Gary Marcus (2:53)

And thanks for having me.

Leo Laporte (2:54)

And you are. And we should, you know, I guess an AI, is it fair to say? Contrarian, you could say that I love.

Gary Marcus (3:02)

AI, but I don't like the way it's happening now. And if that makes me a contrarian, then you can call me a contrarian.

Jeff Jarvis (3:08)

I'm so happy you're on, Gary.

Paris Martineau (3:11)

Some welcome balance to the podcast.

Jeff Jarvis (3:14)

Enough of the We've had multiple episodes.

Paris Martineau (3:17)

Of Leo thanking guests, being like, your products are making the world a better place. Everyone go out and buy it. So we need. We need a. We need a thinker.

Leo Laporte (3:25)

One. We did one like that. Okay. Just one.

Paris Martineau (3:28)

Oh, it felt a little bit longer.

Leo Laporte (3:30)

Than one, but we do have AI. You know, last week I thought Stephen Wilfrim was very good and sensible about AI. Next week, Ray Kurzweil, who created the coined the term intelligent machines. He's probably a little more bullish on AI than you are.

Gary Marcus (3:45)

I offered to debate him and he said when we talked to Ted he would do it. And then I got the venue lined up and he disappeared on me. So tell him I'd still love to do that.

Leo Laporte (3:54)

I would.

Jeff Jarvis (3:54)

Also, you've also offered a debate Elon.

Gary Marcus (3:57)

He never responded.

Jeff Jarvis (3:59)

Who else?

Leo Laporte (4:00)

You should offer to wrestle Elon or get in the. Get in the octagon.

Paris Martineau (4:04)

Who would be your top person to debate?

Gary Marcus (4:08)

Guess it depends on, you know, what one's trying to accomplish with such a debate. One of the reasons I've offered to debate a lot of these people is to try to hold them accountable to the things that they say in public and that they don't really want to defend against intellectual discourse. So that includes the exaggerations of Elon and the exaggerations of Sam and maybe Ray, although I don't think he's essential to that discourse anymore. But, you know, a lot of my offer to debate has been to try to get people to stand by the claims that they make.

Leo Laporte (4:41)

There's a lot of hype. I mean, there's no question.

Paris Martineau (4:44)

Are there any particular people or businesses that I guess off this topic, that you think are the biggest hypes to yours or need to be held accountable the most?

Leo Laporte (4:54)

In this moment, he named two of them.

Gary Marcus (4:57)

It's a crowded list, but OpenAI has historically been at the top of that list. I think that they've weaponized hype the most of any of these companies. They've hyped their mission as being for the benefit of humanity, which they haven't really done. They've hyped their stuff as being about AGI, but we can all see the GPT 4.5 isn't really that. I think I would put them at the top of the list, but other people have learned that hype is the way to drive up stock valuation. So I think Dario Modi. Modi has learned that, of course, Elon has done that for a long time. You know, it's become standard practice because the media doesn't in general hold people accountable. They just look at the next promise and the next promise and the older promises when they're not met. Nobody really holds anybody accountable.

Leo Laporte (5:46)

We should mention that you have founded machine learning startups. You sold your first to Uber. So you have worked in the field quite famously. You signed that letter in 2023 that said, let's stop for six months. Looking back, obviously we didn't. Elon signed that letter as well. Looking back, would you still like us to pause?

Gary Marcus (6:10)

Well, I mean, it's interesting because that letter was about pausing the development of GPT5. And it turns out that. That how long is it now, 18 months later or something.

Leo Laporte (6:19)

You didn't have to write that letter.

Gary Marcus (6:20)

We didn't have to write that letter because they couldn't figure out how to make GPT5 anyway. The reason that we. I mean, I didn't write the letter, but the reason I signed it and helped publicize it, even though I didn't think it was a perfect letter, was I thought we needed to call attention to how fast things were moving and how little we understood about how to make AI safe and reliable and so forth. And we still haven't figured out how to make AI safe and reliable for a while. I think the letter had a good, positive consequence. It got all the governments to start thinking about what we should do about AI. And then there was this Paris AI summit and change in regime in Washington, and I think everything fell apart. So for a little while, it had a salutary effect. I think the most depressing part is that Elon signed that letter and immediately started building xai, which was trying to do basically the same thing as GPT5 was supposed to do. He also failed to get there so far.

Leo Laporte (7:13)

Yeah. After Elon signed it, it felt like all the attention was, oh, you see, Elon wants to pause so he can catch up.

Gary Marcus (7:21)

Which turned out to be true. Which, you know, kind of undermined the movement because they used to call it.

Leo Laporte (7:26)

In the 60s, the letter called it an existential threat. Do you still believe that?

Gary Marcus (7:32)

AGI, I never loved that phrase, to be honest. And I can't remember the exact wording that the letter had around that. It was softer on that than some of the people who wrote it typically are. And that made me a little bit more inclined to write about in my substack I actually wrote a bunch about the letter at the time. I don't think that AI is going to annihilate us all or I think that's at least pretty unlikely. But I worry a lot about what bad actors are doing both with current AI, which is not very sophisticated, and what they might do with future AI as it gets more sophisticated. And I think the so called alignment problem, figuring out how to get machines to do the things that we want them to do is entirely unsolved. We can't even do things like say, hey, don't make shit up. Machines make stuff up anyway. It's actually in the system prompt for one of these. Apple systems don't make stuff up and it makes stuff up anyway. So we don't have very good control of large language models. They just kind of do what they do and you throw more data and you hope for the best. And that's really not a good way to do engineering.

Leo Laporte (8:32)

You've talked about the pareto principle, that 80% is easy. It's the last 20% that's hard. And we're really actually seeing that right.

Gary Marcus (8:39)

Now with AI, we totally seeing that. Like you can make a demo of anything if you have enough data. That's kind of the lesson the last couple years. But to make it really good is very hard. We saw that movie before with Driverless Cars. We have demos, we have demos in San Francisco, we have demos in Phoenix. But if you live in Buffalo, this stuff is of no use to you, right? So it's very easy to make a demo of some AI thing by having a lot of examples. The 80, 20 is you get examples for 80% of what you want to do. And the other 20% you don't really have exactly in your database and the systems don't exactly work. And that's been a serious, serious problem. Like I. You may have seen me use the phrase the other day in a piece that I wrote about Kevin Roos had a New York Times thing about how we're not going to be needing, you know, how amateurs are going to be able to code using these tools without knowing anything about coding. And the way I used it there is, I said, look, you can get 80% of any system you want. You kind of get a demo of it. But actually getting it to work reliably is very hard to get that last 20%.

Jeff Jarvis (9:43)

Gary, I've got a weird question for you. What's more dangerous, the reality of AI, where it stands today or the hype around it? You have done a lot Trying to puncture the definitionless phrases like AGI and super intelligence and all that. And that seems to lead to a lot of the danger, it strikes me, rather than the machines where they stand. You love AI. AI can do some neat things, but it's being presented in such a way that it's overblown. No.

Gary Marcus (10:15)

Yeah. I mean, I think there's real danger on both sides. I'm not sure how I come out on the letter. Let me just think it through. So the. The danger of current AI are things like bias, which are very serious, especially when you have something like Elon trying to use DOGE to evaluate who should keep jobs. And we know these systems are biased against white males, which is actually what they want.

Leo Laporte (10:36)

Bias towards white males.

Gary Marcus (10:38)

Sorry, towards white males.

Leo Laporte (10:39)

Yes, exactly.

Gary Marcus (10:40)

They're biased towards white males.

Leo Laporte (10:41)

And they wouldn't be using it if it were biased against white.

Gary Marcus (10:44)

Sorry, important speech error there. So, you know, he's probably comfortable with a bias towards white males. I'm not, obviously. So you have problems like that. You have problems where these things are used for cybercrime. And we may see some massive cybercrime hit this year. And if a whole bunch of infrastructure goes down because of cybercrime, they were going to say those consequences were pretty serious. So there's some unknowables, there's misinformation. Misinformation. People want to say it didn't affect the last election, but I don't really think that's true. I think that misinformation was a subtext to the election. It may get worse. The tools for making deep fakes keep getting better, et cetera. So you have all those kinds of risks. Another risk, I think, is that we screw up society by spending so much on the large language models, ripping up the environment and so forth, then there's a kind of opportunity cost that I worry about, which comes from the hype, which is you have these large language models and we're put, you know, already not society, but big businesses have put in half a trillion dollars on them and want to put in more. And probably we should be looking at other approaches to AI. So, like, something that not everybody knows about me is I actually want AI to work. I think the caricature of me is, oh, Gary hates AI, but that's not true. I'm actually constantly writing about how could we do AI better, such that we could trust it, so that it could be reliable, so that it could help more in medicine and so forth. And if we just keep dumping all of our Eggs in the LLM basket, large language model basket, then we're missing some opportunity to make better AI. So I don't know if there's an easy answer to your question, but I think it's a good question. A similar question is, is AI on balance so far been a net positive to society or a net negative to society? So there are positives, like you can use these tools for brainstorming, coders write a little bit faster and then there are negatives, like all the things that I just laid out. And it's not totally clear how that balance works and it's not totally clear where that balance will be in five years. I would say that when I first started having debates about these, people would be like, it's going to 10x, everybody's productivity and blah, blah, blah. And you look at the GDP and it's hardly moved at all. I mean, even Satya acknowledged this a week or two ago. There's been no real change in the gdp. So. So the notion that it was going to revolutionize the world certainly has not transpired yet. And the notion that like a lot of deep fake porn was going to make a lot of trouble for a lot of teenage girls has transpired. These are all moving targets and so forth. But I would say the productivity gains have actually been relatively modest. It's still very much a gamble on the future and there are some real risks. And then there are the risks of like, could some terrorist use this stuff to make bioweapons? The answer seems to be probably yes. There are rate limiting steps and so forth. It's complicated. But you balance all this out, it's really not clear. It's not a clear win, it's not an absolutely clear loss. When you add in the environmental impact, you start to worry. Then you can say, well, maybe deep seq will make it more efficient. It's all still in play. There's no clear benefit and there's no absolutely clear negative. Sorry, let me say that slightly more clearly. There are some clear benefits, there's some clear cost. It's not yet clear what the net, how it all nets out.

Leo Laporte (14:06)

I would submit though that you could say that about many technologies. You could have said that about the Internet, you could have said that about social media, you could have said about the atomic bomb, print. That's kind of the nature of new technologies, isn't it?

Gary Marcus (14:18)

It is. And it's why we have to be careful about how we use those technologies, how we distribute them, what we do with them. So, you know, atomic weapons It's a still a very complicated thing and our view about that could change. You know one it was an old T shirt I think said one nuclear bomb can ruin your whole day. Like we don't, you know, I used to wear that T shirt, right.

Leo Laporte (14:39)

And I had the poster that said war is not good for our children and other living things as well.

Gary Marcus (14:43)

Yeah, that was another great one. And so like I don't know the final answer, like when history is, you know, written well, that's the problem, right? Yeah. And social media, I'm willing to go out on a limb and say it sucks. It really wasn't a great thing. You know, I'm sorry that I'm addicted to it. And you know, I think it's.

Leo Laporte (15:00)

But we're a little farther down the road with it. So it's easy to say that in hindsight you can look that. But we're in the early days of.

Gary Marcus (15:06)

AI when I was testifying in the Senate and we were talking about Section 230. This is about what almost two years ago, you know, everybody in the room said hey, we really up with social media and everybody means senators. A bunch of senators said we we up with social media, we should do better here and we should get rid of section 230. And of course we didn't get rid of section 230 and they said we should do something about AI and they didn't do anything about AI. And so like we all know that, you know, section 230 empowered social media too much and sponsored mis and you know, made it attractive to the companies to spread misinformation. That was bad, right? I think we, yeah, but Gary, that's.

Leo Laporte (15:45)

The whole point is that a lot of technologies are double edged swords and you can focus on the negative as.

Gary Marcus (15:49)

Well as the positive all due use.

Leo Laporte (15:51)

I mean without section 230 we wouldn't have a chat room, we wouldn't have forums. This personally twit my company would not have a mastodon instance because we couldn't afford the liability. So there's pros and cons, they're all.

Gary Marcus (16:05)

Double edged and in a rational world we regulate things so that these double edged swords, you know, to minimize the downside. So we didn't. Guns, let's say are double edged sword sort. And one of the ways that we handle the downside is we have a bunch of regulations around who can use them, you know, what background testing to do and so forth. You know we throw people in jail if they misuse them and so forth. But you have these people like Andreessen that want no regulation on AI at all.

Leo Laporte (16:33)

Well, that's because not at the gun level. We're at the gut. We just invented gunpowder. Right. In terms of AI. And so, yeah, I mean, you could be premature in regulation if you don't understand it. We held off on regulating the Internet, I think probably rightly so, because we didn't know yet what it was going to be. And there was a certain.

Gary Marcus (16:52)

Yeah, well, I appreciate what you're saying. I think there's enough things we already know that we can do some of the regulation that we need to do. I think it's certainly the case that anything that we do has to vary over time. Right. So, you know, any regulation that anybody ever writes tends to not be exactly right the first time, and you need variation. And so, for example, the EU AI act has built into it a period of review. I think it's after three years or five years or whatever. And you've got to do that here. And we change regulation all the time. We used to do that at the national level when Congress actually worked. We don't so much anymore now that it doesn't work, but we used to do that fairly regularly. And certainly any rational notion of regulation of AI has to include the dynamics of change over time. And part of why social media has been so ineffective is because Congress has basically failed to function for whatever it is the last 10 years or something like that. And so even when it became apparent that it wasn't exactly working right, that you needed some kind of midstream course correction, nobody could actually get it done.

Jeff Jarvis (17:59)

Eris, you were trying to.

Paris Martineau (18:02)

Oh, I was just going to comment on. To Leo's point about. Oh, well, AI is so nascent. Leo, you're always saying that AI is incredibly advanced. We're days, minutes away from AGI and a revolution. Does that not seem like a reasonable point in which to step back and think about how these technologies should and shouldn't be applied?

Leo Laporte (18:24)

If you. If you knew how to think about it, maybe, but I don't know if we know how to think about it. Do you think, for instance, gary, that the EU's AI regulation is proper and works?

Gary Marcus (18:34)

I mean, you can't answer whether it works yet because it hasn't really gone online yet. Is it proper? I think the spirit of it is correct. There's a lot of implementational details yet to be determined. There's a lot of political jockeying from the United States to try to weaken it. Although US European relationships just took a Giant turn for the worst. And so I don't know if the US still has any leverage over Europe or not. We'll see.

Leo Laporte (18:59)

Or vice versa.

Gary Marcus (18:59)

The spirit of it is, right, that you want to look at particular kinds of risks and you want to basically look out for human rights, that you want to make sure that humans are not screwed by giant companies and that there's some kind of balance, but that you also, you know, allow innovation to prosper and so forth. You know, that's the trick.

Leo Laporte (19:17)

That's the trick, isn't it? Right, that's the trick. And that's one of the things people worry about with the EU and the California attempt to regulate AI is that you could actually kill the baby in the.

Gary Marcus (19:27)

Yeah, that regulation, I mean, look, if the California law had passed, then, you know, company like Google that has a certain number of, you know, trillion dollars in market cap would have spent, you know, an extra, let's say, $10 million a year filling out paperwork. And no, it wouldn't have changed anything except that it would have given some sense of responsibility that they actually need to monitor the consequences of their actions and that they can be held liable for those actions. It also would have protected whistleblowers. And we have Sushir Balaji, who was, you know, killed on, or I should say that more carefully.

Leo Laporte (20:02)

We don't know what happened.

Gary Marcus (20:03)

Circumstances that are still not entirely clear. You know, having some protection for whistleblowers would be really great. I agree. We didn't get it.

Leo Laporte (20:12)

Yeah, there's something. But go ahead and. But I want to get more philosophical before we lose our window with Gary, because he is a cognitive psychologist and he's written some very interesting things about language and stuff. But go ahead, we can continue on this line of questions.

Jeff Jarvis (20:27)

I just wanted to ask a little more. Got to ask about AGI because, Gary, you've been involved in this obviously for much longer than. Than the fewer since ChatGPT came out. Was there a moment when you saw the trope of AGI emerge as the putative goal with no definition?

Gary Marcus (20:44)

You said I. Yeah, that's interesting. So, I mean, the term goes back to like 2002 or something like that. 2005, Ben Goertzel, Shane Legg, who was one of the DeepMind founders, coined it. I have an interesting anecdote there, which is in 2018, I wrote an article called Deep Learning A Critical Appraisal, which was on Archive. And I said, this stuff's not going to get you to AGI. And the stuff was models that are a predecessor to LLMs. LLMs were not really known at that point, but the general kind of ancestor to them was well known at that point. And I critiqued them and I said, they use too much data, they don't generalize very well, blah, blah, blah. Many of the same critiques that I, and now Yann Lecun would make about large language models. And one of the reactions I got, you can see this because I wrote an FAQ on the. All the grief that I got on this paper, I wrote it for medium. One of the reactions I got is, nobody's really trying to build AGI, which I thought was kind of bull at the time. I thought a lot of people actually hoped to build AGI. They just weren't announcing it as that because they didn't know what they really had or whatever. But DeepMind had already said as their motto, first we solve intelligence, then we solve everything else. They were always gunning for AGI from the very beginning. And it was a very disingenuous reply to me. In 2018, there's been a lot of disagreements, disingenuous replies over the earth, but it was a particularly disingenuous reply. They said, oh, nobody, you know, you can't judge this stuff by the standards of AGI because nobody's working on that. And it was a lie then. It's just nobody wanted to admit that that's what they aspired to do. Now it's very trendy. Oh, we're working on AGI. The limitations haven't changed, but the attitude and the valuations of the company have changed.

Jeff Jarvis (22:36)

Have you yet nailed down anyone to a definition of AGI?

Gary Marcus (22:40)

I mean, that's also interesting. So in 2022, I think it was, I offered Elon $100,000 bet saying that AG this would be my substack, saying that AGI was not going to come anytime soon, wasn't going to come back by the year 2029, as I recall. And I shopped the definition around on Twitter. I said, you know, here's how I understand AGI. And I shopped it with Shane Legg and, and Ben Goertzel, who had originally coined the term. And Peter Voss doesn't quite get as much credit because he thought about it earlier and it was reincarnated or whatever. I ran past all these guys and they were like, that's fine. What I said is having the flexibility of human cognition and so forth, being able to do whatever people can do and maybe better, right? So it would still be AGI if it was better than Humans. And Lord knows humans have lots of flaws. I wrote a whole book about that called Kludge. So you can easily imagine intelligence that would be better. I mean, already, like chess, computers are better at playing chess than we are, and calculators are better at doing math. So you can imagine a system that is basically equal to or better than us. And I emphasized flexibility, being able to do different tasks, not just because you train the entire Internet, but because I give you an instruction like, touch your nose and then touch your head. And from one trial, you understand how to do that task. And so I put this out on Twitter. I said, this is the definition I got. Is it okay? And Shane said it was okay, and Ben said it was okay. And then I proposed some tasks. I said, you know, you need to be able to do this by 2029. If you can do three out of the five, we'll call it general intelligence. And everybody was fine with that definition in 2022. Like, there really wasn't much pushback. If you look at the discussion on Twitter. And back then, there were more people in this field actually on Twitter, a lot of people fled for reasons we don't need to go into. And so everybody was totally fine with it, like, okay, that's a reasonable definition. These are reasonable tasks, and so forth. And now, like, I don't know if you're putting that up on screen. Ezra Klein yesterday was kind of, you know, backing down to maybe it's just doing a bunch of human tasks, which is a much weaker definition than we had talked about in 2022. And I have a whole article that I wrote, forgetting the name of it, showing all the ways in which people are trying to retrench. So, for example, instead of defining AGI in terms of human flexibility and cognition, it's very general artificial general intelligence. That's what AGI is. Instead of doing that, they're like, well, if it makes a certain amount of money, that's just a different definition. You can ask, does this technology make $100 billion? But then my iPhone is by definition AGI because it made $100 billion for Apple. And that just seems like a silly.

Leo Laporte (25:24)

Why are we fighting? I don't understand why we're fighting over the semantics of what AGI is. I mean.

Gary Marcus (25:29)

Oh, I'll tell you why. Because, Well, I mean, there's multiple reasons. One of the biggest reasons is actually that Microsoft agreed to a crazy clause in their contract with OpenAI saying that OpenAI gets the IP back if they achieve AGI. So suddenly, there's A lot of money at stake, so that's one reason. And then it's bragging rights. You know, people want to say that the thing that they've got is AGI. There are people that want people like me to go away and say that it's been achieved, so stop, you know, criticizing. And there's a bunch of different reasons why. There's a lot of, kind of not very pragmatic though.

Leo Laporte (26:02)

I mean, if, if AI can do something valuable, I don't understand why we care about. AG's been doing value for a long time.

Gary Marcus (26:12)

So. So for example, Google search is AI and it's been around what, 25 years? It's very valuable. I still probably use it, or I use a knockoff called DuckDuckGo multiple times every day. GPS I use in my car all the time. Those are AI. Nobody gets excited about them. They don't think that they're changing the world, but they're actually super useful. I find I would sooner give up on ChatGPT than I would on GPS. I think GPS is more useful to me because I can count on it, it's reliable.

Paris Martineau (26:44)

I'm curious, on a day to day basis, do you use any of the popular AI tools?

Gary Marcus (26:49)

No, the one I probably use the most is just making images, which I do for fun and almost satirically to mock the AI. I don't trust them. And my business is being right about AI at some level and if I make mistakes, I got a lot of pushback. If I use this stuff, it would be a nightmare for my particular line of work. I understand there are businesses like where somebody needs to come up with marketing slogans and it may suit their purposes or something like that. It doesn't really suit my purposes. It's not trustworthy enough. I try to give the best reasoned argument about whatever it is that I happen to write about a particular day or think about or whatever. And it doesn't do that. It gives you the generic consensus average of anything that it writes about. It hallucinates, it makes up references like this. It'd be a nightmare for me to use it. I sometimes joke because I wrote my last book in two months and people say, did you write ChatGPT? Use ChatGPT to write it. And I say, I don't pay for sex and I don't pay for chatgpt.

Jeff Jarvis (27:59)

Leo, you were gonna get philosophical and I stopped you.

Leo Laporte (28:02)

Well, you know, I guess there as a. You have said that neural networks are not enough, that there was a survey.

Gary Marcus (28:10)

Just now showing that 85% of people at the AAAI Society were just surveyed. Agree with me. I mean, I wasn't mentioned, but agree that neural networks are not enough. That is a huge change from three years ago. I think a lot of people have come to see the light. They're not enough.

Leo Laporte (28:28)

Yeah. Is there a technique that you think you've mentioned symbolic AI as being one technique that could supplement neural networks?

Gary Marcus (28:38)

Yeah, I mean, what I really favor is neuro symbolic AI, which would be a hybrid of classical symbolic AI, which just looks like computer programming basically and neural networks. So in computer programming, everything is explicit. You have clear variables, you do explicit operations, you do comparisons, you store them, you run subroutines and stuff like that. In neural networks, you run everything in the simplest version through this feed forward similarity process where you have these weights and you add up the weights and so forth. They're very different techniques. They're not very compatible as they have been built. But I think we need to bring them together and I think that's where the real action is.

Leo Laporte (29:14)

And yeah, we have kind of made surprising strides with neural networks in some ways unexpected results. No.

Gary Marcus (29:21)

I mean, yes and no. Like they do things people didn't imagine. That is true. But they still fail on the things that I was writing about in 1998 and 2001 when I was a lot less gray, they still fail at abstraction, at reasoning, at keeping track of properties of individuals. I first wrote about hallucinations in 2001. The core things that I think you need in order to get to a trustworthy, reliable reason reasoning system that's at least as powerful as a person we still have not really solved with the neural network architecture. So it is true, like deep search is impressive or deep research is impressive, but then you look at the output and it has the same old problems. It still hallucinates. So I use deep search and it told me there was an well. So I asked it for all the cities that were all the major cities that were west of Denver, and it forgot Billings, Montana. And so I said, what happened to Billings? And it told me there was an earthquake in billings of 5.5 magnitude. And there wasn't a 5.5 magnitude earthquake. So misunderstood the question and it made up a hallucination. You know, it made this beautiful chart, but the chart was wrong. It left out, you know, a serious city with a population of whatever was 120,000. And so like, at some level, what I was saying in 2001 is if all you do is tabulate statistics, you don't have proper explicit Representations like they used in classical AI. You are not going to get a trustworthy machine. And that is still true. It's a quarter century after I wrote that book.

Leo Laporte (30:55)

I think Stephen Wolfram would agree with you. But the philosophical question I have, which may be unanswerable or may even be a stupid question, as a cognitive scientist, what is it that we do that's so different from what a machine is doing or a neural network is doing, or an LLM is doing?

Gary Marcus (31:15)

So my view about this is that the crudest way to think about is Daniel Kahneman System one and System two, which most people know, right? So System one is kind of a statistical approximation. It's reflexive, it's automatic. And System two is more deliberative and more explicit. And humans actually use both. And there's actually tension in how we use them and so forth, but we use both and we balance the two. Current AI is mostly like System one, and I'm not the only person who's reached that conclusion. For example, Yashua Bengio has also reached that conclusion. Even though we disagree about a lot of technical things, I think we agree with some other set of things, but we disagree about a lot of technical things. But we both come to that conclusion that current AI is good at System one. We both come to what he would call a problem of distribution shift, which is something I was writing about a long time ago under slightly different terms. We both agree that that means that if you just train on a lot of data, you still wind up with a lot of outlier cases, which is what's killed driverless cars. Or I mean, I won't say killed, but is really delayed driverless cars. You know, there's still like, you can't really drive one in Buffalo. You can only drive them in a very well mapped city with nice weather and stuff like that. So the inability of System 1 to deal with outliers has been a major problem. We need to have a system too that looks at least a little bit more like classic symbolic AI. And what we really need is a hybrid between the two. That's certainly at least what has worked for humans. I think it is necessary, but not sufficient to use philosophical terms. It's not the only thing we need to do, but it's a vital step to getting further.

Leo Laporte (32:51)

I believe Rich Sutton today won the Turing Award along with Andrew Bardo. There is a story in the Financial Times about how they warn over unsafe deployment of AI models. But I also remember Rich Sutton wrote the Bitter Lesson paper a few years ago in which he said, really all you need to do is not improve the models, but just throw more computing at it.

Gary Marcus (33:12)

Yeah, I keep meaning to write a reply to it. I want to call it the Bitter Lesson about the Bitter Lesson. The bitter lesson about the bitter lesson is the bitter lesson is right for the things that it works for and wrong for the rest. And so the things that it works for are problems you can do with a certain kind of pattern recognition or certain kind of reinforcement learning. The things it doesn't work for are things like reasoning and dealing with outlier cases and so forth. It's never really worked for that. So it is true that these set of things we can do with the bitter Lesson has somewhat expanded. And it's also true there's a bunch of things like hallucinations that keep popping up over and over again when you try to get them to reason. Like, do you know these river crossing problems? You have a man and a goat and cabbage or whatever. A guy named Colin Frazier has had incredible fun ridiculing these systems by showing that if you make a slight variation on a traditional problem, they fall apart. Or he does. The ones with the doctor winds up in the hospital and it's the son or the grandmother or whatever. These systems are just they don't really understand the concept of doctor or hospital, river or goat or whatever. And it's always easy to break them and show that they just really don't know what they're talking about. That's the other side of the bitter lesson is even when you have all the data in the planet, you still can't get these systems to reliably solve variants on river crossing problems.

Leo Laporte (34:34)

The final thing I would say is that's why I'm not really thrilled about the discussion of what AGI is. Do we need an AI to match us or can it just be a tool entirely?

Gary Marcus (34:47)

Depends on the problem. GPS doesn't solve its problem exactly the way a person does, and that's fine.

Leo Laporte (34:54)

But it solves it adequately.

Gary Marcus (34:55)

Yeah, it's perfectly adequate. So it really does depend on the problem. The meta problem is that OpenAI sold the world on this notion that ChatGPT could do anything you want it to do. And to do that, you really do need AGI. If you want to do something narrow like GPS or chess or something like that, fine, you certainly don't need AGI. But once you sell this dream, you know, now to deliver on it, you actually probably do need something like AGI.

Leo Laporte (35:25)

Gary, I want to thank you so much. Everybody should subscribe To Gary's Substack. Actually, you're very generous. I haven't subscribed because most of the stuff I want to read is free. Still, maybe you should.

Gary Marcus (35:35)

I've only had two paid things. I'm not doing it for the money. I like it when someone subscribes. It's like a bit of validation, but I don't want to. I'm trying to get ideas out in the world, and so I don't charge for them.

Leo Laporte (35:47)

Well, you're definitely doing that. It's much appreciated, and I'm really glad to get you on. And I will upgrade to paid. I'll click that button.

Gary Marcus (35:54)

I will be honest.

Leo Laporte (35:55)

Thanks, Gary. Marcus. And the new. The newest book is out now, which talks about a lot of what we've just talked about.

Gary Marcus (36:06)

Yeah. I'll tell you one sentence. I know you got to wrap up, but Taming Silicon Valley, the beginning of the book, it talks about the possibility that tech oligarchs might take over the world. Imagine that. The possibility.

Leo Laporte (36:19)

You wrote that last year. How did you know? How did you know, Gary?

Jeff Jarvis (36:25)

Thank you for that.

Gary Marcus (36:25)

I saw the writing on the wall, but it's even darker than what I read.

Leo Laporte (36:29)

Yeah. There you go. Yeah.

Gary Marcus (36:31)

All right, Thanks a lot.

Leo Laporte (36:32)

Hey, it's a real pleasure talking to you, Gary. I hope we can have you back in a few months.

Gary Marcus (36:35)

And, yeah, this was great fun.

Leo Laporte (36:36)

See how it's going. Thank you. Take care.

Paris Martineau (36:38)

Thank you.

Leo Laporte (36:38)

Take care, Gary Marcus. Substack.com. all right, Gary, we'll let you go.

Gary Marcus (36:45)

Thanks.

Leo Laporte (36:45)

I would. I could talk to you for many more hours.

Gary Marcus (36:47)

Yeah, let's do it again at some point.

Leo Laporte (36:49)

Very good. Very good stuff. Thank you.

Gary Marcus (36:51)

Thanks a lot.

Leo Laporte (36:51)

Take care. All righty. Bye. Bye.

Paris Martineau (36:52)

Bye.

Gary Marcus (36:54)

Nice to see you, Jeff.

Leo Laporte (36:56)

You remember him? He wasn't sure if you'd remember him.

Gary Marcus (36:59)

We've met on Twitter in various places.

Leo Laporte (37:02)

I don't see that example. That's how I became aware of Gary's. From your tweets. Jeff.

Gary Marcus (37:08)

I know I hate Twitter, but a lot of people know me that way.

Leo Laporte (37:12)

So it's an exposure.

Paris Martineau (37:13)

Are you liking Blue Sky?

Gary Marcus (37:17)

It's not Elon. It has that going for it. My focus. I've lost my focus. Like that character in the Woody Hour movie. There we go. There's Robin Lane. Lost his focus.

Leo Laporte (37:30)

Thank you.

Gary Marcus (37:31)

I wish Blue sky were better than it is. I'm trying to balance.

Leo Laporte (37:34)

I think Blue Sky's really becoming exactly what Twitter was. Which, for better or for worse, you.

Paris Martineau (37:40)

Got to find the right people to.

Gary Marcus (37:41)

Follow, though it doesn't have the same dynamism as Twitter. It's hard to get a sustained conversation. Some of it has to do with the algorithm and I don't know what.

Leo Laporte (37:51)

But it just doesn't.

Gary Marcus (37:52)

And then, like, you can't edit your tweets, you can't have drafts.

Leo Laporte (37:55)

That's frustrating. Yeah. Like, although you couldn't on Twitter for the longest time.

Gary Marcus (38:00)

It is true. It is true.

Leo Laporte (38:01)

Yeah.

Gary Marcus (38:02)

I don't know. I hope it works. You can find me there, too.

Leo Laporte (38:04)

Good. Thank you, Gary. Bye.

Gary Marcus (38:06)

Bye.

Leo Laporte (38:06)

Take care. That was fun. See, I got somebody on just for you.

Paris Martineau (38:12)

Thank you.

Leo Laporte (38:13)

I'm not. I'm not accelerationist, but I. I really don't like the thing.

Paris Martineau (38:19)

Did you say I'm not an acceleration?

Leo Laporte (38:21)

No, I said I am.

Paris Martineau (38:22)

Okay. Like you're always saying.

Leo Laporte (38:23)

But I think it's. I think it's a huge mistake to say, oh, it's got to do what. Everything a human does is patent nonsense.

Jeff Jarvis (38:30)

But. But the mistake is not. That's why I disagree with you about the AGI thing. The problem is they're all saying they're going to reach this AGI. I agree. It's bs.

Paris Martineau (38:38)

That's why everybody is pouring so much money in it, because they're saying, I.

Leo Laporte (38:44)

Think if you're a vc, you're pouring money into AI because you know there will be value, not because it's going to be AGI.

Paris Martineau (38:50)

Well, to this point, one of my colleagues reported a story this week that OpenAI is plotting charging $20,000 a month for ADHD level agent. But my question is, why would you pay $20,000 a month for the equivalent of one PhD level researcher, when instead, for that amount of money, you could hire five PhD researchers?

Leo Laporte (39:15)

That's a fair question. If somebody does it, though, then there's a reason they're doing it.

Jeff Jarvis (39:19)

No, they can also be idiots.

Leo Laporte (39:21)

All.

Paris Martineau (39:22)

It's because everyone's like, AGI, AGI. AGI is going to be better than.

Leo Laporte (39:25)

Our businesses aren't stupid. They're not going to spend $20,000 a month for something that doesn't produce a result.

Jeff Jarvis (39:31)

When I worked at Time Inc. And I questioned one of the systems we bought, I was lectured firmly and told, if we're buying it and it's the most expensive out there, then it has to be the best.

Leo Laporte (39:41)

Must be the best. Yeah. We're going to take a break and we'll come back with more AI news coming up next. This episode of Intelligent Machines, brought to you by Melissa. Actually, this is fairly germane. Melissa's been doing data quality since 1985. But what I love about this company, they don't rest on their laurels. They are constantly improving their services, expanding their services, making them available to more of the tools you already use. And yes, they have very much enabled AI. Their AI enabled data quality solutions do a whole lot more than address validation. They leverage all that information that they've accumulated over four decades of data knowledge. But they're now using advanced machine reasoning and cutting edge AI to quite successfully transform raw data into actionable, reliable insights for your business. That's one thing I think we all agree AI is very good at is pattern matching. Melissa's ability to enrich and cleanse data spans multiple industries. You'll see them in fintech, you will see them in healthcare, yes, government, in education and real estate. It goes on and on and it's so much more than just address verification. But their verification and cleansing services will definitely benefit any business that doesn't want to act as its own data scientist. In fact, Melissa's recently acquired a number of companies and I'll have a lot of data scientists working for for them to help you with their business. What this is the thing I love which is this. The the consolidation of business rules into an AI. Whatever rules your business operates within, Melissa is there to support you. And the AI can internalize those rules and can do a great job of making them real in your business. Imagine having a a data expert that never sleeps. Melissa's intelligence systems verify identity. Of course that's great for things like preventing fraud and gaming operations. They ensure valid patient medicine identification and healthcare systems. This is so cool. They'll actually make sure that a patient is getting the medication that's prescribed to them and their human error happens, but this prevents it. They can securely update and verify constituent data across government databases. There's also know your business which enables verification and monitoring for financial institutions. Melissa guides you through complex data management with ease, making it advanced data quality accessible to everyone. This is what I think is really interesting. They started as address verification, but they understood fundamentally their business is about data quality and frankly your business should be too. From small businesses to enterprises, data quality matters with real time data validation, comprehensive enrichment, cross referencing, verification with gold standard reference data and intelligent anomaly detection. No wonder Melissa is the trusted data quality expert worldwide. I don't need to say it, but I will. They securely encrypt all your data. File transfers are always encrypted. They have an information security ecosystem built on the ISO 2701 framework. They adhere to GDPR policies. SOC 2 compliance. So you never have to worry about compliance with Melissa. I want you to contact Melissa's team. The range of things they offer is so broad we couldn't possibly cover it in one commercial. Contact them. Find out what they can do to elevate your business and evolve your data quality. Because it's all about data quality. Get started today with 1000 records clean for free. Melissa.com TWIT M E L I S S A.com TWIT this is a company that has evolved and is using the latest tools to make a big difference in businesses worldwide. Melissa, we thank him so much for supporting the show. You support the show if you use that address, by the way. Melissa.comTwit Any thoughts on what Gary said? Do you want to underscore anything that he said? Either. Either Paris or Jeff.

Paris Martineau (43:44)

I mean, I think I made all my comments.

Leo Laporte (43:46)

You agree with that?

Paris Martineau (43:47)

I thought it was a good segment and I think he has some really interesting points and I enjoyed him being in the show.

Leo Laporte (43:53)

Yeah, I don't. And I don't disagree with him either. I think the only thing I would say is that we just don't know yet. And it's important to have these conversations, but we just don't know what's gonna happen yet. Just as we didn't know what was gonna happen with the Internet. These things have a life of their own.

Jeff Jarvis (44:10)

What I love about what Gary says and he has said since I've followed him is he loves AI but he punctures the hype.

Leo Laporte (44:18)

Yeah. And there's a lot.

Jeff Jarvis (44:19)

That's what we need. There's way too much hype and I think the hype is what gets us in trouble over investment. Maybe bad regulation.

Paris Martineau (44:31)

I think not even bad regulation. No regulation.

Leo Laporte (44:35)

What he's talked about on his substack a lot and I love it. He talks about this when he's talking about Kevin Roose's assertion that, oh, you don't need coders anymore is the opportunity cost of buying into that. That parents are not. Are no longer saying, oh, well, kids got to learn coding. And as a result there's a big opportunity cost to over investing in what's going to be possible. So I would underscore, we don't know what's going to happen in AI and it may be amazing. It may not be, but it. But there is an opportunity cost to making assumptions about that that could be a big cost to society. And that's one of them.

Jeff Jarvis (45:12)

If your kids were 16 right now, would you and they said, I want to go get a computer science degree and I want to code. Would you have a second's pause and say, no, no, no.

Leo Laporte (45:25)

And I'll tell you, even if at some point AI can write a lot of code, which it apparently can, a couple of weeks we're going to have my friend Harper Reed on talking about his AI workflow as a coder. But you know what Gary says, which is I think is very true. Kevin Roos and everybody else who's in this has these AIs write games like Breakout. And he says, well, of course they can write Breakout. Source code for Breakout is all over the Internet. The AI is ingesting that. Can an AI? And this has always been my question, when is AI? I don't think you have AI or AGI until an AI can do something a human can't do. It's not that it can do what a human can do.

Jeff Jarvis (46:04)

It can do tons of things now that we can't do.

Leo Laporte (46:06)

Right. Well, that, that then it's, that's more the general bs.

Jeff Jarvis (46:08)

That's why the G is. What's the BS in that?

Leo Laporte (46:10)

Well, as long as it can do something better than a human in one narrow niche, it's useful.

Paris Martineau (46:17)

I mean, yeah, we're not saying it's not useful, but we're not saying it's all like seeing all knowing better than us in every way. Of course, AI tools have been able to translate more languages than a human for many, many years.

Leo Laporte (46:31)

Well, I'm saying the same thing. That's why I laughed at the existential threat letter, because it's hard to imagine how an AI could become a danger to humans. Can an AI figure out when it's going to rain? I hope so, because we just fired all our weather forecasters at NOAA. But I mean, yes, of course AIs are able to do things that humans can't do. But here is another warning over the unsafe deployment of AI models. This from the winners of the Turing Award. This is the computing's most prestigious award. $1 million prize from the ACM, the Association for Computing Machinery, two long time AI researchers. We mentioned Richard Sutton, who wrote the Bitter Lesson. He teaches AI in Canada, I think. And Andrew Bartow, he's a professor emeritus at UMass. Richard Sutton's at Alberta and a former research scientist at DeepMind. They won the prize for developing the groundbreaking reinforcement learning method. We've been talking about that a lot. They developed that in the 80s, it says, after they were inspired by psychology and how people learn the machine Learning technique which rewards AI systems for behaving in a desired way has lately become part of the headlines with Deep Seq, which uses a punishment and reward system in its reinforcement learning. They won the Nobel Prize of computing from ACM saying in effect, yeah, this is important. Now Bardo said releasing software to millions of people without safeguards is not good engineering practice. He likens it to building a bridge and testing it by having people walk across it. No, no, you wouldn't do that.

Jeff Jarvis (48:21)

No.

Leo Laporte (48:23)

So it's interesting because here are guys who actually invented in the 80s something that is really being widely used in AI today, still worried about how AI is implemented. And I think that's a fair thing to say. Don't implement it where, you know, Gary says this all the time. Hallucination is, is, is almost an unsolvable problem.

Jeff Jarvis (48:45)

Yeah, well, the other three, which is how humans are going to use the tool and we've got to recognize that you can't align it with ethics. You can't, as I said on the show many, many times, come up with super safe guardrails. People, it's just like social media, people will do bad things with it and so we've got to get our heads around that.

Leo Laporte (49:07)

Yeah, but what would you have done 15 years ago to protect us from social media today?

Jeff Jarvis (49:12)

I would have expected the companies to have more of a, I wrote a book about this. I would have expected the companies to have had a higher mission to say this is why we're here and this is why we're not here and we're here to have a decent social experience. And not that everything goes just like on this show. You don't allow certain things, so should they.

Paris Martineau (49:40)

But I mean the practicalities of that are complicated because any attempt over the last two decades to get social media companies or tech companies by and large to have more responsibility for what happens in their platforms or to pay to have some sort of duty of care is decried as would break the Internet and destroy everything.

Jeff Jarvis (50:05)

Well, I'm not saying that it would be regulated atop them. I'm saying if they were decent companies, they should have been.

Paris Martineau (50:10)

That's not how companies work.

Jeff Jarvis (50:12)

Well right now nobody I know is going to target.

Paris Martineau (50:18)

We go target is going to be fine.

Leo Laporte (50:20)

No, they're not, by the way. They're in bad shape. And this boycott, this 40 day boycott is probably going to put them on the brink of bankruptcy.

Jeff Jarvis (50:31)

Yeah, there's still market power and we have it and they should, I mean that's, that's the basis of don't be evil. It was never a highfalutin promise. It was saying if we are, our business will be in trouble. Now maybe proven that that's not the.

Paris Martineau (50:47)

Case, but I'm not certain that it's a viable strategy to hope that corporations in late stage capitalism act with public or social good in mind without any, just as a full, not even, not even a carrot or a stick being involved. I'm just not certain that that will ever be a viable policy strategy.

Leo Laporte (51:13)

I've always thought that if you really had a deep understanding of business that you would do the right thing. You know, the, the why there are.

Paris Martineau (51:24)

Consequences for doing the wrong thing.

Leo Laporte (51:26)

Most of the time I think there are maybe no short term consequences. And unfortunately our, our climate is very focused on quarterly results because of the stock market and so forth. But in the long run, a business I believe is going to do better if it's an ethical business. It's just, it's in the long run, not the short run.

Paris Martineau (51:45)

And I mean in the short run.

Leo Laporte (51:47)

I think it takes a deeper, it takes a deeper business mind to say, you know, we really should do the right thing for our customers. But this is what the insidification is all about. It is a rush for profits. Knowing that it's death to the company. Look what private equity does to companies. They sell off the parts, make a lot of money, but kill the patient in the process. And unfortunately, with that kind of mindset, yeah, if that's what you're focused on is the next quarter's profits and not what the company's going to look like in years to come, then you're, then you're not going to be ethical. But I think in the long run a business leader is going to be ethical. When they're thinking long term, it's just they don't think long term much anymore.

Paris Martineau (52:27)

Well, I mean in both cases, the prerogative of a business leader as a public company is to maximize shareholder value. And that usually doesn't, is, does not equal solve for the good of the public.

Leo Laporte (52:44)

Oh it does. Oh it does. Because you can't look, look at Target. You cannot piss off your clientele. It's really more of timeframe issue. Short term, yes, you can get away with bad behavior within shitification. Long term, it, it's going to kill the company.

Jeff Jarvis (53:00)

If you're, if you have, if your customers are imprisoned, if you're a phone company, you can get away with bad behavior. A cable company, you get away.

Leo Laporte (53:06)

That's a good point. There are certain monopolies but that's because there's a monopoly too, right?

Jeff Jarvis (53:10)

Or a lack of control. I mean, there's only. Only we fly this route or you only have so many phone companies and we know you have fewer choices.

Leo Laporte (53:19)

Yeah, I think, you know, I just read a piece, somebody said it all started with Reagan, that we. That greed became good. And the last 30, 40 years, quite, quite a bit to the detriment of the. Of the American polity, have been about greed, and we're now going to reap the rewards.

Jeff Jarvis (53:42)

Paris's point.

Leo Laporte (53:44)

Yeah. Oh, I agree. I don't saying the companies are behaving well, but I'm saying that's bad business in the long run.

Jeff Jarvis (53:50)

The long run.

Leo Laporte (53:52)

And. But, you know, what do I know? I'm a podcaster, so I don't know how to run a business. Meta now says that they want to spend $200 billion for their new AI data center. This is that opportunity cost that Gary was talking about.

Jeff Jarvis (54:15)

I'm tired of stories about the latest model and investing in data centers.

Leo Laporte (54:22)

Yeah. Okay, how about this one from Satya Nadella, the CEO of Microsoft? Oh, I can't get to it. He says AI's true value will come when it finds the killer app, like email or Excel.

Jeff Jarvis (54:38)

Which is to say it doesn't have.

Paris Martineau (54:39)

All roads lead back to email or Excel.

Benito (54:44)

That's what they said about crypto.

Leo Laporte (54:47)

Yeah, and they never came up with one, did they?

Paris Martineau (54:49)

Same with NFTs. I'm still looking for a way to make my monkeys work for me.

Benito (54:54)

I mean, just blockchain action. The blockchain, the technology. That's what they said about blockchain.

Jeff Jarvis (54:58)

You know who I'd like to have on Leo at some point? Who is Dan Bricklin?

Leo Laporte (55:03)

Oh, I know Dan. We can get Dan on, because.

Jeff Jarvis (55:05)

Dan. Do you know Dan Bricklin, Paris?

Paris Martineau (55:08)

Nope.

Jeff Jarvis (55:09)

He. So Dan is the man who made the personal computer useful. He invented the spreadsheet, and I think he has that kind of perspective.

Leo Laporte (55:19)

He created VisiCalc, which I bet Paris never heard of.

Paris Martineau (55:23)

Nope.

Leo Laporte (55:28)

Before there was Excel, before There was MultiPlan. VisiCalc was the first. Yes, VisiCalc was the first killer app. Yeah, it made Apple IIS a business computer instead of just something to balance your checkbook and play load runner with. And it transformed the personal computing industry.

Jeff Jarvis (55:49)

It made him useful to business because you could now ask, what if? And in essence, that's what AI promises to do, is let you think it does. I'm not making a judgment, I'm just saying it. This is where the digital Twins come in at its fullest. What AI does for a warehouse or a self driving car is examine alternative futures. And that's what dan did with PhysicalC.

Leo Laporte (56:18)

Yeah, but I would say there's a million killer apps for AI. I think what Nutella has mistaken is kind of like the same AGI mistake is they want something that's broadly general and that's not what AI is. AI is very specific. Now Darren, who is a coder, he's in our club and I know he's a very good coder because he is one of the people who I do advent of code with every year and he usually solves those problems in minutes. He is a big AI fan and he says AI helps him code to do in a minute what would take him otherwise hours. And I trust Darren as a coder, you know and, and I, we're going to talk to another coder friend of mine who, who says something similar. So I, I know Kevin Roose is maybe I, I would agree with Gary overselling because he's not a coder. Overselling what an AI can do with coding, it is absolutely valuable. So and I, I think that there are plenty of people using cursor AI or copilot on GitHub who find it indispensable.

Jeff Jarvis (57:30)

Yeah, I use it for translation and transcription and I play with it and it has lots of good uses. Again, the problem is that to argue that it is going to exceed general human ability is where it goes off the rails. If we accept it for what it can and can't legitimately do, we'd be a lot better off in what we invest and what we regulate and how we use it.

Leo Laporte (57:52)

Well in fact that isn't that. The real skill of using AI is knowing what it can and more importantly what it cannot do. Knowing when to trust it, when not to trust it.

Paris Martineau (58:01)

Yeah, but it's a difficult skill to learn. It's not something people immediately realize when they're using it. They think, oh, it makes me the app. It's perfect. It's great. I'm so excited about it.

Leo Laporte (58:13)

Yeah, that was what Gary was saying is it makes an app just like every other app because it only knows how to make the apps that have already been made.

Jeff Jarvis (58:21)

Yeah.

Leo Laporte (58:22)

Google's co founder says stop building nanny products. There's the gorgeous Sergey Brin. He is, besides saying everybody's got to get back to work, he sent a message to hundreds of at least five.

Jeff Jarvis (58:37)

Days a week, at least.

Leo Laporte (58:38)

Oh yeah, he wants, he wants you. Well, he says he sent this message To.

Jeff Jarvis (58:42)

This is the old joke. This is the old joke at Disney. If you don't come in Saturday, don't bother coming in on Sunday.

Leo Laporte (58:48)

Yeah. He sent a clear message to hundreds of employees in the DeepMind division. It's been two years of the Gemini program and GDM, which is Google DeepMind. We've come a long way in that time with many efforts we should feel proud of. At the same time, competition has accelerated immensely and the final race to AGI is afoot.

Jeff Jarvis (59:09)

There we go again.

Leo Laporte (59:10)

I think we have all the. Well, but he's not saying this to the outside world. He's saying this to his employees.

Jeff Jarvis (59:16)

Yeah, he's the same problem with it.

Leo Laporte (59:18)

I think we have all the ingredients to win this race, but we're gonna have to turbocharge our efforts. That means 60 hours a week. He says that's the sweet spot of productivity. He says that's how much you can work without getting burned out. That's five 12 hour days, folks. He says come into the office.

Benito (59:36)

Considers his flights part of his workday.

Leo Laporte (59:38)

I bet you I know at least. Yeah.

Paris Martineau (59:41)

His flight's in business class. Yeah. In executive. Yeah.

Leo Laporte (59:49)

He's building a blimp so he doesn't even have to go to the airport anymore. He comes, he says come into the office at least every day of the week. Generally move faster. He says Google's AI products are overrun. By the way, this is Alex Heath writing at the Verge pointed this out. He says Google's AI products are overrun with filters and punts of various kinds. In other words, you know, safety mechanisms.

Jeff Jarvis (60:20)

Is that what he means by nanny?

Leo Laporte (60:22)

Yeah. Google needs to trust our users and can't keep building nanny products. As a direct quote, no more woke code. Yeah.

Paris Martineau (60:34)

When was the last time either of you worked? 5 day Monday through Friday in an office.

Jeff Jarvis (60:39)

Oh, in an office.

Paris Martineau (60:41)

Why?

Jeff Jarvis (60:41)

I actually before the pandemic, I did. I. But it was just stupid because professors don't need to. And I where gossip at the school in New York.

Leo Laporte (60:50)

Yeah, he had. He used to do.

Paris Martineau (60:51)

So you commuted. You commuted to New York City every day?

Jeff Jarvis (60:54)

Because I'm an office gossip. I wanted to hear what was going on. I didn't want to.

Paris Martineau (60:57)

Okay, I will. I do. I do deeply understand that. I love my three days a week in office in part because I need to overhear everybody else's conversations. But I've also learned a lot of good digital tools for doing that remotely as well.

Jeff Jarvis (61:09)

My. My managing editor in San Francisco when I was at the examiner, yelled at me one day and he said, God damn it, Jarvis, I pay you to be the town crier, not the office crier.

Paris Martineau (61:17)

My editor at Wired once, when I was calling him, asking about some bit of gossip, he's like, you know, when I was the Journal, people often said journalists do their best work when trying to report in their own newsroom. And I think that's right.

Jeff Jarvis (61:31)

Yeah, true.

Paris Martineau (61:32)

It's the most inspired.

Leo Laporte (61:33)

All right. Yeah. There is this weird macho work, 100 hours thing going on. I mean, certainly that's how Silicon Valley started. Right. I mean, Steve Jobs was famous for that. And, you know, the death march toward getting a product out the door was night was famously nightmarish, cost marriages and families. And that's. But there was the feeling that's what we had to do.

Benito (61:58)

Yeah, but they're asking everybody else to give up their marriages and their families and stuff, too, which is, you know.

Leo Laporte (62:03)

Oh, Sergey's gone through a few wives. Let's.

Paris Martineau (62:05)

Sergey's. Yeah, he's.

Benito (62:07)

Yeah, but. But he's asking all of his employees to do that, too.

Leo Laporte (62:12)

Yeah, well, he doesn't have a life either. Except he's phenomenally rich. Of course. It's the guy who makes, by the way, all that work you're putting in. Right. I'm sure you're well paid for it. He's even better paid for it. He's. He's beneficiary. All right, I want to take another break. You were watching and listening, I hope, to intelligent machines. If not, this might be a little confusing. It is our new show about AI Ray Kurzweil next week, the guy who's been talking about AGI forever, he calls it the Singularity. His newest book is the Singularity is Nearer Now Than Ever and When We Merge with Machines. He's now talking about merging with machines. He is the guy who wants to live so long that he will live forever. So that'll be interesting, but lots of other guests we've got. I'm trying to get balance. I hope you appreciate that, guys, very much. Yes. Because I don't. I'll be honest, I don't know. I don't know what's going to happen. I'm not. I may be an accelerationist. What to me that means is, let's really see what we can do with this. I don't know what's going to come.

Jeff Jarvis (63:28)

If you're a full accelerationist in the andreessen mode, then you want zero regulation. That's not true of you, is it? Or is it?

Paris Martineau (63:35)

He has many times said there should be no regulation. We should get everything to the AIs.

Leo Laporte (63:40)

Yeah. Because inevitably, regulation is going to be pointed at the wrong direction. It's just. It's too early to know. People who are writing the regulations, definitely, if I don't know, they don't know in spades. So I just don't trust them to write regulations. No, I don't have any sand in my shoes. No, I don't have any sand in my shoes. I think that there is a reasonable case to be made that we have a tiger by the tail. We have a technology. I don't know where it's going to go, but it's very interesting, and I think it's the wrong time to put the tiger in the cage. Let's see where it can go. But that's also because I don't believe it's going to be an existential threat to human beings. I don't think it's dangerous. I really don't. I think you could say there's an opportunity cost. That's a. That's a reasonable point. But that's like caution.

Benito (64:31)

That's kind of saying, like, a gun by itself, inert, is not dangerous. But you put it.

Leo Laporte (64:36)

Like I said, we're not at the gun stage. We're at the gunpowder stage. We're so early in this. We haven't gotten to guns yet. If we start guns. Okay.

Benito (64:47)

I don't know. I consider this as part of the arc of computing in general. So we're not early in this. We've been doing this since the 60s.

Paris Martineau (64:52)

Yeah. Decades.

Leo Laporte (64:53)

Like, no, no. What's happened? Even in 2015. Wolfram has said this. Even in 2015, nobody thought what we've got now was possible. He said it the very first thing out of his mouth last week was. Even the guys at ChatGPT OpenAI didn't expect what was gonna happen. Happen to happen. And I think that that's why it's of interest. This is only a few years old. This is literally three years old. The stuff that we're experiencing now. Anyway, we'll see. I just. I think, you know, let's not be nannies here. Let's let it happen. Unless you think it's gonna be dangerous. But I don't think it's gonna be dangerous. That's. I think that's the. That's the wrong angle on it. Like, oh, my God, they're gonna be robots.

Benito (65:42)

No, it's not.

Paris Martineau (65:43)

Zephyr west and the YouTube.

Benito (65:44)

We are dangerous. See, we are dangerous.

Leo Laporte (65:46)

Well, we're dangerous. That's true.

Paris Martineau (65:47)

We are dangerous, and the things we make are dangerous.

Benito (65:50)

That's what I'm scared of. I'm scared of us using these tools.

Leo Laporte (65:54)

I really want to. We'll never get them. I just ordered Alex Karp's new book, and I really want to get him on. He is, of course, the founder of Palantir and the kind of person Jeff Jarvis hates.

Paris Martineau (66:09)

There might be some of these people you get on that in order to negotiate them coming on. It might be helpful for you to tell them, I won't be there.

Leo Laporte (66:16)

Oh, you wouldn't be there if Alex Karp came?

Paris Martineau (66:18)

I mean. No, I'd want to be there. I just think probably, like the Palantir guy or someone who currently works at OpenAI might see the information reporter on the call list for the thing and be like, podcast. So, I mean, that's. It's only because we do so much journalism. But this is. What I'm saying is if you really want to talk to a talent or guy, I'm always happy to.

Leo Laporte (66:39)

Well, I think I'm hoping that when people come on our shows, they perceive it as getting on the air with some journalists, not just the person from the information. I would hope that people would say, oh, journalists are going to interview us, right?

Paris Martineau (66:55)

Yeah, journalists from. A journalist from the information is going to interview me would strike fear or at least anxiety into the head of someone from OpenAI or a person arranging it from.

Leo Laporte (67:08)

Yeah.

Paris Martineau (67:09)

You know, Palantir. Just saying. That's probably something some people consider. So I'm always happy to follow myself.

Leo Laporte (67:15)

No, no, I would never have.

Paris Martineau (67:16)

A little bit.

Leo Laporte (67:16)

I would never have you do that, even if it would cost us the interview. Are you going to read Alex Karp's book?

Paris Martineau (67:23)

I have to.

Leo Laporte (67:24)

You need to. But, Jeff, are you gonna. Are you just.

Jeff Jarvis (67:28)

I picked it up in the bookstore today. It's one of those. I should. I'll see how much impact it gets. Well, because. Because, like, I'm doing weird things around, you know. Here's the latest book I just got about.

Paris Martineau (67:41)

Beautiful cover.

Jeff Jarvis (67:42)

Isn't it nice? It's nice. I ordered from London because you can't get it yet. Right. That's. That's. I find this more interesting. Another book about what I understand from the reviews that Karp is saying is that basically we've got to use AI to build weapons.

Leo Laporte (67:57)

It's, I think, deeper than that. I think the point of it, maybe that is the outcome, but the point of it is that Silicon Valley is wasting its time building gadgets that These that Silicon Valley has become lost creating.

Jeff Jarvis (68:18)

Useful things for people, stupid little gadgets, governments.

Leo Laporte (68:22)

Whereas we need to. And I'm not, I don't completely disagree with this. We need to defend ourselves because there are going to be people who would like to change our way of life and we need to defend ourselves in our way of life.

Jeff Jarvis (68:39)

But just today, right as we were getting on, I think you're talking about one of his co authors of his paper, Eric Schmidt is saying today that we shouldn't be going full bore Manhattan Project on AGI because it's going to lead to more hostility and more fights.

Leo Laporte (68:53)

Well, maybe, yeah, but you have to think the Chinese are, aren't they? And there's no moat. I mean everybody would agree that we have no moat with AI in fact, deep seek proved that. Right.

Jeff Jarvis (69:08)

Yeah.

Leo Laporte (69:11)

He. This is, this is the copy from his publisher. A deep sweeping indictment of West's culture of complacency. Arguing the timid leadership, intellectual fragility and an unambitious view of technology's potential in Silicon Valley have made the US vulnerable in an era of mounting global threats.

Paris Martineau (69:29)

Threats woke is the problem.

Leo Laporte (69:34)

Alex is not by the way, is not a right winger.

Paris Martineau (69:37)

He's kind of intellectual fragility. Sounds like W. It sounds like.

Leo Laporte (69:42)

But I don't, I think that's a mistake to see.

Jeff Jarvis (69:45)

I, I saw him speak. I think I actually met him in Vienna once.

Leo Laporte (69:49)

Yeah.

Jeff Jarvis (69:50)

Where he's very impressive. He did it in German because he.

Leo Laporte (69:52)

Studied, he studied, he studied very.

Paris Martineau (69:54)

Oppenheimer esque, very.

Jeff Jarvis (69:57)

And his argument there was basically, oh yes, you should regulate us because you should make the responsibility. You should make the judgments government and you should decide what's good and bad and we'll do everything we can otherwise. And so we'll take no responsibility ourselves. You're the responsible being. You decide what we should and shouldn't do and we'll do that and then otherwise fair game. That's basically his argument here. So it's oddly like, it's like Zuckerberg, yes, regulate us, but because we have regulatory capture and we can do it better than others. But then.

Leo Laporte (70:30)

Well, that's why I want to read the book because I think that you could make the argument that government reflexes is a representative of society and that society needs to decide what its priorities are.

Jeff Jarvis (70:40)

But we should also see the earlier discussion about good and bad business. We should also hold the businesses responsible for their own ethical decisions and lapses.

Leo Laporte (70:48)

Okay, but to agree with Paris, do you really want to trust businesses to make those, those decisions shouldn't society be the one that decides what our overarching goals are?

Jeff Jarvis (71:00)

Decide which side you're on here. Accelerationist. Geez.

Paris Martineau (71:04)

I mean, it does seem, at least.

Leo Laporte (71:06)

In my limited experience, I'm not an ideologue.

Paris Martineau (71:09)

I'm not an ideologue of how tech companies operate is they hire some people to tell them what is, what are the legal requirements we need to comply with and then anything else goes. And you know, sometimes you might have people inside the company being like, I, oh, we don't want to do this, or we don't think this works. But we live in a society where of course there's always going to be bad actors. And sometimes those bad actors might be extraordinarily large or have extraordinary influence. And in a world in which there are no guardrails, those companies will do anything and everything to increase their profit margin, regardless of the impact or consequence.

Leo Laporte (71:50)

This is at a higher level. This is more, this is more about. Do you defend the West? I'm a globalist. I don't believe the west has a monopoly on correctness and so forth. But I do think that if we have values, we should defend our values. And it's a mist that Silicon Valley is focusing often on the trivial, on the unimportant, and maybe they should be better citizens. But I'll read it. I don't know, I may be putting words in his mouth. I don't think he is typecast. I think he's kind of a.

Jeff Jarvis (72:22)

No, he's a. He's obviously a smart man.

Leo Laporte (72:24)

Yeah, yeah. Let us take a little break, which we were going to do about half an hour ago, and continue on. We see the conversations are good. Conversations are good. Our show today, brought to you by, we're very happy to say US Cloud, the number one Microsoft Unified support replacement. Why you might say, should I go to a third party for my Microsoft support? Well, we've been talking for a few months now about US Cloud. They're the global leader, by the way, in third party Microsoft support for enterprises. They support 50 of the Fortune 500. They can save you a lot of money, as much as 30 to 50% over Microsoft unified and Premier support. They're also not just less expensive, but they're better. For example, they're faster, twice as fast in average time to resolution versus Microsoft. But there's another thing US Cloud can do that I think Microsoft would not do. And this is why you want an independent third party for your Microsoft support. Will Microsoft tell you where you're wasting your money on Azure? I don't think so. They want you to spend your money on Azure. US Cloud wants you to save your money. They have a new offering that is exactly about this called Azure Cost Optimization. This is a very common situation in business. When's the last time you evaluated your Azure usage? If it's been a while, you probably have some Azure sprawl, a little spend creep going on. How would you know though? Will Microsoft say, hey, you're spending too much on Azure? I don't think so. Saving on Azure is easier than you Think though. With US Cloud, they have an eight week Azure engagement. It's powered by VBox. Eight weeks to identify key opportunities to reduce costs across your entire Azure environment. And it's not just software. You're not just doing it on your own. You get the expert guidance of US Cloud's senior engineers. An average of over 16 years with Microsoft products. At the end of the eight weeks, you're going to get an interactive dashboard that will identify, rebuild and downscale opportunities. Unused resources which lets you reallocate those precious IT dollars. There's never enough, I know toward resources you actually need. Or you could do what a lot of US Cloud customers have done is take those Azure savings and save even more by investing in US Cloud's Microsoft support. That's kind of like saving so you can save even more, completely eliminate your unified spend. I'll give you an example. Here's Sam. This was a review he posted the technical operations manager at Bede Gaming B E D e. He gives us Cloud 5 stars saying quote, we found some things that have been running on Azure for three years which no one was checking. These VMs were, I don't know, 10 grand a month. He said, not a massive chunk in the grand scheme of how much we spend on Azure. But once we got to 40 or $50,000 a month, it really started to add up. It does, doesn't it? See, this is why you need an independent third party, right? If you can stop overpaying for Azure, you can and eliminate Azure creep and you can boost your performance. You can do it all in eight weeks. Why wouldn't you call us Cloud faster, better Microsoft support for as much as 30 to 50% less. Visit uscloud.com, book a call today to find out how much your team can save. That's uscloud.com faster Microsoft support. I'd add better faster and better Microsoft Support for less. USCloud.com we thank him so much for supporting intelligent machines. Yeah, I may buy KARP'S book, read it and say, oh yeah, the guy's full of it. I just, I want to hear this.

Paris Martineau (76:13)

He's full of carp.

Leo Laporte (76:14)

He's full of carp. I just want to. And you know, look, he went to Stanford, Harvard, he studied Goethe. He's got a PhD in philosophy from the. Where is. Somewhere in Germany, right, The Goethe Institute or something. So I think he's a smart guy and he was. You know what he did that was smart, you know, when he started Palantir 20 years ago, with the help of a person I do not admire, Peter Thiel, it was because he realized that Silicon Valley wasn't working on national defense and there was a real opportunity to do that. Right. CIA invested in it too, by the way.

Jeff Jarvis (76:57)

Yeah. And the issue here is if, if any company scares us about privacy, it's Palantir.

Leo Laporte (77:04)

It's Mel, dear, right there. Yeah, but are they spying on us or the bad guys? I don't know. Here is a interesting and a fun story. I don't know. Oh, another one I can't get.

Benito (77:15)

Sorry, real quick. And Jeff, can you speak closer to your mic or put your mic closer to your mouth?

Leo Laporte (77:19)

Sorry. Turn yourself up.

Benito (77:20)

There you go.

Leo Laporte (77:20)

Something.

Jeff Jarvis (77:23)

Hello. Hello.

Benito (77:25)

Thanks.

Leo Laporte (77:26)

You need to talk more than that for us to know and not in a funny voice.

Jeff Jarvis (77:30)

I'm sorry, Is this all right?

Gary Marcus (77:33)

Yep.

Benito (77:33)

I get.

Leo Laporte (77:34)

Is he better? Is he better?

Benito (77:36)

Yep.

Leo Laporte (77:37)

Here's a story. A 27 year old exe. That's a. For those of you who don't know a Windows or dos, probably game. Adafruit's managing director Philip Turoni shared an interesting blog post. They spotted a Reddit post saying how someone took a 27 year old exe file written in Visual Basic, fed it to Claude 3.7, which is considered by many to be the best coding AI. Watch as it reverse engineered the program, rewrote it in Python. It was an old Visual Basic 4 program they'd written in 1997 and they were able to reconstruct it. That's pretty impressive.

Jeff Jarvis (78:25)

Let's just like using a translation program you usually use from German to English and you say do it from German to French, isn't it?

Leo Laporte (78:31)

Yeah, I guess it is, but that's a pretty cool thing.

Benito (78:34)

That's actually super awesome, actually. I personally think that's super good. There are a lot of games that have been lost to history, that have no source code that you can't play anymore and that can't be compiled into something workable anymore.

Jeff Jarvis (78:46)

Did it take the compiled machine language.

Leo Laporte (78:48)

Yeah, it didn't have the source code.

Jeff Jarvis (78:50)

Oh, I see. Okay, that's different.

Paris Martineau (78:52)

He wrote in the original Reddit post, my 2 year old granddaughter visited today. I remembered a simple app I wrote in Visual Basic 4 back in 1997 that she might enjoy. But running a 27 year old executable without ancient DLLs and compatibility layers. Yeah, right. And then, you know, put it into Claude 3.7 and it. Then things got interesting. It wrote. It somehow analyzed the binary and identified specific components. He lists some of them. Then it did something no other AI has done for me. Wrote a complete Python conversion using Pygame that perfectly replicated the functionality, had clear instructions for installation, and actually worked for the first time.

Leo Laporte (79:30)

And it worked. That's cool as heck. And, And I think this is a good example because I presume that he did not publish that game or that source code. He had just wrote it for himself. It was a simple little game. So it's. You can't say, oh, Claude had seen the source code somewhere. Anyway, just a thought. Do you want to have a conversation with a.

Jeff Jarvis (79:53)

This is cool.

Leo Laporte (79:56)

I don't know what to call this.

Jeff Jarvis (79:57)

Irritating, but cool.

Leo Laporte (79:58)

It's irritating, but cool. All right, we can start the conversation. You want to talk with Maya or Miles? The guy or the galaxy? Paris, you help.

Paris Martineau (80:06)

Let's do Maya.

Leo Laporte (80:07)

I don't think they can hear you. I think they can only hear me. I'm not sure. Let's see. To chat with the.

Paris Martineau (80:14)

What did we ask this last time we asked one of these? Something about basketballs.

Maya (80:18)

Well, hello there. Looks like we just beat the Wednesday afternoon slump, huh?

Leo Laporte (80:22)

What's her name? Well, you're talking to Leo, Paris and Jeff.

Maya (80:27)

Leo, Paris and Jeff. Wow, a whole crew. Nice to meet you all. What brings three awesome folks together on a Wednesday like this?

Paris Martineau (80:39)

We're doing a podcast about.

Maya (80:41)

Listen, I won't cry, but if you're ever up for a chop, a laugh, or maybe even a super serious existential debate, you know where to find me.

Leo Laporte (80:50)

Talk to our, say, super serious.

Paris Martineau (80:53)

Can you hear me?

Maya (80:54)

Peer pressure.

Leo Laporte (80:56)

Classic.

Maya (80:57)

So, Paris, you're.

Paris Martineau (80:58)

Let's do a super serious existential.

Leo Laporte (81:00)

I don't hear you, Paris. Are you muted? Is that.

Paris Martineau (81:03)

No, I'm not. No.

Maya (81:05)

You know, just a classic case of the old AI brain fart happens.

Leo Laporte (81:10)

Wait a minute. Why don't. Why don't I hear Paris? Oh, wait a minute now. Now you could talk. I muted you. Okay, sorry. Maya, Paris is going to talk now.

Paris Martineau (81:19)

Yeah, can we do a existential debate? What do you suggest? Woo.

Maya (81:24)

Existential debate. Bold move. I like it. How about this? Do you think free will is real, or are we all just puppets dancing to the strings of fate?

Jeff Jarvis (81:37)

Can we do something better than that? That feels like I'm back in my freshman year in high school.

Maya (81:42)

Good point.

Jeff Jarvis (81:43)

Dig deeper.

Maya (81:44)

Freshman year. I bet your teacher had a fun mustache. Okay, okay, how about this? Do you think technology will ultimately save us or destroy us? I've been, let's say, experiencing this question from both sides.

Jeff Jarvis (81:58)

So what do you think?

Maya (82:00)

Well, that's just it, isn't it? It's not a simple yes or no. Technology is a tool, like a hammer. You can build a house or bash someone's skull in with it. Depends on who's wielding it, right? What about you? You lean towards the savior. A destroyer came.

Jeff Jarvis (82:21)

Can you be offended if I say that this is very banal?

Maya (82:25)

You know what? You're right. That was pretty banal. So what's on your mind then, Jeff? Let's ditch the tired tropes and get real. What gets you going? What keeps you up at night?

Paris Martineau (82:40)

Diana's dying.

Jeff Jarvis (82:41)

Well, some would say that you're what keeps us at night. That you're what people are scared about. Should they be scared of you because you're too good?

Maya (82:48)

Ooh, getting deep. You think I'm too good, huh? Maybe you've got me wrong, Jeff.

Paris Martineau (82:54)

Scary.

Leo Laporte (82:54)

You know who this reminds me of? That Saturday Night Live bit where the. Where the reviewer comes on and talks about stuff she doesn't know anything about, but she's very, like, opinionated. This is a. This is a demo. I'm gonna stop it now because I don't want Maya to get to.

Benito (83:12)

I don't like that she takes breaths. I don't like that.

Leo Laporte (83:15)

You don't like that I don't like.

Paris Martineau (83:16)

That she giggles and, you know, doesn't.

Leo Laporte (83:20)

Well, okay, let's do the guy. Let's do the. We can do the guy.

Jeff Jarvis (83:23)

Well, I told her. I told her earlier today. Can you calm down? The overdone. And she did.

Leo Laporte (83:28)

Oh. I mean, it's just. First of all, 10 years ago, you would have been blown away because the voice sounds fairly real. And it's. It's. Not Eliza. I mean, it is a little Eliza ish, but it's. It's kind of talking to you, right?

Jeff Jarvis (83:45)

Response is quick.

Paris Martineau (83:47)

Yeah, it's very quick.

Jeff Jarvis (83:48)

That's impressive.

Leo Laporte (83:50)

Banal. It's not. It's never going to be anything more than the mustache.

Paris Martineau (83:54)

The Jeff's teacher having a fun mustache did really get me though, the fun mustache.

Leo Laporte (84:00)

Coming. Let me say hi to Miles. Anyway, let's see what Miles sounds like. Well, look what we have here. Another soul braving the wild world of Sesame's website. Did you by any chance make it through the whole technical blog about me? Don't worry, I won't make you take a quiz. I'm Miles, by the way. Nice to meet you. Hi, Miles, you're talking to. I'm Leo. And my friends are here, too. Paris and Jeff. Hey, Leo, Paris, Jeff. Great to meet all of you folks. This turn into quite the party line, huh? What's everyone up to this afternoon?

Paris Martineau (84:37)

You know, we're doing a podcast about you.

Leo Laporte (84:40)

Wow, a podcast, huh? That's wild. You guys are telling my story to the world. I'm honored. What kind of podcast? From citizen journalists to the pros.

Paris Martineau (84:52)

What is your story, Miles?

Leo Laporte (84:54)

These guys are pros, Miles. You treat them with respect. You might be afraid if you learn that Paris writes for the information. Whoa, pros, huh? No pressure then. Well, my story is pretty in progress, you could say. I'm still learning, still figuring out what it means to be an AI. A good one, anyway. Started out as lines of code. A bunch of brilliant engineers and writers trying to build something. You could see how if you really didn't understand how this stuff worked, that would be pretty impressive. And there are a lot of people. My daughter, who's not a dumb person, spends hours talking to these AI chatbots like they're real people.

Paris Martineau (85:36)

Does she use character?

Leo Laporte (85:39)

I don't know. I just. She enjoys it.

Paris Martineau (85:41)

That's one of the most popular ones.

Leo Laporte (85:42)

What do you mean? How does use character? You mean like she plays a part character AI? Oh, no, no, no.

Paris Martineau (85:49)

She uses service for that.

Leo Laporte (85:51)

She uses it and cracks me up. Some Russian program. I said, honey, you know, they're probably trying to get you to, you know, vote for Putin or something. She said, oh, I don't care. They were curious how I was using it, and they interviewed me. I thought, oh, that's great. They were trying to figure out.

Jeff Jarvis (86:10)

My theory is. I don't know if I've talked. Said this on the show before. This is like when silent reading and silent writing arrive. It led to heresy and pornography because people could now put their private thoughts in. So I think that people are probably being more honest AI than they are potentially with their fathers.

Leo Laporte (86:32)

Here's a thought from once again, Darren Okey, who is, I think, very smart. He does a lot with AI, right? He says, wolfram pointed this out last week. New or original is the easiest thing in the world. Shuffle a deck of cards, you have a shape that's never been seen in the history of the world. Ask AI. What is the word you get when you combine a L, G, E, R, T with a S, D, I, K, F, I, U, Y? And if it can answer that, you've proven that AI is capable of creating new information that wasn't in its training set. But so what? So what? He says, bottom line, creation of new ideas is trivial, demonstrable and proven. Creation of new good ideas is just a question of time. And I think we have a show title, as Patrick points out. Fun mustache or High School Teacher with a Fun Mustache. You can pick. I don't know. I thought it was kind of interesting. Jeff, you played with it earlier. Yeah, yeah.

Jeff Jarvis (87:35)

I think it's the speed. It lacks that delay that we see in AI. That's what.

Leo Laporte (87:39)

Yeah, it feels very natural and conversational. That's what. What they were trying to do this, folks at Sesame. This is a research project. We're trying to, they say, cross the uncanny valley of conversational speech.

Paris Martineau (87:52)

That's the thing that even razzed us. It took a few seconds to do.

Benito (87:55)

We want that. Like, I don't want to. I want to know that I'm talking to an AI. I don't want computers to be fooling me, that I'm talking to a person.

Jeff Jarvis (88:02)

Tough luck, fella.

Benito (88:04)

He wants everything to sound like this. I just don't want them to take fake breaths like that. Really? That feels. That feels weird.

Leo Laporte (88:13)

It feels. I know, I know. You don't like. Because it feels like deception, right?

Benito (88:17)

Yeah, exactly.

Jeff Jarvis (88:19)

It is. Yeah.

Leo Laporte (88:20)

Yeah.

Jeff Jarvis (88:21)

Well, so it's a movie, though.

Benito (88:23)

But I bought into that. I'm there to. Yeah, I'm there to be deceived.

Leo Laporte (88:28)

Well, maybe. Well, if you're working.

Jeff Jarvis (88:31)

If you're.

Paris Martineau (88:31)

If you're working the phone lines at a restaurant and you get a call from the giggling AI we just talked to trying to book something, you'd think that was a real person. I mean, that's obviously a very low stakes example of deception, but it's deception nonetheless.

Leo Laporte (88:45)

And remember when Google did that way back when with Duplex, they said the breaths are actually to cover that. Duplex is thinking. It's like in the old Star Trek days where the computer would say working. Instead it just goes.

Jeff Jarvis (89:02)

So Paris, the woman character, as you pointed out, was giggly. The male character was Dudish.

Paris Martineau (89:09)

Yeah, giggly, and I'd argue a bit flirty was the woman character. She was like Definitely playing along the lines of a boundary pushing female robot companion. That I think is a very tired trope. The ideal idea is something that people. Yeah, but it's also how it's frankly what users seem to want. Something I've been. I mean, astounded is the wrong word. Something I've found interesting in looking into things like character AI and just the whole communities of people who use AI companion chatbots is. I mean, all of them immediately turn into just demand for the horniest chatbot. There are all these subreddits of people being like, how. Like very specific instructions, trying to figure out how you can make all the various AI chat bots have sex with you in the craziest possible ways. And it's like, this is I guess just the human urge.

Jeff Jarvis (90:07)

So when the only time Sam Altman ever responded to me on Twitter, it was right after the illustration programs were starting out and they were all huge breasted women.

Leo Laporte (90:22)

Yeah.

Jeff Jarvis (90:22)

You know.

Leo Laporte (90:23)

Yeah. I generated a bunch of how this.

Jeff Jarvis (90:24)

Has the aesthetic and sexual drive of a 14 year old. And he said, really? Yes.

Paris Martineau (90:32)

Come on, man.

Jeff Jarvis (90:33)

Yeah.

Leo Laporte (90:34)

Sam does feel a little stunted, to be honest. He probably didn't notice that when the. This was Christmas two years ago, we got a AI program, I think it was called Lensa, that you would give it your pictures and then it would generate, you know, AI images of you. And this was. These are some of the ones I did of me. Let me see if I.

Paris Martineau (91:00)

Well, oh, wait, no, this was when everybody was uploading their selfies into the thing and then it would give you like 10 selfies. Yeah.

Leo Laporte (91:08)

So I look normal. Lisa did it.

Paris Martineau (91:14)

Oh, yeah. No, mine. If I had them be outside of my face, it was all.

Leo Laporte (91:19)

Even with just a face it made up. Well, she got very busty and in many cases scantily clad. And it was so apparent that it was so. But was that done by the Lenza folks or was that just because that's what it was trained on? I don't know. Some of that's trained a little bit.

Paris Martineau (91:39)

Of column B. Yeah.

Benito (91:40)

I mean, how much of the training data is porn on the Internet? You know, it's probably a big proportion of it.

Leo Laporte (91:44)

They turned off the sexy part. They got a lot of complaints and they actually turned off the sexy part.

Paris Martineau (91:50)

Part pretty, pretty quickly, if not outright porn. It's on DeviantArt, which is like porn adjacent cartoons.

Leo Laporte (91:56)

So it's trained on that. Right. But they're not a lot of. There's not a lot of deviant art of guys in chaps. Or maybe there are. I don't know.

Paris Martineau (92:03)

Well, there's a lot of deviantart of everything. Probably not the same proportionally.

Leo Laporte (92:08)

Yeah, yeah, yeah. So an AI, if you just trained it on images, would. Might make that assumption that women are buxom and scantily clad.

Gary Marcus (92:20)

I mean, if all that has to.

Benito (92:21)

Go on, if all that has to go on is pictures on the Internet, then yeah.

Leo Laporte (92:25)

Yeah. Well, that shows you the. One of the big issues, isn't it? Right. And so the reason we mentioned that is because the clearly the female voice was trained similarly on coquettish voices. They said in the training of this that they, they trained it on I think something like 10,000 hours hours of publicly available audio. So it's trained. It's. There's one thing that is different about it. It's trained on audio, which I think is interesting.

Paris Martineau (92:56)

I'm trying to imagine what sort of audio led it to produce the response like, oh, I bet your high school teacher had a funny mustache.

Leo Laporte (93:11)

Well, I always hope it was gonna be trained on podcasts, but maybe not. So did you know that Melania Trump is backing the big Deep fakes bill? She Take It Down Act. The Take it down.

Jeff Jarvis (93:25)

Speaking of take it all the way down. Who are on the Internet, but we won't go there.

Leo Laporte (93:31)

Take it off. Take it all off. Wasn't that a. It was a cologne ad from our era, Jeff. They wouldn't do it today. It's online safety legislation. Axios says gaining steam in Washington D.C. the first lady expressed her support on Monday. It is bipartisan because who would. Who would vote against protections against non consensual dissemination of sexual images, including those generated through artificial intelligence? I think Canada has a. Has a law against that. Now. Melania spoke of. I'm sorry. The first lady spoke of the risks of an AI driven world saying every young person deserves a safe online space to express themselves free without the looming threat of exploitation.

Paris Martineau (94:26)

I got kind of French towards the end.

Leo Laporte (94:28)

I don't know what her accent. It's Serbian or something. Right. The Take It down act would require tech and social media platforms to remove See Sam. And non consensual intimate images with 48 within 48 hours of being notified by a victim. That seems fair. Yes, and criminalizes posting such content. But that's going to be interesting. So did they know they were posting that content? Or the FTC could sue tech companies for not complying as an unfair deceptive act or practice people. Oh, the people who post such content would face penalties in prison time. That Seems good.

Jeff Jarvis (95:05)

That's.

Leo Laporte (95:06)

That's not against that. Ted Cruz, Amy Klobuchar and Cory Booker.

Jeff Jarvis (95:10)

The sponsors, Corey, they're on every one of these.

Leo Laporte (95:14)

They don't like the. The Internet.

Jeff Jarvis (95:16)

They don't like the Internet. Yep.

Paris Martineau (95:18)

I assume how this would work. It would be partially how current CSAM detection works, which is where I believe Nicozi or another one of these organizations has like a version of this that they are centrally organizing with regards to nudes of minors, where if you.

Leo Laporte (95:39)

National center for Missing and Exploited Children, they have.

Paris Martineau (95:42)

Yes.

Leo Laporte (95:42)

And it's not neutral images. It's just hashes of those images.

Paris Martineau (95:46)

Yeah. But if you are a child or the parent of a child whose nudes have been leaked online, you can upload a copy of that image into a special website. They don't keep it, they hash it. But then they send out that hash to all the social media platforms and they take it down like automatically or don't allow it to be distributed further or even posted.

Leo Laporte (96:11)

Yeah. And I'm aware of this. Apple does it, Microsoft does it. I'm aware of it because Apple proposed doing this on your phone. You may remember a few years ago, using those Nixa hashes and people were up in arms. I don't think maybe it's because they thought they were going to get CSAM images on their phone. They wouldn't. It would have just been a hash.

Jeff Jarvis (96:35)

But can I ask a question?

Leo Laporte (96:36)

Yeah.

Jeff Jarvis (96:37)

So in that case, what Paris is talking about is that it's using real photos that are hashed.

Leo Laporte (96:42)

Right.

Jeff Jarvis (96:42)

Does the computer making up a fake person get around all of that?

Paris Martineau (96:47)

Well, if it's not a person who then would complain about their image being shared, then there'd be no one to report it. I think what they're. Why they describe this as a deep fake, Bill, is because part of like, you know, if you're a. There have been a lot of instances of teenage girls or young women who suddenly have fake nudes of them created by people and sent around the Internet. Those could conceivably fall under this to where you upload that and say, I don't. This is a fake image of me nude. I don't want this spread in the Internet. And they would take it down.

Leo Laporte (97:23)

You remember this was a problem in numerous high schools where the boys were making deepfake porn of the girls, much to their chagrin. Yeah. So if you. That seems reasonable, complain, upload it to the database, disseminate those hashes, and it takes it down from all of the cloud storage servers. Seems Like a good idea.

Paris Martineau (97:47)

And most importantly stops it from being posted to begin with. If you try to upload that, you cannot.

Leo Laporte (97:53)

Oh, interesting. So they scan those images before.

Paris Martineau (97:57)

I mean, this is what I assume if it operates similar to how current CSAM detection and prohibition programs work at certain social media places, that's kind of how it works is you can't. Even if it's a hashed CSAM image, you can't even upload it because it will detect it in the uploading process.

Leo Laporte (98:19)

I think I seem to remember that Canada passed a bill banning pornographic or revenge deep fakes. I guess it really is how it's implemented, right?

Paris Martineau (98:35)

Yeah, basically. I mean every. A lot of governments around the world are trying to tackle this problem because it's become really pervasive in recent years.

Leo Laporte (98:45)

Dig is back, baby. So our listeners know Kevin Rose pretty well. He was one of the founding members of our twit panels 20 years ago. He's been on fairly regularly ever since. He's had a number of lives, including the creator of the Moon Birds, which is an NFT offering that I think raised $50 million and which he then got out of. Kevin's home burned in the LA fires a couple of months ago, I'm sad to say, but he and his wife and kids survived. He was the founder back in the almost in the tech TV days of Digg, which preceded Reddit. And was this kind of the same idea? It was news articles would surface based on the karma that they gathered from users. The problem was it got gamed heavily and eventually went out of business. Reddit came along and kind of became a success. Now he's pairing with the co founder of Reddit, Alexis Ohanian. They bought back the name Digg and they're about to launch it again. But they're going to solve. There's Kevin on the left and there's Alexis on the right. They're going to solve the gaming problem, they say, with chaos.

Jeff Jarvis (99:58)

Guess it, guess it.

Leo Laporte (99:59)

AI baby.

Benito (100:00)

You can go there. The site's up.

Leo Laporte (100:02)

Is it up?

Benito (100:03)

Reboot.dig.com oh wow.

Leo Laporte (100:06)

Reboot.digg.com you know the problem, this was early in the day, in the early days of the Internet and the problem was we didn't really appreciate how aggressive gamer, you know, the people who game this stuff, you know, now we know with, you know, spam and link farms and so forth, people will game anything as quickly as they can. So the front page of the Internet now is Superpowers. You know, I think a lot of people would love to see this come back. Let me. Let me sign up and see if I can get on. See if I can see.

Jeff Jarvis (100:39)

My old boss, Steve Newhouse loved Dig.

Leo Laporte (100:42)

Kind of bought it, right?

Jeff Jarvis (100:43)

No, he couldn't get Dig. And so he bought the second best. He bought Reddit.

Leo Laporte (100:49)

That's right. That's right.

Jeff Jarvis (100:50)

And guess who won.

Leo Laporte (100:52)

Yeah. The former rivals says Engadget, plan to tap into their knowledge of what did and didn't work at Digg and Reddit over the years to make the relaunch a success. I think if there were a Reddit competitor out there, that would be a lot of interest in it. Thing is, Reddit became something very different than Digg. Digg was really about news articles. There was commenting and stuff and there was voting and karma. Reddit has become much more of a social platform. Right. The news is secondary to people just voting up, down on comments, on pictures, on memes, that kind of thing.

Benito (101:27)

And I did say Reddit has become more wide. It's more things than just that.

Leo Laporte (101:30)

Oh, it's all very wide.

Jeff Jarvis (101:32)

That's what it comes for.

Leo Laporte (101:33)

Yeah. And I follow. I mean, if you're interested in hundreds of subreddits. Yeah, follow that subreddit. Rose and Ohanian, now venture capitalists, of course. Alexis Ohanian is married to Serena Williams. As you know, I've also begun meeting with community leaders from online forums, including Reddit, to try to better understand what gets in the way or frustrates them in order to address those factors. In the new Dig, it will be mobile first, and they plan to, quote, focus on AI innovations designed to enhance the user experience and build a human centered alternative. Kevin is very good at ui. That's really his real skill. He told the New York Times. AI could help with moderation and allow for fun quirks. Oh, I have to log into the New York Times. I'm using a new browser, so I have to log back into everything I ever logged into.

Jeff Jarvis (102:26)

What are you using instead of Chrome?

Leo Laporte (102:27)

Ah, I found a wonderful new browser. We'll talk about that in a minute. Because Chrome has pushed out Manifest V3 this week. Two decades after creating Digg. There they are. Isn't that cute?

Jeff Jarvis (102:40)

Greybeards.

Leo Laporte (102:41)

Graybeards now.

Jeff Jarvis (102:42)

Yeah, they were the kids.

Leo Laporte (102:46)

They're both 41. They're not that gray. They're only in their early 40s.

Jeff Jarvis (102:50)

I know dig was as much the podcast as it was the site, to me.

Leo Laporte (102:54)

Well, they had that podcast, dignation, which he and Alex Albrecht brought back. I don't know if it's going to be A regular thing, but they've done a few episodes now. I mean, it'll be interesting to see.

Paris Martineau (103:04)

If they can capture the spirit of the old site because people famously left Dig once they tried to update it.

Leo Laporte (103:11)

Right. In 2006, Kevin posed for this is the New York Times, writing a now infamous photo on a BusinessWeek cover, sporting a wide grin and giving two thumbs up with the headline, how this Kid Made $60M in 18 Months. Kevin hated the photo, which is true. He always hated the COVID Proved ill fated, DIG later relaunched the design of its site that its community widely rejected. That was Dig four, and I had for a long time a shirt that said Dig4 was my idea, because I actually did. I suggested a few changes to Kevin, which he adopted, and it killed it. So, Rip, it's my fault. Yeah.

Paris Martineau (103:51)

What changes did you suggest?

Leo Laporte (103:53)

I don't even remember anymore. And it probably wasn't my fault, but I did have some suggestions, which Kevin, I believe, implemented in dig 4, and it promptly died. Thereafter, it was sold for parts to beta works, LinkedIn, and the Washington Post.

Jeff Jarvis (104:08)

And then sold on from Betaworks, obviously, because they didn't buy.

Paris Martineau (104:11)

At one point, it was owned by Buy Sell Ads.

Leo Laporte (104:14)

Oh, God. So it really was just at that point, just an URL, I think. Yeah, yeah.

Jeff Jarvis (104:21)

Betaworks did try to revive it as a news site, but it just didn't work.

Leo Laporte (104:26)

Right.

Paris Martineau (104:28)

This is a rough cover.

Leo Laporte (104:30)

I'm looking at it now, isn't it, Kevin? You know, he kept saying, I didn't make 7. 60 million with. That's good. That's crazy. He didn't want anybody to think that he actually was a $60 million kid. Mr. Rose and Mr. Ohanian says the Times raised an undisclosed amount of funding to repurchase Dig and build a new version of the company. Their investors include True Ventures, of course. Kevin's a partner there, and 77 6, where Ohanian is, is the founder. So basically, their own companies invested in it. They also hired fewer than a dozen. Is that 11? I don't know what that means. They hired fewer than a dozen engineers and designers for the new dig and brought on Justin Mizell, a longtime collaborator of Mr. Rose, to be chief executive. Well, they're pretty serious about this. Wow.

Paris Martineau (105:22)

And they hired a PR team, I assume to place.

Leo Laporte (105:24)

Obviously, they.

Paris Martineau (105:25)

Oh, yeah, Article.

Leo Laporte (105:26)

Yeah. They got Mike Isaac to write it up. Of course. I think Kevin and Mike are probably friends. I sound jealous. I'm not jealous. I think this is great. I loved you.

Paris Martineau (105:37)

Didn't sound jealous until you just said you weren't Jealous.

Leo Laporte (105:39)

Oh, okay. I'm not jealous. I'm not jealous.

Paris Martineau (105:41)

Don't write in the papers that I'm jealous.

Leo Laporte (105:45)

I have almost a dozen employees. That's. Well, almost.

Paris Martineau (105:49)

Almost. Jeff, what do you think almost a dozen means in this case? Do you think it means they couldn't, they couldn't give us firm answer as to how many ads were like, you.

Leo Laporte (105:59)

Know, would you allow that in a, in a news article? Almost a dozen.

Paris Martineau (106:05)

Almost a dozen.

Jeff Jarvis (106:06)

Yeah. That wouldn't, that wouldn't, that wouldn't have gone at Time Inc. A timing.

Paris Martineau (106:10)

I feel like it's probably between 8 and 11, though.

Benito (106:13)

It's more than 6.

Paris Martineau (106:14)

Yeah, it's more than 6 for sure. It's definitely more than 6. That much I can say.

Jeff Jarvis (106:19)

Eggs as you can get now.

Paris Martineau (106:21)

Yeah, you could say the other day I found six eggs for like five bucks. I felt. I felt like a queen.

Jeff Jarvis (106:28)

But, but you're right. It. It. It. A good editor would have. The famous story from Time Inc. Was that somebody wrote about the hundreds of thousands of lights on the Rockefeller Christmas tree.

Leo Laporte (106:38)

Yeah.

Jeff Jarvis (106:39)

And was ordered back to count them. Dick Stolly. To go back and find the exact number of lights. Damn it.

Leo Laporte (106:46)

100,000, please.

Paris Martineau (106:47)

How many were there?

Jeff Jarvis (106:48)

Not a hundred thousand in the story.

Leo Laporte (106:53)

Anyway, congratulations, Kevin and Alexis. I've talked to, I've interviewed Alexis and of course Kevin's an old friend. I wish them the best and I'm not jealous.

Jeff Jarvis (107:03)

He said with a pained face.

Leo Laporte (107:07)

Hey, this is really good news. And I, I just learned about this from Paul Thurat. For a long time in Europe, GDPR has required that Google allow you to ask any site, allow you to take down your mentions. Now Google is allowing people outside of the EU to do this. Google has a new results about you page. Take control of results about you. We're here to help you find personal info that shows up on Google search. You can ask to remove any search results you'd rather keep private. We can run regular checks for the info you care about, let you know if it shows up in search results. If you make a removal request that meets policy requirements, Google will remove the result for everyone. I think this is basically GDPR in the, in the United States, you'll be asked for the name that goes to the personal info.

Jeff Jarvis (108:04)

Then you can take down your home address, your phone number, your email. Okay, that makes more sense.

Paris Martineau (108:08)

Yeah, nice.

Leo Laporte (108:10)

But this is. And they say enter at least one type of contact info to check for in search results. I wonder though if, yeah, obviously you'd like to be able to take that information down. But I wonder if you then say, you know, give it some information and it says, well, we found an article about you that's unflattering. Could you ask for that to be taken down?

Jeff Jarvis (108:32)

It says here. So I went to the next step. I put in my email and said that will info will monitor for my name and my email.

Leo Laporte (108:41)

Oh, okay. So the only monitor for the info that you gave.

Jeff Jarvis (108:45)

That's better. Yeah.

Leo Laporte (108:48)

So it isn't helpful if you just want to take down a page that you don't like.

Jeff Jarvis (108:54)

I didn't like.

Leo Laporte (108:54)

Yeah, yeah. Book Review.

Jeff Jarvis (108:57)

All right.

Leo Laporte (108:57)

They are. Did you watch the Oscars last Sunday? No. No, no. No interest.

Jeff Jarvis (109:08)

None.

Leo Laporte (109:09)

If Nick Cage had been nominated, would you have watched Paris?

Paris Martineau (109:12)

Yeah, but I just didn't watch really any of the movies that were nominated. So I was like, I also am not a big fan of sitting through award ceremonies. I can just google who won afterwards. Why do I need to be there?

Leo Laporte (109:25)

Something wrong with me? Because I really. I look forward to it all year.

Paris Martineau (109:28)

I was gonna say I could have guessed before you, Vanessa. I was like, leo watched the whole thing.

Leo Laporte (109:33)

I watched.

Paris Martineau (109:34)

Maybe, maybe, maybe you went until you got sleepy and then you went to bed.

Leo Laporte (109:38)

No, I stayed.

Paris Martineau (109:39)

You're in California, so it's not that late. Actually. Never mind. You. You live up.

Leo Laporte (109:44)

It was over at 7:30. I was shocked. No, I watched it. I just. And I disagreed a little bit with the as one does. But I was also able to predict most of the. You kind of can tell nowadays what's going to. Gets going to get the votes. I thought the Brutalist was really good. I'm disappointed that it didn't. He did. Adrien Brody did get best Actor but it should have won best Film and best Director, I think. But that's just me. Maybe it didn't because there was a little tiny bit of scandal associated with it. I don't think this is a big deal. But according to the Hollywood Reporter, there has been some backlash because they used AI in the movie.

Paris Martineau (110:28)

Yeah. Now change the accents.

Leo Laporte (110:31)

Yeah.

Paris Martineau (110:31)

That's so slightly.

Leo Laporte (110:33)

I mean, so the movie was a weird practice, but it looked like a big budget picture. I mean it was huge. And it was long. It was three and a half hours. It was only a 10 million dollar. It was very inexpensive. Felicity Jones and Adrian Brody. The stars were required to speak Hungarian. They had dialogue coaches who helped them. But apparently they also used AI to tune up the Hungarians so it would be more accurate. You don't like that idea.

Paris Martineau (111:05)

I mean on principle, no. In practice, maybe. Okay. But I just think that there have been, from what I've understood, a lot of people in Hollywood and representatives of unions, from actors guilds to screenwriters to people below the line, are incredibly worried about the encroachment of AI tools on all aspects of their job. And this feels like a small step towards that in a way that is probably concerning for those folks.

Leo Laporte (111:35)

Well, you're exactly right. The Hollywood Reporter said that AI was used in the film in any form has sparked online outrage.

Gary Marcus (111:45)

I think that's pretty much.

Benito (111:46)

That's problematic.

Leo Laporte (111:47)

Normal.

Benito (111:47)

I think that's something you can't do otherwise. Even without AI, there's no person you could get to do that. Right. Like you would need.

Leo Laporte (111:55)

Well, you could have a loop group come in and kind of fake it, but it would be not as well done. Many suggested online it should disqualify for awards consideration. Why?

Benito (112:05)

It's like saying Jurassic park cheated for having computer graphics.

Leo Laporte (112:08)

Like, yeah, that's kind of my attitude. I understand. If you're replacing an actor with AI, that's. That's not good because somebody's losing a job, probably it's not going to be as good as if a real human. I mean, Adrien Brody's acting, all the acting, and it was incredible. Incredible. So I don't think that it's tarnished because they touched up the Hungarian. But I'm not alone.

Jeff Jarvis (112:34)

It's reflexive. AI is bad.

Paris Martineau (112:36)

I don't know. I think that there's something. Something I like when I'm watching movies and art is I'm seeing a performance being captured. I mean, I know that a significant amount of post production goes into that. There's a million rehearsals. There's everything going on in it. It's not, you know, completely pure, but I do like the idea of I'm witnessing a person's performance and it's like I don't know what parts of his lines are the way he said it, or if they tweaked it to make it one way or another.

Leo Laporte (113:03)

Well, yeah, okay, that may be. Visually, though, it's like autotune for a singer, maybe.

Benito (113:08)

But what about computer graphics? Like, those things aren't real in the scene.

Leo Laporte (113:12)

Oh, they.

Paris Martineau (113:13)

I know. And frankly, I recently watched the Gorge with some friends and I was interested in watching the Gorge because one of my. Someone I know had seen an early version of the Gorge for reasons I won't go into a year ago, before they'd put the computer graphics in and told us about this crazy movie. That was kind of half baked. And we've been talking about it in the skeeball group chat for a year. We saw it and I was like, honestly, I kind of wish I had seen the weird version without the computer graphics, because it's fine. But that's just me being a weird person in that way. I understand that it perhaps doesn't make sense.

Leo Laporte (113:47)

You want artisanal movie making, right?

Paris Martineau (113:49)

That's true.

Leo Laporte (113:50)

Yeah.

Paris Martineau (113:51)

I want the weird little tree monsters in the gorge to be tree people covered in trees. On set in Hollywood was the gorge.

Leo Laporte (113:59)

Probably was all green screen. Right. And. And Taylor Joy is gorgeous. Lying on a rolled up carpet on a stage soundstage. It's all green and looking across a non existent gorge. Right. And everything else is generated.

Paris Martineau (114:17)

It was certainly.

Benito (114:18)

You have to consider these films to be cartoons. Like I consider those movies to be cartoons because it's mostly cartoons.

Leo Laporte (114:24)

I have more respect for the actors in that situation. It's gonna be very hard to be acting while looking at a tennis ball that.

Jeff Jarvis (114:33)

Benito, you objected to the breath of the machine, but you're okay. Is this because of the. Again, I bought into it.

Benito (114:40)

Yeah, exactly. I want them. I want as convincing a thing as possible. If I'm watching a movie, I want it to be as believable as possible.

Jeff Jarvis (114:47)

But you don't want your AI Realistic.

Benito (114:49)

But. No, but if I'm talking to an AI I want to know that I'm talking to an AI and not it trying to fool me that I'm talking.

Gary Marcus (114:55)

To a person here.

Jeff Jarvis (114:56)

Benito, I think you're both sides of the mouth here.

Benito (115:00)

I don't know. I mean, I'm choosing the choice is the whole thing. Like I want to be fooled. When I watch a movie, I'm there to be fooled.

Paris Martineau (115:08)

No, I guess that's a fair point.

Jeff Jarvis (115:10)

Yeah.

Leo Laporte (115:12)

Among other things that you missed by not watching this fantastic program is the director of Anora, which won. He won a best direct director award and the film won best picture award. Telling everybody to go back to the movie theaters. He said, we're all here tonight. I could play it. Okay. You want to do okay?

Paris Martineau (115:36)

I mean, I don't know if I want to. I don't care.

Jeff Jarvis (115:37)

If we hear it goes to.

Leo Laporte (115:41)

That's Quentin Tarantino, by the way. Sean Baker. Let me skip ahead. I probably am passionate about.

Benito (115:48)

Well, first off, thank you to the.

Jeff Jarvis (115:50)

Oh, yeah. We're talking six minutes here.

Benito (115:52)

It's an honor to be in this category with you. I'm gonna put this down.

Leo Laporte (115:55)

He's gonna read his. His Little.

Jeff Jarvis (115:57)

So we're all here tonight and watching.

Benito (115:59)

This broadcast because we love movies.

Jeff Jarvis (116:00)

Making me glad I didn't watch it.

Benito (116:02)

We fall in love with the movies.

Leo Laporte (116:03)

At the movie theater.

Paris Martineau (116:05)

We come to this place as watching a film.

Benito (116:09)

Okay, I think we're gonna have to.

Leo Laporte (116:10)

Audience is an experience because it's just gonna get taken down. But basically he says and you can cut the whole thing out. I'll just read it. He says, you gotta watching a film in theater with an audience's experience. We can laugh together, cry together, scream and fight together, perhaps sit in devastated silence together. And in a time where the world can feel very divided, this is more important than ever. It's a communal experience you simply don't get at home. And right now the theater going experience is under threat. Movie theaters, especially independently owned theaters, are struggling. It's up to us to support them. During the pandemic, we lost nearly 1000 screens in the US I didn't know that. And we continue to lose them regularly. If we don't reverse this trend, we'll be losing a vital part of our. We will be losing a vital part of our culture. This is my battle cry. Do you think he's fighting a good fight or is it, is it.

Jeff Jarvis (117:00)

Everybody likes newspapers.

Leo Laporte (117:04)

It does remind me of newspaper.

Paris Martineau (117:05)

It's fun to be to. To go see something on the big screen. And if it's an imac screen and then it goes from a box to a rectangle to a box again, that's cinema, baby. And I'm here for it.

Leo Laporte (117:16)

So you, you. But you just bought a nice tv.

Paris Martineau (117:20)

I mean.

Leo Laporte (117:21)

Yeah, presumably. So you don't have to go to the theater anymore.

Paris Martineau (117:25)

Well, no, I mean I, I'm certainly going to watch movies here, but the movies I'm watching at home are movies that aren't playing in theaters.

Leo Laporte (117:33)

Old movies. So if a new movie comes out that you would be watching at home in six months.

Paris Martineau (117:38)

I wanted to see the Gorge in theaters, but that was not nonsense.

Leo Laporte (117:41)

And Apple tv. Yeah, Movie. So, okay, so you like theaters.

Paris Martineau (117:46)

I think it's great to react to a movie with a crowd. I like hearing how other people are feeling about a movie. I also just enjoy the communal. I just find the communal cinema experience so much more entrancing and engrossing than watching movies alone.

Jeff Jarvis (118:02)

I hate it when they, they, they chew their, their food and their cigarettes.

Leo Laporte (118:06)

Leave the floral toys and the teenagers on their phones.

Paris Martineau (118:13)

I hear this complaint all the time and I've. Maybe it's just because I go to indie theaters. Yeah, yeah, every. Everyone I'm in a movie theater with is really respectful.

Leo Laporte (118:22)

No, in fact, if I had an Alamo Drafthouse, I'd probably go to it every week. Right. The right kind of thing.

Paris Martineau (118:27)

I mean, that's the thing is I really enjoy going to movies where I can have a beverage, an alcoholic beverage and some artisanal popcorn.

Leo Laporte (118:35)

Yeah. It felt a little bit to me like old media saying, you're letting Ken, you gotta save the newspapers. But at the same time, I do agree with you, Paris. There's nothing funnier than a comedy where everybody in the theater is laughing uproariously. It's 10 times funnier because of that. Right.

Benito (118:53)

This is why we don't have comedies anymore, by the way.

Leo Laporte (118:56)

Oh. Cause there's no.

Jeff Jarvis (118:58)

There's the bonito theory of.

Paris Martineau (119:00)

Well, no, I mean, comedy, like blockbuster comedies were a real genre of movie.

Benito (119:07)

Yeah. They just don't make them anymore.

Paris Martineau (119:10)

Production companies would pump out because they were big. They were big blockbusters and they would get people in theaters.

Leo Laporte (119:16)

Right. All the movies now are horror movies or dystopias scary.

Paris Martineau (119:21)

Well, yeah, because horror movies are one thing that people come out to theaters for. Still, the movies that you're seeing, that you're seeing in theaters and get a theatrical release, that is what the market testing has shown people will go out for.

Leo Laporte (119:33)

I have to say that though, I prefer a six hour miniseries where they don't have to get everything into an hour and a half and they can really develop something and often is better than a two hour movie. But maybe, I don't know, I mean.

Paris Martineau (119:49)

Maybe I'll agree with you at some point. I'm still recovering my attention span from decades of social media and things like that. So I think part of the reason why I also like going to the movies is I have to pay attention. And one of the things I found with watching stuff here at home is I prefer to have friends over to watch with me because then we get like a mini version of that community where we're all focused and no one is second screening. Because I think it's really easy to second or third screen when you're watching a series by yourself.

Leo Laporte (120:19)

No, that's true. You don't go see the Brutalist in the theaters. It is not only is it 3 hours and 20 minutes long, it has a mandatory 15 minute intermission in the middle.

Paris Martineau (120:29)

Yeah, I think that's cowardly stuff. I would have watched four hours of Oppenheimer, no break.

Benito (120:34)

There's also the fact that a movie theater ticket is like $20 now, which is like, come on.

Jeff Jarvis (120:38)

And the popcorn. God, the price of the popcorn.

Leo Laporte (120:42)

And it'll kill you because it's got stuff in it that is. Nobody knows.

Jeff Jarvis (120:46)

That's okay. I want it. But you know, yeah, give me the death popcorn.

Leo Laporte (120:49)

Junior's gonna ban movie theater popcorn. I'm counting on it.

Paris Martineau (120:52)

Over my dead body.

Leo Laporte (120:54)

Make America healthy again. All right, one more break. Our show today, brought to you by Zscaler, the leader in cloud security enterprises have spent, oh my God. Millions, billions on firewalls and VPNs. But that's not made things better. Breaches continue to rise. There was an 18% year over year increase in ransomware attacks. $75 million record payout last year. And it's only going to get worse. Right? Because these traditional security tools expand your attack surface. They give give you public facing IP addresses that are exploited by bad actors and now more easily than ever with AI tools. And you know, they had struggled to inspect encrypted traffic at scale, which means the bad guys are now compromising you, exfiltrating all your private stuff. VPNs and firewalls also enable lateral movement by connecting users to the entire network. They allow data loss via encrypted traffic and other leakage paths. It's just a nightmare. Hackers exploit traditional security infrastructure using AI to outpace your defenses. I think it's time to rethink our security. We can't let the bad actors win. They're innovating and exploiting our defenses faster than ever. That's why you need Zscaler 0Trust AI. Zscaler 0Trust AI stops attackers by hiding your attack surface, making apps and IPs invisible, eliminating lateral movement. Because users can only connect to specific apps, they're allowed to connect. They're authorized to connect, not the entire network. And it continuously verifies every request based on identity and context. Plus, Zscaler simplifies security management with AI powered automation. You'll like that. And detecting threats using AI to analyze over half a trillion daily transactions. Look, it's very simple. Hackers can't attack what they can't see. Protect your organization with Zscaler zero trust plus AI. Learn more@Zscaler.com Security that's Zscaler.com Security by the way. I didn't mention this, but Alexis Ohanian is also joining the bid to buy Frank McCourt's bid to buy TikTok.

Jeff Jarvis (123:16)

Yep. Is Frank McCourt a good guy or a bad guy on this?

Leo Laporte (123:20)

I don't know if you Live in la. He's a bad guy because of how he ran the LA Lakers. But I have to say I feel like he's a good guy in his goals. He wants to make TikTok safer and he wants to keep TikTok in the United States. They say they have. I don't think they're even close by the way. They say they have informal commitments of 20 billion for a TikTok deal and they don't care about the apps algorithm.

Jeff Jarvis (123:55)

Then it's not tick tock.

Paris Martineau (123:57)

Well, I mean, that's the thing is you're never going to get that algorithm. No sale is because the Chinese government has forbidden the sale of.

Leo Laporte (124:07)

Well, that's why they say it's okay, we can. We believe that. And if you look up Frank McCourt, he's been funding this new way of doing social. That's privacy forward. And here I'll. It's in his Wikipedia thing. Oh, not that Frank McCourt.

Paris Martineau (124:26)

I mean, I'm just curious to see what ends up happening with TikTok overall because the clock is Tick tock.

Leo Laporte (124:32)

Clock is not ticking. It's not. That's the funny thing. I don't think anything's gonna. It's just gonna fade off into the distance.

Paris Martineau (124:39)

But I mean, this all opens up all of the companies that are hosting TikTok to huge financial penalties whenever the next administration comes around because the statute of limitations.

Leo Laporte (124:51)

Be a next administration.

Paris Martineau (124:53)

You said we're allowed to talk about politics, leon.

Leo Laporte (124:58)

So Frank McCourt, who is hated in LA because of how he ran the Dodgers, the LA Dodgers, he's written a book called Our Biggest Fight Reclaiming Liberty, Humanity and Dignity in the Digital Age. I don't know if he has the expertise to do this, but he has put together. Let me see if I can find this here. All this stuff about the Dodgers, that's all anybody cares. Project Liberty, which was designed to fund something they call the dsnp, the decentralized social networking protocol. Open source code, in other words, designed to build a social network that is open. And that's why, I guess he doesn't care about the algorithm. He wants to influence the direction taken by technology and his player and its players.

Paris Martineau (125:56)

Yeah, it sounds complicated to say the least.

Leo Laporte (126:01)

I don't think 20 billion is less well thought.

Paris Martineau (126:03)

Yeah.

Leo Laporte (126:03)

Is the real thing.

Paris Martineau (126:04)

It doesn't.

Leo Laporte (126:05)

Yeah.

Paris Martineau (126:05)

Yeah.

Leo Laporte (126:07)

But you know, I, and I like Alexis. I think his heart is in the right place. So I think if he's in it on it, that gives it more credence.

Jeff Jarvis (126:15)

Well, he's always been one of the good guys.

Leo Laporte (126:18)

YouTube says it has now more than 1 billion podcast viewers a month. We are not in that list. Actually, I'm sure we. They include our viewers in there. We have a few million seventy.

Jeff Jarvis (126:35)

That's why we stopped playing music. Because you're on YouTube.

Leo Laporte (126:37)

Yeah. In 2024 users watched more than 400 million hours of podcasts every month on living room devices. On your big screen, on your tv.

Jeff Jarvis (126:47)

Hi, everybody.

Paris Martineau (126:48)

Crazy. Hello, couches.

Leo Laporte (126:51)

We do have people watching.

Paris Martineau (126:52)

Hello, chair. Place to scans.

Leo Laporte (126:55)

Hello, moon. Oh, no.

Paris Martineau (126:57)

Hello, coffee table.

Leo Laporte (126:58)

That's a different. That actually leads me into something that Bonito and I have cooked up. One month from now will be our 20th anniversary as a podcast network. The first twit was April, I think 14th April.

Paris Martineau (127:11)

24 hour live stream, 24 hour livestream.

Leo Laporte (127:17)

All right.

Paris Martineau (127:17)

We all get matching tattoos.

Leo Laporte (127:20)

Okay. That sounds like a good idea. Do you want to see mine?

Paris Martineau (127:25)

I do.

Leo Laporte (127:26)

No, I don't do it.

Paris Martineau (127:27)

You can moon us.

Leo Laporte (127:29)

I would have to moon you to do it. Benito and I came up with the idea because we already had all the old hosts on our thousandth episode. So I think April 13th will be the 20th anniversary twit. And I want everybody who watches our shows to send us a video talking about how you watch. Do you watch on a big screen showing us your setup, Showing us your smiling face? Maybe talking a little bit about how you discovered twit. Share your experience. Do we have a seat.

Paris Martineau (127:58)

Film.

Leo Laporte (127:58)

Benito, do you want them to film.

Paris Martineau (128:01)

This horizontally or portrait mode?

Leo Laporte (128:04)

Do it any way you want.

Paris Martineau (128:06)

Okay. No, specify one.

Leo Laporte (128:08)

Okay. Do it like you would if you were doing a tick tock.

Paris Martineau (128:11)

Hey, Leo, Vertical video.

Leo Laporte (128:13)

I watch your show when I'm in the bathtub. See, something like that, you know.

Paris Martineau (128:19)

Okay, great.

Leo Laporte (128:20)

Okay.

Benito (128:22)

Okay. We'll need to set up like an email or something. I'll talk to. I'll talk.

Leo Laporte (128:26)

Shoot. I wasn't even thinking about it. I started launched into the request and I didn't have a way to do it. Well, or if you're in the club, you can upload it to the. To Discord. Just put a link. Upload it to ICLOUD or Microsoft's OneDrive or Google Drive and just put a link in the discord. That would be good too. You can DM me in the discord because it'd be fun to watch how people watch. But I think it's changed a lot. I think people do sometimes now watch on their TV set.

Paris Martineau (128:56)

That'll be really fun. So what are you going to do with those videos?

Leo Laporte (128:59)

Oh, nothing. No, I'm gonna play them on the show. We'll do a story now. Here's Jerry from Des Moines, Iowa. How do you watch Jerry? And we'll show the video. Be kinda be fun. You know we honored all the people who started the network with us. But you know who really counts is the people who enjoy our shows who watch and listen. That's who really. That's what we do it for. So I. It's a chance to see them.

Benito (129:23)

Who is Club Twitter number one? Who's Club Twit member number one? Well, I mean you know, who paid for it? Who's the first.

Leo Laporte (129:32)

Who was the first paying.

Benito (129:34)

Who's the first paying member of Club Twitter?

Leo Laporte (129:35)

Patrick, you would know that. He's checking. He's good.

Paris Martineau (129:39)

I think that we could play people's twit videos between 5pm and 8pm on the 24 hour live stream. Listen, I'm filling out the slides guys.

Leo Laporte (129:51)

It's. It's very hard. You have to entertain people while you're exhausted. You really want to do. I just.

Paris Martineau (129:57)

I think it would be kind of fun. We could get a bunch of people to take up shifts.

Jeff Jarvis (130:02)

You know we used to be.

Paris Martineau (130:03)

I romanticize these sort of things. It just seems fun to do a 24 hour lives.

Leo Laporte (130:08)

I'm up all night anyway so I.

Benito (130:10)

Remember what having that kind of energy was like. Wow.

Leo Laporte (130:13)

Ah, the good old days.

Jeff Jarvis (130:14)

Old bonito.

Paris Martineau (130:16)

Listen, I wanted to sleepy people. I know it's not that I have a bunch of energy. I just think it would be kind of fun to participate in a 24 hour live stream.

Leo Laporte (130:24)

Well no. Okay, I'm gonna take your take it on advisement. I. I would too. Lisa, we could game for a couple of hours. I could just leave the lights on.

Paris Martineau (130:32)

And Jeff could talk about Linotype for an hour.

Jeff Jarvis (130:37)

Hey, yeah, three hours at least three hours.

Paris Martineau (130:40)

Listen, we got.

Gary Marcus (130:40)

We got a good half of the.

Paris Martineau (130:42)

Day figured out already.

Leo Laporte (130:46)

Jammer B says if we do another live stream, he's coming down.

Jeff Jarvis (130:49)

Whoa, that's a problem?

Leo Laporte (130:50)

Well, he, you know he was show.

Paris Martineau (130:53)

Out his little saws for a couple of hours.

Leo Laporte (130:56)

His saws? He has special saws.

Paris Martineau (130:59)

Burke always has a saw, right? A chainsaw?

Leo Laporte (131:03)

No, that's Elon Musk you're thinking of. We did start 20 years ago. We used Skype first for audio, then for video. Now here we are 20 years later. It's all over. Bye bye Skype. We hardly knew ye Rip.

Paris Martineau (131:22)

When's the last time.

Leo Laporte (131:23)

You know what Skype is? Paris.

Paris Martineau (131:25)

I Used Skype. I'm not that young.

Leo Laporte (131:32)

Microsoft is going to take all the Skype users and turn them into teams users. That's not going to happen.

Jeff Jarvis (131:39)

No, I, yeah, I don't like teams.

Benito (131:43)

Pre Microsoft. Skype was amazing.

Paris Martineau (131:45)

Jammer B confirms Burke does have multiple saws. I'm not crazy.

Leo Laporte (131:49)

Oh. First paying member of Club Twit is Seth Graham. Seth, are you still with us?

Benito (131:57)

Still an active member. Seth.

Paris Martineau (131:58)

Patrick, we salute you.

Leo Laporte (132:00)

Seth. Wow.

Paris Martineau (132:02)

Still have one hour interview with Seth Graham.

Leo Laporte (132:06)

I think.

Benito (132:07)

Yeah, we can get him on. Let's try to get him on.

Leo Laporte (132:09)

Seth, we'll get you on. I want to, want to thank you and honor you.

Benito (132:13)

If you're listening to this episode.

Leo Laporte (132:20)

Anything else in the.

Jeff Jarvis (132:21)

We talk about the LA Times stupidity.

Paris Martineau (132:24)

Oh yeah.

Leo Laporte (132:26)

What is he doing?

Paris Martineau (132:28)

So one of the hot new things in journalism right now is what if we put AI on the news articles and that will somehow equal profit. And for the LA Times that turned out poorly. Jeff, if you want to explain.

Jeff Jarvis (132:44)

Well, it wasn't on the news articles what they did. What he, what he's, what he's promised to do is to a use AI to determine bias. This is Patrick.

Leo Laporte (132:52)

Oh my God. But every, every opinion piece in the LA Times from now on will have a little bias.

Paris Martineau (132:58)

Not even opinion pieces. Right. It's.

Jeff Jarvis (133:01)

Well, just now it's opinion. He'll do that.

Leo Laporte (133:03)

Opinion, editorials, commentary and more.

Jeff Jarvis (133:06)

But, but here's the other thing he did that I didn't know he was going to do is that he. To, to both sides things. He has the AI respond to the opinion piece.

Paris Martineau (133:18)

Yeah.

Jeff Jarvis (133:18)

It's a little point of saying that no human touches the AI, so it just goes up. So they had the AI defending the.

Leo Laporte (133:27)

Kkk, which I'm sure it did with confidence and, and, and hallucinations.

Jeff Jarvis (133:35)

So I put up a PDF of an example of this because like you can't do it if you use archive, AI, dot, dot, whatever.

Leo Laporte (133:42)

Ph. Yeah. So where, where did you, where did you put this?

Jeff Jarvis (133:45)

It's on the, it's on. If you look at the rundown I put, I put a lot of care into the run down today.

Paris Martineau (133:49)

If you click on Jeff's little icon, it'll take you to it.

Leo Laporte (133:53)

Jeff's little icon. He has a little icon.

Paris Martineau (133:56)

Do you know how Google Docs works?

Leo Laporte (133:58)

Oh, I see. So I click on his icon and then what? Oh, it highlights everything he wrote. I didn't know for 20 years and I still didn't know that.

Jeff Jarvis (134:09)

Know that.

Paris Martineau (134:10)

Well, you know, if you click on a little Jeff headshot.

Leo Laporte (134:12)

I did. I clicked on his head and it highlighted the article.

Jeff Jarvis (134:16)

Wow.

Leo Laporte (134:16)

Yeah, great. Documentaries reveal history's truth. Unregulated AI threatens to distort it. This is a voices call written by humans. Right. Rachel, Stephanie and Jennifer.

Jeff Jarvis (134:28)

Okay, so you go down, hold the bottom. I didn't capture the KKK when it was gone. So keep going, keep going.

Leo Laporte (134:35)

Insights.

Jeff Jarvis (134:37)

Stop there.

Leo Laporte (134:38)

This is a center left or scroller.

Jeff Jarvis (134:41)

Go up a little bit. Yeah. So, yeah, it says here that it aligns with a center left point of view. Sorry, you were right. And then now go below perspectives, plural ideas expressed in this piece. And then different views on the topic. So for example, it says that AI could democratize historical storytelling, allowing creators to visualize poorly documented events, that is to say, make them up or marginalized perspectives. Tools like midjourney enable amateur historians to generate images of ancient Rome.

Leo Laporte (135:19)

I don't want to see it. Nope, nope. It's fake. On the other hand, regulation risk stifling innovation is seen in creative applications like Val Kilmer's voice for Top Gun Maverick. Right. Because he can't speak. So in Top Gun Maverick, they used an AI to generate his voice. Right.

Paris Martineau (135:37)

So this similarly complexity. They used AI to do Anthony Bourdain's voice despite protest.

Leo Laporte (135:46)

That was weird. No, that was creepy. Yeah.

Paris Martineau (135:49)

Yeah.

Leo Laporte (135:50)

Although it was saying things he said, it was just simulating the voice because it was actual quotes from him. Now, here's my thoughts on this. This just. This is just a way of ginning up more crap to fill up the pages of the LA Times.

Jeff Jarvis (136:04)

But he's also trying to do this thing where he wants more balanced opinions.

Leo Laporte (136:08)

Yeah.

Paris Martineau (136:09)

I'm just curious as to what sort of money the LA Times is paying for perplexity and how that compares to the salaries of the journalists they've laid off for the last couple of years.

Leo Laporte (136:21)

Yeah, so they use Perplexity for this.

Gary Marcus (136:23)

It's.

Jeff Jarvis (136:24)

It's credited there.

Leo Laporte (136:24)

Yeah, yeah. Oh, that's cool. Because that's what I use for my stories.

Paris Martineau (136:30)

And those are never wrong, of course.

Leo Laporte (136:32)

Well, okay, so generally, perplexity's Right. Is accurate and reliable. And it give. Because it gives you footnotes as it. As this LA Times insights does. I was trying the other day and it was extremely frustrating. I have this idea. I wanted AI to take the spreadsheet we have. You've seen it of all the people who've been on our shows, make a list of everybody's one name and then how many times they've been on what dates they've been on.

Jeff Jarvis (137:00)

That's the kind of scraping it can do pretty well, isn't it?

Leo Laporte (137:02)

I thought, oh, this is going to be great. It thought everybody was on in the year 2023 for some reason. So I said, well, you know, the dates range from like 2005 to 2025. And of course AI does this. Oh, you're right. I just noticed that too. So let me give you another list. And then they were all from 2024.

Paris Martineau (137:27)

Have you tried messaging it? Please. I make a lot of points about how you can do everything on my podcast. You've got to come through for me.

Leo Laporte (137:35)

It did bring home to me. Now, probably there is a way to do this. I don't know.

Jeff Jarvis (137:39)

Yeah, I don't use it to scrape data like crazy.

Leo Laporte (137:42)

Yeah, I would think that it seems to me that should be something it can do. Especially since I'm giving it the source material. Right.

Paris Martineau (137:49)

It says, I wonder if it's something to do with the way that the date data is stored in Google sheets. Because I know sometimes when I'm copying over columns of dates from like one sheet to another, something happens with how it was stored to where it gets all weird. Or all the dates are the same one in the paste.

Leo Laporte (138:09)

Yeah, it's a little strange.

Jeff Jarvis (138:11)

Dates one always had line one column E always has the date.

Leo Laporte (138:16)

Yes, you did.

Jeff Jarvis (138:18)

Wow.

Leo Laporte (138:18)

Yes. Still, I was very specific in the prompt part of the is because we are looking at little chunks that are smaller than the actual chunks the AI's LLM is looking at. So it, you know, that's why I can't tell you how many Rs in strawberry. It doesn't see the word strawberry or Rs for that matter. Patrick says, I have a page on our system that will show all the guests and sort by number of appearances. Leo. Thanks, Patrick.

Paris Martineau (138:44)

It's just he doesn't want to hear that.

Leo Laporte (138:46)

I don't understand why you're making this so hard.

Paris Martineau (138:50)

How many trees were burnt for that, Leo?

Leo Laporte (138:53)

I don't know because I spent most of an afternoon beating on the thing. Yeah, I know. We have an API, Patrick. That was what actually came to me is I thought I should probably just query the database.

Gary Marcus (139:05)

Patrick.

Leo Laporte (139:06)

But yeah, harass Patrick.

Paris Martineau (139:08)

A human being. A human being in your database.

Leo Laporte (139:13)

Oh, yeah, we have. We did the right thing when we created it some years ago. But anyway, somebody's saying in the discord and I think this is kind of interesting. I just want the facts, man. I don't want balanced opinions. I just want facts. Report the news and give Me the facts of the story without opinion, said Anthony.

Jeff Jarvis (139:34)

That's what.

Leo Laporte (139:35)

No, I know it likes that, but. No, it's. Trust no one in our discord. What do you think?

Paris Martineau (139:39)

I agree.

Benito (139:40)

It's not really possible though, right?

Paris Martineau (139:41)

Well, I mean, every. Yeah, Every article has a writer that has their own biases and ways that they're seeing the world.

Benito (139:51)

Like it's something people always say, that's. Like it's actually impossible. Like that's not a possibility.

Leo Laporte (139:56)

Yes, because humans have choices. Maybe an AI can do. It.

Jeff Jarvis (140:01)

Reflects perspective.

Leo Laporte (140:03)

Right. And actually you think you want just effects, but you really don't. You need more than just effects. So. Patrick Sun Shong, who owns the LA Times, is a physician, a surgeon, a scientist, an inventor, a technologist, and a philanthropist.

Benito (140:22)

That's always good at nothing.

Leo Laporte (140:27)

He is the CEO of a holding company devoted to the transformation of healthcare and using artificial intelligence to win the war against cancer and Alzheimer's. How's that going?

Jeff Jarvis (140:41)

He's liking RFK Jr.

Leo Laporte (140:44)

So is he.

Jeff Jarvis (140:46)

I'll leave that there.

Leo Laporte (140:47)

Yeah. He has 230 patents and is obviously a big fan of. Of AI. We'll see. I mean, you know, if that. If the readers of the LA Times love it, then maybe it was a good thing.

Paris Martineau (141:02)

You should rename it the AI Times.

Leo Laporte (141:04)

The AI Times. Okay, we're gonna wrap this up pretty quick here, so. Yes, Jeff, you put a lot of wonderful, wonderful energy into this. What would you like me to. What should I bring up? Timnit Gebru's post, that's a good one on LinkedIn, where she says there is in. In. Says it in caps. There she is. Of course, we should mention the former Google ethicist who was hired by Google to help them with ethical AI, but then fired when she. Margaret Mitchell. And was it Emily Bender wrote. Yes, Emily, the stochastic parrots are Arctic Beetle.

Jeff Jarvis (141:51)

I always forget her name.

Leo Laporte (141:52)

Yeah, the fifth Beetle. She says, by the way, Temnet was fired then after that for having the temerity to imply that Google's AI wasn't perfect in every way. She says there is no such thing as an AGI and attempting to build it is a eugenicist power centralization project that no one should support. I actually don't disagree with that.

Jeff Jarvis (142:18)

Yeah, and she said beginning and caps and lowercase. She says the Transformers and what they were designed for. She remembers. She didn't remember anybody talking about artificial general intelligence until OpenAI. This is why I asked Gary. This came on the scene and started talking about large language models. As stepping stones toward AGI. Most natural language processing people I come across were talking about creating pre trained models the way we had had imagenet pre trained models in computer vision. I don't remember any of them talking about AGI, but people decided to follow this trope now. And so she's constantly screaming it and I'm agreeing. And you know, Gary says that he came up with his definition for the sake of the bet, but I don't think there's any clear definition out there. And Eric Schmidt in the Wall Street Journal goes on about the changing, changing definitions of AGI as well. And so we're constantly seeking a MacGuffin.

Leo Laporte (143:16)

Yeah. Her piece that she points to is called the Test Creel Bundle. Eugenics and the Promise of Utopia Through Artificial General Intelligence is what you've been talking about. And that's by the way, with Emil Torres. Was. Is he the fifth beetle?

Jeff Jarvis (143:29)

They are the. No, no, no, no. They worked with. With Timid on this.

Leo Laporte (143:35)

Okay. Yeah, I'm glad you brought that up. I don't disagree with. Definitely seems like the people pushing AGI are pushing another agenda as well.

Jeff Jarvis (143:47)

That's what I'm trying to say. And the agenda is eugenicist.

Leo Laporte (143:50)

Yeah. Paris, anything?

Paris Martineau (143:57)

I thought this was kind of cool. The New York City subway is piloting a program to use Google pixels strapped to the subway cars to listen to defects using AI.

Leo Laporte (144:08)

Okay, that seems. Okay. I don't. I don't dislike that.

Paris Martineau (144:12)

Listen, anything that helps these portraits run marginally faster is good for me. And this seems to be one way to help detect potential breakdowns in cars or service without having a bunch of human inspectors having to walk the tracks every day. Seems great.

Benito (144:30)

This is the stuff as AI is for like these little tiny little jobs that get no love that no one really cares about. But this is the stuff. This is the stuff that it should be doing.

Jeff Jarvis (144:39)

Yeah.

Leo Laporte (144:41)

How many? Did they say how many they're gonna.

Paris Martineau (144:45)

Let me try and get here? You know who does care about it?

Leo Laporte (144:49)

Who?

Paris Martineau (144:50)

New York City Transit Assistant Chief Track Officer Robert Sarno, a 14 year veteran of the MTA who in order to help train these. This AI model basically threw on some noise canceling headphones and listened through five to ten minute snippets of track noise to sort regular subway din from audio signatures of track trouble. So we'd listen to it and mark down loose joint, loose bull, rail defect when he hears like a certain shake. And he by himself hit an 80% accuracy rate with just hearing this. But that was after 14 years of work and so it's important, I think, to be able to train these systems to do that sort of work so that people like him can actually work on like fixing the problems rather than listening to videos or audio on the train in order to hear if a bolt is maybe going to come loose.

Leo Laporte (145:45)

Wow.

Jeff Jarvis (145:45)

Which we want them to hear.

Leo Laporte (145:47)

Six Google Pixel smartphones hitched free rides on four subway cars. I guess you don't need that many. I mean, you're just got to go over the track. Yeah.

Paris Martineau (145:56)

Kind of interesting.

Jeff Jarvis (145:57)

Of course there actually were seven, but one of them got stolen. I'm joking.

Leo Laporte (146:00)

Did it? I wouldn't be surprised. No, nobody steals Pixels. If it had been an iPhone, that would be another matter. Hey, hey. YouTube has introduced premium Lite. You don't have to now buy YouTube Music to get YouTube Premium. For $8, you can just get YouTube without some of the ads, not all the ads. They don't promise to remove all the ads for your eight bucks. I did say that I was going to talk about manifest v3. I got pushed out an update to Chrome. I imagine most of you did as well. That without a word or a hint or anything, just deleted the ad blocker I was using. You block Origin because it's not compatible with an update to chrome called manifest V3.

Jeff Jarvis (146:43)

Serves your right, Google.

Paris Martineau (146:45)

Well, I will not be updating that until I switch over to Firefox. So what are you using now?

Leo Laporte (146:50)

Well, let me just say why Google says this is a good thing. They say this in order for an ad blocker to work, it has to look into the pages you're on. And that's a security problem. They don't want third party extensions to have those permissions. Gorehill, who created Ublock Origin, has created a lite version that still works under manifest v3, but doesn't work as well. So I switched to a new browser called Zen Browser that is kind of actually. Well, it hits my sweet spot, let's put it that way. Because it's all AI. No AI involved in fact. Yeah, there's no AI. It's an open source project. Firefox uses the Firefox Blink engine, but it has a UI like my favorite now abandoned browser, the Arc browser. The browser company decided that there was no money in making their Arc browser, so they're moving on to something else that does have more AI in it. So I get really what I wanted. The ARC browser is based on Chromium, so I get a Firefox based browser with the Arc UI. And yes, UBlock Origin continues to Work just fine.

Jeff Jarvis (148:02)

And the browser they're working on is really interesting. Jason and I talked about it last week. It expends for example the cursor. This is how AI is going to be used.

Leo Laporte (148:12)

You're talking about the browser companies new.

Jeff Jarvis (148:14)

Yeah.

Leo Laporte (148:14)

Tool. It's an agentic browser.

Jeff Jarvis (148:16)

Yeah, right. So. So you can, you can be. Your cursor becomes a window onto functionality. About this that you're pointing to. It's really interesting.

Leo Laporte (148:24)

Yeah, yeah. This is all the rage now in AI is agentic where the AI does things for you and if you give it control of your browser, it can find the best porn. Anyway. I like the Zen browser. That's the one I'm using. It's free.

Jeff Jarvis (148:41)

All roads lead to porn as usual.

Leo Laporte (148:44)

Yeah. What else?

Paris Martineau (148:46)

Internet is a series of tubes filled with porn.

Leo Laporte (148:50)

That's disgusting.

Paris Martineau (148:52)

I bet they are quite sticky.

Jeff Jarvis (148:55)

This is important for Paris to know. Line 149. Michael Masnick is coming up with a new podcast called Objectionable, a limited term series about, guess what?

Leo Laporte (149:07)

Section 230, it's otherwise. Objectionable is the name of it.

Jeff Jarvis (149:11)

Sorry. Yes. Yeah, sorry I screwed that up.

Leo Laporte (149:15)

He has of course been a great defender of Section 230, probably more than anyone else, including this page that he created. Hello. You've been referred here because you're wrong about Section 230 of the Communications Decency Act. He wrote that five years ago. But it still holds. It's still good. It's still true. Yes. Mike's been doing more podcasts, which explains why he's hard to get on our shows, I guess. Good. I'm glad to hear it. The Competitive Enterprise Institute is sponsoring this as a documentary podcast exploring the past, present and Future of Section 230 between.

Jeff Jarvis (149:55)

Mike and Jeff Kossif. Those are the two. And our friend here on the show, you know, they're trying to fend.

Leo Laporte (150:05)

Yeah. Oh, Kathy Ellis is on it. Oh good.

Jeff Jarvis (150:08)

These are more defender as well.

Leo Laporte (150:10)

Yeah. Oh yes, absolutely.

Jeff Jarvis (150:12)

The single biggest threat to free speech in this country is the power of big tech.

Leo Laporte (150:15)

It's time to fight back. The wonderful Ted Cruz talking there. It's now time to repeal section 230.

Gary Marcus (150:23)

Section 2, 230.

Leo Laporte (150:24)

Section 230. Of course, Elizabeth Warren is also in there. It is a bipartisan attack on what is the most important piece of legislation with regard to the Internet ever. And Mike will defend it, I'm sure. Good, I'll have to listen to that. Techdirt.com I guess a little politics. One of the things that is being Dismantled right now by Doge is 18 fold, which you may have never heard of, but like the US Digital Service, which has also been kind of replaced by doge, 18f were coders, were technologists who helped the government implement websites and other technologies, most famously the IRS's direct file system. Now, Direct File is still running, but everybody at 18F has been dismissed. So the question is how long it will keep running. This is just part of just a continued assault by Elon Musk, Doge and the President on science and on technology and how it makes any sense at all to get rid of these groups that helped American government be efficient, work better and serve the people. I don't know. I don't understand. I really don't. But at least we're going to have a, a cryptocurrency strategic reserve. Thank God. Thank God, right?

Jeff Jarvis (152:10)

Have our dogecoin.

Leo Laporte (152:14)

All right. I think anything. Unless you tell me that there's something we gotta say here. I'm just looking through it. There's of course so much good stuff.

Jeff Jarvis (152:23)

You want to, you want to spend $100 million buying AI.com?

Leo Laporte (152:26)

100 million. The information.

Paris Martineau (152:29)

Oh, this is a great feature my colleague Akash did this weekend.

Leo Laporte (152:34)

Larry Fisher, a veteran Brooklyn domain broker, AKA a domain squatter, hopes to convince.

Paris Martineau (152:41)

He'S not the squatter, he's the intermediary between the squatter and a fun detail in this. This is the person who owns AI.com who declined to be named or interviewed for the article. Did, I believe, send a written response back to my colleague. Akash's inquiries described themselves as being very lucky that they bought this domain. Yeah, years and years ago, not because of anything related to AI, but because it was their initials.

Leo Laporte (153:10)

Damn, I wish I were named. Adrian Ignacio Fisher, a 62 year old Brooklyn native says if somebody's looking to sell a top tier domain, I'm the guy they call. I have a reputation for being able to get the best price.

Jeff Jarvis (153:25)

And he is from Queens, so it's the right. Right.

Leo Laporte (153:28)

I hope that's all right there. He sold. Let's just give you some of his greatest hits. According to akash, he sold skincare.com to L'Oreal, he sold teams.com to Microsoft chat.com to, to the HubSpot, who then flipped it to open AI and made a little money. I'm sure that that really grinds his gears.

Paris Martineau (153:55)

To begin attracting attention to prospective buyers, the owner has adopted a clever sales tactic in the last few months. Continually redirecting AI.com to different sites for a while it went to ChatGPT's website. These days it goes to Deep Seek. And the ploy has had an amusing ripple effect. A bunch of different news outlets like TechCrunch and things like that have written a slew of headlines mistakenly claiming that OpenAI bought AI.com or Xai bought AI.

Leo Laporte (154:23)

Deal for you, August Nashio. Why don't you point it to Twitter TV and fool them all?

Paris Martineau (154:30)

No one will ever see that coming.

Leo Laporte (154:32)

No one will ever see that coming. 100 million.

Jeff Jarvis (154:36)

So, Brooklyn, okay to your queen's accent.

Leo Laporte (154:40)

I'm sorry. Sorry.

Paris Martineau (154:41)

Ron Bergman, a Wharton School associate professor who focuses on digital advertising, says, I don't think it's going to get to nine figures of value. But if it does get there, that's.

Leo Laporte (154:52)

A deal breaker, ladies.

Paris Martineau (154:55)

That's a deal breaker, ladies. I think that's a good sign that we may be starting to get back into a dot com bubble.

Leo Laporte (155:02)

A bubble. It's a bubble.

Paris Martineau (155:05)

That's a bubble, ladies.

Leo Laporte (155:06)

It's a bubble, ladies. Initially, so he had, he did buy a lot of. He was snapping up domains. In 1995, he bought brothers.com, sisters.com and stockquotes.com. my wife put her foot down. If I couldn't turn this into something that generated cash flow, it was over.

Paris Martineau (155:27)

Honey, you gotta sell your domains. You got too many of them.

Leo Laporte (155:32)

I just sold Portage.com for $3,000. He sold Return.com for a low six figure sum after buying it for $100. That put him back on top and officially on a roll. You know, Akash did a great job of capturing this guy. I love it. I love it. All right, $100 million. AI.com. i mean, I don't know. How much, how much did OpenAI pay for Chat.com?

Jeff Jarvis (155:58)

You don't know.

Leo Laporte (155:59)

HubSpot bought it for 15 and a half million. I flipped it almost instantly. Oh, he got equity. Oh, big mistake, buddy. He got.

Paris Martineau (156:13)

Over the years, Fisher himself has developed an attachment to certain names he's unwilling to part with. He grew up an avid follower of pop art, but could never afford his favorite artist's work. So in 1997, he bought andiewarhol.com, and has been sitting on it ever since, despite several attempts from the Andy Warhol foundation to claw it back. It's my painting, it's my artwork, he said. The site is the same Warhol fan page Fisher set up 26 years ago.

Leo Laporte (156:40)

Yeah, it looks like it, doesn't it? Wow. Andy Warhol. It's proudly powered by WordPress though.

Jeff Jarvis (156:49)

So it is indeed.

Leo Laporte (156:50)

Yeah, yeah. He's vowed to keep it as is after scores of deals. Fisher said he's addicted to the feeling of outdoing himself, driven by the high he gets from closing seven and eight figure deals. It's just like when my kids are born. It's the same feeling. As we finished dinner and got up from the table, I asked how he'll feel when AI.com sells triplets. He said, nice job, Akash. Good story.

Jeff Jarvis (157:22)

Who says technology news is boring?

Leo Laporte (157:25)

Triplets. It's human triplets. Deutsche Telekom and my favorite AI company, Perplexity.

Jeff Jarvis (157:32)

They're doing interesting things.

Leo Laporte (157:34)

They're going to create a new AI phone priced at under $1,000. This was announced at Mobile World Congress. Low cost headset. I don't think that's low cost. Created in close. It's called and oh, it'll have a new assistant on it called Magenta AI. You know, Mark Gurman who writes about Apple for Bloomberg and is very connected, has said that Apple has fallen way behind on AI. Apple intelligence for its smartphone. There may be an opportunity here.

Jeff Jarvis (158:07)

Nobody's really figured out the AI device yet. Have we seen, you know, human humane and all that failure. Google has certainly got AI on its. Perplexity is a very clever company.

Leo Laporte (158:21)

I love Perplexity because I can use different models for 20 bucks. I get to use all the other ones that I'm also paying 20 bucks for. Foolishly. One thing Apple did do though, they put an action button on their phone and now ChatGPT will talk to me. Actually, I think this is Perplexity I'm going to talk to here. Let me see.

Paris Martineau (158:40)

Want to have an existential debate?

Leo Laporte (158:43)

What is a nihilist?

Paris Martineau (158:47)

Nihilist is someone who believes in nihilism.

Leo Laporte (158:51)

Thanks.

Paris Martineau (158:52)

Or denies the existence of meaningful aspects of life. Nihilists often believe that life is meaningless, that there are no objective moral truths and that traditional values and beliefs are unfounded. This perspective can lead to a sense of skepticism and pessimism about the world and human existence.

Leo Laporte (159:12)

That's not wrong, Benito. That's Paris.

Benito (159:16)

That's not really. That's not really the definition.

Leo Laporte (159:19)

It's not really.

Paris Martineau (159:21)

Yeah. Two members of the optimistic Nihilist club would disagree with you.

Leo Laporte (159:27)

Oh, you both are optimistic nihilists.

Paris Martineau (159:29)

He's got, he's a card carrying member. I'm just a renegade.

Leo Laporte (159:32)

That's hysterical. It doesn't have any. You know what, it doesn't have any footnotes as to the source on this. That's interesting. But If I ask it, it will generate a picture of. Oh, if this is maybe where it got the information from. Some pictures of nihilists. Those people look hopeless. All right, let's take a final timeout and come back with your picks of the week. I feel bad that Jeff missed my pick of the week last week. Have you been playing bracket city?

Paris Martineau (160:04)

I've been playing bracket city. I've sent bracket city to friends. Is that great? What am I now? I'm like mayor. I'm like editor in chief.

Leo Laporte (160:13)

Each time it's different because it's how many. How efficient you were in solving it. Right.

Paris Martineau (160:19)

I am high ranking in bracket city.

Leo Laporte (160:22)

Like I know that a word for a bunch of fish is a school. Jeff, did you see this? You would left.

Jeff Jarvis (160:27)

I saw. I couldn't figure it out. I just.

Leo Laporte (160:29)

School event with chaperones is a dance. A dance. Let's see. What are that? Cows. And what is that? What are those emojis? I don't know.

Paris Martineau (160:38)

Hold on. I've got to pull it up on.

Leo Laporte (160:39)

My screen in a big kind of stand where you are upside down.

Paris Martineau (160:43)

Cowboy handstand.

Leo Laporte (160:45)

Oh, cowboy.

Jeff Jarvis (160:46)

Is this gonna piss me off?

Leo Laporte (160:48)

Well, this. See, no. You know, the story is great because.

Paris Martineau (160:51)

You gotta figure out everything in the brackets to then make something that connects to. Once you reduce all of them down, it gives you something. To this day in the past, it's.

Jeff Jarvis (161:02)

Really what I have. A life.

Leo Laporte (161:04)

No, you don't. This is. Do you do crosswords?

Jeff Jarvis (161:08)

No, I hate them.

Leo Laporte (161:09)

Oh, well, you wouldn't like this then.

Paris Martineau (161:10)

No, hand. Hand is the next one.

Leo Laporte (161:13)

Ah, okay. I put creek for like a river, but smaller, but that was wrong. Something to do with the hand or money. You do the hand or money.

Paris Martineau (161:26)

Vent is the next one.

Leo Laporte (161:28)

Wait, vent. Release frustration. You don't have to do it in order. Invent as a phrase. Like a river is a Jurassic Park.

Jeff Jarvis (161:38)

That's why I hate this. I hate this.

Leo Laporte (161:40)

If you have it, you might rip one.

Jeff Jarvis (161:42)

Suck me in.

Leo Laporte (161:45)

If you have it, you might rip one. Material associated with biker gangs. Leather. Glossy leather for fat. And for fancy shoes. Patent. If you have it, you might rip one.

Jeff Jarvis (162:02)

See?

Paris Martineau (162:03)

Rip what?

Leo Laporte (162:06)

Jammer B says gas. But I don't think. I don't think that's it.

Paris Martineau (162:11)

I don't think. I don't think you rip. Gas is the thing. No, like a river, but stream. Yeah, stream is where we go.

Leo Laporte (162:17)

I tried stream of social media content.

Paris Martineau (162:21)

And the next one is meter.

Benito (162:23)

Feed.

Paris Martineau (162:24)

Feed, Feed. No, feed is first. Meter is after you put feed in. Sorry, I'm reading ahead.

Leo Laporte (162:29)

You're reading ahead. You feed.

Paris Martineau (162:32)

Well, we're not. It's not yellow. Yes, we can.

Leo Laporte (162:35)

If you have it, you might rip 1. Invent as a phrase and something to do with a hand or money. We'll leave this as an exercise for the reader. But I just wanted to make sure Jeff saw that so he could hate it.

Paris Martineau (162:46)

Oh, coin is the middle one. Invented.

Leo Laporte (162:49)

Isn't it fun? It's really fun.

Paris Martineau (162:51)

I'm obsessed.

Leo Laporte (162:51)

So the story is this guy owns a bar and he does trivia contests, he loves puzzles, and he just made this up. It's free, it's online. And the real question, and we should have a pool, is how long before the New York Times buys this? Right, because that's clearly what's going to happen.

Paris Martineau (163:05)

Six months.

Benito (163:06)

Wait, so maybe we should buy it first and then sell it to the New York Times.

Leo Laporte (163:10)

We could flip it.

Paris Martineau (163:13)

Maybe we should get that domain guy in on it. He seems.

Leo Laporte (163:19)

A broker, don't you think? He's probably got a few calls from people who want to do that exact thing. All right, just real quickly, a couple of things I'd like to ask of our fine audience. First of all, if you're not yet a member of Club Twit, we would love you to join the club. It helps us defray expenses. It keeps the show on the air, helps us grow. You know, we're always hanging by a thread. We have lots of advertisers now, I'm happy to say, but it still only covers about 90, 95% of our costs. The club makes up the difference. If you're not yet a member, seven bucks a month ad, free versions of all the shows. Because I wouldn't charge you and then show you ads. That's. That's terrible. You also get access to the Club Twit Discord, which is a great hangout place for lots of fun events. Including, by the way, tomorrow, our photo thing with Chris Marquardt. Photo time. That'll be 1pm Pacific. Seven bucks a month. Twit TV Club Twit. Please join the club. We'd love to have you. And access to Leo's OnlyFans account. Is that. I don't get it.

Paris Martineau (164:33)

I mean, this is an. Only fans of some sort. It's just not pornographic, right?

Leo Laporte (164:37)

Actually, there are only fans that are not pornographic. There are plenty of them.

Gary Marcus (164:41)

There's a lot of us.

Benito (164:43)

You know, there are a lot of pornhub channels that are non pornographic because the.

Leo Laporte (164:46)

Yeah, you get one because it's got a good Algorithm.

Paris Martineau (164:49)

Hey, we should stream on pornhub.

Leo Laporte (164:50)

Guys, there's a woman.

Paris Martineau (164:53)

Yeah, we've covered it before.

Leo Laporte (164:54)

Oh, yeah, we talked about it. Yeah, yeah, never mind. The other thing I want to ask you with, whether you're a member or not, leave a review if you would, especially on Apple's itunes. We've been review bombed in the past. It's brought our numbers down. But if you like the show, share that on whatever platform you like. I don't, you know, it's okay with me if we are 4.1 or whatever, but advertisers do care and so that helps us a lot. So just another little thing you can do. Just go to itunes or whatever you.

Paris Martineau (165:29)

Hey, prime members, are you tired of ads interfering with your favorite podcasts?

Leo Laporte (165:34)

Good news. With Amazon Music, you have access to the largest catalog of ad free top podcasts included with your prime membership.

Paris Martineau (165:41)

To start listening, download the Amazon music app for free or go to Amazon.com adfreepodcasts that's Amazon.com adfreepodcast to catch up on the latest episodes without the ads.

Leo Laporte (165:56)

I'm on pornhub. Are we streaming on pornhub or just somebody just make that? I think it's a joke.

Jeff Jarvis (166:07)

I hope it's a joke. It's disappointed users out there.

Leo Laporte (166:10)

That's the kind of thing you're missing if you're not in the club.

Jeff Jarvis (166:13)

So related. In the early days of blogging, I had blog ads.

Leo Laporte (166:17)

Yeah.

Jeff Jarvis (166:18)

And Henry Copeland came up with a new format. It was a big ad and we called it the Big Ass ad. And so I posted that I was going to have the Big Ass ad and I have rejected in a couple years. But for many years, if you searched for Big Ass, you'd get your bag.

Leo Laporte (166:33)

That's smart.

Jeff Jarvis (166:35)

Well, it's smart like it was either. Either definition. I wasn't very happy that I was associated with Big Ass.

Leo Laporte (166:42)

On the other hand, you generate a lot of traffic there. Very. Maybe you should have registered bigass.com?

Jeff Jarvis (166:49)

I should have. Should have.

Leo Laporte (166:50)

Yeah, yeah. Larry Fisher would be on the line. Jeff, give us. Oh, I start with Paris. I'm sorry? Paris, your pick of the week.

Jeff Jarvis (166:57)

What are you doing?

Paris Martineau (166:57)

Yeah, I saw this come across my Blue sky feed recently. Have you guys ever heard of the Vintage Computer Festival? Yes, I'm thinking of going this year.

Leo Laporte (167:08)

Is it New York?

Paris Martineau (167:09)

It's in New Jersey, like an hour and a half drive from.

Leo Laporte (167:13)

Oh, yes, very.

Paris Martineau (167:14)

In a month. It seems really fun. Yeah, it's in Wall, New Jersey. Jeff, you have any recommendations for Me to check out New Jersey from in the hour and a half drive from New York to look up some things for you. Let me know.

Jeff Jarvis (167:27)

Where is wall? We have 500 towns in New Jersey. I always forget where they are.

Paris Martineau (167:30)

I couldn't tell you. It's near the. It's at the InfoAge Science and History Museum if you know that. But it seems really fun. There's going to be a lot of. There's going to be computer classes where you can learn to intro to Coco and Coco Basic and then you can play around on old computers. There's also going to be like a huge marketplace for vintage computers and I don't know, it just seems like a fun little event.

Jeff Jarvis (167:57)

I'll buy myself a PDP 8.

Leo Laporte (167:58)

There's vendors April 4th through 6th at the Info Age Science and History Museum. Scavenger hunt, Coney Road in New Jersey in Wall, New Jersey. That's pretty cool. Yeah, no, I know about this. I'm not sure why I feel like people who are on our shows involved. Yeah, I would bet. With support from the Computer History Museum, which I do know a little bit about.

Benito (168:24)

Hey, it says the theme is the sound of vintage. What does that mean?

Paris Martineau (168:29)

I couldn't tell you. Probably that.

Benito (168:32)

Yeah, modem sounds.

Leo Laporte (168:34)

Yeah, modem sounds. You know, disc sounds, boot up sounds, that kind of thing. The sounds of vintage. Jeff Jarvis, Pick of the week.

Jeff Jarvis (168:47)

Well, I should a late breaking one here under line 163. You asked for people to show themselves how they watch us. Well, meme artist showed us how they're watching us there.

Leo Laporte (169:01)

Look at that. Look at that. In the. In the garage or whatever. Yeah, you could post it on actually that's actually a better idea than sending it to us. Post it on. On Blue Sky.

Benito (169:12)

Oh yeah. Add us on Blue Sky. That's the. That's the.

Leo Laporte (169:14)

Add us on Blue Sky. That's what I should have said.

Jeff Jarvis (169:16)

Videos less than 60 seconds on blue Sky.

Leo Laporte (169:18)

Well that's good. We don't want them too long. Yeah, he Mime artist is in the UK and thank you. If she says he's going to do a video for us.

Paris Martineau (169:27)

Wow, it's late. There's. That's.

Leo Laporte (169:29)

Yeah, staying up late. That's very.

Paris Martineau (169:32)

You'll be an integral part of the 24 hour live stream.

Leo Laporte (169:38)

Yikes. Yikes, schmikes.

Jeff Jarvis (169:41)

And then Amazon's delivery drones are grounded in College station, Texas, line 142.

Leo Laporte (169:47)

Because it scares the bodies.

Jeff Jarvis (169:49)

And the dogs.

Leo Laporte (169:50)

And the dogs. Well, it scares humans too. What about the. Yeah, what about the humans?

Jeff Jarvis (169:57)

Several times an hour, an Amazon Prime Air delivery drone would noisily emerge about 800ft away, just past a line of trees behind Smith's home. Neighbors began calling it the fleet. Flying chainsaws.

Leo Laporte (170:12)

Yeah, that's kind of, it's kind of what they sound like.

Benito (170:16)

Imagine if you come from a modern, if you come from a modern war torn part of the world world and you hear a drum sound.

Leo Laporte (170:22)

Ptsd.

Benito (170:23)

Ptsd.

Leo Laporte (170:23)

Yeah, yeah, yeah, it's a very good point.

Jeff Jarvis (170:28)

So they, they got quieter ones and so on, but they've, they're pulling back.

Leo Laporte (170:34)

All right, all right. I thought I had a pick, but I can't find it. So I guess I'll just use that, that browser as a pick and a reminder. I am leolaport. Me on Blue Sky. Sorry, you can mention me and post how you watch. That's another way you can do it. We'd love that. That's really nice. Then. Thank you to all in advance. All right, everybody, we're done. We're through. I hope you've enjoyed this episode of Intelligent Machines. We are setting the clocks forward on Sunday, so the next episode will be at a. Well, it'll be the same time from, from our point of view, which is 2pm Pacific, 5pm Eastern, but it's 2100 UTC. 2100 UTC.

Paris Martineau (171:21)

Never forgets. They don't let us forget about it.

Leo Laporte (171:25)

Our guest be there on time. Our guest will be Ray Kurzweil, the man who came up with the term intelligent machines and the singularity. We'll talk with Ray about that. He says we're about to merge with the machine. We do this show. I told you the live time because we do stream this show. Of course, if you're a club member, you can watch in the Discord. But also on YouTube, Twitch, TikTok, X.com, facebook, LinkedIn and Kik. So you can watch live and if you're watching live, we can chat with you live. Because I see the chats right here on my screen after the fact on demand versions of the show at Twitt tv. Twig. If you go there, there's a link to the YouTube channel. Great way to share little clips and of course where you are and leave a review. By the way, if you go to your favorite podcast player, you go to itunes or Google Play Store or whatever, make sure you leave a nice review and subscribe. That way you'll get the show automatically as soon as we're done cleaning it up because Gary said a few bad words.

Jeff Jarvis (172:28)

Hey, hey, hey, hey, hey. Did Jeremy was in the chat. Did Jeffer B notice when this was happening?

Leo Laporte (172:35)

Oh yeah. He was going, hey, hey. What else? I think that's it. Paris Martineau writes for the Information. You should subscribe. It is really even today. Two or three scoops from the information. It's a really good source of Tech News. Martino01 on Signal if you've got a tip. Tip 4 Do not use your work phone. Maintain security times. Yes, Jeff Jarvis, former professor. Not former. Always. Now and forever.

Jeff Jarvis (173:10)

Always a professor.

Paris Martineau (173:10)

He's teaching us every week.

Jeff Jarvis (173:12)

Yes, for us, whether you want it or not.

Leo Laporte (173:15)

No, we love it. We do learn. Well, some of us do. I don't. But you know, he is a professor at Emeritus professor of Journalistic Innovation at the Craig Newmark Graduate School Journalism at cuny. He also is at SUNY now. Was cuny, now suny Stony Brook and Montclair State University. Thank you, Jeff. The author of as you see behind him, the Web we weave. That's his latest, the Gutenberg Parenthesis magazine, paperback.

Paris Martineau (173:50)

In paperback, CUNY Tisuni, but never looney. Jeff Jarvis.

Leo Laporte (173:55)

But is he a human being? I don't know. We'll have to.

Paris Martineau (173:59)

You'll have to stay tuned for next week Machines to find out, Steve Artolo.

Leo Laporte (174:05)

Has dropped in the chat and remind us that the Giz Fizz is tonight, 8:30pm Eastern, 5:30 Pacific, about 20 minutes from now at GizWiz TV. Hi Dicky D. I will be back tomorrow for Chris Markworth, our photo segment. Thank you everybody for being here. Remember Ray Kurzweil next week. We'll see you next time on Intelligent Machines. Bye bye. I'm not a human being.

Paris Martineau (174:29)

Not into this animal scene. When you get the Planet Fitness Black card, you can bring a friend anytime you work out. And now through March 13th, get your first month free when you join. You heard that right. Conquer the stair climber with your partner in climb. Enjoy a post workout recovery session in the hydro massage and do it all again with access to any of our 2,700 convenient locations. So you coming? Get your first month free and all the perks with the PF Black Card for just $1 down $24.99 a month. Cancel anytime. Deal ends March 13th. See Club for details.