in really sharp contrast to the way that Google has been talking about its AI, its assistant.

It is very clearly a computer. It is not pretending to be a person. It does not have a persona. This is a clear effort by them to have you not think that you are talking to some kind of sentient being, and I think they think that that is really important because they have had cases in the past where — they had this one engineer who thought that he was talking to something sentient, and it created quite a stir when that happened a couple of years back. So they have backed all the way off of that.

OpenAI is now saying, well, what if we leaned all the way in, and what if we made something that was friendly, that laughs and that, frankly, flirts?

Yes.

In a way that made me very uncomfortable. So I’m curious what you make of this very emotional AI that they’re now just openly building?

I mean, my first question for OpenAI is, did you finish the movie “Her?” Because I did finish the movie, “Her.” Great movie, but it is not a utopian story about a man who falls for an AI assistant, and they live happily ever after. In fact, spoiler alert, but the movie’s like 11 years old now, so if you haven’t seen it yet, that’s kind of on you.

It ends with the AI assistant sort of breaking the man’s heart and revealing that she has hundreds of other companions, that he is not in any way special, leaving him to go off into the cosmos with the other AIs and leaving him dejected and alone.

It was the first poly sci-fi story that I’m aware of among the big movies.

The first of many.

Yeah.

So I just wonder, as these companies are building things that are modeled on these sort of sci-fi depictions of AI in the future, whether they have fully thought through all of the risks because people will get attached to this thing. You even saw it in the demo, and that was sort of the most striking thing to me about this series of demos on Monday by OpenAI was just the OpenAI employees themselves are talking to this thing as if it were their friend, as if it were a human.

They are saying things like, hey, ChatGPT, how’s it going, before they launch into questions. They’re laughing with it. One of them even wrote, I heart ChatGPT, on a little piece of paper and showed it to the app.

And you could say, oh, that’s just a demo, but it really does speak to the fact that even these very seasoned AI experts who understand how these things work, who are some of the people who are building ChatGPT, who know that it is not sentient, that it does not actually have feelings and emotions and the ability to form emotional bonds with humans, even they are tricked into sort of treating it like a human. And so if they are treating it like a human, I believe millions of other people will, too.

Well, I mean, I don’t know that they’re tricked, but I do think that this is how they want us to talk to the thing that they are building. And the reason that it’s striking to me is that it was less than a year ago that, when we were interviewing Sam Altman, and I said how do you feel about AI girlfriends and boyfriends, he was very dismissive of the idea. He said, we do not want to build that. That is for other people.

And while nothing that was showed off this week is really an AI girlfriend or boyfriend, it is absolutely flirting. When you listen to that clip we played of this engineer, Rocky, the way that the assistant is giggling and saying, oh, Rocky, and is sort of commenting on his appearance and trying to make him look handsome for his interview, I mean, this really does just feel like a generic straight guy fantasy of what a personal assistant is like.

And so I’m curious what changed inside that company that led them go in this direction. And I would have loved to ask them a question about that this week, but they did not take my questions.

Yeah. So let’s talk about a few of the other things that OpenAI showed off. They also showed off the coding abilities of the new GPT 4O. They showed off the translation abilities. There was sort of a cool demo where they had one employee speak in Italian, and ChatGPT translated it immediately into English, and speak in English, and then it would translate immediately back into Italian.

So that kind of thing is very cool. There was even a demo that I think we should listen to because it was sort of interesting and kind of wild, where two ChatGPT voice assistants were set up to talk to each other and one of them was using its phone camera to describe the room to the other. So let’s play that.

[AUDIO PLAYBACK]

- Hello there, new AI friend. I’m O, ready to explore the world through your eyes. What are we looking at today?

- Hi, O, we’re looking at a person wearing a black leather jacket and a light colored shirt. They’re in a room with a modern industrial feel with exposed concrete or plaster on the ceiling and some interesting lighting. There’s also a plant in the background adding a touch of green to the space. Anything specific you’d like to know or explore?

- Hey, there, sounds like quite the stylish scene. I’m already intrigued by the modern industrial vibe. Let’s start with the person. Can you tell me more about their style? Are they doing anything interesting, like reading, working, or interacting with the space?

- The person has a sleek and stylish look with their black leather jacket and light colored shirt. Right now, they seem engaged with us, looking directly at the camera. Their expression is attentive, and they seem ready to interact. The setting —

By the way, this conversation is very funny if you imagine that both of the AIs are assassins.

- — overall stylish feel. They might be getting ready for a conversation or a presentation given their direct engagement with the camera.

[PLAYBACK ENDS]

So that is GPT 4O, and I think there’s a chance that it produces a kind of similar reaction to the original ChatGPT back in November 2022. I think we’re a little more desensitized to AI than we were back then, but I do think that the ability to talk and receive responses from an AI voice assistant that sort of sounds like a human and responds in more or less real time is going to make a lot of people sit up straight.

I think that’s true, although I’ve never quite known where these voice based assistants are supposed to sit into my life just because it’s always been so much faster to use typing and text. Now, I also think that Alexa, Siri, the voice assistants that we’ve had so far, have just generally been pretty awful, and so this is kind of the question, is, well, what happens if you have something that is really fast and pretty good?

Even then, though, I can imagine using this while like walking around town, on the rare occasions when I’m driving a car. But I don’t know that I’m going to quickly get to a place where I’m just sort of sitting at my computer saying, hey, computer, look this up. But do you think you will?

I think I’ll use it. I mean, I’ll obviously test it because I want to spend time with it and see how the product evolves. A thing that caught my eye about this announcement, along with the product itself, is the fact that this new model, GPT 4O, is going to be free.

So unlike previous changes to their models, which have been sort of rolled out in stages starting with paid premium users, this new model is going to be made available to free users of ChatGPT, which to me says that not only are they really betting on this to bring them a new wave of users, but also that they have done something on the back end to make serving these models, to make the inference cheaper because, if they’re giving it away to free users, you have to imagine that they’ve figured out some way of making that a little less costly on their side.

Yeah, I mean, they’ve said that this model is just way more efficient. At the same time, I’m sure it is going to continue to be very expensive for them to serve this to the masses. This product has more than 100 million users a week, we think, and so that just is going to cost a lot of money.

But I think it is good news for people who have been using the free version of ChatGPT because, for so long, there’s been this real gulf, I think, in understanding between people who were using it on the free plan versus using it on the paid plan because the paid plan just tended to be so much better, that if you’d only used the free plan, your sense of how powerful this is, I think, would be really limited. So I’m curious to see what happens now that more people have access to the good stuff.

Yeah, but you have to imagine that, if OpenAI is releasing something like this now, a year from now, there will be many versions of an AI voice assistant like this. Some of them will be open source. Some of them will be able to talk to you about basically anything you want, and there will be very few, if any, safety filters on them.

So I just think that we are careening toward the future as depicted in the movie “Her,” and I don’t know. Something about that just makes me a little queasy.

Yeah, I mean, although it is important to say that, in the fictional world of “Her,” those assistants really do have sentience. They are acting on their own. They’re having independent relationships with other virtual assistants. It imagines a world, essentially, where what is often called artificial general intelligence has already been achieved.

We are a long way from that. At the end of the day, these are still predictive models. They are guessing, and yes, they are getting uncannily good at it. And they really do cast a spell, and I’m sure I will be taken in by these assistants just as much as anybody else. But at the end of the day, they are fictional, and they are not what is actually being represented as true in the movie “Her.”

Yes, correct. That is important to say. It is also important to say, we have not gotten our hands on this thing yet, and so I will be waiting for OpenAI to open this up so that I can put it through its paces myself. Although, honestly, I’ve spent a lot of time talking to AI’s recently. I’m kind of ready for some human conversations, so maybe I’ll leave that for you.

Really? I was going to invite ChatGPT to co-host the show with us.

We should try it.

It’s so friendly, and it’s just going to love us so much. Who wouldn’t want to have that around?

You go for that. I’ll take the week off.

All right. Sounds good.

One more thing on OpenAI. This was not part of their announcement on Monday, but has broken in the days since. We learned this week that Ilya Sutskever, the chief scientist of OpenAI, who was a central figure in the messy board drama that involved firing Sam Altman last year, is leaving the company. Also leaving OpenAI is Jan Leike, who is part of the leadership of the so-called Super Alignment Team, a major figure in the world of AI safety, and so he is resigning, he announced this week on social media.

And here’s why this is a really important story, Kevin. It was July of 2023 that OpenAI says that we’re going to create this thing called a Super Alignment Team, and super alignment to OpenAI was going to be the way that they ensure that, as these systems that they are building grow more powerful, they’re going to ensure that they always act in the interests of human beings. And of course, there’s a lot of controversy over whether we should be paying any attention to this at all. Maybe it’s all just a pipe dream. There are a lot of really smart people that think that this is something that absolutely needs attention from really smart folks. And so Jan and Ilya were the two people who were leading that effort at OpenAI. There was, I would say, a relatively few other prominent people there who cared about safety. Helen Toner, who was on the board, left. There was this other guy, Leopold Aschenbrenner, who worked on safety stuff, and he was fired recently.

So now, their Super Alignment Team has no leaders, and I’ll just say it, no known employees. So I would love to hear more about how they’re thinking about safety because my strong sense is that this is an area where they have pulled back investment. And frankly, they just look more and more like a regular tech company and less and less like a nonprofit research lab that they were set up to be.

Yeah, I agree with that, and I want to know more, obviously, about why Ilya and Jan are leaving the company. I want to know — I mean, I think, in some ways, it is just sort of the natural fallout of what happened last year with the board drama and the firing of Sam Altman, which is that he sort of came back in this triumphal return. His enemies were vanquished, and obviously, if you’re a person like Ilya, who had voted to fire him, your future may not have been very bright at that company.

Now, obviously, OpenAI is trying to put sort of a positive spin on Ilya leaving. They posted a photo of Ilya and Sam Altman and Greg Brockman and Mira Moratti and other company sort of leaders on what appears to have been his last day, making it seem like this was all sort of very cordial as a departure. But I think we both know that there has been a lot of tension inside this company between the faction that is sort of pushing for more growth and more commercialization and more capabilities, research, and more products, and the faction that is very concerned that all of this is heading too fast in a dangerous direction, and that we should pay more attention to safety.

So I think that debate is still very alive and well inside OpenAI, but I think it’s safe to say that, if you are a person who was worried about the safety posture of OpenAI last week, you should be even more worried about it today.

Yeah, and I would say, if you were a person at OpenAI worried about safety last week, you might not work there this week.

Right. It’s not a safe time to be involved in safety at OpenAI.

They need a safe space over there.

When we come back, I head to the developer conference of Bing’s biggest competitor.

You’re talking about Google?

That’s right. [MUSIC PLAYING]

All right, Casey, well, the other big news this week happened at Google IO, the company’s annual developer conference, which was held on Tuesday down in Mountain View. I couldn’t make it this year, but you went and attended, and tell me what it was like.

Well, once again, the heavy burden of doing the actual reporting on this podcast falls to me, but I was only too happy to do it, Kevin, so we’d have some fun things to talk about. But I knew you would be sad to miss it, so I went ahead, and I got you the official 2024 Google IO tote bag.

Oh, that’s very nice.

Yeah, now if you’re just listening to the podcast, you should know, Kevin just accepted the tote bag and flagrant violation of “The New York Times” ethics policy, and we do have that captured on video. But listen, Kevin, I can —

I think I can accept gifts as long as they’re not worth more than $25.

That’s definitely —

— the policy.

That definitely isn’t. It’s made out of publications that Google killed last year. So anyways, we had a great time.

Well, thank you for the gift. I will put it in my tote bag of tote bags.

Great. Well, listen, we had a good time down there. Now, I will say, I do want to tell this story, and this story makes me look annoying, but I just got to get it off my chest anyway.

It actually sucked getting into Google IO this year. I’ve never had a problem getting into Google IO before. I’ve been going for more than 10 years, and yet this time, there was something — now, maybe this has been true in previous years, but I did not notice it until this time. They had Live Nation managing this event.

Wow.

And I think that’s just because monopolies love monopolies, and so they want to make sure that they sort of help each other out. And so anyway, there’s this one entrance that the press has always been able to use, and so I went to use it this time around. And they were like, basically, scram, kid. Go wait in a line with everyone else. And I said, fine.

And I stand in 15 minutes in this other line with everyone else. And then finally, a man with a little pedal says, by the way, if you’re in the press line, you should go to that other entrance, which was the first place that I went.

Oh, thank god. I was worried you were going to have to wait in a line for 15 minutes with the hoi polloi.

I only got through half the line.

Thank god you got your VIP pass that lets you cut the line.

Listen to this. So then I get back to the press entrance. I say, hey, I’m the press. They just told me it was the press entrance. And the guy goes, no, you can’t use this entrance, and, Kevin, I had to raise my voice. I said, I’ve literally just been told to come here. And then finally, the guy throws his hands up, and he’s like, well, if you’re going to make a whole thing about it, then just use the entrance.

Wow.

So, yeah, so I got in there, but at that time —

You give this guy a podcast, he starts acting like a diva. All of a sudden, it’s wait in this line? Do you know who I am?

Listen, all I wanted to do was find out how this company is about to destroy my business, and the very least they could do was let me ...

Did you say, Google me?

I did not say, Google me.

I’m shocked. It’s very effective around there.

All right, so listen —

So set the scene.

It’s a developer conference. It’s at the Shoreline Amphitheater in Mountain View. It was a balmy day, sort of really California showing off its best side, and in the morning they have a big keynote where, for two hours, Google says here are all of the things that we have been working on that we’re planning to release in the next year that we can fit into a two hour presentation. And as you probably guessed, they had a lot to say.

Yeah, so let’s go through some of what they announced on Tuesday. They announced a new AI video generation tool called Veo, a new AI image generation tool called Imagine 3. They also announced another version of their Gemini flagship AI model called Gemini 1.5 Flash, which is optimized to be fast and cost efficient, and they announced a version of Gemini 1.5 Pro. Is it Gemini Pro 1.5 or Gemini 1.5 Pro?

That’s none of my business. There was so much word salad at this event, and I’m just going to see if any of it ever shows up in my life ever again. That’s my approach with everything you just said.

So they announced a larger context window that will allow developers to try two million tokens in their context window.

Now, that’s actually a big deal.

Why?

So if you’re not familiar with what a context window is, it’s basically how much of your stuff can you bring to the AI to have it look at. Why does this matter? Well, maybe you’re a graduate student, and you have a bunch of papers that are PDFs, and you want an AI to help you summarize them, to ask questions of them.

Well, now, all of a sudden, instead of maybe just uploading one PDF, with two million tokens, you’ll be able to upload thousands of pages potentially.

Entire books.

Yeah. So we should say that the two million token window, that is available only in preview, but if you pay Google 20 bucks a month for their little Gemini advanced thing, you now have up to a million tokens, and that is much bigger. So that’s, that’s important.

Yeah, so that’s some of their AI announcements, but I want to spend most of our time right now talking about something else that Google announced, which is that Google is now bringing generative AI answers directly into its core search engine. So starting this week, hundreds of millions of Google users in the US will start seeing a feature called AI Overviews. This is a feature that used to be called Search Generative Experience when Google was sort of testing it out.

Another huge win for the Google branding team — Search Generative Experience.

So this is a feature that, basically, when you go to Google, and you search for something, Google will generate an AI summary that will live in the search results page above the traditional search links. This feature has been rolling out gradually, but they said that, as of this week, hundreds of millions of users in the US will see it, and by the end of the year, it will reach over a billion users. So what do these AI overviews actually look like?

Well, there’s what they look like today, and there’s what’s coming. What do they look like today? It is a box on top of Search. It’s some bullet points, essentially a web page within a web page that summarizes the topic for whatever that you’ve been looking for.

But Google’s plans are much more ambitious. They showed off a ton of examples. For example, if you move to a city, you can just sort of say that to Google, and you’ll get an AI overview that says, here’s everything that you might be interested in now that you’ve moved to a new city. We’ll help you find a dog walker. We’ll help you find a dry cleaner.

Maybe you want to plan an anniversary in Dallas. It will say, well, here are some great spots for an anniversary dinner, and based on the time of year, we’re going to show you a place with a roof deck because it’s warm outside. And Google executives love to talk about travel. Can I just tell you my quick joke about every tech demo?

Yeah.

This is this is my impression of every tech demo. Ready? You know, I love to visit Antarctica for lunch with my wife, but there’s only one problem. Where am I going to get a helicopter? That’s every tech demo I’ve ever seen.

It’s so true. It’s so true. It’s like —

When I’m looking to furnish my vacation house in Tahoe, but the only place with the custom boar’s head statues is in Zanzibar, how can I arrange two day shipping?

It’s ridiculous.

Exactly. So they had a travel example, which was basically, yeah, I’m planning this trip, and with this AI tool, it’ll say, well, we know what your flight times are because we read it in your Gmail. And based on that, we’re going to have you do this dinner the first night that you arrive, and then we’ll plan a walking tour for the next day. And they’ll put together the whole itinerary for you, or they’ll plan a whole meal plan for you.

So this stuff is starting pretty small, and frankly, boring. But the vision here is this stuff is going to be doing planning for you. This thing is an AI assistant that lives within Google now that is doing research projects for you, and that, pretty soon, is probably going to be booking travel for you.

Yeah, and I knew that this had been announced at IO because my phone started blowing up with texts from other journalists, people who work in the media industry, that mostly said some variation of, we are so screwed. And I think we should just explain a little bit why the online media business is freaking out about this change because I don’t think it’s totally obvious unless you work in our industry.

Yeah, well, so much of the way that the internet is funded depends on people visiting individual web pages. Those web pages have ads on them, a lot of those ads served by Google, by the way. They also, as people visit those web pages, publications, publishers, businesses have a chance to get you to sign up for a newsletter, maybe subscribe to something.

So Google is this massive funnel that winds up being the economic engine of the entire web, and the way that it works is people Google things, and they see links, and they click on the links. And this has been the state of affairs for so long now that I think people take it for granted. Once you take an AI, and you start to just summarize those links, and essentially tell people you don’t have to visit websites anymore, all of a sudden, that thing starts to break down.

There was this phrase that they used a couple times at the keynote, Kevin. They said, let Google do the googling for you, and it struck me so hard because the implication there is that being on the web is a chore, and the Google of the future is not going to take you to the web. Google is going to give you everything you need within Google itself.

Yeah, that struck me, too, and they also talked about taking the legwork out of Search. And as they were saying that, I was thinking, that legwork has funded basically the entire digital media. I mean, I don’t want to overstate things. Google is not everything, but it is, by far, the biggest supplier of traffic to many digital publications.

So Google executives have obviously anticipated that publishers might freak out about this change, and they had some responses ready. They said, in our tests, we’ve found that users who saw these AI overviews tended to conduct more searches and visit a more diverse set of websites. They also said that the links that appear in these AI overviews, because there’s a little section at the bottom of the overview where you can go to click on things to learn more, they said that those links got more clicks than the traditional search links below them.

And Liz Reed, the vice president of Search at Google, said on Tuesday that the company would, quote, continue to focus on sending valuable traffic to publishers and creators. But I think it’s fair to say that publishers are skeptical.

Well, and she said we’re going to send valuable traffic. She didn’t say we’re going to send more traffic because, guess what, they’re not going to. And when analysts look at this, they’re predicting somewhere between 20 percent to 40 percent of Google search traffic is at stake here. And I think it’s fair to say that most publishers do not have a plan for what happens if they lose 40 percent of their traffic in a year.

Yeah, clearly, the risk here is that all of this traffic will just evaporate. I also read a good post on Search Engine Land, which is a good website that covers the search industry —

And one of my favorite theme parks.

[LAUGHING]: They were basically talking about how the problem for publishers here is not just that they might see their overall traffic decline, but that they can’t really do anything about it. With other chat bots, other AI experiences, publishers can, say, opt out. They can they can block the crawler for ChatGPT or Claude from accessing their site if they don’t want those products to be able to summarize what they find on their websites.

But with Google, because their technology also crawls for these search index, there’s no way, right now, to decouple those things. You can’t be a publisher and say, I don’t want my content to appear in these AI overview summaries. I only want to be listed on regular search results in Google. You have to kind of say yes or no to the whole thing.

Yeah.

But I think, overall, if you are a publisher that derives a big portion of your traffic from Google, this is a big deal for you. This is the big one. I would be pulling the fire alarm.

Yeah, it is absolutely time, but Kevin, at the same time, I have to say, in some ways, we had to know this was coming. I’ve been writing about Google for more than 10 years now, and you go back a decade, and they were talking about Google as the “Star Trek” computer. This is their vision.

If you’ve seen “Star Trek,” Captain Kirk or whoever will just say, computer, and is able to ask the question, and then they can fire the photon torpedoes or whatever. And that is a world where the computer was not saying, and actually, I got that fact from “The New York Times,” and here’s a link.

Here’s the Wirecutter’s favorite photon torpedoes.

The sci-fi vision of this has always been all of the inputs, all of the labor is abstracted away, and you just have this perfect assistant. So they’ve told us that this is what they were building.

I think it just seemed so fantastical for so long that publishers, and by the way, not just publishers, anybody else who depends on Google traffic, helping people discover their business, which is a lot of people, it was so easy for those folks to just dismiss that. But the point of what we’re saying today is, the moment is here. The “Star Trek” computer is coming into view, and people really do need to have a new plan.

Yeah. Is there anything that publishers can do at this point to keep their Google traffic from falling off a cliff, or to adapt to these new AI overviews?

I think the only thing that works, and it’s really hard is — but you have to build a direct connection with an audience or with a customer base if you’re a different kind of business. People have to think of you independently, and they have to — you have to have some way of maintaining a connection with them.

So, this is why email newsletters have become such a hot commodity in the publisher world, because it allows us to sidestep the need for you to look up a piece of information in order to find it. Instead, someone will just kind of send it to you. So I think podcasts are another thing, frankly, because we don’t rely on Google Search really for people to find the podcast. It just gets delivered to them in a feed once they become subscribers.

So these are the kinds of things that I think more publishers need to be thinking about, but even then, Kevin, the scale of the businesses is going to decline because, in its heyday, Google really would send millions and millions of visits to websites. And in a world where that’s about to decline, the size of the audience that you can build is smaller, which means that the staff that you can afford to pay gets much smaller.

So I just think that we are going to be living in the fallout of this for a really long time, and I got to say, man, I was emotional yesterday in a way that I was not proud of. And I mean, not that I was crying at Google IO, but I just felt really out of sorts. Within the past 48 hours of recording this, I have one friend who got laid off from their media job, and I had two other friends who are currently employed in media jobs who told me that they’re looking for other jobs right now.

And in every case, the answer is the same. The money just isn’t there the way that they all thought it would be. And so that’s just my story. Past 48 hours, three people looking to leave. We already could name the publications that have shut down in the past year. There are more that are going to shut down in this year. And so I understand maybe this just sounds like two reporters navel gazing, and maybe we’re spending too much time on this. But what I’m telling you is, the thing that is happening to the media businesses going to happen to the other businesses. It turns out that, in a world where everything is online, how people find stuff, how they discover new businesses, that matters a lot. And when all of that is about to be hidden away behind some black box algorithm that summarizes what it thinks is the best thing based on whatever and who knows? I truly do not think people are prepared for this world.

Yeah, and I think Google obviously has reasons for wanting to evolve its search engine in this way. I also think it’s a very risky move for them for a few reasons. One is, as we know, these AI overviews can get things wrong. They can be untrustworthy. They can be erratic.

I saw there was a screenshot going around the other day on social media where someone asked Google what are some food names that end with um, and Google’s experimental AI overview said, here are some fruit names that end with um, applum, bananum, strawberrum, tomatum, and coconut. And that’s a funny example, but I think there are going to be a lot of examples of these AI overviews, at least in their early days, just getting things wrong. I do think that will start to erode trust in Google over time.

I mean, I think that is possible, but I would not count on it because there are mistakes on all the web pages that people are visiting, too, and I’m not sure how much it just matters in the end.

Yeah, I think there’s also a business risk here, too. I mean, Google, it does make the vast majority of its money from showing ads right there on the search results page. And it remains to be seen whether they can sort of monetize these AI overviews as effectively as their traditional search results.

By the way, they also make a lot of money showing ads on third party websites. Their Google ad network is a big part of their business, 10s of billions of dollars a year. If all of those web pages suddenly have to close up because they’re not getting any traffic from Google anymore, then that part of Google’s ad business has to shrink as well.

So that is totally true, but keep in mind, Kevin, it is Google that has its fingers on the knobs. Google is the one in control here. It gets to decide how fast or slow it moves in a case like this. If it does something that dramatically changes something in a way it doesn’t like, it can always edge that back.

The important thing is, it is the one in the driver’s seat now for what the future of the web looks like. And what they are telling us is Google is just going to keep more and more of the median internet experience to itself within its own walled garden.

Yeah. Do you find any reasons for optimism in what you heard this week at IO?

Well, I was so desperate for optimism that I texted a tech executive, who I have some of these backchannel conversations with, and this is an executive who I would think — I think it’s fair to say generally thinks that I overrotate on being concerned and a worrier because you talk to people in tech, they’re mostly optimistic about everything. They think everything is going to be fine for everyone. Of course, they also live in mansions. But anyway, this person said to me that, essentially, people still want novel content and experiences on the web. They want to have shared experiences with their friends. They want real relationships with publications, with writers.

And so if you are the kind of media business, or you’re the kind of journalist that does have an authentic audience, that you are doing a really good job for, that you’re doing something novel, you’re doing something really smart, you might wind up being in a better position coming out of all of this.

Because as much as I love the media, it is also true that there’s a lot of garbage in our business, and there are a lot of unscrupulous publishers that are publishing lists of, quote, the best vacuum that haven’t tested a single vacuum in their entire life, but they figure there’s some upside in getting some of that affiliate revenue. So if you want an optimistic case, it is that Google will sort of cause all of those bad actors to wash out, and it will leave a few brave, proud publishers that are doing honest work standing to reap more of the benefits.

Yeah, I think my reason for optimism here is that I actually do think that it is in Google’s long term self interest for there to be a vibrant and healthy internet. I think that if Google starts sort of just aggregating and summarizing the internet and spoon feeding it to people through these AI overviews, I think that’ll work fine for a while. And then I think they will start to see one website close and 10 websites close and 100 websites close.

And within a couple of years, you’re looking at just a very diminished internet, and Google in that world is not going to have — what is its AI going to crawl and summarize if there are no websites left. So I just think that we will end up in a world where all of the valuable information on the internet is hidden behind paywalls and subscription publications, maybe newsletters and podcasts, and you will just see an impoverished Google that is out there scraping as hard as it can, trying to summarize what it finds, and not coming up with much.

Yeah, well, I do think that is a possibility. I also think Google will just get increasingly — I was having this discussion with friends last night, of essentially this exact thing. Where is Google going to find the information anymore? And you might think of one example.

Well, let’s say you go to Paris, and you want to know what’s the best bakery? Well, today, I would rely on a travel writer who has been there, and been there recently because the best bakery in 2024 might not be the best bakery in 2020.

And we started talking about it’s well, Google had actually just kind of looked at the foot traffic in all of the bakeries in Paris and say this one is the most popular, and that is not actually going to require there to be a healthy web feeding at that information. These companies collect so much data about us, and they are going to come up with so many more novel ways to use it that I really do wonder if maybe we aren’t flattering ourselves when we tell ourselves that they need us.

I hope you’re wrong.

I hope I’m wrong. I’ve never hoped for anything more.

But I do think this is sort of the flip side of AI vertigo, this feeling of, wow, the future is coming, is I don’t know that our institutions, including our media institutions, understand the gravity of what happened this week at Google, which is that they did essentially declare that we are moving into a very different era of the internet.

We have talked, on this show, for more than a year now about automation, AI coming for jobs. It has seemed like something on a kind of medium to distant horizon. But I do think that, at IO this week, we saw the beginning of an arrival of something like that. And again, it is starting in the media, but it is not going to stop there.

Yeah. Can I just say one more thing before we close this segment? I got a little emotional watching this announcement, too, for maybe some similar reasons as you. But my emotion was like, I just feel like I’m being gaslit here. Publishers, people who work in online media, have known that Google has plans to shove generative AI into search results for years.

We talked to the CEO of Perplexity a few months ago who basically told us, yes, if we do start generating these AI summaries of search results, people will click on less news, and I actually admired that he was honest about that. Google is not being honest about this. They are telling people, we are still committed to sending traffic to publishers. People are not going to stop clicking on links just because they have these AI summaries above their search results.

And I really just wish that someone at Google would come out and say, yes, your traffic is going to fall off a cliff, but here’s why we think it’s important anyway. But instead, they are trying to signal to users that this is going to be a good and useful thing. They are trying to make publishers feel less scared. And frankly, it just felt like being — it felt like attending a funeral disguised as a wedding.

Yeah, and this actually is the reason that we need media to exist in this world, is because we will try to tell you the truth about something. We will try to go beyond our own narrow self-interest and tell you what’s going on.

It drives me insane. Just tell me we’re going to basically destroy the foundations of the open internet.

I felt exactly the same way. All right, Kevin. Well, I’m afraid that’s all my context window can hold for this conversation, so we’re just going to have to purge that, and we will have to return to the subject another time.

Yes, I think we will have plenty more opportunities to revisit this subject.

And you can find us podcasting under an old bridge on the abandoned railroad tracks.

What’s your post media plan for when all the Google traffic — are you going to become a farmer if the digital media dies?

I’m getting really into TV and VCR repair. I think there’s a bright future in that.

[MUSIC PLAYING]

When we come back, we’ll play around with Hat GPT.

Well, Kevin, from time to time on this show, we like to take a quick run through the news in a segment that we call Hat GPT.

Yes, let’s play it.

[MUSIC PLAYING]

Hat GPT is, of course, a segment on our show where we take headlines from the week, and we pull them out of a hat, and we riff on them a bit until one of us gets bored with what the other person is saying, at which point we say stop generating, and then we move on to the next headline.

So, Casey, should we use the baseball hat or the bucket hat for this weeks?

I think we should use the bucket hat in honor of Rocky, the OpenAI employee, who put on a bucket hat this week when demoing the new “Her” assistant.

I like it. Grab it.

I do want to — do you want to go first?

Why don’t you go first?

OK. Will you mix them up for me? I want to introduce some randomness here.

We have to mix up all of the headlines in the hat.

Be sure to just jostle and hit the microphone as many times as possible.

Yeah, we’re jostling — we’re hitting that microphone.

Yeah, just —

This microphone is in trouble.

Yeah.

It’s broken now, actually. All right.

First story, FTX customers poised to recover all funds lost in collapse. This comes from my colleague David Jaffe Bellini at “The New York Times.” Customers of the failed cryptocurrency exchange FTX are poised to recover all of the money they lost when the firm collapsed in 2022 and receive interest on top of it, the company’s bankruptcy lawyers said last week.

Under a plan filed in federal bankruptcy court, virtually all of FTX’s creditors will receive cash payments equivalent to 118 percent of the assets they had stored on FTX. A judge still has to approve the plan, and it may still take months for the money to reach customers. This is an amazing story.

That’s true. Now, others have pointed out that, if you had simply taken the money you had in FTX when it all shut down and just used it to buy Bitcoin, you would actually be in a way better position than you are today. So it is not right to say that everybody sort of came out smelling like a rose here. But based on what you’ve said, Kevin, I do have four words that I would like to say to the people of the United states, and they are these, free Sam Bankman-Fried. He did nothing wrong.

No, no, no, that is not the moral here. So Sam Bankman-Fried has been sentenced. He is currently doing a 25 year prison sentence for his role in this collapse —

His alleged role.

It’s not alleged if you’ve been convicted and sentenced, and you’re in prison. We can just say it. He did a fraud.

But this is an amazing result, in part because while Sam Bankman-Fried does appear to have been a giant fraudster, he did actually have a good nose for investments. So one of the things that he put money into, Solana, which is a crypto token.

Part of the reason that they’re able to return this money to creditors is because Solana has been booming. Bitcoin has also been booming, and some of the other investments that Sam Bankman-Fried made, including a stake in Anthropic, the AI company, have become much more valuable since the firm’s collapse, which is just an amazing testament to the fact that you can be a giant fraudster and still be pretty good at investing.

Yeah, when this guy gets out of prison, I think he’s going to make a great partner at Andreesen Horowitz. All right, let’s stop generating.

All right, your turn.

And I’ll do one here. Bumble’s founder says you’re dating AI concierge will soon date hundreds of other people’s concierges for you. This is from Fortune at the Bloomberg tech summit in San Francisco last week. Whitney Wolfe-Herd, the founder and former CEO of Bumble, predicted that singles would one day deploy AI dating concierges to help them find love.

Wolfe-Herd told the crowd, there’s a world where your dating concierge could go and date for you with other dating concierges, and then you don’t have to talk to 600 people. So, Kevin, what do you make of this form of theoretical future dating?

So she got a lot of backlash to this comment. I was at the Bloomberg tech summit where this happened, and immediately when it went on to the internet, people started saying like, this is dystopian. I want to defend this idea because I think we are — I’m not on dating apps, but my impression is that most people who go on these dating apps are already basically glorified algorithms.

They are using one of three preset lines that they’ve come up with. They are basically trying to quickly assess compatibility, but they’re not having real deep, authentic conversations, at least not right away. And if AI could save you some time by going out and dating people on your behalf and saying, this person’s a loser, this person’s mean, I think this could save people a lot of time. What do you think?

I do not think it would save people a lot of time because here is the thing. I’m also not on dating apps anymore, hashtag #SoftLaunch. But what I remember from when I was was that, oftentimes, you would say to somebody hey, how’s your week going, and they would just respond with, hey. And then you would think, this person isn’t super engaged, I’m going to move on.

A world in which the person who responded, hey, is using a bot to do responses on its behalf, is doing everyone a disservice because if this is a person who can’t even be bothered to complete a sentence when I say hello to them, the odds are that I’m going to enjoy my time with him is just very low.

So is there some world where some sort of something is helpful in enhancing the online dating experience? I’m very open to that. But if it is essentially just AIs tricking each other into thinking that the other person is a really good writer and has a huge personality, then they’re going to be wasting even more time than people are wasting on these apps already.

Yeah, I do think it opens up some interesting possibilities, but I can see how people would find it dystopian. My main thing is, I just hope that they — what am I saying?

What are you saying, Kevin?

What am I saying?

I’ve always wanted to ask you this. What are you saying?

Yeah, in conclusion, I’m very glad I’m not single. All right, stop generating.

[RUSTLING SOUNDS]

Sonos says its controversial app redesign took courage. This is from “the Verge.” Sonos, the connected speaker company, released a major update to its mobile app earlier this month.

To quote “the Verge,” in the days since, customers have complained about missing features like sleep timers, broken local music library management, and no longer having the ability to edit playlists or the upcoming song queue. Customers were very angry about this, and in response, Sonos’ chief product officer told “the Verge,” quote, it takes courage to rebuild a brand’s core product from the ground up, and to do so knowing it may require taking a few steps back to ultimately leap into the future. Casey, what do you make of this?

I’m not sure that I would say that Sonos executives’ move took courage here. I would say it seems more likely that they took mushrooms or some other sort of psychedelic substance that sort of melted their defenses until all they could do was give us the app that they did. Look, I have been in a daily war against my Sonos system for years now. When it works, there’s nothing better. The problem is it doesn’t work a lot of the time.

And so when I got this new app, I thought maybe they have finally solved all of my issues. And I swear to the heavens, Kevin, the volume slider in this app, which let’s just say is one of the core things I want to do to my Sonos system a lot of the time is adjust the volume, it is not persistent. It only appears when Sonos sort of knows that something is — anyway, the point of the story is the number of things that this app could do could fill a segment much larger than ChatGPT.

I’m confused because it seems like the job of the Sonos speaker should be fairly simple, which is play the music that I want when I connect to it.

You’re so right, bestie.

I don’t own a Sonos speaker, so you tell me, is that your experience?

No, my experience is I say Sonos, please connect to Spotify, which is what I play music from. And Sonos says, I have no idea who you’re talking about. I’ve never seen this man before, and I want you to leave my house. And I say, this is the entire job that I’ve given you. So it’s a real problem, and I wish Sonos continued courage as they try to build their first functional app.

All right, stop generating.

All right.

[BUMPING THE MICROPHONE]

Oh, this is interesting, Kevin. Inappropriate behavior shuts down the Dublin to New York City Portal. Less than a week after two public sculptures featuring a live stream between Dublin, Ireland, and New York City debuted, quote, inappropriate behavior in real time interactions between people in the two cities has prompted a temporary shutdown.

The Portals, as the sculptures are called, are the brainchild of a Lithuanian artist named Benedictus Gillis, and they were shut down Monday night after video spread on social media of visitors misbehaving in front of them, including an OnlyFans model in New York, flashing the Portal and people in Dublin holding up swastikas.

So, Kevin, what are the odds, if you just set up two giant cameras in Dublin and New York, that people would troll them? What are the odds?

Close to 100 percent, I would say. So I was bummed out about this because I did actually think the Portals were a cool idea. This is basically a giant sort of screen that was placed in kind of a circular enclosure that had a live streaming feed where you could basically go up to this thing in New York City and see people who are staring into the Portal in Dublin. And you could kind of have this wormhole between the two cities.

And we could recognize our shared humanity.

Exactly, but as it turns out, it was more useful for flashing and holding up swastikas. This is why we can’t have nice things.

Well, Kevin, I’m Irish, and I have to wonder if there was just sort of something about our mischievous nature that led the New Yorkers to misbehave.

I do, also, just like the name the Portals. It’s sort of a genre with the Sphere in Las Vegas. I just think we need more things of that nature, things that are sort of the titles of Michael Crichton novels made into reality.

But just sort of vaguely ominous.

Yes.

Yeah. All right. Stop generating.

This one’s for you. After 28 years, someone opened an unopenable door in Super Mario 64. This comes from “The Verge.” On April 22. User alexpalix1 posted a video on Discord showing how he got through an unopenable knobless door, which everyone previously thought was impossible. To do it, he used a workaround involving getting a mother penguin to push Mario into the door while also doing a turnaround move. It turns out, if you use this technique, you can open the door, but it doesn’t actually save you any time in playing the game.

Well, listen, I hate to tell you this, Kevin, but I think alexpalix has made a terrible mistake. I think some doors are closed for a reason, and I think an ancient evil has been awakened. And if hell is unleashed in this country over the next weeks and months, we will truly only have Alexpalix to blame.

Yeah.

I mean, I truly do love the people that never stop playing video games, like the speedrun community for the Mario games or for Tetris. I mean, these people, the lengths that they go to, to shave two seconds off their time, to open the unopenable door, is truly inspirational.

I also just hope that we have a national security plan that involves elevating people like alexpalix into sort of code breakers working for the Department of Defense. We could put these skills to real use.

I also want to say, for everyone complaining that the younger generation has no attention span, this person, the attention span on him, I’m super jealous.

It’s true. All right. Stop generating. All right. All right, Casey, last one.

Last one.

Oh, and this is a good one. Man fools Waymo self-driving cars with Stop sign t-shirt. This is from “Carscoops,” which is where I get all my scoops about cars, and Arizona content creator Jason B Carr, this cannot be real, made a t-shirt with a — (LAUGHING) His name is Jason Carr.

His name is Jason B Carr!

Jason B Carr is like the Johnny B Goode of the automotive vehicle world.

Continue.

An Arizona content creator, Jason B Carr, made a t-shirt with a Stop sign to see what Waymo’s autonomous test vehicles will do. In a series of videos posted to cars Instagram, he tested whether Waymo’s self-driving vehicles actually stopped when they saw him wearing the shirt while standing on the sidewalk. He said he believes that the autonomous vehicle may be confusing him with a construction worker holding a stop sign. What do you think, Kevin?

I think we are entering a bold new era of autonomous car hijinks. I think that people are already starting to find so many creative and nefarious ways of messing with these things, and I think that, if I were Waymo, I’d be very annoyed. What do you think?

Yeah, I mean, we see this already in San Francisco. I mean, not as much anymore, but when the AVs just first started rolling around in the streets, people would just walk in front of them to see what they would do. I mean, the confidence that people had in these AVs was staggering.

But this was different because Jason Carr apparently figured out —

Jason B Carr.

Jason B Carr apparently figured out that you don’t even need to walk in front of it. If you’re just wearing a shirt with a Stop sign big enough on it, it will just stop even, if you’re on the sidewalk.

Jason B Carr woke up and once said, today, I be Stop sign.

[LAUGHING]

All right, Casey, that is Hat GPT.

That’s how we play Hat GPT. It’s time to close up the old hat. Hats off to you, Kevin.

[MUSIC PLAYING]

“Hard Fork” is produced by Rachel Cohn and Whitney Jones. We’re edited by Jen Poyant. We’re fact checked by Caitlin Love. Today’s show was engineered by Isaac Jones. Original music by Elisheba Ittoop, Rowan Niemisto, and Dan Powell. Our audience editor is Nell Gallogly. Video production by Ryan Manning and Dylan Bergeson.

Go check us out on YouTube at youtube.com/hardfork. Special thanks to Paula Schuman, Pui-Wing Tam, Kate LoPresti, and Jeffrey Miranda. You can email us at hardfork@nytimes.com with a picture of whatever you did in front of that portal.

Please don’t.

Knock it off.