All-In with Chamath, Jason, Sacks & Friedberg - E106: SBF's media strategy, FTX culpability, ChatGPT, SaaS slowdown & more

Episode Date: December 3, 2022

(0:00) Bestie hangover! (1:05) Analyzing SBF's media tour: his angle, media coverage, and more (21:09) FTX culpability: media, investors, regulators (53:41) Challenging media coverage of other countri...es, China's current situation, Xi Jinping's standing (1:10:04) What OpenAI's new ChatGPT tool means for the future (1:26:30) David Sacks on the slowdown in SaaS, use case endgame for generative AI Follow the besties: https://twitter.com/chamath https://linktr.ee/calacanis https://twitter.com/DavidSacks https://twitter.com/friedberg Follow the pod: https://twitter.com/theallinpod https://linktr.ee/allinpodcast Intro Music Credit: https://rb.gy/tppkzl https://twitter.com/yung_spielburg Intro Video Credit: https://twitter.com/TheZachEffect Referenced in the show: https://www.youtube.com/watch?v=KMZckrBPw38 https://www.coindesk.com/layer2/2022/11/30/ftxs-collapse-was-a-crime-not-an-accident https://www.wsj.com/articles/sequoia-capital-apologizes-to-limited-partners-for-ftx-investment-11669144914 https://www.nytimes.com/2022/11/27/opinion/ftx-sam-bankman-fried-fullenkamp.html https://www.nytimes.com/2022/11/14/technology/ftx-sam-bankman-fried-crypto-bankruptcy.html https://twitter.com/lizrhoffman/status/1595193884438568960 https://taibbi.substack.com/p/be-it-resolved-dont-trust-mainstream https://www.newcomer.co/p/taking-kid-gloves-to-all-in-my-reflections https://chat.openai.com/chat https://twitter.com/jdjkelly/status/1598021488795586561 https://twitter.com/pmarca/status/1598413401705021440 https://twitter.com/jdjkelly/status/1598021488795586561 https://twitter.com/DavidSacks/status/1598076726671642624 https://twitter.com/DavidSacks/status/1598363968547876864

Transcript
Discussion (0)
Starting point is 00:00:00 I'm now recording. Jesus, you look terrible. What's going on? Did you sleep last night? Do I look tired? Do you look a little tired? You look unshaven. Yeah, what happened last night? I had a holiday party at my house last night for my office and...
Starting point is 00:00:12 You look destroyed. Yeah, what's going on? I mean, did you drink? I did drink, yeah. What does vodka and oatmeal taste like? It tastes like that. It tastes like that. You had a white Russian?
Starting point is 00:00:21 A white Russian people that's... With oatmeal. He's like, I want a white Russian with A white Russian b- what the f- With O- He's like, I want a white Russian with O- Oh my god. Actually, my white Russian is made with O- And please compliment that with a huge punch in the face. Give me five minutes. I'm gonna go- I'm gonna go shave and-
Starting point is 00:00:36 It's called a hair of the dog. Yeah. Either a little bloody Mary. Banana butt. Banana man. Should I go get a beer? I might get a beer just to beat this hangover. Go do it. Yeah, go get a beer. I'll be right back All right, listen, we have to start with scam, bank run, fraud.
Starting point is 00:01:08 I mean, Sam, I've been free. I get that wrong sometimes. He was interviewed by Andrew War, Sorkin, the suit at Dealbook, who gave him softball after softball. Then the next day, he was on Good Morning. I'm really passive aggressive right now. A little bit. I'm very little shabby. We got our friend next to him.
Starting point is 00:01:29 Little choppy. He's sticking the knife in. He's sticking the knife in, but J. Cal's got a point. He's got a point. A little bit. A little bit. A little bit. Anyway, the New York Times continues to embarrass themselves
Starting point is 00:01:40 by handling Sam back and fro with kick gloves. Wow. George Stephanopoulos, my Greek brother, Stephanopoulos, the Spartan came in and absolutely fricassade and filet, Sandbagma Fried on Good Morning America. Very important to note that Good Morning America, the segment was between holiday cocktails
Starting point is 00:02:01 and the cast of the White Lotus. And Andrew Arsorkin was at the Dealbook Finance Conference. But you know that that that stuff in office interview was two hours, but they reduced it down to 10 minutes. So there were probably a lot of sort of cordial conversation, banter, and then softball questions. And then he does stick the knife in and does the fricking seat, but he cuts out all the other stuff. So he just gets it down to the time. Absolutely.
Starting point is 00:02:28 What Stefanopoulos did to him was extraordinary in that he said over and over again, in the FTX terms of service, you cannot touch the user accounts, but you at Alameda were taking them and you were loaning them out. I don't know who is advising Sam Bankman Fried at this point, but why he is talking so much. He was also on a two-hour Twitter spaces after all this. At this point, Saks, what do you think is going on here in the mind of Sam Bankman Fried and also the media, which seems to have a very variable way of dealing with this obvious fraud and crime. Right.
Starting point is 00:03:12 Okay. Well, I can speculate about SPF. I think if there is a strategy here, it is this. He is basically copying two criminal negligence in order to avoid the more serious charges of fraud. And I think, again, if there's a strategy here, it is he saw himself being defined as Bernie made off 2.0 in the press. And if that image, which may well be true, cemented around him, then prosecutors would never stop. They would never accept a plea that
Starting point is 00:03:45 basically gave him anything less than a made-off like sentence, which would be, you know, decades in prison, maybe a life sentence. So he is out there doing what lawyers would tell you never to do, which is basically increment yourself, create more of a record, but he's doing it to change the public perception, maybe muddy up the public perception, get people thinking that, okay, he's a mini, he's a mini, he did something wrong, but it wasn't deliberate, it wasn't fraudulent, it was just basically carelessness or sloppiness,
Starting point is 00:04:17 and if he succeeds in mudding the waters enough, then maybe the prosecutors will give him a plea deal that allows him to have his life back at some point. I think that would be the crazy like a fox explanation of what's happening. Now there is an alternative explanation as well, which is I just think that these types of guys, you can call it a narcissistic fraudster, they think they can talk the way out of anything. Because they have. They have.
Starting point is 00:04:46 Yes, they, and they've talked their way into getting hundreds of millions of dollars of investment, billions, billions, in some cases. And so they just feel, and they've been trained by employees, partners, investors, the press that they can talk their way out of, and the stuff. Yeah, the average person is not really used to dealing with one of these
Starting point is 00:05:06 personality types, who is, I mean, they clearly are smart and they're articulate, articulate and they know what to say, and they're crafting their words. What they've learned through their life is that if they use the precise magic words with a person, they can pretty much convince them of anything, get them to do anything. And in particular, I would say investors tend to fall for this, not because investors are dumb, but because investors are so clear about what they're looking for and what they want.
Starting point is 00:05:32 They're pretty good. Yeah, like VCs, especially, we're looking for the 100X outcome or whatever. So it's easy for this type of personality to construct a story, to essentially stroke the origin of zones of a VC. Yeah, and sort of trick them. And so there is probably a positive reinforcement loop that gets created in the minds of one of these people, and they start to think that they can basically
Starting point is 00:05:56 talk their way out of any situation. So I think that would be part of what's going on here. And if you look at sort of the tactics that he's using to do this, you know, all of a sudden, he's trying to portray himself, you know, before this, he was portraying himself as a smart guy in the room. Now, all of a sudden, it's this babe in the woods in question where I didn't know, it was my subordinates.
Starting point is 00:06:18 I wasn't really in control. That was somebody else. Right. Right. Each individual decision, he says, looked sensible to him. It's just that all added up to something he didn't anticipate, like really? Loaning yourself a billion dollars of basically the company's money, which was basically customer money, that seemed reasonable to you.
Starting point is 00:06:37 I don't know how you defend that individual decision, and there's many like that. But this is sort of the narrative that he's trying to construct. And let me stop there, but I think there's a lot more that can be said to dismantle the narrative he's trying to create. But I want to look at the poll. What's your take on this in the Freiburg? Can I make a comparison to SPF and Trump through the lens of the media? So if you go back to 2016, you know, Donald Trump violated every single establishment bias that these left progressive journalists elites had. And so they basically just attacked, attacked, attacked, attacked. But then you went into the election and there was a very clear data point that said whatever you thought was at best limited
Starting point is 00:07:28 and you missed the tone of the country because 50% of the country held a very different view about this person. And instead of taking a step back and then the left media, the mainstream media, re-underwriting and learning and then saying, you know what, mea culpa, I got this wrong, they just double down. And they said, no, it still doesn't meet our priors. And so we're just going to ring fence this problem. And we're going to just try to destroy this issue because, you know, we want to control
Starting point is 00:08:01 the narrative and and and by result result we want to control power. Now you look at SPF, it's the exact opposite. He went to the perfect elite private high school. Then he went to one of the most prestigious elite private universities. MIT is parents teach governance of all things at one of the most elite liberal institutions in America. Stanford. They are in the establishment of the progressive left.
Starting point is 00:08:30 And what happened was he took customer funds and all of this money. He made tens of millions of dollars of political donations. He wrapped himself in this blanket of a progressive left-leaning cause called effective altruism, and all of the mainstream media fell for it and embraced him, as well as some politicians, because it met everything that they themselves also bought into. Yes. And now you have this cataclysmic event, multi-decadekabillion dollar fraud or bankruptcy, millions of customer accounts who are frozen, tens of millions to hundreds of millions to billions of dollars lost and stolen from them, and they refuse to reunderwrite this kid.
Starting point is 00:09:17 And the reason is because in order to do so, it's like eating your own tail. And that's why they don't want to do it. And so this is why you have the media basically allowing him to do an apology tour. Now, this is his second time manipulating them. The first time he was able to manipulate them by basically being one of them. And now he's allowing them and their desire to basically protect themselves so that he can create some kind of a defense for himself. And I just think the whole thing is gross because it misses the entire mood of the nation.
Starting point is 00:09:51 This is an enormous financial fraud that was perpetrated on tens of millions of people. And there's no accountability because in order to do so, the media would effectively have to admit that they missed it and they got it wrong and they refused to do it. And I think that is the really big problem that nobody is really speaking out about. It's like, well, if these folks are meant to be the last stop to make sure that there's truth and honesty and transparency in society, and you can't count on them, and in fact, they're just going to reflect their own narrative. What is one supposed to do to learn the truth? in the state of the state of the state. And so, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know, you know of America. It reflects every single aspect of institutional rot that every non-elite talks about all the time, but elites when they have those labels will refuse to give up.
Starting point is 00:10:51 And just to add to that, the thing that's missing, I'd say one of the big issues with the institutional rot in our country is the lack of accountability when somebody gets it wrong. We saw this with COVID, right? The health establishment is saying that they want amnesty and a landing magazine was willing to give it to them. So the point is that this this class of people think that when they get it wrong, that they're the experts, but when they get it wrong, there should be no accountability. And so Jamoth, to your point, the media and these institutions are not willing to rewrite SBF when he's so clearly as a fraudster. Freiberg, what do you think of this theory? You had a large amount of donations to politicians.
Starting point is 00:11:34 Obviously, you have coming from Stanford, MIT, et cetera. And then you have these investments, gifts slash advertising, slash donations to pro public of Vox, this new publication, Semaphore, the intercept that have all been uncovered now. Did he do this paying off of all the elites, you know, splashy cashy giving money to everybody because he knew he was doing a fraud and that this is evidence of this is a premeditated fraud. Or do you think this is a premeditated fraud or do you think this is a deranged individual who just was seeking status? I don't know.
Starting point is 00:12:10 There's a video you can watch at this guy. For some reason, FTX has left up all of their videos on YouTube from three years ago called quantitative trading, seven and a half thousand cell wall of Bitcoin on Binance. It's a 17 and a half minute YouTube video of SBF trading arbitrage across markets. I think it provides probably the best natural, non-scripted insight into this guy's behavior that you could see, you know, because it's not like him being interviewed. It's just him living in his world. And he's just, you know, a mouse trying to get a piece of cheese. Like he's, you know, he's like
Starting point is 00:12:52 out there. He's, you know, scrambling around in the markets. He's finding edges. He's finding advantages. And he's clearly just taking advantage of him all day, every day. That's who he is. Now you put a person like that in an unregulated environment, and there was this clustering demand for an unregulated environment because of a lot of what you guys are saying, which is people have this disdain for the elitism and the institutional rot and all these things. So Bitcoin emerged as a solution out of 2008 to the, you know, the, what felt like institutional rot that governments have a key role in. But when you have no regulation and you have no trusted central authority involved, mice
Starting point is 00:13:38 that are trying to find cheese will rule the day. And I think that's what happened here. If it wasn't this guy, it was someone else. It was going to be someone else. And then all of a sudden, everyone's clamoring and saying, Hey, we needed the government to protect us. No one protected us. Someone's got to save us. We're the regulators. We're people that are supposed to keep an eye on this stuff. When the whole premise of so much of what was being sold was non-regulatory regimes, was openness, was peer-to-peer trust protocols. And it turns out that in that sort of an environment, the mouse that is hungriest for the cheese
Starting point is 00:14:08 will get the cheese, and that's exactly what happened. And I don't know how much of it was... I don't agree with this. Him saying I'm creating intentional fraud, which certainly seems to be the case, versus him saying I'm gonna pay these guys. I don't know how much of it was even that intelligent, but the guy was clearly like trying to get a piece of cheese.
Starting point is 00:14:24 Okay, so this cheese eater, this rat is a league of legends, you know, expert playing on eight different monitors at a time, the cryptocurrency game, while hopped up on speed. I'm not saying that to be cruel. I'm saying that because they admitted it. They talked about it in their staff meetings, instructing their traders and team members of how to take speed. He admitted to it in an interview this week. Yes.
Starting point is 00:14:51 He said that it was all legal prescription drugs, but they were taking them, yes. Yes. And literally in the same video, as you're referencing, people see speed patches, or I don't even understand this, but there are patches you can put on your body to deliver speed to you at some, you know, dose or whatever, sacks you by this theory. No. Care that this isn't about the elite side of it. It's about the non-elite, the energy side of it.
Starting point is 00:15:14 No. And this cheese eating rat was just wanted to eat more cheese. No, I don't buy this narrative because I see too much design intentionality between what happened. So in other words, it wasn't just a series of individual decisions that didn't add up. Many of those individual decisions by themselves were totally unjustifiable. And moreover, there were too many,
Starting point is 00:15:38 there's too much evidence of sophisticated behavior here. Again, he overnight went from portraying self as a smart guy in the room to the to the babe in the woods. And so for example, when you look at the construction of all these entities and the corporate org chart, you know, of all the related entities, it's a very sophisticated attempt to obscure and construct certain, you know, protections. When you look at the way that Alameda was exempted from the normal margaric
Starting point is 00:16:08 requirements and ftx there was this so called back doors there was intentionality there was intentionality in terms of who was hired to staff these organizations again they was in hired no board no cfo yeah exactly and the guy the guy who was in charge of compliance, what like Jamal talked about in previous episode, was the guy who was involved in the ultimate bet poker cheating scandal, you know, not super mode. Yeah, exactly. Right. Or look at this goofy goofball Caroline Ellis, and it was put in charge of Alameda, right? His girlfriend. It's it's being done for a reason, right? He's setting it up in a certain way. And you know, the one time I interacted with him at this tech conference, he was sitting there holding court and he had all of his minions around him who were following his orders. This was a guy who was controlling his business.
Starting point is 00:16:57 He was making the decisions at, I think, a task level. And he knew exactly what was going on here. So look, I just don't buy. I do not buy this idea that he was like a blind mouse who's just stimulus response in the moment. Oh my God. By the way, that wasn't my point, Sacks. My point was whether it was him or it was gonna be someone else, it was bound to happen.
Starting point is 00:17:23 That the idea, another criminal would have emerged. that the idea that we want to have completely free unregulated Bahamian based trading, you know environments that we can supposedly trust because someone puts on a good face when there is no real regulatory body and regulatory authority overseeing it at some point it was gonna happen. Well, no, hold on. It is. Look, coin base is a fully regulated institution. They're not set up in the Bahamas and they're not unregulated. He set up and he had no oversight. He had no board. There was no regulatory regime. There was nothing. But how is he able? Okay. So first of all, look, I don't think this had to happen. I think that, again, I think that excuses too much because it implies that
Starting point is 00:18:01 if it wasn't SBF, it'd be somebody else. I actually think that this was a highly concerted effort. Listen, he courted regulators. He donated to politicians. He courted the media and donated to them. This was really good at it. He was really good at it. He was actually good at it. No one, I totally agree on that.
Starting point is 00:18:17 Yeah, super smart, super connected, really thoughtful design on how he committed this. I only think an insider could have pulled off something at the scale. I think this is where it's your exactly right. He needed to be an insider. He knew the playbook and he admitted it. You pointed this out with the chats that were released where he said he, he, he, yeah, look, I mean, just like he,
Starting point is 00:18:38 he chat, he looked like convoluted and intertwined. All these people are like gensers intertwined with the parents. Yeah. Parents apparently bundled a bunch of money to Elizabeth Warren. You know, he was dating the CEO of the business at EO 90 percent in. There are all these other random shell companies that he owned 100 percent of where they were lending back and forth hundreds of millions to billions of dollars. Yeah.
Starting point is 00:19:02 To David's point, that is a sophisticated con that you have to architect. And the way that he was able to get away with it is that not a single reporter or regulator thought to dig in. And the reason I think is because he said all of the right things that wanted them to embrace him. And the reason is, he admitted. This is a dumb game that we woke Westerners have to play. Like a maddie. The right should be less. And then reason is, he admitted, this is the dumb game that we woke Westerners have to play. You say the right shibbolas and then everyone thinks we're a good
Starting point is 00:19:28 person. Exactly. Imagine, hold on, quote up on what he said, because it's actually good. It was what I just said. Exactly. He said, it's the game that we woke Westerners have to play. We say the right shibbolas, or everyone likes us. He actually said the most uncomfortable thing out loud, which is, look, by having gone to Crystal Springs High School, by having professors, by parents that went to Stanford, by having gone to MIT, I can pull this off. That's what he said, because he can go with those things, because I'm a champion of effective altruism that I can justify any of these decisions, how amoral or immoral that they be, because I'm trying to help, you know,
Starting point is 00:20:05 my brother stand up a multimillion dollar pandemic response business, I'm trying to do this, I'm trying to do that. And all of these regulators and all of these reporters said, okay, you get the hall passed. Now, imagine if you replaced him with some random kid in some developing country, or even from the United States who did went to public high school, who went to some random state school. Do you think that they could have pulled any of this stuff off?
Starting point is 00:20:34 No. You need the patina of the privilege class. The New York Times. That's what he had, the patina of the privilege class. Even after this fraud, the New York Times wrote more of a puff piece on him than the hit piece they wrote on Brian Armstrong last year, when Brian Armstrong wouldn't tow the line on allowing politics at work. Remember that?
Starting point is 00:20:53 Yeah. Unbelievable. Yeah. So the big end, I think what Jamalath is kind of saying here is that the big enabler here is not crypto per se. It's all these institutional biases and elite biases that he was able to play into, partly because he was a big insider. I mean, in a way, he monetized his parents' life work. The problem that I think this allows us to put a fine point on is the following.
Starting point is 00:21:15 You know, in society, we've confused a lot of people to think that the opposite of liberal is conservative or Republican. And I think that's the cycle that drives the mind virus inside the mainstream media. The problem is the opposite of liberal is illiberal, okay? And what a liberal means is to be narrow-minded and unenlightened. It means to be puritanical. It means to be fundamentalist. And this is really what it allows us to see now.
Starting point is 00:21:46 We have now had six years of data, case after case after case, where if you are woke, if you are a social justice warrior, if you have the right credentials that justify your upbringing, if you have institutional bonafides that come from your parents, you get to create the narrative and you get a hall pass. And everybody else basically is at the subject and the mercy of the mainstream media. And so if you don't kiss the ring and bow down to them, they will try to destroy you or run you out of town. But if you are one of them, they will give you a hall pass. And when it's time for them to change their
Starting point is 00:22:29 mind in order to tell the truth, they won't do it. And so these types of griffs will continue as Friedberg said, because there is no check and balance without a healthy, independent media. There is no way for all of us to actually know what's really going on. Guys, some person in the media could have asked the question and dug in deeper around the connections between Alameda and FTX for the last 24 months. No, could have delegents at Adventure firm. At no point, could any person have asked these questions and found ex employees and said, are there any unseemly
Starting point is 00:23:05 connections here between FTX and Alameda? There was no disgruntled employee. I mean, every company has disgruntled employee whistleblowers. But here, where there was billions of dollars being made by tens of people, not a single person who felt on the outs said anything. Well, he was also giving millions of dollars to press outlets. Hold on. It's because the questions weren't asked. And then this kid paid hush money to the mainstream
Starting point is 00:23:28 media. Let me ask you a question of you guys. Do you think that it's the media's responsibility in this context or do you think that there should have been a regulatory authority that had oversight of this business like there is for every bank and every training operation in the United States and every one of those businesses has a compliance officer and has regulators up the wazoo making sure that customers are kept safe and protected. Or do we think that that should should offshore vehicles be allowed like this that allow people to operate?
Starting point is 00:23:54 It's a reasonable question, but there was a chicken and egg question. We were all standing around holding our hands while the CFTC and the SEC were fighting. That's not something that consumers can be expected to adjudicate. So yes, we should have legislation that clearly defines all of this, but there were enough parameters that created regulatory frameworks where a bunch of good actors did operate in them and are continuing to do so like Coinbase. So I don't think this is a regulatory issue. I think that if you believe there are people who are supposed to forensically examine things and get to the bottom of things and ask hard questions
Starting point is 00:24:30 those people did none of that here and and what's what's even more worrisome is what they're showing is now with an massive amount of data that shows that you could ask hard questions They don't care too because it makes them look bad. I disagree with this, Tremont. I think regulators failed here because they have been reactive to crypto. They have not been proactive and they have not been clear with the crypto community that what they were doing was illegal and they should have put the regulations in quicker and they're playing catch up. But all three groups failed. The media failed, the regulators failed, and VCs failed capital allocators failed I apparently to do diligence here and install proper governance you cannot put a company like this You know in business Millions of dollars and have no board of directors. No, I agree with you or he lied to them
Starting point is 00:25:17 I'm just possible my point is that while regulators are are basically fighting a territorial turf war Yeah, okay, the media could have still done their job. They chose not to guys while regulators are are basically fighting a territorial turf war. Yeah. Okay. The media could have still done their job. They chose not to. Guys, it was worse than that because not just a case where the SEC failed to exercise any oversight of him or dig into any of these questions. He was in the room with them crafting the next set of regulations.
Starting point is 00:25:40 He was working on the regulations that you're talking about that are supposedly needed. Well, breaking them. They let the fox in the hen house. He was going to craft a new type of regulatory license for these types of exchanges with the result that he was going to get one as some of his competitors weren't. This is one of the things that triggered CZ to basically do what he did, which is basically that SPF was trying to get finance and competitors like that band while SPF would be one of the sole people to get the license. By the way, Jason, here's a example.
Starting point is 00:26:16 Here's a work, Jason. We're the regulators. Yeah, Jason, you just said something derogatory towards CZ. He rug pulled them. Huh? Did he do that or did he actually expose the fraud? That's what I mean by rug pulling. Yeah. He was partners with him. That's what rug pull means, Jason.
Starting point is 00:26:28 Okay. Well, he was partners with him. And then he realized he was weak and that he was doing some stuff that was shady and excited. He would eliminate a partner who was creating regulation. A sac said, whatever you want to say, he knife. All he did was indicate a desire to liquidate his position in a token that was supposedly
Starting point is 00:26:45 perfectly liquid. That's basically that caused everything to unravel. But these were partners, right? These were partners. No, they're partners. And they were partners. They were collaborating on these tokens together. So they weren't competitors.
Starting point is 00:26:58 No, they weren't. They weren't. Jason, part of the big loan that initiated all of this stuff like a year and a half ago was to buy FTX off the cap table. So, you know, all I'm saying is like, you used words and you're framing of a guy, you know, who's built a business is like, he is this nefarious bad actor.
Starting point is 00:27:19 But, the idea that he accesses first investor, hold on a second, but David's right, all the guy did as far as we can tell right now is tweet, I'm selling this token because I don't believe in the capital structure of this entity and he got those tokens by being bought out of the cap table. I know he was partners with them.
Starting point is 00:27:36 So if you, if you're all like rugpulled, how about backstab? These were business partners. They're not partners. You still don't understand, Jason. Of course I understand. They, he was the first investor. So to do this, he got part out. No, no, he got part out.
Starting point is 00:27:50 If you're in the consideration, part of the consideration were these tokens, these FET tokens. I understand, yes. Jason, when Uber went public, and you got distributed stock, did you distribute and sell Uber at any point? Previous to that, I had, I sold some to Massacre.
Starting point is 00:28:07 No, no, no, no, no, no, no, no, I'm asking you a question. When Uber went public and you got distributed from Uber, I didn't, you were stock. So you've never sold a single share of Uber and it's this public. No, I sold it before in private markets. Okay, but I'm sorry, but that doesn't make Jason a partner of Uber. You're just a stock holder. Yeah, this is slightly different, I think. But okay, fine, you guys, if you guys want to consider it,
Starting point is 00:28:27 you were the first investor in the company. They were a business- My business- They were a historical situation, but their status at the time that CZ tweeted, wasn't they were competitors? Okay, fine, I mean, they became competitors, I agree. And by the way, to Tomas Point about this rug pulling language, I think we're getting kind of done a rabbit hole here, but we still have a wee there.
Starting point is 00:28:45 Well, CZ did perform a service in this sense, okay? SBF claims that four billion more was about to come in. I personally don't believe that. Sounds like bullshit to me. But if it is true, that would have been a bad thing. The more money that came in to that operation, SBF proved that he was a very poor custodian of customer funds.
Starting point is 00:29:04 For sure. For sure. I'm not defending this. Yeah, but the longer this one or not, I'm just highlighting the language that you use is sort of like, again, part of that establishment elite narrative. And I'm just questioning, you should maybe steal men. Take a second to just steal men. Yeah. A more dispassionate view, which is, here's a counterparty, okay?
Starting point is 00:29:23 Yeah. Who, when he left the cap table, was given half cash, half tokens. Okay. And he decided to sell his tokens. Yeah. And tweet it publicly and cause a run on the bank. So, it was not a run on the bank. There was no bank. Where's the bank?
Starting point is 00:29:40 This run on the bank language, okay? Is something, this was in the semifore coverage, okay? He did it publicly. That's my point. So I'll still manage. No, no, no, no, no. These tokens are worthless. I need to liquidate them as fast as possible. But why would you do that publicly? Why would you do it privately? You're about to move the market. He wanted to move the market to zero. Yes, he wanted to keep him.
Starting point is 00:30:00 He's letting people know why. But he wanted to kill his competitor, as Tramoff was just saying. He's he wanted to kill his competitor as Tremoff was just saying. He's he wanted to kill his competitor. He told the market. I am. He was trying to do that. We got a backup here because I think we've done a lot of like 30,000 foot like lessons and like take away from this whole thing, but we haven't really established what it is
Starting point is 00:30:17 that SBF did wrong. So I think we need to sort of take a second to unmutty the waters. Okay. And part of that, I think we should start with this idea of a run on the bank because the press who've been writing puff pieces about SBF, I'd say mainly SOME-A-FOR, which he was a big donor too. We've been trying to frame it as a run on the bank,
Starting point is 00:30:35 and then that implies that it's not really his fault. It could happen to anybody, lots of banks have had this problem. Okay, first of all, they're not a bank. Banks actually have the legal right under certain conditions to take customer deposits and loan them out. Okay.
Starting point is 00:30:49 They did not. Their terms of use did not allow that as stuff in office pointed out. SVF's answer to that was, well, we had this like margin account program. There were other provisions in other terms of use. But most of the customers who lost money, the vast majority, did not opt into that program. They never agreed to that. So, that's point number one. Point number two is, I think we need to look at this language of margin account.
Starting point is 00:31:12 Okay? SBS explanation of how customer money was siphoned off for his own personal use, i.e. to Alameda, is that Alameda had a margin account. So I think we could perform a service here by explaining why it wasn't a margin account. And you know, Chimath and you guys understand this really well. The way that a margin account works is the following, okay, because I think some of us have them set up with investment banks. You go to an investment bank, say Morgan Stanley, and you over, you post collateral, You actually overclad
Starting point is 00:31:46 it lies. So for example, you might take a hundred million dollars of stock posted at the investment bank, and then they will let you loan a certain percentage, nowhere near 100 percent, maybe 50 percent. And that's what you're doing. So if you have a very, very liquid security, you may get 50 percent coverage, which means if you posted a hundred million dollars, you could get 50% coverage, which means if you posted $100 million, you could get a $50 million loan. Okay.
Starting point is 00:32:08 But typically 100 million in Amazon stock, you're some Amazon VP, you can get 50 million loaned. And if it's a private asset, it's anywhere as high as 30%, 35%, but typically it's about 25%. My expectation is an illiquid token like this would have basically gotten 5% or 10% coverage ratio at the best of it. And then what happens is you have these maintenance values. So if all of a sudden the value of these entities multiplied by that percentage that you're allowed to loan falls below, you have to post money. That's how a margin of care works. It's just
Starting point is 00:32:41 there is no free lunch in that. Yeah, exactly. There's a quite simply, very simply what I, it appears this guy did. He took customer deposits in US dollars. He then converted those dollars into some other asset. And he had a mark on that asset. Let's call it a dollar, a token. And then those dollars were moved to somewhere else. No, this is because someone transferred in some other token. But that's it. But we have to see that we need to finish the explainer around the margin account. Okay, because what SPF did is this he took customer deposits, gave them to himself. Just be clear. And no, he gave it he took customer deposits in US dollars. They were wired in.
Starting point is 00:33:27 Correct. He took those dollars out and he put a fake token in and he called that. That's right. He said that's right. And therefore he said the balance sheet is good. But the value of that token it turns out isn't a dollar. It's 10 cents. That's right. It was his it was his sort of it was sort of of his made up token that he tightly controlled the training of and artificially prompted the price. And by the way, it wasn't just FTT. But yeah. Yeah, but but here's the thing, it wasn't just the fact that his collateral was no good.
Starting point is 00:33:56 It was also the fact that, and this is from the bankruptcy filing by the the the Nron trustee guy. He specifically said that Alameda, like every other margin account on the platform, had the auto liquidation provisions turned off. So we have to finish the thought around how margin works. So like Tomas said, you over post collateral. And if the value of that collateral goes down, or the position your training account, the value of that goes down, you either have to post more collateral or they will actually liquidate your collateral to pay off the loan. So Morgan Stanley will never lose money on a margin account. Never.
Starting point is 00:34:38 The whole point is because they don't make money on it, they loan you the money at like a few percent, like very cheap loan. Lime more plus. Exactly. That is not a risk account to them. So in the example, let's use an example. In the case of the VP at Amazon, it's got a hundred million in Amazon, they have a fifty million dollar loan. If Amazon loses half its value, then that triggers the automatic selling of Amazon shares to get it back down to 50% coverage. So now you have sell 25 million of Amazon shares if the full 50 million was pulled down to get back down to 25 50% leverage. Yes, and they don't wait until like Amazon stock is at the exact level where now the collateral equals 100% of the loan.
Starting point is 00:35:20 They will keep that 50% loan to value. Yes. And they will liquidate you, you know, and by the way, you can lose your entire amount, right? So, you know, this is why I'm trading on margin is so risky, is that you get wiped out completely. You get wiped out very, very quickly with a small move down. Because they are the custodians of that Amazon stock, they are holding it for you now, and they have the right to sell it to cover your margin.
Starting point is 00:35:43 Right. You're saying that governor, that basic tenant, that basic safety control was turned off by Alameda. And it's even more sinister. Alameda controlled like 90 or 95% of these FTT tokens and was owned by Sam Bankman fraud. So he owned that company. Then he claims he had no operating position. Listen, what should have happened is with that collateral, is that as the value of their position was
Starting point is 00:36:09 going down and or as the value the collateral was going down, it should have been liquidated to pay off the margin loan. And that did not happen. And the reason it didn't happen is that Alameda got a special exception on the platform to turn off auto liquidation. Therefore it was never a margin account. If, even if it was a margin account, okay, and FTX somehow misadministered the margin account, it should never have taken other customers deposits
Starting point is 00:36:35 and use them to pay back that money. What should have happened is if FTX was gonna lose money on a margin account, that would hit the FTX corporate treasury. Okay, and when the FTX corporate treasury ran out, the company follows for bankruptcy then, and then all the other customers hold on. Their account is still there. Their money is there, in segregated accounts, and in bankruptcy, they get their money back.
Starting point is 00:36:58 The idea that a margin account could ever cause another customer to lose money. Like whatever that is, that's not a market. There's a great article there's a great article this one was a journalist that did his job properly his name is David Z. Morris. He wrote an article in coin desk that summed up for anybody that's interested. All of the actual fraud and all of the crimes that were committed in excruciating detail and And what's so sad about all these interviews and this press tour is, if anybody would just read this article, you can construct the right questions to ask this guy, just based on this one article. But the point I wanted to make is that one of the most interesting insights was these guys had lost an enormous amount of money already in calendar year 21.
Starting point is 00:37:47 had lost an enormous amount of money already in calendar year 21. And so this is what's so crazy, Jason, about, you know, you using language like rug pulling and like, you know, nobody backs actually trying to like be clear. Like you guys are giving this guy a hot pass. I'm not gonna be more honest. Any industrious reporter could have found an employee who said, wait a minute, we just blew a $3 billion hole in our balance sheet and calendar year 21. And now we're sitting here at the end of point two. It's a hard time. Hold on a second. Hold on.
Starting point is 00:38:14 I need to respond. I am not giving them a pass. And for you to blame journalists who are reflecting the crime and not putting any light on VCs and the Capitol allocators who made this investment and who did no diligence and now put governance in it is the height of arrogance, Shema. This is not the press is doing that. I this is the VCs. Where's that? Is the Capitol allocators? Well, you're blaming the people who are telling the story after the story.
Starting point is 00:38:40 They're covering the story. They're covering the story. I can't handle the truth. Jason, they're covering the story up. Okay, listen, I'm not talking about it. Can I get in here? Can I get in here? All right, listen, Jason, I will defend you against Tomas saying that somehow you're letting
Starting point is 00:38:53 SBF off the hook. I know you don't want to let SBF off the hook. However, you are letting the press off the hook. And the reason why, hold on a second, the reason why you're using this inaccurate language like rug pulling and run on the bank when there was no run and there was no bank is because you've been infected by this language that the media has inserted into the discourse. The media, listen, and hold on a second, investors may have got it wrong last year. Investors may have got it wrong when they did that last round, but I think investors now
Starting point is 00:39:21 understand what's happening, but the media is still covering for S.V.F. by mis-explaining what happened. Okay, give me a percentage act of who's to blame here. VCs who invested and didn't set up any governance, regulators who did not set rules around crypto and then three of the media. What percentage out of 100% is the investors, the regulators and the press go. Three numbers. I would say that before the fraud got exposed, one third, one third, one third. One third each before the fraud got exposed, but they were all extremely and severally liable. But after the fraud has been exposed, no investor is still defending SPF.
Starting point is 00:40:01 But I think that the investors who were swindled by him, they feel bad about it. So 30, 30, 30 is absurd. The press had no way to know the fraud was going on. Just like the VC with the money, and we're talking about. Jason, are you stupid? Like, was it your stupid journalist that exposed to fraud at Thernos? He's the guy that went and did all the work. John Kerry, you should be celebrated.
Starting point is 00:40:24 Hold on a second. John Kerry, you should be celebrated. Hold on a second. John Kerry, you went and found this thing. When everybody else was like, this is perfect. It meets all of our priors. Let me finish, please. It meets all of our priors. This is great. And then John Kerry, and so John Kerry was like,
Starting point is 00:40:37 this doesn't pass. The smell test to me. Let me go do some work. And he pulled one little string. And over the course of 18 months, he exposed the whole bloody thing. So hold on a second. So what is incredible to me is that it was possible to expose this thing before. Nobody did. I agree with David. It's about equal responsibility before, but afterwards, the bulk of the
Starting point is 00:40:56 responsibilities now sits with regulators to clean it up and journalists to tell the truth. Okay, and now may I respond to that since you call me stupid? You are delusional. Number one, every one of those investors in Theranos could have taken a fucking blood test at two different places like Jean-Louis Gassier did and write a blog post and prove that Theranos didn't work. And they, with hell disbelief, investors putting in a hundred million dollars, including Rupert Murdoch, didn't even take a fucking blood test or tell one of their diligence teams
Starting point is 00:41:30 to do it. The same thing happened here with the investors in FTX. They did zero diligence. They set up zero governance. This was a failure of the investors and the governance for 99% of the problem. And then regulators should have caught it, and the regulators in fact did catch their nose, so you're completely wrong, Jamoth, again.
Starting point is 00:41:51 The journalists come in after the fraud is happening, the investors and governance is responsible for stopping these things. FTX was a failure of governance and investors, and so is their nose. The end. You're completely wrong. The question is post, post exposure.
Starting point is 00:42:07 Why are you guys obsessed with post? How about avoiding these things? You guys are blaming. Because it's a story is ongoing. Because it's a story is ongoing. You're blaming journalists for something that is capital allocators responsibility. It is our responsibility to do diligence.
Starting point is 00:42:19 It is our responsibility to create a board of directors that checks on Elizabeth Holmes and Sam. I didn't disagree, I didn't try to. Nobody disagree, but just call me stupid. You just call me stupid for pointing out something that you refuse to accept. What are you talking about? I'm the founder that has the most
Starting point is 00:42:35 sole creators created this. I'm the older brother. I'm sorry, you didn't mean what I was trying to do. I was skipped over. You guys are giving a pass to the investors Impression again, I'm not doing Frado. I'm not doing Frado People You can't call dumb. Totally, he loses it. He goes berserk. No, we're not going berserk. You guys have a point. Yeah, you have the kind of culture responsible.
Starting point is 00:43:08 He's like, don't you, don't call me dumb. I'm not going to defend any single one of those investors. I mean, I think that they did a horrible job too. It's a great episode. But the reality is just right up. But the reality is I think that if you think that you can, if you, it's your decision to defend the mainstream media, I think that that's fine.
Starting point is 00:43:28 I'm not defending them. No, you are. You said they have no risk. Blaming the VCs, it's different. The copability is with the investor class that has not had proper governance and you know what Jason, how many articles have been written excoriating them? Oh, yeah, some where.
Starting point is 00:43:44 A lot of people like fools. Yeah, yeah, some. We're handling. It sounds like fools. Yeah, I mean, show me the Washington coil is capital. No, show me the Washington coil is capital. New York Times that's like digging in to that malfeasance or that lack of oversight and holding them accountable in a way that you feel exposes this problem to create change. Well, if we look at there, Enos, those people who invested, including Draper and
Starting point is 00:44:08 just show me these examples. River Murdoch, they really went after them, for sure. Yeah. What about here? Wall Street Journal, one day ago, Sequoia Capital apologizes to its fund investors for FTX loss. Venture Capital firms tell fund investors that it will improve due diligence on future investments after a hundred got a lot they really got me let me let me read you cover story journal. I'm gonna I'm gonna read you I'm gonna read you a sentence from the New York Times coverage of sbf and Sam I'm not afraid of second Sam Bank would free does neither a visionary nor a criminal mastermind He is a human who made the same poor choice that generations of money managers have made before him. Are you effing kidney?
Starting point is 00:44:46 No, I am not defending them. That was the New York Times coverage. Yes, you are. They also said, I am not defending them. I just called the New York Times to get a suit. I just called the New York Times to get a suit. And then, Simma Four, who was on the take, who received millions of dollars of money, said it was a run on the bank.
Starting point is 00:44:59 How much did they get? Now, where is their apology? Hold on a second. Where is their apology? Sequoia has apologized. Where is their apology? Oh, it has to come. I'm not defending the press. Yes, you are. Yes, you are. You are. I am not. I am literally telling you that the New York Times has been asleep for three times apology. The press is always demanding an apology from everybody else. Hold on a second. The press is always demanding. The Twitter spaces yesterday did a better job of trying to ask questions and getting
Starting point is 00:45:26 to the truth than a single journalist has done or the collective body of all of journalists. Absolutely. Totally. Literally randos on Twitter spaces did a better job than Sorkin. Let me tell you why that why no one trusted press Jason. First of all, they have an agenda. I agree with it. Second of all, when they make a mistake, they never admit it.
Starting point is 00:45:42 When's the last time they did an apology or retraction. Once the last time they did what Sequoia did. I don't know. And they need to apologize about your time. I am in agreement with you on that. But I think we have to first say, and this is where you guys have a mind-sponsored. I have a mind-sponsored.
Starting point is 00:45:56 Is what is the responsibility of capital allocators and governance and regulators? I think it's one, two, three. Our industry is responsible for sending our proper governance. The regulators are responsible for making sure that scientific claims are backstaffed. And then press is a distant third. You know who I think is responsible, SVF.
Starting point is 00:46:16 One, two, and three. And then we can talk about four, five, and six. Okay, four, five, and six. Capital allocators, regulators, the press, a distance six. I agree. Let's go on to China. God, it's so spicy today. God, it's so hot.
Starting point is 00:46:29 I mean, I do think when we attack the mainstream media, Jason feels a little twintinge of like insecurity and illegitimacy because you were a journalist. My personal perception is I think that's bullshit. I have it. I think that you have an incredibly romantic view of the craft as you practiced it back then, which I think I do. Yes, full of integrity. Yes, I do. I think that you don't adequately realize how massively the industry has changed in the last 20 years since you've come to that.
Starting point is 00:47:01 I realize it more than you do. I fully realize that the media has absolutely become biased and they have lost, in some cases, yes. I mean, if you're taking money, are they for SPF? Are they giving him, they are corrupt if they're taking money from SPF and then giving him kick-love coverage.
Starting point is 00:47:17 Absolutely. That is the definition of corruption in my mind. What is it called when you don't take money necessarily like the New York Times and still treat them with kick-lobs? What is that? It is extreme bias. And the New York Times became incredibly biased. Why do you think the bias? Why do you think that bias exists? They were always left leaning, but I can tell you why. They, when Trump came in, a generation of new journalists became activist journalists. They didn't want to tell stories
Starting point is 00:47:43 and take a straight down the middle and let the facts tell the story and let the audience make their own decision. They felt that existential risk when Trump came into office, they got Trump to arrangement syndrome. They picked aside like MSNBC and Fox did and the business model became for the New York Times, pick aside and get the subscribers. It was a deliberate cynical choice on the New York Times part to go full MSNBC for full Fox, the two extremes in mainstream media in order to get the subs. And they literally rallied the troops there to do anti-tech, anti-Trump coverage, and they became activists. And when journalists become activists, they are no longer journalists, they're activists
Starting point is 00:48:22 or commentators. And that's the problem. It's being presented as journalism when in fact it's activism. So you're right. So just shut out to Matt Taibi who just did a month debate. That's well said by the way. Yeah, on this very topic and he has a great, great sub stack basically saying what you're saying Jason and the best quote is the story is no longer the boss.
Starting point is 00:48:43 Instead we sell narrative. He's a lifelong journalist whose father was lifelong journalist and he understands the way the business has changed. And it's like what you're saying. And this is why independent media, whether it's substacts, whether it's calling shows, whether it's oil and podcasts or other podcasts, Joe Rogan, Sam Harris, whoever it is, independent voices are now what consumers are seeking out because they can sense the bias.
Starting point is 00:49:07 They know Rachel Maddo and Tucker have an axe to grind and they're left and right. They didn't expect these New York Times, Washington Post and Wall Street Journal to, you know, they knew they were leaning. They didn't expect them to pick a side. Do you think we should cancel? If folks, do you think folks are better off keeping their New York time subscription or replacing that New York time subscription with a basket of substats?
Starting point is 00:49:31 And yeah, you answered your own question. It's the latter. I think you're on your own as a consumer now. You're gonna have to, and I think this podcast, and the nuance we have to shout out to Freeberg for nuance. What we've done on this podcast is what's the funny stuff? To explain to people. Freeberg's not. Well, we've done on this podcast is the funny stuff to explain to people.
Starting point is 00:49:46 Freeberg's not the only one with nuance, Jake. Nobody would describe David Sacks with the word nuance. Why do you use a nuance department on this podcast? What am I? 100% he is. But you wouldn't know that because you leave in science for a true department. I'm the truth department.
Starting point is 00:49:58 Sometimes new ones. Your truth bombs. I'm the truth department. The point is, consumers need to become extremely literate and they have to do their own search for truth in today's age. They shouldn't trust New York Times, they shouldn't trust us, they should trust themselves, they shouldn't trust necessarily the CDC or the World Health Organization, they should trust themselves and come up with their own process for figuring out the truth in the middle of this mess. By the way, this is a good reflection on what's happened
Starting point is 00:50:27 with the rest of media with respect to the creator class, where it used to be the movie studios and a handful of aggregated creators that made all of the content, the record labels. And now independent artists, independent producers, independent creators, and now independent journalists are gonna become the bulk of volume that's gonna be consumed.
Starting point is 00:50:49 It's just a different consumption model. But we've only seen it happen in terms of... We saw it happen with movies and we've seen this disruption happen across all of these other media classes. Journalism and what we call the press is very likely gonna be kind of that next layer of disruption.
Starting point is 00:51:04 I would trust having a conversation with you about science topics, over reading a science article. 100%. You know, in the New York Times, they're Wall Street Journal, if I'm being 100%. I would much prefer to talk to you about it. And if it was markets, I'd rather talk to Schumann, and if it was SaaS, I would talk to SaaS, or operating a company, speaking of operating a company. Corporal politics.
Starting point is 00:51:23 Mmm. Mmmal politics. Hmm. Hmm. Hmm. Hmm. We'll see. We'll see. But I think it's about having unique insight, right? Like, that wasn't the case.
Starting point is 00:51:35 And what's interesting is that the people who are the professionals that have the knowledge and the touch points are also becoming journalists in the sense that they're also becoming speakers of their truth, right? And I think Twitter is a good enabling platform for this. We see it on YouTube where scientists are putting out their own videos or market actors like people that are traders in the market go out and they put out their own videos and they put out their own podcasts. And I think we're probably a good reflection of that in the sense that like we are the actors in the market and we're not just the independent observer that has kind of a surface level view. We have the depth to be able to talk about the
Starting point is 00:52:11 things that we choose to talk about. And I think that's where consumers find value and we'll continue to find value in terms of who the journalist or speaker is if they're going to start to trust for their information. I had. I saw that interview you did with newcomer. Oh yeah. Yeah. Yeah. I saw that. Yeah. I saw that. I mean, he speaks a lot about the this phenomenon of going direct. And of course, he's against it. Now, he interprets going direct as an attempt by newsmakers to avoid answering tough questions or take tough questions. I think it's ridiculous because for example, I go on CMBC all the time, I go on Emily Cheng and
Starting point is 00:52:52 Bloomberg all the time. I submit to like really tough questions. I actually like those sort of sparring sessions. Yeah, I did hard talk this week. Have you ever done that? Yeah, exactly. So that that's not what's going on here. I think what's going on is we have expertise We want to communicate them and we do feel like the media has become a very unreliable narrator There is too bias and Loppiness not all of it is agenda so much is pure sloppiness and there's no reason why we shouldn't go direct and people want to hear from us They're audience wants to hear from us same Same for look, look at Dremont. Look at Dremont in the success he's had with his pause.
Starting point is 00:53:27 I'm no basketball player has ever gone direct and created content like Dremont's created and it's totally changed the game. And he was so clear he's like, we are, I am the media now. I mean, that's, JJ Reddit, you know, old man and the three amazing, amazing podcasts. I was gonna tell you guys a story. So I was in the Middle East last week or this week, sorry. And I had this crazy experience where I was trying to understand
Starting point is 00:53:50 what was going on in China. And so I started on CNN. And the whole thing was the propaganda machine around a democratic revolt, you know, pushing for democracy and trying to depose G. ocratic revolt, you know, pushing for democracy and trying to depose G. Then I moved to al Arabia. So one channel up, I went from channel 10 to channel 11. And instead what they were actually doing was interviewing people on the ground. And what they were talking about was literally how these PCR tests had become far too burdensome. And they just wanted it to end and more reasonable restrictions to get in and out of quarantine. Then I went from there to a BBC and in BBC they had a China scholar who was talking about how for decades actually the Communist Party supports local level protests and demonstrations
Starting point is 00:54:37 because they've realized that it is a part of their political system to make sure that people feel like they have a say. And I was like, taken a step back. And I'm like, if you listen to the US narrative in even Jason, like in our group chat, people for menting for like revolution, and this is Tiananmen 2.0. And I'm like, well, I'm reading two other channels that tell us a completely different set of things. And I just thought, man, people just really fit the data. That's such a good point to fit their bias. Yeah, we are projecting. We want to see our revolution in China. The people in China want you to have their lives back. I would love to see more
Starting point is 00:55:13 democracy in the world. Yes, guilty as charged. I would like to see people be more free in the world. Dictator, I think most people just want to improve their condition. And I don't think people are as tied up on the philosophy of the government as they are about improving their condition. And as long as their condition is improving, they're willing to put up with any form of government. And history shows that. By the way, the conditions in China have improved better than everybody's in the last
Starting point is 00:55:38 day. It's better than any one 500 million people out of abject poverty. And that's the great success of engagement. Isolationism would not have created that amazing outcome. 500 million people going out of object. You're referring to us throwing up all the factors. You're saying. That's what I'm referring to.
Starting point is 00:55:58 Oh, okay. So if they want to build something over there, I guess that's better than us throwing out open our markets and giving China MFN status to destroy American manufacturing and build up their economies so they can become a peer competitor to the United States. Yeah, I mean, this is the balance of engagement. If you engage too much, you give everything up. Sex, which of the current Republican agenda do you disagree with most strongly, just as an aside? Well, most Republicans are in favor of, are you crane policy, this sort of unlimited appropriation
Starting point is 00:56:33 of weapons and aid to them? Don't you disagree with immigration policy of Republicans and Democrats? Well, I have a more nuanced position of immigration, which is I think we need to have a border and it can't be just like an open border, which is the day factor policy to have a border and it can't be just like an open border, which is the day factor policy we have now. But at the same time, I do think that we should have H1B visas and we want to, like Jamassah, we want to be an all-star team for the world. We want to have the best people want to come here. So there's a balance.
Starting point is 00:56:56 It's a balance. And then, you know, look, I think that I was happy to see the marriage, a quality bill, finally passed the Senate. Yes, they did get about a dozen. 12 Republicans voted for it. So that's great. But that's not the majority, unfortunately. You know, look, on what I would categorize as the old social issues, like a marriage, like Canvass legalization, I was on the liberal side. Yeah, I don't think banning abortion entirely a total abolition is going to work for this country. I think Republicans will lose elections if they insist on that, and I think they're getting that message.
Starting point is 00:57:33 So, yeah, I mean, look, I think that I'm always considered myself to be pretty centrist. And so you're not a globalist. You don't believe in open global markets with the US. In general, I understand the benefits of free trade. And I don't think we should be isolationist with respect to trade. I don't think that we can be a successful country if we are, we isolate our economy.
Starting point is 00:57:57 So I do want to trade. However, with China in particular, I think we made a mistake in throwing open our markets to their products, giving them MFN status while they go to the North. You favor nation in reaching them to the point where they became a peer competitor of the United States. Now, look, I understand why we made that mistake 20 years ago because everybody thought the theory was that if we help China become rich, that China would inevitably become more democratic and they
Starting point is 00:58:25 will be filled with gratitude towards the United States and they will become more hospital towards us, more westernized. I think that theory has just proven to be wrong. I mean, they have not. Or it's going very slowly, one or the other. Let's own our clips here. Here is Shamaat's prediction from episode 61, and we'll see you on the other side of this quick clip. My worldwide biggest political winner for 2022
Starting point is 00:58:51 is Xi Jinping. I think this guy is, he's firing on all cylinders, and he is basically ascendant. So 2022 marks the first year where he's essentially really ruler for life. And so I don't think we really know what he's capable of and what he's gonna do.
Starting point is 00:59:10 And so that's just gonna play out. You think he's the biggest political winner, really? Oh my God. I think it's going to be a, he's gonna run rough shot, not just domestically but also internationally, because you have to remember, he controls so much of the critical supply chain
Starting point is 00:59:24 that the Western world needs to be completely right. I think you're completely right. I think he's losing his power. He's scared. That's why he took out all these CEOs. He's consolidating power because he fears that they're going to win too big and then displace him.
Starting point is 00:59:39 And he has massive real estate problems over there that could blow up at any moment in time. He could face a civil war there. I think he's totally isolated himself. Civil war, and they don't even have great major country is removing their factories and removing his dependency. What are you talking about? What are they going to riot with? Did you not see Tiananmen Square? Did you not see the riots in Hong Kong? Are you not paying attention to Shemoth? There's been many riots in China. They just haven't killed the police. So those were crushed. And that's not the story of the actual control.
Starting point is 01:00:07 But he still will have massive amounts of, I believe, protests. And yeah, he'll have to be. I think the bigger risk is that China gets better for Xi Jinping, but worse for everybody else in China. It's already worse for all the billionaires over there. It's worse for the tech industry. You've now got Evergrande, that whole gigantic debt implosion. I think there could be contagion from China next year.
Starting point is 01:00:32 I don't think she's gonna lose his grip in any way, but I'm not sure China's gonna have a good year next year. Wow, nailed it. I think all three of us kind of got this right. What are you talking about? You got none of it right. Well, I said that we're gonna be right. It's a negative of us kind of got this right. What are you talking about? You got none of it right? I said there were gonna be there were gonna be riots and they're gonna have a Reception I mean you said that they've squashed look that's exactly what happened both things happened
Starting point is 01:00:53 I actually think I have a pretty decent ability to steal men pretty concretely the details I think that at best when it comes to things like democracy and Your belief in US exceptionalism and a specific political world, do you? At best, you straw men. And I think that you get very biased without seeing the forest from the trees. The reason I said that is not because I'm like, you know, some huge G supporter. I'm just trying to steal men.
Starting point is 01:01:17 What happens when one individual person gets anointed leader for life of 1.3 billion people that then controls 20% of the world's GDP. There is no other single human being as powerful as him as of this month. Can I just say that this show is going to become insufferable if every time you sort of said something in the past that was sort of correct, we're going to have to replay it. I would have to replay it. I was actually playing that one for you, Sacks. I didn't use it when I nailed it. I was giving, that was a softball to you, actually.
Starting point is 01:01:53 I know, every week, Jake, hell. All right. This show is going to slow down if we play every clip that I got right. You guys are asking to pull clips all the time. I just pulled one clip about China, where you nailed it. No, no, no, look, I think like and also look what he did. The king of pull a clip, the, the Evergrand thing. Look what he did this week. They said, okay, you know what, the real estate industry can now issue secondary stock sales, raise equity and equitize themselves. So they're
Starting point is 01:02:16 going to find a soft landing for the equity part of for the real estate industry in China. And now they're reopening. So I don't know. I mean, like, I'm not sure what we're supposed to comment. What I will stand by is what I said, which is, I don't think we have a very clear view of what's going on, what the substance of these protests are, and what people actually want if you're only consuming US media. And so if you find a way to get a diet from a bunch of different sources all around the world, you may get a better sense. I had an accidental window into that by being in a completely different part of the world
Starting point is 01:02:50 this past week. Freeberg any final thoughts on China and what's going on there before we move on to chat GPT? You're a favorite story. I think one of the things we often miss is that China, the CCP does have their hand on the throttle. Like they throttle up and down. We always think that it's a linear line and that it's super dogmatic and fixed, but there's certainly responsiveness in the release of the lockdowns in Guangzhou.
Starting point is 01:03:20 And Beijing this week seems to have been a pretty good indication that when things do get, and Beijing this week seems to have been a pretty good indication that when things do get, when the tides do change, leadership there seems to respond not always, but enough to kind of keep things going. Should they reopen? I think it's 60% of the population or so is vaccinated, with obviously vaccines that maybe aren't as, don't have the same efficacy as the ones here in the United States. Do you think they should open up and just let it rip or do you think they should still try to maintain the zero COVID policy? Because that is the debate right now. For what's going on there? What's what's the objective? Because I'm asking you. Yeah. Well, from the objective of economic growth, they need to open up and
Starting point is 01:04:01 they need to keep their economy working and they need to keep their labor force engaged. Or else they're going to continue to suffer. So if economic growth is the objective, they need to open up. If the long term health cost of the nation balance against that is the calculus that they're kind of weighing, there's probably some more nuance to that. And certainly, my understanding is there may be a precedent setting, which is, hey, we've said that it's a zero-covid policy. Therefore, we have to hold strict to it, hold to the line. Else, it looks like we're weak. And so there's also this, you know, maintaining the authority of the CCP objective. So there's a lot of maybe competing objectives right now.
Starting point is 01:04:47 Certainly don't have a sense of how they're weighing them all. But I think that once all those videos came out this week, you guys saw them, but people were screaming. There was an apartment on fire with the doors, where it's locked with steel beams on the base of the building. At least that's what the video said. I don't know how much truth there is to that, but that's what we said. And clearly, people are extremely distraught and unhappy with the conditions of the lockdown.
Starting point is 01:05:12 At some point, enough people with enough loud voices, something's going to change. I mean, let's just remember, like the bargain that struck in that country, and with all countries, is that, you know, the citizenry, to some extent, are willing to tolerate their government so long as their conditions continue to improve. And there's a bargain. There's some bargain that struck. And as soon as that bargain starts to go south for the citizenry, then that governing
Starting point is 01:05:44 entity is at risk. And I think that that's what we sort of started to see this week was the conditions are getting far, far worse and far less livable for so many people in that country that the government had to shift. You think, Chimoff, this COVID strategy and then we'll move on was basically Xi Jinping wanting to get to that Congress his coronation. And now that that's over, maybe he can change gears.
Starting point is 01:06:10 And then like I said, my belief is that I have a very poor access to enough data to have a to steal man. What is actually going on there? But one explanation could actually be that in the absence of enough hospital infrastructure and ventilators and a bunch of these other things, they had to take a pretty severe approach to this disease. I don't know what they know or didn't know. Maybe they understood the virulence of it, be that they have slightly different aging characteristics of their population, maybe they genetically responded to the SARS-CoV-2 virus.
Starting point is 01:06:50 I don't know any of these things enough to tell you, Jason. Yeah. But the reality is what Freeperick says is right, which is that you cannot grow an economy if people are inside locked in their apartments. And it looks like they have decided that that's coming to an end and they're going to deconstruct all of these things. So the Chinese growth engine is coming back. And I think that that's going to be an important factor economically that we're going to have to figure out because it's going to have a huge implication to American growth and American inflation.
Starting point is 01:07:25 Sachs, if in fact, if the lab league theory is correct, trying to have some insights into this disease that maybe the West didn't, maybe that plays into their policy a bit. Well, I'm just surprised to hear that you have a problem with their lockdown policy over there. Because aren't they just implementing Democratic Party orthodoxy? I mean, isn't this the policy that Tony Fauci and Barbara Ferrer are the, you know, that all the health experts? I was not in favor of lockdowns. What are you talking about?
Starting point is 01:07:58 You're the one who had or your mask and had ventilators day one. Isn't this the lockdown policy? Why am I getting those getting because you're the first Party I'm just asking a question as the moderator isn't this basically why am I getting a straight isn't this what I'm gonna flinch you can't I'll answer the question. Yes Downs I was in favor of people wanted to stay home stay home And then if people wanted to go out and take the rest take the rest I was always in Isn't this what Gretchen Whitmer in michigan and gavan uson in california subscribe to the idea that the way
Starting point is 01:08:32 to fight kovid was through lockdowns now yes new sima ten pages of exceptions first political donors i'm telling you didn't use the police to lock people in apartment buildings he may have wanted to but they didn't actually do that but can you you really tell me that this lockdown policy has been disavowed by people like Fauci or by the health authorities like the Barbara Ferreres of this world? They still subscribe to this view. Do they really? Is anybody doing a lockdown now? Show me, show me, well, they're not able to do it because no one agrees anymore. But tell me, tell me where anybody, tell me were any
Starting point is 01:09:06 of the health experts who said that lockdowns were the correct response have repented and disavowed that view. Yeah, I don't know. I haven't been tracking their meocopus. And you yourself were in favor of lockdowns for a period of time, you sure? No.
Starting point is 01:09:21 You absolutely were. I'll pull the tape for the next episode. No, I was in favor of a mass mandate. No, it's not true. I was in favor of a mass mandate. No, it's not true. I was in favor of a mass mandate. And I said the mass mandate was the alternative to lockdowns. Okay.
Starting point is 01:09:31 I was saying that by May of 2020. All right, listen, let's move on to the next thing. I don't represent, I'm an independent. I don't represent a Democratic party. I don't represent Fauci. No, you represent mainstream media. I do not represent mainstream media. You just said I was an old school journalist who's mortified with where it is today.
Starting point is 01:09:47 I'm giving you a hard time. I thought your explanation was fabulous. Oh, thank you. Thank you. Obviously, Jake, I'm giving you a hard time too. I know that you were not a big lockdown proponent, but you understand the point I was making. I do understand your point. There were a lot of opponents in the US.
Starting point is 01:10:01 Let's stop making me the democratic spokesperson. I know. I'm feeling a lot better after my beer. Let's talk about. Come on. All right. So listen, let's talk about open AI. All right.
Starting point is 01:10:12 Open AI is a company that builds artificial intelligence, software and platforms. They have one platform called GPT. It is on its third version. As part of GPT3, they created chat GPT, which is a chat interface where you can ask questions to AI. The results are nothing short of stunning when they hit. Some of them are a little bit mixed, but Freeberg has spent the last 48 hours drinking white Russians with Oatley Milk and playing with chat GPT, including his question to the chat GPT, which was right a script of Chamoff, Sachs, and J-Cal talking about the future of AI in the style of a Quentin Tarantino
Starting point is 01:11:00 movie, and I have to say, it was pretty great, the result. Go ahead, Freeberg, tell us what you described. I think you guys should read this real quick. We can cut it out if it's stupid, but okay, just actually read the script. Yeah, I don't think you got the Quentin Tarantino part right. I mean, I think it was impressive, but there's no F-bombs, there's no like Tarantino S dial out.
Starting point is 01:11:19 And by the way, they excluded all of that from O.A. They took out all cursing and violent, cursing and violence from O.A. opening up that explains it because it's a Tarantino script there would be some choice language. Oh, it's interesting. It's like the PG Tarantino script Cussing no violence no sense you do the narrators is yeah, you do the narrative go ahead The scene opens on Chimup Palai hapatiha David Sachs and Jason Calakana sitting at a dimly lit table in a smoky bar. A bottle of whiskey sits in the center of the table, half empty.
Starting point is 01:11:53 Chimab's leaning forward, his eyes intense. So what do you guys think about this chat GPT thing? David Sachs takes a sip of his drink. It's impressive, note out about it, a large language model trained by OpenAI that can generate human-like texts in a variety of styles and formats as a game changer. Jason nods. Definitely. It's one of the most advanced AI systems we've seen to date.
Starting point is 01:12:14 It's going to have a huge impact on the way we use and interact with AI. To mouth, friends. That's what I'm worried about. With a technology like this, the possibilities are endless, but so are the potential dangers! Saks, Leans back in his chair. Oh, come on, Chimath, you're not still stuck on that whole AI, is going to kill us all thing, are you? Chimath, Leans forward again, his voice low and serious. Look, I'm not saying.
Starting point is 01:12:40 The chat GPT is going to turn into SkyNet overnight. But we need to be careful about the way we develop and deploy AI. We need to make sure that we're using it for good and not just for our own game. Well, take out nods. I agree. We need to make sure that we're responsible in a way we use AI and that includes making sure it's accessible and affordable to everyone, not just to select few. Timoth, with a dirty smirk.
Starting point is 01:13:07 And let's not forget about the imports of regulation. We need to make sure that we have the right laws in place. Oh, this is difficult. This is useful. Oh, the director's calling cut. Cut, that's it, scene. I mean, we're not going to finish it. I got that far off. I mean, it's 60% of the way there.
Starting point is 01:13:28 Actually, there's even better one. Oh, I have to do it in a bid in for sacks. If you blame bidon, it would have been perfect. Let me tell you guys something stunning about this platform. So this is GPT 3.5, which is an interim model to the, what people are saying is the belong away to GPT 4.0 model, which I think they announced in 2020 and has been in development for some time.
Starting point is 01:13:50 So the model, this GPT 3.5 model was trained in three steps. They do a great job explaining it on the OpenAI blog site where they collect some data and then there's a supervised model, meaning that there are humans that are involved in tagging. And then the model learns from that system, then you ask the model questions you get output. And then humans rank the output, and so the model learns through that ranking system. And then there's this third optimization thing,
Starting point is 01:14:18 and then it's fine to you. So the model itself has several steps of human involvement, and it sources its own data and builds it. You know what's incredible about this model? The total size of the software package that runs the model is about 100 gigabytes. Isn't that amazing? You could fit this model on probably what, 20% of the storage space on your iPhone. And you could run this thing and you could probably just talk to it for the rest of your life. And it's really kind of an incredible milestone. But I think what was so stunning to me about this, I know you guys are probably expecting something
Starting point is 01:14:54 to be said like this, but you could see so many human knowledge worker roles and functions being replaced by this extraordinary interface. So kids can do homework. That's easy. Software engineers can get their code optimized and can get their code written for them. There's great examples of how software code has been written by this interface. You could see real estate insurance salespeople being replaced by some sort of software like interface actors. sales people being replaced by some sort of software like in face like this. Copy writers, you know, make me a hundred
Starting point is 01:15:28 versions of a commercial or an ad. Customers support completely replaced, right? If you guys remember there were these automated customer support companies that started, you know, two decades ago, that was a great flurry. All BPO businesses were all about lower cost human labor. Now the cost of human labor goes to zero. My prediction, which is, so everyone's got the obvious prediction, which is there's going to be a hundred thousand startups that are going to emerge. I mean, this is kind of like this moment where the internet came along and everyone's like, this changes everything. I do think everyone thinks and feels that.
Starting point is 01:16:00 So the obvious next step is a bubble will form. So I just got technical question though, Freiberg. And then, I'll probably be thinking the same thing. Let's just finish my market prediction. But I think because everyone's so hyped about this, and we all know this, it'll be all the easy attention. All the investor attention is shifting to this capability. And how do you apply this sort of capability across all of these different industries
Starting point is 01:16:23 and all these different applications? And as a result, my guess is the next hype cycle, the next bubble cycle in Silicon Valley will absolutely be this generative AI business. Okay, but this is a little technical, but how would it know the difference between like why you are and you are when it is processing natural language if you were to do like your anus or your anus,
Starting point is 01:16:46 how would that freeberg, how would it know the difference between your anus and your space anus? It'll learn that, you know? It's chocolate content. It was a joke about your anus. It was a demo. I think it was trying to be AI. Yeah, I probably would have made a better joke than that.
Starting point is 01:17:00 Would have made a better joke. For sure. So, so, so, so, so, can I introduce like J-CAL and they were terrible. So I have a way to offer another. I'm going to ask the AI to pretend you're the all-in-pod besties telling Uranus jokes. That would be pretty cool. Sorry, let me just say one more thing about this open AI thing. I do think that the biggest and most interesting thing to think about is how this will disrupt
Starting point is 01:17:24 the search box. The way Search works at Google and the Internet search, is there are these servers, these web crawlers that go out and gather data, some of structured data feeds, and some of them are just crawlers. Then that data is indexed or in the structured way, it's made available for serving directly on the search page. And so much of that is indexing. So I searched for a bunch of keywords as keywords and perhaps
Starting point is 01:17:52 some natural language contacts are matched to a result page and I click on that and it's linked out. Years ago, Google started a product called the OneBox where they could take structured data, like what is the weather in San Francisco today? And that top of the search result page just presented that data, because it knows with high certainty, the question you're asking and it knows with high certainty the answer it can give you.
Starting point is 01:18:13 Yeah, cliff to that. Somebody's website, right? So if that starts to become everything, then that OneBox interface, and it's not just Google's ability to access all this data and index it and serve it and store it. There could be a lot of competitors to the one box and a lot of competitors ultimately to search. And ultimately, you know, Google's core product, their search engine, could be radically disrupted
Starting point is 01:18:39 by an alternative system or set of systems that have more of a natural language chat interface. Which literally, which is literally why alternative system or set of systems that have more of a natural language chat interface. Which literally, which is literally why Google bought DeepMind and there were a collection of human-powered search engines, Mahalo included, Chacha, Answers.com who are trying to do the human-based version of this. It's just in scale. No, we don't want to get ahead of ourselves because one of the things we don't know is how much it's going on in DeepMind.
Starting point is 01:19:03 They're not very open like OpenAI is. They talk about some of the advanced frontier stuff like Alpha Fold and so on. They've been public about that. A lot of that is really to generate interest and hype and what's next. My understanding is DeepMind has been applied to everything from ads, ad optimization, but also the ranking on YouTube videos to get people more engagement on YouTube, etc etc So there's all these ways that deep minds have been applied within Google services that we don't see and certainly within search Yeah, but the question is is there an entirely new interface for search?
Starting point is 01:19:35 Yes, that risks Google's core search business And I think that there certainly will be a lot of money thrown at this and if anyone has any interesting ideas Send me an email sacks and then schema Yeah, I think that's a really interesting point. I saw a thread on this where somebody was asking GPT, you know, a bunch of questions, like they were generally like coding questions, and they were actually comparing the result in Google versus GPT. And Google would just give you a reference to a link to some page, whereas GPT-3 would actually construct the answer, like a multi-paragraph answer that was far more detailed and
Starting point is 01:20:14 in a way user-friendly. Whereas the Google page would kick you over to a reference where it was like this one, two, three, maybe someone created a checklist, but it just wasn't that detailed. It really is pretty interesting. I thought Andrewson tweeted a really interesting example as well where he asked GPT to create a scene from a play starring a New York Times journalist in a Silicon Valley tech entrepreneur. They were arguing about free speech and each passing of the asserts the view associated with his profession and social circle. We don't need to read the whole
Starting point is 01:20:48 thing, but I thought this was like spot on where I was actually like both sides are making their best arguments and it's like to each other in a conversation that seems intelligible like they're making their points at the right time in the conversation. It's like they're playing off each other. In other words, it actually reads like a conversation. I actually thought this one was more impressive than the one with the best impersonation because I actually thought that the one about all in didn't really capture our personalities per se,
Starting point is 01:21:18 but this one actually does a pretty good job capturing the arguments in this debate. So pretty impressive. Any thoughts here? Yeah, lots. I mean, I've been spending a lot of time learning about this area six years ago, a team that I partnered with who was at Google that built TPU. We've been building silicon for this space.
Starting point is 01:21:39 So we've been kind of going from the ground up for the last six years. Couple of things that I'll say. The first is that I think we're going to replace SAS with what I call MAS, which is models as a service. And so a lot of what software will be particularly in the enterprise will get replaced with a single use model that allows you to solve a function. So these chat examples are one, and you can name a bunch of SAS companies that
Starting point is 01:22:05 were purveyors of SAS that will get replaced by essentially GPT-3 or some other language model. And then there'll be a whole bunch of other things like that. If it's a, you know, expense management company, they'll have a model that'll allow them to actually do expense management or blah, blah, blah forecasting better. So I think SaaS will get replaced over time with these models incrementally. That's phase one. But the problem with all of these models in my opinion is that they're still largely brittle. They are good at one thing. They are a single mode way of interfacing with data. The next big leap, and I think it will come from one of the big tech companies or from OpenAI, and we talked about this a few episodes ago, a multimodal model,
Starting point is 01:22:54 which then allows you to actually bring together and join video voice data in a unique way to answer real substantive problems. So if I had to steal man, the opposite side reaction, so I think there's a lot of people gushing over the novelty of GPT-3. If I had to, or chat GPT, if I had to steal man, the opposite, what I would say is, it's gonna get somewhere between 95 to 99%
Starting point is 01:23:21 of all of these very simple questions right, because they're kind of cute and simple. There is no consequence of saying right of play because there is no wrong answer, right? You either kind of it tickles your fancy or it doesn't, it kind of entertains you or it doesn't. When this stuff becomes very valuable, is that when you really need a precise answer and you can guarantee that to be overwhelmingly right. That's the last one to 2% that is exceptionally hard.
Starting point is 01:23:49 And I don't think that we're at a place yet where these models can do that. But when we get there, all of these models as a service will be very much commoditized. And I think the real value is finding non-obvious sources of data that feed it. So it's all about training. So meaning you can break down machine learning and AI into two simple things. There's training, which is what you do asynchronously.
Starting point is 01:24:16 And then there's inference, which is what you're doing in real time. So when you're typing something into chat API or a chat GPT, that's an inference that's running and then you're generating an output. But the real key is where do you find proprietary sources of data that you can learn on top of? That's the real arms race. So one example would be, let's say you build a model to detect tumors, right? There's a lot of people doing that.
Starting point is 01:24:43 Well, the company that will win may be the company that actually then vertically integrates, buys a hospital system, and get access to patient data that is completely proprietary to them, and covers the most number of women of all age groups and of all ethnic categories. Those are the kinds of moves in business that we will see in the next five to 10 years that I find much more exciting and trying to figure out how to play in that space. But I do think that JGBT is a wonderful example to point us in that direction. But I'm sort of more of that case, which is it's acute toy, but we haven't yet cracked the one to two percent of use cases that
Starting point is 01:25:23 makes it super useful. But I think the first step, but just sorry, but the first step will be the transformation of SaaS to Mass. And then from there, we think we can try to figure this out. It reminds me of it in a way when you, when you give that description of like, hey, this is really interesting, but it's not complete. Is remember when GPS came out and like people were like doing turn-by-turn navigation, they drive off the road because they were trusting it too much And then you know over 20 years of GPS We're kind of like yeah, it's pretty bulletproof, but keep your eyes on the road same thing that's happening And these changes tend to be right these last 100 or 200 basis points literally takes decades
Starting point is 01:25:58 Exactly, so the last 15% of self-driving is like the decade long, you know, slot That may take a century 15% may take a century. But the last 2% will take a few days. It's like the change happens very slowly and then all at once. For people who don't know what a TPU is, that's a tensor processing unit. This is Google's application-specific circuits, right? And custom silicon that they invented for tensor flow at the time. Yeah, so if you want to try this.
Starting point is 01:26:21 Although now the modality of AI, we've changed that as well. So now we're totally in the world of transformers. So we're not even using, you know, you're not letting the tensors flow the way they used to. All right, there's been a slowdown in SaaS. SaaS, what is happening in the software as a service world? There was a good update by Jammin Ball, who works for all Timner, our friend, Brad Gerson, or he does these really great updates on what's happening in the SaaS world. The big thing this week is that Salesforce had its quarter, and I would consider Salesforce to be the bell weather for the whole SaaS category.
Starting point is 01:26:51 I think they're the largest pure SaaS company. They were the first multi-tenant SaaS like company at scale. And what they've shown is a huge slowdown. Basically, their NetNew ARR that they just added in the previous quarter dropped two-thirds compared to the previous quarter. But because their sales and marketing spend was the same as the previous quarter, it exploded their CAC payback, which means the amount of time it takes to pay back your customer acquisition costs for a given customer. So you see there are 155 months. It would take now to pay back the customer acquisition costs. That's over 10 years. That doesn't work. I mean, I think before this quarter, it was more like two
Starting point is 01:27:37 and a half years. That's something that you can afford. A company can't, you know, if you're spending 10 years of, you know, gross profit on a customer to acquire them, the business doesn't make sense. So now I'm not saying any of this to pick on Salesforce. It's an exceptionally run company, you know, one of the absolute best Mark Banny off fantastic CEO founder, great human being. But I think the point here is that what you're seeing is the whole SaaS industry is really slowing down here. In the first half of the year, you saw SaaS valuations correct.
Starting point is 01:28:11 Now we're actually seeing SaaS top line correct. There's an interesting question here. If your CAC payback goes from 2.5 years to 10 years, you have to bring your CAC down. How do you do that? You can either reduce marketing or you can reduce sales. In other words, you can reduce sales. pack down. How do you do that? You can either reduce marketing, or you can reduce sales. So in other words, you can reduce sales. You can cut the sales team. You can either cut people and head count from your own team, or you can cut spending you do on advertising or events, or money
Starting point is 01:28:38 that you spend on other companies. Either way, there's going to be a big contraction in jobs basically around this industry. And I think that what that could do is cause a vicious cycle where we start seeing, I wouldn't say, a death spiral. I think this vicious cycle for the next year or so, where seat contraction becomes the norm instead of seat expansion. So if you go back over the last 10 years, a major tailwind at the backs of SaaS startups has been that every year you start with 120%, 130%, 150% of last year's revenue
Starting point is 01:29:13 just from your existing customers. Why? Because they were hiring more and more people and they needed to buy more and more seats. But now headcount growth is frozen and in fact, companies are doing major layoffs. So the baseline for next year could be seat contraction. So instead of starting with 120% of last year's revenue, you might start with 80% or 90% because there's going to be so much churn. So I think that SaaS companies need to take this into account. This idea that growth is on autopilot, that could start to go in reverse. I don't think permanently, but I think for the next year or so. This is why I also tweeted, you know, two X's and new three X. If
Starting point is 01:29:48 you can grow two X year over year, and this entire, that is as good as or better than growing three X last year. Oh, clearly, it's clearly better. Like a lot of companies that that break had grown three X last year because it was so times are so frothy. Everyone was buying everything. But now it is going to be really hard to even double year over year. Companies need to take that into account into their financial planning. You need to restrain your burn because a lot of the revenue that you predict is going to be there may not be there. All right. Thanks so much to the Secretary of SAS. I think you got a board meeting. I did. I got to run. One of the interesting things I saw in terms of use cases
Starting point is 01:30:25 is somebody used the chat GPT to describe rooms. Then they took the descriptions of those rooms, and then they put them into like Dolly or Stable diffusion, one of those, and it created the visual. I'm curious if you think the self-driving APIs and machine learning that's going on, then you got images, then you got chat, maybe you have proteins going on with the alpha-fold stuff. When these things start talking to each other,
Starting point is 01:30:51 is that going to be the emergent behavior that we see of general AI, and that's how we'll interpret it in our world is these hundred different vertical AI's hitting some level of reasonableness to Chimaltz Point on data sets. And then all of a sudden, the self-driving AI is talking to the one that's looking at cancer and tumor diagnosis
Starting point is 01:31:12 in the chat and the image ones. It may be stable diffusion, the protein AI, and the one that's looking at cancer cells start talking to each other. Yeah, I'm not sure that's as likely as the, there's a lot of solutions that will emerge within verticals, and I think you can distinguish them. So I kind of gave this example a few months ago.
Starting point is 01:31:37 If you remember Kai's Power Tools was a plug-in for Adobe Photoshop came out in 1993, I believe. Of course. And Kai's Power Tools completely transformed the potential of Adobe Photoshop came out in 1993, I believe. Of course. And Kai's Power Tools completely transformed the potential of Adobe Photoshop, because Photoshop had all the basic brushing and editing capabilities within it. Kai's Power Tools was statistical models that basically took the matrix of the pixels and created some evolution of them into some visual output, like a blur. And so you could blur motion blur or something, and you could change the parameters.
Starting point is 01:32:07 And now your photo looked like it was going through a motion blur. Ultimately, Photoshop bought and implemented those tools. But those were similar. There were statistical models that made some representation of the input, which was the image, and then created an output, which was an adjusted image. I would argue that that is very similar, although the models behind it are very different in terms of the contextual application of statistical models in software.
Starting point is 01:32:34 And you could see stuff like, for example, a chatbot that replaces, help me figure out whether my credit card charges are correct or not, instead of having a customer service agent, an offshore customer service agent helping you resolve that, or help me return my item, or there are very specific kind of verticalized applications that can plug in that ultimately replace what was manual and human driven before, because humans used to manually make the motion blur and Photoshop, and then it was automated with the software packages. And I think you can kind of think about it in that same way
Starting point is 01:33:08 that these these are known knowns. They don't require necessarily a human physical labor or some you know human responsiveness that if 95% of the work can be handled it will get handled by some verticalized solution. So I think the physical labor versus the non-physical labor is one way to think about the distinction. Meaning is there's some change in the physical world. Driving is absolutely a change in the physical world. You have to move physically through space. So that one is a very distinct class.
Starting point is 01:33:36 All the stuff that's like communication, imagery, static imagery, audio, and then visual, video, there's some stacking that happens there. And some of those will be kind of siloed, and then some of them will merge, and you'll have these kind of unique kind of combo models. And so look, as they start to work together, I think we'll see them, you know, completely rewrite some of these verticals, like movie production or music production, right, or advertising, or we're seeing it now with video and creative arts with some of the visual stuff on open.
Starting point is 01:34:11 And to be honest, a lot of journalism, a lot of creative arts have become the wisdom of the crowds over the last two decades, where artists were looking at the collective works of the internet interpreting it and then coming up with content, which is kind of what these AI's are doing, and then who legally owns the collective content is going to be
Starting point is 01:34:31 a big question. Shamaafi talked about data sets, and Microsoft is being sued right now and GitHub because they used open source to create tools in AI to help augment programmers like, well, they're programming right writing code, it gives them suggestions. And now the open source community is suing them for using their data sets. So what do you think about the legality of data sets,
Starting point is 01:34:52 Tramoth, and should they get some kind of protection if you make a GPT-3 based on Cora or based on Wikipedia, should you have to get approval to use that data? What's, we can see exact opposite. Yeah, it's the exact opposite. They say that this is actually your work. And I think that that's the right legal framework. But the answer to your other question is,
Starting point is 01:35:13 this is why I think the hunt for proprietary data actually becomes the hunt that matters. All of this other stuff, I think, is a lot less important because I think you have to assume that all of these models will eventually just get commoditized. So there'll be a, you know, like you see like Jasper AI and you see a bunch of these generative AI companies, it's really interesting. But the problem is when you sit it on top of the same substrate, you'll have a convergence.
Starting point is 01:35:38 Right? Everybody's chat model will eventually look and sound and feel like the same thing, unless you're giving it a few special ingredients that other people are not. And so it's the hunt for those ingredients that will make this next generation of models really valuable. So to give it an example, you would have Wikipedia, which is creative comments anybody can use, but Kora as a data set, not everybody can use that's owned by a company.
Starting point is 01:36:03 So Kora would have an advantage. the data set, not everybody can use that's owned by a company. So for a good advantage, take an extreme example. If Kora didn't allow themselves to be crawled, but then they developed their own language model, which used the best of the internet, so call it GPT, and Kora, maybe they are slightly better in certain domains and others. The other extreme example is the one that I use in healthcare, which is, you know, if you have access to patient data that you will not license to anybody else, you know, it stands to reason that that model actually then has much better chances of highly effective clinical outcomes versus any other model.
Starting point is 01:36:45 Apple Watch comes to mind, right? Apple has all that watch data. They could pair that with EPCs. It's another very good example. That's a good example. What could they do together? So this is going to be like, this is the new oil is going to be data. And by the way, like to talk about Apple for a second, the smart thing is they've gotten
Starting point is 01:37:02 so methodically, they've never touted the AI. They introduce one or two distinguishing features every year, right? So like the ECG, which was introduced many, many years ago, has only gotten slightly more usable like five or six years later, but in the meantime, there's tens of millions of watches collecting this kind of data. So to your point, it's using these devices as Trojan horses to collect training data. That is the oil. Uber and Tesla have all this data of the data being collected by, well hold on, so far, or the cameras in the cars. The other difference though is that you have to be in a realm where you don't need regulators
Starting point is 01:37:47 to go the last mile. So the problem with ADAS I think or level 5 autonomy is that eventually you get to a point where even if the model becomes quote unquote perfect, you still need regulatory approval. And what I'm saying is I think you have to focus on areas of the economy that are not subject to that or where the regulatory pathways already defined. So for example, if you use that healthcare example, let's say that you had the largest corpus of breast cancer image data and you could actually build an AI that was a much better classifier for tumors versus other things. The FDA actually has a pathway to get that approved very quickly.
Starting point is 01:38:23 The problem with, you know, level five autonomy is that there is no clear pathway. It's not, again, we go back to almost a crypto example. We don't really know who will govern that decision, and we don't know how that will be governed. So I think the thing that investors have to do, entrepreneurs, entrepreneurs have to pick their end market very carefully, and investors have to realize that this dynamic exists as well. If you're going to do this right, imagine the Robinhood trading, you know, trader or data set, watching people sell and share, and then predicting markets with it with AI, it could be crazy. You have that or payment for order flow that's used by Citadel and the other big, but not AI. Right. So that's what they are. Maybe they are losing it on their side.
Starting point is 01:39:01 They are. I can tell you as somebody who sells, we sell a lot of machine learning hardware into this market. The biggest buyers are the US government and these ultra high frequency trading organizations. Freeberg any final votes here? I'll give you the final word. How could this affect astronomy? How could this affect our search of the galaxies, you know, going out past Pluto, Saturn, breaching Uranus?
Starting point is 01:39:27 Any of those things? How could it impact? Any of them. I'm trying to get a Uranus joke to lead. Help me out there, Tramon. You got to. I think you need to have more space related, which workshoped this one with me. Or got biome related, you know, you need to be.
Starting point is 01:39:48 Oh, got biome, yeah. So how would this affect super gut? Use the promo code twist. You have to trick Friedberg into thinking we're asking a serious question. Get him down the science path. And then rug pull him. Now that's the right use of rug pull. That's the right use of rug pull.
Starting point is 01:40:00 Exactly, let's do it. Here we go. That's the rug pull. So tell us, you know, when you're doing like super gut, use promo code twist to get 25% off. When you're doing super gut, you're analyzing let's workshop. That's the road. So tell us, you know, when you're doing like super gut, use promo code twist to get 25% off. When you're doing super gut, you're analyzing people's guts. How would you then have machine learning in this, you know, API, this chat API and GPT-3? How could that help with processing all of that,
Starting point is 01:40:19 especially when it passes through Uranus? Freebar. You okay with that freebar? You were hung over. passes through Uranus. Free bird. He'll care if they're free bird. You are hung over. I'm hung over, but I also had like a 7A on board meeting, so I'm also just a little beat up. Will you grumpy on the board meeting? Did you get a little contactorous with your finance?
Starting point is 01:40:37 It's far fine. You can keep the rage and contrabad. I think I had my caffeine fuel and then I kind of crank down afterwards. All right, everybody. We will see you next time for the Secretary of SAS, the dictator, and the Sultan of hungover. We will see you next time. Bye bye. Love you guys. Bye bye. We'll let your winners ride Rainman David Sat I'm doing all the And it said we open source it to the fans and they've just gone crazy with Love you. I sweet up
Starting point is 01:41:20 Besties are gone, go thrifted. That's my dog taking it away. She's driving away. She's in the sex. Wait it up. Oh man, my ham is the actual meat. We should all just get a room and just have one big hug. Because they're all just like this sexual tension that we just need to release that out. What, you're the bee?
Starting point is 01:41:40 What, you're the bee? Be your bee. Be your bee. What? We need to get merch. I'm going on leave. I'm going on leave.

There aren't comments yet for this episode. Click on any sentence in the transcript to leave a comment.