GPT-4o launches, Glue demo, Ohalo breakthrough, Druckenmiller's bet, did Google kill Perplexity?
发布时间 2024-05-18 05:04:19 来源
摘要
(0:00) Bestie Intros: Recapping Phil Hellmuth's birthday weekend (7:38) OpenAI launches GPT-4o: better, faster, cheaper (29:40) ...
GPT-4正在为你翻译摘要中......
中英文字稿 
All right, everybody. Welcome to your favorite podcast in the world's number one podcast, the all in podcast. It's episode 1,790. Oh wait, that's just how it feels. Welcome to episode 179 with me today. Of course, is your sultan of science. I don't know if that's a movie background or it's just his favorite vegetables. What's going on there? What's the crop? That's AI generated. It's AI generated crop. Okay. I'm trying AI backgrounds. I'm going to try it out for a while with different crops. Your fans are going to be crushed that you're not doing deep movie polls with us. Of course, man, about town, DC, new products being launched. David Sachs, the rain man. Yeah. How you doing, buddy? Good. Good. Yeah. Good week. What's going on? Yeah. Yeah, definitely good week. Trimoth Polyapotia, chairman dictator. He puts the chairman.
好的，大家。欢迎收听你们最喜爱的播客——世界排名第一的播客，全能播客。这是第1790集。哦，等等，这只是感觉像第1790集。欢迎收听第179集。今天和我一起的是你们的科学苏丹。我不知道那是电影背景还是他最喜欢的蔬菜。那是什么情况？那是AI生成的。是的，AI生成的作物。好吧。我正在尝试AI背景，我会用不同的作物试一段时间。你的粉丝们会很失望，因为你不再和我们一起做深入的电影引用。当然了，这位就是满城风云，DC的新产品推出者，大卫·萨克斯，雨人。你怎么样，兄弟？很好。很好。是的，过得不错。发生了什么？是的，是的，确实是个好星期。Trimoth Polyapotia，主席兼独裁者。他就是那个掌握全局的人。
I would like to take this opportunity to wish. My child a happy birthday. I absolutely love you. Well, now the rest just look like shit. Yeah, great. I've never done that before. Zach, in your desk, in your desk is a piece of paper with your children's names and their birthday. You want to pull it out? I got three birthdays a year and I've never done one. What your winter ride. Rain man, David Sachs. And we open source it to the fans and they've just got a reason. Love you guys. I see. Queen of King. Rob. Going. Oh, yeah. No, no, no, but I'm saying it rarely lands on the same day. Today is the day. Today is the day. Today is the day. OK, yeah. Today is the day. Good. Congratulations, child. Oh, congratulations. Yeah. How old? Jamov. No gender name or any other specifications, folks. We can't we can't tip anybody off. No pronouns.
我想借此机会祝我孩子生日快乐。我非常爱你。呃，其他的都显得很糟糕。对，从来没这样过。扎克，你桌子上的文件里有你孩子的名字和生日。你能拿出来吗？我每年有三个生日，但从来没做过什么。你冬天的游乐项目，大卫·萨克斯。而我们将其开源给粉丝们，他们刚好有个理由。爱你们。我明白了，君王女王，Rob。前行。哦，对，不不不，但我只是说很少会在同一天。今天是那一天。今天是那一天。今天是那一天。好，恭喜，孩子。哦，祝贺。多大了？Jamov，不能提及性别，还没有其他具体信息，大家。我们不能让任何人提前知道。没有代词。
No pronouns. No pronouns. Yes, absolutely. So how are they? This child experiencing their birthday. This child has experienced a wonderful life. And this child is an incredible person. For whom I have tremendous admiration and love and compassion and hope for the future. All right. And did you order them some chicken fingers? I cannot comment on who this person is. Chicken. Are you talking, of course, about Phil Helmuth's child, Phil Helmuth. Can we please talk about last weekend's festivities in what a disaster he is? Oh, my God. Do you guys you see you guys know? So we missed you last weekend. We missed you so much fun. Come on. We missed you on Saturday night. Saturday night was really fun. I had such a lovely time coming home to be totally honest with you. We had a cabana set up on Saturday, played blackjack.
好的，绝对没问题。他们怎么样了？这个孩子正在庆祝生日。这个孩子有过精彩的生活。这个孩子是个了不起的人，我对他有巨大的崇拜、爱、同情，并对他的未来充满希望。好吧，有没有为他们点一些鸡柳？无法评论这个人是谁。鸡柳，你当然是在说菲尔·赫尔穆斯的孩子，菲尔·赫尔穆斯。我们可以谈谈上周末的庆祝活动吗？真是一场灾难，天哪。你们知道吗？我们上周末真的错过你了，非常想念你。周六晚上真的很好玩，非常想念你。回来后的感觉真的很好。我们周六设置了一个小亭子，玩了二十一点。
I miss you guys too. I had a phone. I saw the videos. It was so fun. Well, you don't have to have too much phone mode because Phil sent the entire group chat to poker news.com. They didn't run it twice. The flop. Horg poker dash. Up there. Yeah. It was like he kept tweeting all week. He leaked every single person who's there and the he said he's like, look, here's me and Elon. He's like, Elon came by for my dinner. No, no, no, no, it was worse than that. No, it was worse than that. He said, I got to hang out with our guy, Elon, for 10 minutes and 14 seconds. Hey, what? He died. He intercepted him at the valet. Wait, what? I'm coming. It's 10 minutes and 14 seconds.
我也想你们了。我有手机，看到了那些视频，真是太有趣了。好吧，你们不必太沉迷于手机模式，因为菲尔把整个群聊都发到poker news.com了。他们并没有两次发布，全都是实时的。这一周他一直在发推文，泄露了在场的每一个人，他还说，“看，这是我和埃隆的合照。”“埃隆来参加我的晚餐了。”不，不，不，比这更夸张。他说，“我和我们的好朋友埃隆相处了10分14秒。”你说什么？他是在代客泊车那儿截住埃隆的。等等，什么？我来了，就是这10分14秒。
He had the exact time down to the second. Oh, I got Melissa. And I want to wish Phil home with the happy birthday because I did miss his 60th party. Yeah, it's coming back to his birthday. His birthday wasn't actually his birthday. It was Bill Gurley. So we just hijacked Bill Gurley's birth. I also got to enjoy it for my first time ever, uh, the experience of bakarot, which I've decided is the most DJ DJ game on earth. It's literally. The most you just flip points. It's flipping points. Well, this is crazy. You make many decisions. All you do in bakarot is you say thing or player and then you freak yourself out about how you flip the cards and the smartest people I know on earth are all sitting around the table at two three in the morning saying, turn this corner this way. No, no, no, no, no, turn it this way. Turn it this way. There's two dots and they're debating the right way to flip a part.
他精确地掌握了时间，精确到秒。哦，我联系到了Melissa。我希望能够祝Phil生日快乐，因为我错过了他的60岁生日宴会。对，话题又回到了他的生日。其实，那天庆祝的并不是Phil的生日，而是Bill Gurley的生日。所以我们其实是“劫持”了Bill Gurley的生日。我还第一次体验了百家乐，这让我觉得这是世界上最具有娱乐场感的游戏。它真的很简单，就是翻牌的游戏。你根本不需要做什么复杂的决定，你只需要选择是“庄”还是“闲”，然后就开始紧张地翻牌。我认识的最聪明的人都会在凌晨两三点围坐在桌边，说着“把这个角这样翻”，“不不不，应该这样翻”。他们会为了怎么翻出正确的牌而争论不休。
That's true. No, the sweat is the most incredible performative act in the game. Don't have to say. Yeah, you're right. Everyone's got their own little tech. Take a look at how they bend the card. So exactly destroyed by the end of the deck. They don't. I, you can get me. I go like this and I try to see. Oh, like you're selling your mustache like an e-mail. You got to go like this. And then you call it. Oh, my God. No spotter. If you see a rose. But we're too gross. So. And then you get to decide whether the bank turns over their cards and it. What when they turn over, then you lose a small house and then you're like, yeah, you're convincing yourself that you have all this control and ways to change the outcome. Right. Because you're literally flipping a car. It's high card.
没错。流汗是这个游戏中最不可思议的表演。真的不用多说。对，每个人都有自己的小技巧。看看他们是如何把牌弯曲的，到牌组结束时就完全毁了。我是，我像这样做，试图看清，哦，就像你在展示你的胡子一样，你得这样做，然后你再说：“哦，我的天，没有瞭望者。如果你看到了玫瑰。”我们都太恶心了。所以，然后你可以决定银行是否翻开他们的牌。当他们翻牌时，你会失去一小部分赌注，你就会说，你让自己相信你有全盘的控制权和改变结果的方法。对吧，因为你实际上是在翻牌。这是一场比大小的牌局。
Well, it's all it is. It's high card. It's even worse than that. You're basically sitting down at the casino's table and then they tell you whether you've won or lost in order to convince yourself that that's not what's going on. You have to play with the card. But really tell you you either win or lose. And I'm watching the smartest guys we know staring at the window at the little machine that tells you whether bank or player one and they're studying it. Doing a salad. It's been at work. Words. It's not a go black. Hell be like I'm calling it now bank, bank, player, player, player. And all the guys are like, let's do it. And then everyone gets heads, heads, tails. Tell me.
嗯，这就是全部了。就是比大小。一点技巧都没有。你基本上是坐在赌场的桌子旁，然后他们告诉你，你是赢了还是输了。为了让你相信这不是纯赌博，你必须拿到牌才能玩。然而实际上，他们直接告诉你你是赢了还是输了。我看到我们认识的那些最聪明的人盯着显示屏，那个屏幕告诉你“庄家赢”还是“闲家赢”，他们还在认真研究。简直是在浪费功夫。他们不停地猜测，像是预测未来似的，比如“我现在敢肯定庄家赢，庄家赢，闲家，闲家，闲家。”所有的人都像是准备行动似的喊着“干吧！”然后每个人都得到相同的结果：不是全头就是全尾。告诉我吧，这有什么意义呢？
So tell me fast. Us to play in the high stakes poker game on poker go. So it was me, Elmuth Stanley, Sammy, House, and then gently and Nick airball and Roble. So most of the guys from the house came plus. Gently and Nick airball. Jennifer Tilly is amazing. Why not? Listen to this. Well, listen to this hand. Literally the second hand. Of the actual poker game. Gently. Is in the big blind. No, sorry. She's under the gun. She raises. How's them both three bets. It comes all the way around to me on the button. I look and I have pocket kings. Oh, I ship the whole cheeseburger. Comes back to Tilly. She ships house ships. Listen to these hands. Gently has aces. Jeff Hausen, both have kings. I have kings. Oh my God.
所以，快点告诉我。我们要参加Poker Go上的高额赌注扑克游戏。参与的有我、埃尔穆斯·斯坦利、萨米、豪斯、还有Gently和Nick Airball以及Roble。几乎所有房子里的玩家都来了，再加上Gently和Nick Airball。Jennifer Tilly简直太棒了。为什么不来呢？听听这一手牌吧。真的是比赛的第二手牌。Gently在大盲位，不，抱歉，她在早位。她加注，豪斯三次下注，这轮一直到我在按钮位置，我看了一眼，我有一对口袋K。我全押了。到了Tilly，她也全押，豪斯全押。来听听这些牌，Gently的是一对A，Jeff Hausen和我都是一对K。哦天哪。
I've never seen a cooler hand like this in my life. Out and the second in the second hand of the game. Anyways, wow. Don't worry, guys. It's too back. And I want to tell you. She tripled up. She triples up and then interlock them. The first time I ever played with her, I was going to stop this game. Then I stacked her right. Anyway, so I don't want to reveal the game, but it was wonderful. It was wonderful. This one. I show up at a mutual friend of ours game and there's a beautiful Porsche or something in the driveway. It's a really notable car. And the I noticed on the license plate, it says DJEN. But it's spelled with a J and I'm like, oh, degenerate. What a great license. I don't wonder who that is. I go and it's Jennifer telling. She is so cool. She's very charming. She's very cool. Great actress. Great actress. Great actress. She was in Bow. Bow.
我这辈子从没见过这么酷的牌。游戏刚开始的第二回合她就出了局。不过，哇，不用担心，伙计们。一切都能回到正轨。我告诉你，她翻倍了三次，然后把牌组合了起来。我第一次跟她玩的时候，本来打算不玩了，但后来我把她的牌给收了。无论如何，我不想透露是什么游戏，但那真的很精彩，真的很精彩。
有一次，我去参加一个我们共同朋友的游戏聚会，看到车道上停了一辆漂亮的保时捷之类的名车，车牌上写着“DJEN”，用的是J打头，我心想，噢，"degenerate"（"堕落者"，这词也可以形容爱赌博的人）。真是个好牌照，不知道是谁的。结果进去一看，是珍妮弗在那里。她太酷了，非常迷人，非常酷。她是个很棒的演员。她演过《Bow》（译者注：可能指的是某个作品的名字）。
That's what it was. Yeah. Me twice. Yeah, exactly. Towards the other. What a very gangster film. Yeah. With Gina Gertman. Gina Gertman. That's a little bit. Oh my God. That film. Oh my God. Well, let's not get canceled here. Okay. It is quite a film. All right. Speaking of action. Big week. The AI industrial complex is dominating our docket here. Apologies to Biden, Ukraine and Nikki Haley, but we got to go AI right now. Open AI. Large chat. GPT for oh. 4.0. Monday. Three days after Sam Wise came on all in as a programming note. And we'll go to freeberg about this. We probably made a bit of a surgical or tactical era in not postponing a apparent appearance in fairness. Freeberg Sam Wise did tell us originally he was coming on to talk about those things, but then it got pushed back and it will add to that as a programming note because people are wondering what happened.
那就是意思。对，对，我也是被邀请了两次。对，完全正确。向另一个方向。那么黑帮电影，真是够可以的。对，有吉娜·格特曼出演。吉娜·格特曼。真是让人惊讶。天啊，那部电影。天啊。好吧，我们不要被取消了。好吧，那真是部电影。说到动作。那可是个大事件。这周与AI相关的事情占据了我们的议程。对不起拜登，乌克兰，还有尼基·黑利，但现在我们得先谈AI。Open AI。大型聊天。GPT-4.0。星期一。山姆·怀斯在《All In》节目上出现后的三天。作为一个节目备注，我们得请弗里伯格来谈谈这事。我们可能在没有推迟他来访这件事上，犯了些策略错误。公平地说，山姆·怀斯最初告诉我们他会来谈这些事情，但后来被推迟了，我们会在节目备注里加上这一点，因为人们在好奇发生了什么。
I've been talking with Sam for a while a year about coming on the show and every time I see him I'm we're like, Hey, you should come on the show. He's like, I want to come on the show. Okay. Let's find a date. We never got a date that worked. I saw him in March and he said, Hey, I want to come on the show. I said, Okay, well, come on. Let me know when works in a couple of weeks later. He's like, What about this date in May? And I'm like, Yeah, that's that's fine. We can make that work. He's like, Well, I've got a big announcement. We're going to be doing. And I was like, Perfect. Come on the show that that sounds great. And then the night before he asked me, he told me he texted me. He's like, Hey, we're actually not going to have this announcement happen tomorrow. It's going to be delayed. He didn't tell me how long and I'm like, Well, is it chat? Is it GPT five? He's like, No, it's not GPT five.
我已经和萨姆谈了一年多关于上节目的事了，每次见到他我们都会说：“嘿，你应该上节目。”他也总是说：“我想上节目。”我说：“好的，那我们找个日期吧。”但总是找不到合适的时间。今年三月我又见到他，他说：“嘿，我想上节目。”我说：“好啊，告诉我什么时间可以。”几周后，他说：“五月份这个日期怎么样？”我答道：“没问题，我们可以安排的。”他说：“我们有个重大公告要发布。”我想：“太好了，上节目吧，这听上去很棒。”但就在前一天晚上，他发短信告诉我说：“我们实际上明天不能发布这个公告了，要推迟。”他没有说推迟到什么时候，我问：“是不是GPT-5？”他说：“不是GPT-5。”
And I was like, Okay, well, you know, come on the show anyway, because he didn't tell me when he's doing the announcement and when it's being pushed to so it didn't seem like that big a deal. And I thought we were just going to be able to have a good chat anyway. So it's really unfortunate. I think the fact that the announcement happened two days after and he had to stay quiet about it during our interview. But that's the story. I think in the future, if someone says they've got a big announcement to do, we should probably push him. If they if they have to listen, don't be. But I don't think we're going to be doing a lot of these interviews anyway. I think people clearly don't love them and it's better for us to just kind of hang out and talk.
我当时想，好吧，反正你也来上节目吧，因为他没有告诉我具体什么时候会宣布消息，以及消息推迟到什么时候，所以我觉得问题不大。我本以为我们可以好好聊一聊。所以结果有点遗憾。那次采访后两天，他才宣布了消息，而在采访时他必须保持沉默。不过，这就是事实。我想以后如果有人说他们有重要的公告，我们应该推一下他们，让他们说清楚。如果他们不愿意，就算了吧。但我觉得我们以后可能不会做很多这样的采访了，看来大家不太喜欢这样的节目，我们还是随意聊天更好。
I think I think if we had just gotten Sam on the day after the launch of GPT four on the, as opposed to what was it three days before, you could have talked much more freely about it. It would have been great. Yeah, it was supposed to happen same day. So it's unfortunate. This all worked out this way. Yeah, I think a little trick is to say you can tell us under embargo. But my understanding is they were still doing the videos over the weekend. So I think those videos and stuff, they were still figuring them out. And so yeah, lesson learned in terms of the interviews on the show.
我觉得，如果我们能在GPT-4发布后的第二天采访到Sam，而不是发布前三天，那他就能更自由地谈论这件事了。那样会更好。本该是同一天进行的采访，所以这样安排很遗憾。我的小技巧是，可以告诉他，我们会保密。不过据我了解，他们周末还在制作视频，所以那时候他们还在弄清楚视频的内容。对节目中的采访安排，这算是一次经验教训。
Just a recap for people. We've done a dozen half of them have been presidential candidates. Sometimes they break out. Sometimes they don't. But we follow our interest and our passion here on the pod. It's got to be interesting for us too. So if we think this person is going to be interesting, we do it. Yeah, we understand you miss a news subject, but yeah, it is what it is. And to your point, a lot of the people that come on and increasingly a lot of people ask to come on because they know we're not journalists. And so for all of those folks that expect us to be journalists, that's not what we are.
为大家简单回顾一下。我们已经做了十二期，其中一半的嘉宾是总统候选人。有时候他们会出名，有时候不会。但我们在这个播客上是跟随我们的兴趣和热情的。内容也得对我们有吸引力。所以如果我们觉得这个人有趣，我们就会邀请他上节目。是的，我们理解你可能会错过一些新闻话题，但这就是我们的风格。说到你的问题，越来越多的人主动要求来我们节目，因为他们知道我们不是记者。对于那些期望我们像记者一样的人，我们并不是那样的。
We're for entrepreneurs, we're for business people, we're for friends, we're for technologists, we're for curious people, we're for poker players. But we're not for journalists. And so we're going to ask whatever we feel like asking. Sometimes those things will touch a chord because it's what you want it to have asked. And sometimes we won't go to a place whether we didn't have time to or whether we forgot or whether we chose not to. And I think it's important to have that disclaimer. Like we have day jobs and this is what we do to coalesce a bunch of information in the way that we're thinking about the world. So we are not journalists.
我们支持企业家、商人、朋友、技术专家和好奇心强的人，我们甚至支持扑克玩家。但是我们不支持记者。因此我们会随心所欲地提问。有时我们的问题会引起共鸣，因为那正是你们希望被问到的。有时我们则可能没有涵盖某些内容，可能是因为时间不够、记忘了或者我们选择避开。我认为有必要声明一下：我们都有全职工作，而这个平台只是我们收集并表达我们对世界看法的一种方式。所以我们不是记者。
So I think what that means is that if the guest doesn't want to talk about something, we're not going to start peppering him with gotcha questions and things like that. I appeared at a conference a couple of days ago at remote glue, which we'll get to. And the first half of the conversation was like a normal conversation about what we were launching. And then the second half was basically the reporter peppering me with fastball questions, which is fine. I knew what I was signing up for. It's a totally different style. It's a totally different style than coming on the pod and just having a normal conversation. But it's not really our job to make somebody open up if they don't want to talk.
所以，我的理解是，如果嘉宾不愿意谈论某件事，我们不会强行用刁钻的问题逼迫对方回答。几天前我在Remote Glue的一个会议上发言，稍后会提到具体内容。开头部分的对话像是正常的谈话，主要讨论我们将要发布的内容。然后到了后半部分，记者开始不断抛出尖锐的问题给我，这毫无问题，因为我知道这是我需要面对的。这种风格和来我们的播客节目进行正常对话是完全不同的。但如果有人不愿意谈论某个话题，我们也没必要让他们勉强开口。
That was the fastest question, Sax. That was the fastball. Anything come close to your head? No, I mean, it's not worth really getting into. You can watch it. I was just curious. Look, I kind of like sometimes when reporters pitch me fastballs because, yeah, you can strike out or you can hit it out of the park when they do that.
那是个最快的问题，萨克斯。那是个直球。有打到你头附近吗？没有，我觉得没必要深入讨论。你可以自己去看。我只是有点好奇。你看，我其实有时候挺喜欢记者给我抛直球的，因为，嗯，你可能会被三振出局，但也可能会把球打出全垒打。
That's an important part here. I think, you know, as a former editor and chief journalist myself, I sometimes like to ask, I would say a challenging question in a respectful way. I did that, for example, vague, you know, just clarifying his thoughts on trans and gay rights. Wasn't disrespectful? Was thoughtful? Would you consider it spicy or hardcore? I don't think it was hardcore. He likes to talk about it.
这一点非常重要。你知道，作为前编辑和首席记者，有时候我喜欢以尊重的方式提出挑战性的问题。例如，我曾经这样做过，只是明确他对跨性别和同性恋权利的看法。这并不是不尊重，而是经过深思熟虑的。你会认为这样的问题尖锐或激进吗？我不认为它是激进的。他喜欢谈论这个话题。
No, but that's because you asked it from a position of curiosity. You weren't trying to catch the guy. No, I'm actually interested in his opinion. No, this is my point. That's why it comes out differently. And that's why I think people enjoy these conversations. And sometimes we don't get to the other kind of answer because I'm not interested in trying to got you somebody that's working hard.
不，但那是因为你带着好奇心提出这个问题的。你并不是在试图抓住那个家伙的错误。不是的，我实际上对他的观点很感兴趣。不是的，这是我的观点。这就是为什么结果会有所不同。这也是为什么我认为人们喜欢这些对话的原因。而且有时候我们得不到另一种答案，是因为我不感兴趣去挑刺那些辛勤工作的人。
I always have the same conditions when I do interviews, which is I don't clear questions and I don't let people edit it. But, you know, everybody's got a different view on how to do interviews and feel like different if you like it, if you like Lex Friedman's version or Tim Ferriss's version or you prefer, you know, Fox or CNN, go watch those interviews there. You can have a whole range of different interviews and interview styles available to you in the media landscape. We are but one.
我在做采访时总有相同的条件，就是我不提前知道问题，也不让人编辑采访内容。但是，你知道，每个人对采访的方式都有不同的看法。如果你喜欢 Lex Friedman 或 Tim Ferriss 的风格，或者更喜欢看 Fox 或 CNN 的采访，那就去看他们的吧。在媒体环境中，有各种各样不同的采访和采访风格可供选择。我们只是其中一种。
Sam Weiss mentioned on the pilot last week that the next big model might not be called GPT five. So on Monday, they launched GPT four. Oh, the O stands for Omni. It's everything you love about tech. It's faster. It's cheaper and it's better.
萨姆·魏斯上周在试播节目中提到，下一个大型模型可能不会叫做 GPT-5。所以他们在周一发布了 GPT-4.O。这里的O代表全能（Omni）。它包含了你喜欢的所有科技特点：更快、更便宜、更好。
But from my perspective, the real show was the massive amount of progress they made on the UI UX. The O stands for Omni as an omnivore. It takes in audio, text, images, even your desktop and video from your camera to inform what it's doing. You can consider it like 360 degree AI. Producer Nick will show a couple of videos while I describe them here before we go to the besties for the reaction to the announcement.
但在我看来，真正精彩的是他们在用户界面和用户体验方面取得的巨大进展。“O”代表“全能”（Omni），就像是杂食动物一样。它可以接收音频、文本、图像，甚至是你的桌面和摄像头的视频，用来指导它的操作。你可以把它看作是一个360度的人工智能。制片人尼克将在我这里描述的时候播放几个视频，然后我们再去听听大家对这个发布的反应。
First, they made great progress in solving the CB problem we mentioned last week. That's where like we use Siri or any of these tools, you say, you know, hey, Jatchy P.T., what's two plus two over and you have to wait. And then if you talk over each other, it breaks. They now have that working much smoother. They did an example of counting where they said speed up, slow down.
首先，他们在解决我们上周提到的CB问题上取得了很大进展。就是说，比如我们使用Siri或其他类似工具时，你说“嘿，Jatchy P.T.，二加二等于多少”，然后需要等待。如果你和它同时说话，这个过程就会中断。现在，他们已经让这个过程变得更加顺畅了。他们还做了一个计数的示例，在那个示例中，他们说“加快速度，减慢速度”来调整。
They did a translator that worked really well. I would like you to function as a translator. I have a friend here who only speaks Italian and I only speak English. And every time you hear English, I want you to translate it to Italian. And if you hear Italian, I want you to translate it back to English. Is that good? Perfecto. Mike, you're my kid. Celebrate the letter. I want you to read it. Mike, she wonders if Wales could talk. What would they tell us?
他们做了一个效果很好的翻译器。我希望你能作为翻译。我有一个朋友只会说意大利语，而我只会说英语。每次你听到英语时，我希望你能把它翻译成意大利语。如果你听到意大利语，我希望你能把它翻译成英语。这样可以吗？完美。迈克，你是我的孩子。庆祝那封信。我想让你读一下。迈克，她想知道如果鲸鱼会说话，它们会告诉我们什么？
They might ask, how do we solve linear equations? I would like to read the letter to you. I would like to read the letter to you. I think to lingo stock took a hit during that. Most impressive, to me at least. And also I had Sandeep Madra on my other podcast and we talked about it was their desktop and iOS app. What this app does is fascinating. It watches your desktop on your Macintosh or on your iPad or iPhone. And it does.
他们可能会问：我们如何解线性方程？我想把这封信读给你听。我觉得在那期间，Lingo Stock 公司遭受了打击。这对我来说，至少是非常令人印象深刻。此外，我在另一个播客上邀请了 Sandeep Madra，我们讨论了他们的桌面和 iOS 应用程序。这款应用程序非常有趣，它会监控你在 Mac 电脑、iPad 或 iPhone 上的桌面操作。
Things like adaptive learning. Here's a clip of Sal Khan from Khan Academy and his son basically using a drawing app to do some arithmetic or geometry. And it does adaptive learning and basically makes a personal coach because the app is watching his son try to solve a problem. I'm here with my son and I love you to tutor him on my website. I'm here with my son and I love you to tutor him on this math problem. But don't give him the answer. You can ask questions and nudge him in the right direction. But I really want to make sure he understands it himself. And he's here in the room so you can talk to him directly.
像自适应学习这样的东西。这里有一段影片，是来自可汗学院的Sal Khan和他的儿子，基本上他们在用一个绘图应用程序做一些算术或几何题。这个程序具有自适应学习功能，基本上可以成为个人教练，因为应用程序在观察他的儿子如何尝试解决问题。我在这里和我的儿子一起，我希望你在我的网站上辅导他。我在这里和我的儿子一起，我希望你可以辅导他解决这个数学问题。但不要直接告诉他答案。你可以提问并引导他走向正确的方向，但我真的想确保他自己理解问题的本质。他就在房间里，所以你可以直接和他说话。
Can you first identify which sides of the triangle are the opposite, adjacent, anti-pontinus relative to angle alpha? Alright, so I'm pretty sure this is the angle alpha right here, right? Ficked. Confirmed. Now looking at the triangle, which side do you think is the hypotenus? Um. Remember the hypotenus? I'm not totally sure. I think it might be this one, but I really am not sure. This side AC. Your close. Actually, side AC is called the adjacent side to the angle alpha. The hypotenus is the longest side of a right triangle and is directly opposite the right angle.
你能先确定三角形哪几条边是相对于角α的对边、邻边和斜边吗？好的，我确定这个就是角α，对吧？没错。确定。那么看看三角形，你觉得哪一条边是斜边？嗯，记住斜边？我不太确定。我觉得可能是这条，但我真的不确定。是边AC。你很接近。实际上，边AC是相对于角α的邻边。斜边是直角三角形中最长的边，并且直接在直角的对面。
Can you find which one is the hypotenus? Oh, okay, I see. So, um, I think the hypotenus is this really long side from A to B. Would that be correct? Exactly. Well done. It can also participate in Zoom calls, explain charts, all that great stuff. And so it's going to be your guide on the side. It's going to be a present, you know, personality while you're using your apps. It's really impressive, I have to say. So I guess let's start Freeburg with your takeaways on all of these innovations that we saw.
你能找到哪条边是斜边吗？哦，我明白了。那么，我想斜边应该就是从A到B的这条比较长的边，对吗？完全正确。做得好。它还可以参加Zoom会议，解释图表等等所有这些很棒的功能。所以它会成为你身边的向导。在你使用应用程序时，它会像一个有存在感的人一样，真是令人印象深刻。我想我们可以从Freeburg开始，让他分享一下对这些创新的看法。
I think it's become quite apparent that there's an evolution underway in model architecture. And I think you may remember we talked about this briefly with Sam last week, but we're moving away from these very big bulky models that are released every couple of months or quarters and cost a lot of money to rebuild every time they get re-released. Towards a system of models. So this multimodal system basically leverages several models at once that work together or that are linked together to respond to the inputs and to provide some generative output and that those individual models themselves can be continuously tuned and or continuously updated.
我认为，现在已经很明显可以看出模型架构正在发生变化。我记得我们上星期跟Sam简短讨论过这个问题。我们正在转变，以前是每隔几个月或每个季度就发布一次非常庞大的模型，这些模型每次重新发布时都花费很多钱。而现在，我们正朝着一个模型系统的方向发展。这个多模态系统基本上是利用多个模型一起工作或互相连接，以响应输入并生成一些输出。而且这些单独的模型本身可以不断地调优或更新。
So rather than have, you know, hey, there's this big new release that just happened, this new model just got trained cost $10 million to train it and it's been pushed. These models can be upgraded with tuning with upgrade features and then linked together with other new smaller models that are perhaps specialized for specific tasks like doing mathematics or rendering an image or rendering a movie. And so I think what we're going to see is soon more of an obfuscation of the individual models and more of this general service type approach where the updates are happening in in a more continuous fashion.
所以，与其说有一个大规模的新发布，像什么"哇，一个刚刚花了1000万美元训练的新模型已经发布了"，不如说这些模型可以通过调优和增加新功能来升级，然后与其他专门用于特定任务（比如数学计算、图像渲染或电影渲染）的小型模型连接在一起。因此，我认为我们很快会看到的是，单个模型的重要性会被淡化，取而代之的是一种更像是通用服务的方式，更新会以比较连续的方式进行。
I think this is the first step of open AI taking that architectural approach with GPT 4.0 and what's behind the curtains. We don't know. We don't know how many models are there. We don't know how frequently they're being changed, whether they're being changed through actually upgrading the parameters or whether they're being fine tuned. And so this seems to be pretty obvious. If you look at this link, one of the criticisms that initially came out when they released GPT 4.0 was that there was some performance degradation.
我认为这是开放AI在GPT 4.0中采用这种架构方法的第一步，幕后发生了什么我们并不清楚。我们不知道有多少模型，也不知道它们被改变的频率，是通过实际升级参数还是进行微调。所以这似乎是显而易见的。如果你看这个链接，当他们发布GPT 4.0时，最初出现的批评之一就是性能有所下降。
And Stanford actually runs this massive multitask language understanding assessment. And they publish it, I think, daily or pretty frequently on how all the models perform. And you can see the scorecard here that GPT 4.0 actually outperforms GPT 4. And so this goes counter to some of the narrative that in order to get some of the performance improvements and speed improvements they got in 4.0, that they actually made the model worse. And it seems actually the opposite is true that the model's gotten slightly better. It's still underperforms Cloud 3.0. Opus, which you can see here at ranked top of these charts. But there's lots of different charts. All the companies publish it on charts. They all claim that they're better than everyone else. But I like Stanford because it's independent. Trim up any thoughts after seeing it in combination with our interview.
斯坦福实际上运行着一个大规模的多任务语言理解评估系统。他们发布这个评估结果的频率很高，我记得是每天或者非常频繁地发布各个模型的表现。你可以在这里看到成绩单，GPT 4.0 其实比 GPT 4 表现得更好。这和一些说法相反，有些人认为为了提升性能和速度，GPT 4.0 其实变得更差了。但实际上，似乎情况相反，GPT 4.0 的表现稍有改善。尽管如此，它还是不如 Cloud 3.0 和排名表首位的 Opus 表现好。不过有很多不同的排行榜，各家公司都发布自己的榜单，声称自己最好。但我更喜欢斯坦福的评估，因为它是独立的。结合我们的访谈，你有什么看法吗？
Do you think chat GPT is running away with the consumer experience? Or do you think this is like neck and neck with some of the other players? Not to tell tales out of school, but somebody that we all know in our group chat hosted something about the fact that the consumer growth had stalled. I don't know how they knew that, that they maybe they got some data or maybe they're an investor. You guys know what I'm talking about. And they said that they're trying to reinvigorate growth into the consumer app into. I don't open AI. I mean, any insights as to why it might be plateauing in your perspective?
你认为 Chat GPT 在用户体验方面是否遥遥领先，还是和其他竞争者不相上下？不想在背后议论别人，但我们群聊中有个朋友提到用户增长停滞了。我不清楚他们是从哪里得来的消息，可能是通过数据或者他们是投资人。你们明白我在说什么。他们还提到 OpenAI 正在试图重振其消费应用的增长。对于你来说，为什么增长可能会趋于平稳，有什么见解吗？
I wrote this in my annual letter, but there are these phases of growth. And when you look at like social networks as a perfect example, Friendster was magical when it was first created. Right. And then you had my space that just ran circles around them because Friendster didn't really invest the money and the quality that it took to to create a moat. And then my space really wasn't able to compete. So we were, you know, Facebook, we were the eighth or ninth when we showed up on the scene and we ran circles around everybody. I think what it means is that there are these phases of product development which exist in many markets.
我在年度信中写过这些内容：成长是分阶段的。以社交网络为例，当初 Friendster 刚推出时非常神奇。但随后 MySpace 迅速超越了他们，因为 Friendster 没有在资金和质量上做足够的投入来形成护城河。而后 MySpace 也无法继续竞争。这样一来，当我们 Facebook 出现在市场时，我们是第八或第九名，但我们最终超越了所有竞争对手。这表明，许多市场中的产品开发都有类似的阶段性。
This market, I think is going through the same thing. And right now we're in the first, what I would call primordial ooze phase, which is everybody's kind of like running around like a chicken with their heads cut off. There's all these core basic capabilities that are still so magical when you see them, but we all know that five and 10 years from now, these things will be table sticks. Right. And what Freeburg just showed is a table of many companies and many trillions of market cap all effectively running to the same destination. So I think where we are is probably within two years of where the basic building blocks are standardized. And then I think the real businesses get built.
我认为，这个市场正在经历同样的状况。而目前，我们正处于我称之为"原始混沌"阶段，大家就像无头苍蝇一样乱撞。尽管这些核心基本功能在现在看来依然是那么神奇，但我们都清楚，在未来五到十年内，这些东西将会成为标配。而Freeburg刚刚展示了一张表格，里面列出了许多公司和数万亿市值的市场，实际上都在奔向同一个目标。所以我认为，我们大概还有两年的时间，基本构建模块会标准化。然后，真正的生意才会开始建立。
So I will maintain my perspective here, which is the quote unquote Facebook of AI has yet to be created. Okay. And here it is. Chat, CPT web visits, as you can see, have plateaued. This data is similar web. I would agree with you, Jamaf. It seems like the use cases and the lucky lose who were just trying the software because they heard about it. They've gone away and then we have to find actual use cases. Sax, I'm wondering, but our friend Jason, just to kind of completely said something about the premium conversion. Right. That's what he said. I don't know how he knows that paid paid. Well, pay it.
我会在这里坚持我的观点，也就是所谓的“AI的Facebook”尚未出现。好吧。这里有一些数据。ChatGPT的网页访问量，如你所见，已经趋于平稳。这些数据来自SimilarWeb。我同意你的看法，Jamaf。看起来那些因为听说了这个软件而来尝试一下的用户已经走了，我们现在需要找到实际的应用场景。Sax，我在想，但我们的朋友Jason曾提到过关于付费转换的一些事情。对吧。他说了什么我不知道，但他说付费用户转换。
So to be clear, paid versus free. And then what Sam said on the podcast last week was it seems like whenever they come out with something new, the old stuff becomes free. And in my talk with Sonny this week, he mentioned that these new models are so much more efficient that you actually can throw the old model in the garbage because it's so inefficient. And these are now becoming about 90% cheaper every year, which means every two years these things would be 99% cheaper and better. Yep.
所以，为了明确一下，付费版本和免费版本的区别。上周，Sam在播客中提到，每次他们推出新产品时，旧产品似乎都会变成免费的。而我本周与Sonny的谈话中，他提到这些新模型的效率要高得多，以至于你实际上可以把旧模型扔掉，因为它太低效了。这些新模型的成本现在每年下降约90%，这意味着每两年它们的成本会降低99%，并且性能更好。是的。
And it might be that opening eye sacks on a strategic level is going to make all this free or close to free and maybe just charge for multiplayer version. That seems to be where it's heading. You don't have to log into use 3.5. You don't have to log in to use Google, no, you do have to log in still on Google services, but I think these are going to just be free. So on a product basis, what are your thoughts?
从战略层面来看，可能打开眼袋让这一切变得免费或接近免费，可能只对多人版本收费。看起来这正是发展的趋势。你不需要登录就能使用3.5版本。你不需要登录就可以使用谷歌，不，使用谷歌服务还是需要登录，但我认为这些将会是免费的。那么，从产品的角度来看，你有什么想法？
And then maybe you could talk about free to pay. Do you think everybody in the world is going to pay 20, 30, 40 bucks, 500 a year, 200 a year to have one of these? Or are they just going to all be free? Well, I think you're assuming there that the long term business model of open AI is in B to C subscriptions. And I think that's probably the least attractive business model they have available to them. It's sort of the first one and the most obvious one because they put out touch EPT and then it's pretty easy to roll out premium version.
然后你可以谈谈免费到付费的模式。你认为全世界的人都会愿意花20、30、40美元，或者每年花500、200美元来拥有这样一个产品吗？还是他们宁愿全都免费使用？我觉得你的假设是OpenAI的长期商业模式是面向消费者的订阅制。但我认为这可能是他们可选商业模式中最不具吸引力的一种。这是一种最先想到也是最明显的模式，因为他们推出了TouchGPT，然后推出高级版本相对比较容易。
But in my experience, B to C subscriptions, since I'm very attractive as a small because consumers disarmamentally to pay a lot and they have high churn rates and there's no possibility of expansion, really. So I suspect they're going to move in more of a B to B direction over time because that's where the real money is. And probably the way they do that is by monetizing all the apps that are built on top of it. And I think that in that sense, GPT 4.0 is a really important innovation. By the way, the O stands for Omni, which I think stands for Omni channel.
根据我的经验，B到C的订阅模式由于我是一个小企业，这点非常吸引人，因为消费者通常不愿意支付太多，并且他们的流失率很高，实际上也没有扩展的可能性。因此，我怀疑他们将会随着时间的推移转向B到B的方向，因为那里才是真正的利润来源。而且他们可能会通过将所有基于其构建的应用程序变现来实现这一点。我认为，在这个意义上，GPT 4.0是一个非常重要的创新。顺便说一句，O代表Omni，我认为这表示全渠道。
I think you may have some omnivore. Well, I think it's Omni, which means all the different media types currently coming in. That's the difference. It's not like you just give it an image or give it a video. It's absorbing all those at the same time in power, I believe. That's right. So there's three big innovations with the small. One is Omni channel, which means text, audio, video and images. Second, it's more conversational. Like it understands the tone of people talking and understands sort of sentiment in a way it didn't before.
我认为你可能有一些全媒体。嗯，我认为这里的“全（Omni）”是指目前所有不同类型的媒体。这就是区别。它不仅仅是给它一张图片或一个视频，而是同时吸收所有这些媒体类型的信息。我相信这是对的。所以这个新技术有三个大的创新点。第一个是全媒体渠道，这意味着可以处理文本、音频、视频和图像。第二个是它更能进行对话式交流，比如它能理解人们说话的语气，并以一种以前做不到的方式理解情感。
And then the third thing, which is really important is that it's just much faster and more performant than the previous version, GPT 4 Turbo. In the speed test, they say it's twice as fast. We've played with it at GLU. We can talk about that in a minute. And it feels 10 times as fast. It is much faster. But it's the combination of all three of these things that really makes some magical experience as possible because when you increase the speed, of processing, you can now actually have conversations within a much more natural way.
第三点，也是非常重要的一点，就是它比之前的版本——GPT-4 Turbo——快得多，性能更强。在速度测试中，据说它的速度是之前的两倍。我们在GLU也试用了它，可以稍后再谈。用起来感觉速度快了10倍，确实快了很多。但真正神奇的体验源于这三点的综合，因为当处理速度提高后，你就可以进行更加自然的对话。
Before the models were just too slow, so they'd be a long delay after every prompt. So now, like you showed, it can do things like you point the camera at a blackboard or something with math equations on it. And it can walk you through how to solve that problem. Or two people can be talking and it does real-time translation. There's that old saying that every Star Trek technology eventually becomes true. They've just basically invented the whole natural language real-time universal translator. So anyway, those are some interesting use cases. But I just think they're going to be able to unleash a whole lot of new applications. And if they're metering the usage of the models and providing the best dev tools, I think there is a business model there. And the next thing is moving so fast there in Leonardo DiCaprio mode. Every two years they throw the old model away.
之前，这些模型运行速度太慢，所以每输入一个提示都会有很长的延迟。现在，就像你展示的那样，它可以做一些事情，比如你用相机对准黑板或一些数学方程式，它可以一步步引导你解决问题。或者，两个人在交谈，它可以进行实时翻译。有一句老话说，每一种《星际迷航》中的技术最终都会成为现实。他们现在基本上已经发明了全自然语言的实时通用翻译器。所以，这些是一些有趣的应用场景。但是我认为他们将能够释放出大量的新应用。如果他们对模型使用进行计量，并提供最好的开发工具，我认为这其中有一个商业模式。此外，进展如此迅速，就像莱昂纳多·迪卡普里奥模式，每两年就更新一次旧模型。
Okay, let's keep saying sex. But I'm being. Hey, is this thing on? Did you write that ahead of time or? I was in the moment. That was good. Just one point on that is there are a whole bunch of startups out there that work creating virtual customer support agents. And they've been spending the last couple of years working on trying to make those agents more conversational, quicker, more responsive. I think their product roadmaps just became obsolete. Now, that's not to say there isn't more work for them to do in workflow in terms of integrating the AI with customer support tools and doing that last mile of customizing the model for the vertical specific problems of customer support. But my guess is that hundreds of millions of dollars of R&D just went out the window. And probably this is the best time to be creating a customer support agent company. If you're doing it two years ago, five years ago, your work has just been obsolete.
好的，让我们继续说性。呃，我是说。嘿，这东西在运作吗？你是提前写好的吗还是？我是在当下即兴的。那很好。只是要指出一点，现在有大量初创公司在致力于创建虚拟客户支持代理。过去几年里，他们一直在努力使这些代理更具对话性、更快捷、更响应。我认为他们的产品路线图已经过时了。不过，这并不意味着他们在工作流程方面没有更多的工作要做，比如将 AI 与客户支持工具集成，并为客户支持的特定问题量身定制模型。但我猜，数亿美元的研发费用就这样打水漂了。而且现在可能正是创建客户支持代理公司的最佳时机。如果你是在两年前、五年前做这件事，现在你的工作已经过时了。
Well, I mean, that is the thing with this pace. You used to have to throw away client server stuff or whatever. You had a web-based thing. You get an app out. You throw away some of the old code. But this is like every 18 months your work has been replaced. If you're an app developer, the key thing to understand is where does model innovation end and your innovation begin? Because if you get wrong, you'll end up doing a bunch of stuff that the model will just obsolete. I think you're totally right. I think that's such a really important observation. That's why I think the incentive for these folks is going to be to push this stuff into the open source. Because if you solve a problem that's operationally necessary for your business, but it isn't the core part of your business, what incentive do you have to really keep investing in this for the next five and ten years to improve it?
嗯，我是说，这就是这速度的问题。你以前得扔掉客户服务器的东西或者其他什么，用一个基于网页的东西。你发布一个应用程序，扔掉一些旧代码。但现在像是每18个月你的工作就被替代一次。作为一个应用开发者，关键在于要理解模型创新在哪里结束，而你的创新从哪里开始。因为如果弄错了，你就会做一堆模型很快就会淘汰的东西。我觉得你完全正确，我觉得这是一个非常重要的观察。这也是为什么我认为这些人会倾向于把这些东西推向开源社区。因为如果你解决了一个对你的业务运营来说是必须的问题，但它并不是你业务的核心部分，那么你有什么动力在未来的五到十年里继续投资改进它呢？
You're much better off like Klarna, for example. We talked about the amazing improvement and savings that Klarna had by improving customer support. Release it in the open source, guys. Let the rest of the community take it over so that it's available to everybody else. Otherwise, you're going to be stuck supporting it. Then if and when you ever wanted to switch out a model, GPT 404 to 404 to Claude to Lama, it's going to be near impossible and it's going to be costly. I also think, Zach, the incentive to just push towards open source in this market, if you will, is so much more meaningful than any other market. Listen, you were there. I think you were there. Facebook, when they did the Open Compute project, and they just were like, Oh my gosh. Talk about torching an entire market. Explain what it is. There was this moment where when you were trying to build data centers, you'd have these one-year rack-mounted machines that you used.
你会赶上一大截，比如Klarna。我们谈到了Klarna通过改善客户支持而取得的惊人进步和节省。把它开源吧，伙计们。让其他社区成员接手，这样大家都能用上。否则你会被自己支持的系统困住。如果你以后想更换模型，比如从GPT 404到Claude再到Lama，几乎是不可能的，而且成本高昂。我还认为，Zach，在这个市场上推动开源的动机会比其他市场意义更大。你知道的，Facebook做开放计算项目的时候，真的搞砸了整个市场。解释一下这是什么情况。曾经有一段时间，当你试图建立数据中心时，你会使用这些一年一换的一体机。
What Facebook observed was there was only a handful of companies that provided it. It was unnecessarily expensive. Facebook just designed their own and then released the specs online. Here it is. They went to these Taiwanese manufacturers and other folks and said, Please make these for your cost plus a few bucks. It was revolutionary in that market because it allowed this open platform to embrace this very critical element that everybody needs. I think there's going to be a lot of these examples inside of AI because the costs are so extreme, so much more than just building a data center for a traditional web app, that the incentives to do it are just so meaningful.
Facebook观察到，只有少数几家公司提供他们需要的服务，而且价格昂贵得不必要。于是，Facebook自己设计了相应的产品，并把规格发布到网上。他们找到了台湾的制造商和其他一些公司，要求他们以成本价加几美元的价格生产这些产品。这在市场上是一次革命性的改变，因为它让一个开放平台能够拥抱所有人都需要的这一关键元素。我认为，在人工智能领域也会出现很多类似的例子，因为其成本极其高昂，远远超过建立一个传统的网络应用数据中心，驱动创新的动力非常强大。
Yeah, and I just showed it on the screen. Sacks, you've actually been dancing along this line last night. I was using your new Slack killer, or I'm not sure. It feels like a Slack killer to me because I'm moving my company to it on over the weekend. We're moving to glue. Nice. And when I were doing some very, I make our mini to wet my beak on this one. We want you to wet your beak. I feel like a hundred bagger to me. I'm in. It's a Slack killer. That's the way we're thinking about it. Killer S because, Jake, can you do that again in Chris for a walk in voice, please? I get to wet my beak. It was like a hundred X slide in 500. Wow.
是啊，我刚刚在屏幕上展示了这一点。Sacks，你昨晚其实一直在这一行上跳舞。我在用你的新Slack替代品，或者我也不确定。不过对我来说感觉它就是个Slack杀手，因为这个周末我就要把我的公司迁移过去。我们要换成Glue。不错。当我在做一些事情时，我也想从中沾点好处。我们也希望你能从中受益。这对我来说就像是个百倍回报。我参与了。这就是个Slack杀手，我们也是这么想的。Jake，你能用Christopher Walken的声音再来一遍吗？我能从中沾点好处。这就像是百倍回报，500倍的幻灯片。哇。
Sacks, tell me about product decisions. Where does the AI end? And your product begin. Yeah. Well, it's a good point. I mean, I think where the AI ends, we want to use the most powerful AI models possible. And we want to focus on enterprise chat. So you could think of us as for sure, a Slack killer or Slack competitor. This is that Slack wasn't built for the AI era. Glue is AI native. What does that mean? No channels. You know, I showed this to Jonathan. First thing he said is you had me in no channels, right? People are so sick of channels. You have to keep up with all these hundreds and hundreds of channels. And the real problem with channels is there's one thread in a channel that you want to see. In order to see it, you have to join the whole channel. And now you're getting all this noise. People just want the threads.
萨克斯，跟我谈谈产品决策。AI的作用到哪里结束？你们的产品从哪里开始？嗯，这是个好问题。我认为，我们希望使用最强大的AI模型，并且专注于企业聊天。你可以把我们看作是Slack的替代者或竞争者。Slack并不是为AI时代而设计的，而Glue是AI原生产品。这意味着什么呢？没有频道。我给Jonathan展示这个产品时，他第一句话就是“没有频道这点吸引了我”，人们真的是受够了频道。你得跟上数百个频道中的所有内容。频道的真正问题在于，你想看的只有其中的一个线程，但为了看到它，你必须加入整个频道，结果你会收到很多无关的信息。人们其实只想要线程。
So if you look at what's the chat model inside of chat GPT, it's just threads, right? You create a topic based thread in chat GPT. The AI comes up with a name for it, puts it in the sidebar. And then if you want to talk about something else, you create a new chat. That's exactly the way that glue works. It's just multiplayer. You just put the groups and individuals you want on the thread. Let me just show you real quick. Here's my glue here. And you can see that in the sidebar, I've got all the threads that have been involved in. Like I said, you can address them to multiple people or groups. And then you've got the chat here. Now we've also fully integrated AI.
所以，如果你看一下 ChatGPT 内部的聊天模型，它其实就是线程，对吧？你在 ChatGPT 中创建一个以主题为基础的线程。AI 会给它起一个名字，并将其放在侧边栏中。如果你想讨论其他话题，你就创建一个新的聊天。这正是 Glue 的工作方式，只是它是多人参与的。你只需要将你想要的群组和个人加入到线程中。让我快速示范一下。这是我的 Glue，你可以看到在侧边栏上，有我参与的所有线程。就像我说的，你可以将它们发给多个个人或群组，然后你就可以在这里聊天了。现在我们也已经完全整合了 AI。
And so Nick, who's our producer, just in this thread, said, at glue AI, what countries to SACs talk about most in episodes. Episodes is a group we created to be the repository of all of the transcripts of our episodes. And so, glue did a search and it said, David SACs frequently discusses Ukraine the most. What? So then Nick said, be more specific about SACs stance on Ukraine, Russia, war. Oh boy. And basically. It's going to overload the server. Well, here it said here, David SACs has articulated a nuanced and critical perspective on the Ukraine, Russia, war across various episodes. The all in pod.
因此，Nick，我们的制片人，在这个对话中提到，在Glue AI上，哪些国家是SACs在节目中最多谈论的。Episodes是我们创建的一个组，用来存放我们所有节目的转录文本。于是，Glue进行了搜索，结果显示David SACs最常谈论的是乌克兰。什么？然后Nick说，能具体说一下SACs对乌克兰和俄罗斯战争的立场吗？天哪。这基本上要让服务器超载了。这里的结果是，David SACs在各种节目中，对乌克兰和俄罗斯战争表达了一个细致而批判的观点。这是在All In Pod中。
Here's some key points encapsulating his stance. And it like nailed it. It's talked about prevention through diplomacy, opposition to the expansion, humanitarian concerns, skepticism, military intervention, peace, still proposal. You know, I'll copy and paste this onto Twitter, X later today. But the point is it like nailed it across all these different episodes. And then this is a feature of glue. It provided sources. So it cites where it got all the information from. So imagine, you know, we're doing this for the all in pod, but you could imagine that instead of it being transcripts of a podcast, it could be your work documents.
下面是一些关键点，概括了他的立场。而且说得非常准确。它谈到了通过外交预防、反对扩张、人道主义关切、怀疑军事干预、和平、仍然提案等方面。今天晚些时候我会把这些发布到Twitter（现在叫X）上。但重点是它在这些不同的方面都讲得非常到位。而且这是一个重要的特性，它提供了信息来源，所以它引用了所有信息的出处。所以，想象一下，我们为这个播客做这些工作，但你可以想象，这些不仅仅是播客的文字记录，也可以是你的工作文档。
You now have in your main chat the ability just to ask, Hey, at glue AI. Remind me where we left that project or tell me who the expert is on this subject matter or who's contributed to the most of this project. I've actually figured out using glue AI who's contributed the most deal flow at craft is pretty amazing. Now, let me show you like. What's the answer? What? What's the answer? I'm not going to say here. I make it's Brian. Brian's my guy. Those two. Brian's my guy. I want to know if I got to go Daniel and Brian. Boom. I want to go. That's how I get sacks on them. Okay. You take Daniel all higher, Brian. I don't think I'll do a substitute craft. We'll call it a raft.
现在你的主聊天里可以直接问：“Hey, Glue AI，提醒我我们这个项目进展到哪儿了”或者“告诉我这个主题的专家是谁”、“谁对这个项目的贡献最大”等等。我实际上已经用Glue AI弄清楚了谁在Craft里贡献了最多的项目流量，这真是太神奇了。现在，我给你展示一下答案。答案是什么？答案是什么？我在这里不说。我会说，是Brian。Brian是我的人，就是他了。如果我得找Daniel和Brian，那就是他。我想去找，我就是这么锁定目标的。好，你把Daniel提拔，我会把Brian放在更高的位置。我不认为我会用替代Craft，我们叫它Raft。
这样翻译应该更容易读懂。
Let me show you a couple of seconds. Sax, I just looked at the chat JPT for Omni server. And when you did that query, it actually rolled its eyes. Keep going. OK. Hey, so so we talked about how chat to be T40 understand sentiment in conversations. And I think this is a really good example. So Evan, who's my co-founder, Glue was just testing this for us. And he asked, what is each besties personality type based on conversations and episodes? And first of all, it figured out who the besties are. Like we didn't program that. It just figured it out on its own, which is pretty impressive.
让我给你展示几秒钟。Sax，我刚才看了Omni服务器的聊天记录。当你做那个查询的时候，它实际上翻了个白眼。继续吧。好的。嘿，所以我们之前讨论了聊天机器人T40如何理解对话中的情感。我觉得这是一个很好的例子。Evan，他是我的联合创始人，Glue，他为我们测试这个。他问了一个问题：根据对话和集数，每个好朋友的性格类型是什么？首先，它知道“好朋友”是谁。我们并没有专门编程告诉它这点，它是自己找出来的，真的很令人印象深刻。
And here's what I said about each besties personality. So it says Jason Cowcanis roll the moderator and entertainer personality trace, charismatic, humorous, lively, and the glue of the group. Same. And praise often praised for his ability to make the podcast entertaining and keep the conversation flowing. Jason's energy and ability to bring humor and discussions or keelness that defines role in the podcast comments. He's acknowledged for his role, bringing the group together. Shema, Polly, Hapatia, the visionary and hustler personality traits and insightful, driven, persistent, shema relentless drive and ability to hustle her and my or my peers, making the corporate podcast and lecture discussions.
这就是我对每个朋友性格的评价。比如说，杰森·考柯尼斯担任主持人兼娱乐者的角色，性格特点是有魅力、幽默、生动，是团队的粘合剂。他常常因为能够让播客变得有趣并让讨论顺利进行而受到赞赏。杰森的精力和幽默感让讨论充满活力，这是他在播客中的重要作用。他也因能把团队凝聚在一起而得到认可。
雪玛·波莉·哈帕提亚是一个有远见且能干的人，性格特点是洞察力强、驱动力强、坚持不懈。雪玛不懈的努力和推动能力不仅激励着她自己，也激励着我的同行们，使得我们的企业播客和讲座讨论更加精彩。
I'll skip me, but does freeberg the pragmatic scientists and realists pragmatic and methodical and a bit reserved. Oh, freebers. Often the voice of reason bringing a scientific and realistic perspective that discussion he focuses on analysis, logical reasoning. And then it cites where it got this from. And it says here overall, the dynamic between the four besties creates a well rounded and engaging podcast with each member, bringing their unique strengths and personality traits to the table. I think that's pretty incredible.
我就不提我自己了，但是Freeberg作为一个务实的科学家和现实主义者，他既务实又有条理，有点内敛。哦，Freeberg。经常是理性的声音，为讨论带来科学和现实的观点，他专注于分析和逻辑推理。然后它引用了来源。总体而言，这四位好友之间的互动营造了一个全面且引人入胜的播客，每个成员都带来了自己独特的优点和性格特质。我觉得这非常了不起。
How woke is this? Have you, uh, have you put any rails on or is this just pure? Chats EPT 40. Comparing with the data. Yeah. Yeah. So what we're doing here is we're wrapping Chats EPT 40 with blue features that we've implemented to get the most out of the conversation. There's things we have to do to scope the prompt. And then we're using a retrieve augmented generation service called Ragi, which does RAG as a service that basically slurps in our transcripts and makes them accessible to the AI.
这个有多“觉醒”（woke）？你有没有加上任何限制，还是完全自由的？这是 Chats EPT 40 和数据进行对比的结果。对，我们在这里做的是给 Chats EPT 40 加上我们实现的蓝色功能，以便最大化对话效果。我们需要做一些事情来限定提示的范围。然后我们使用了一种叫做 Ragi 的检索增强生成服务。这种服务基本上会吸收我们的对话记录，并使其对 AI 可用。
So that's basically the stack that we're using. But as the models get better and better, glue just gets better and better again. Can I just make a comment on this? It's just so clean. J Cal was the key for me in abandoning Slack. He told me two or three years ago, he called me and he said, I have, you can tell me the exact channels. I eliminated some channels that were random. There was like two or three channels. Yeah. The random channel, your Slack instance wasn't allowed to have. And I was like, this is genius.
所以，这基本上就是我们在使用的技术栈。但随着模型的不断改进，Glue 也在不断变得更好。我能发表个意见吗？它真的非常简洁。J Cal 是让我放弃 Slack 的关键人物。两三年前，他给我打电话，他告诉我可以具体地删除哪些频道。我取消了一些随机频道，有两三个吧。是的，随机频道在你的 Slack 实例中是不允许存在的。我当时觉得，这真是天才之举。
And I went in and I was like, all of our companies should just eliminate these channels. And we could only get like 20% or 30% compliance, but it really started to turn me off Slack because I would get caught in these threads that were just so totally useless. And I thought, why aren't people working? And this is really great because you cannot blather on about nonsense include, which I find really useful. Well, this is what happens when Slack, we use it at 80 90, just so you know, so we were the when we got into the early get into Slack too much.
我进去后说，我们所有的公司都应该取消这些频道。但是我们只能得到大概 20% 或 30% 的配合，这让我对 Slack 这种工具开始反感。因为我经常被困在一些毫无意义的讨论中，我就在想，人们为什么不去工作呢？这真的很棒，因为这样你就不能胡说八道了，我觉得很有用。这就是我们在使用 Slack 时的经历，我们大约有 80% 到 90% 的时间在用它，以至于我们一开始都陷进去了。
People start to think Slack is the job and replying to Slack and having conversations is the job when there's actually a job to be done. There's a job to be done. Yeah. And so it's important. And what I liked about this implementation facts was it's like the ability to make a feed or a data source inside of your communication platform. So the fact that you imported all of the episodes and the transcripts is great. But what I want is like our HubSpot or our cell CRM. I want our Zendes.
人们开始认为使用Slack就是他们的工作，他们以为回复消息和聊天就是全部工作，而实际上还有真正的工作要做。确实有一项工作要完成。所以这一点非常重要。让我喜欢这个实现事实的原因是，它可以在你的通信平台内创建一个信息流或数据源。你已经导入了所有的节目和文本记录，这一点非常好。但我要的是类似于我们的HubSpot或我们的客户管理系统。我希望我们的Zendesk系统也能有这样的功能。
I want our LinkedIn jobs and our LinkedIn job applications. I want our notion. I want a CODA to each have the ability. And when I was using it last night, what you do is you use the at symbol to evoke and to summon in a way, it's like summoning Beetlejuice. So you summon your AI, but then you tell it what data set you want to go after. So you say, you know, at AI, let's talk about, I don't know, how do you manage your deal flow at craft? Do you use software like CRM software to manage deals?
我希望我们在LinkedIn上的职位和申请都能整合起来。我希望我们使用Notion和CODA，每个人都能使用这些工具。昨晚我在使用它时发现，你可以用@符号来唤起和调用这个系统，有点像召唤Beetlejuice。你可以唤起你的AI，然后告诉它你需要什么数据集。比如，你可以说：“@AI，让我们聊聊如何管理在Craft的交易流程，你们是用CRM软件来管理交易的吗？”
Brian just do it on. Daniel, but we do it all in glue. So it's already right there, but you're right. So so the first thing that glue AI has access to is all of your chat history, which is amazing because you get like, you know, that we can look at all your attachments and we've got, I think six integrations at launch a little bit more. So yeah, like all of your enterprise data will be there. In the short term, you're right. You have to summon the repository by app mentioning because the AI needs a little bit of help of where to look, but in the future, it's going to figure it out on its own.
Brian 就直接做了。Daniel，但我们用的是Glue。所以它已经完全具备了，但是你说的没错。那么，Glue AI首先可以访问的就是你所有的聊天记录，这很棒，因为你知道，我们可以查看你所有的附件。我们在上线时有大约六个集成，稍微多一点。所以，是的，你所有的企业数据都会在那里的。短期来看，你说的没错，你需要通过在应用中提到来调用存储库，因为AI需要一些指引来知道去哪里查找，但未来它会自己弄清楚的。
So it's just going to become more and more seamless, but it'll insert itself. So we have a discussion about sales and then you might have a sales bot that says, Hey, by the way, nobody's called this client in three months. Well, that's where I want to go with it is I call that promptly, which is I want the AI just to chime in when it determines that it has relevant information and can help the team even if it hasn't been summoned yet. But we need some model improvement for that, frankly, I mean, we'll be able to get there by GPT five, but that's totally where this headed.
所以，这个过程将变得越来越无缝，但是它会介入进来。比如，我们在讨论销售时，可能会有一个销售机器人提示说：“顺便提一下，已经三个月没有人联系这个客户了。” 这正是我想要的——我称之为“及时提醒”，即我希望AI在判断出有相关信息并能帮助团队时，即使没有被召唤，也能主动参与进来。但是，坦率地说，我们需要一些模型改进才能实现这一点。到GPT-5的时候，我们应该能够做到，但这确实是发展的方向。
I'll show you just one more fun example. If I could, let me just show you this. So I asked it to write a letter to Lena Khan to be a guest at the All in Summit. And I told it mention positive things we've said about Lena Khan in episodes of the All in Pod. And so it wrote this letter, dear chair Khan, we hope this message finds you well on behalf of the host, the All in Pod. We're excited to see the invitation for you to speak at the upcoming All in Summit. And then it says in our conversations, we have frequently highlighted your impressive credentials and the impactful work you've undertaken. For example, in episode 36, we acknowledge your trailblazing role. And so the letter was able to quote episodes of the All in Pod. Just without anyone having to go do that research and figure out like, what would be the best? Cause I told it, only say positive things. Don't say anything negative. Right.
让我给你再展示一个有趣的例子。如果可以的话，让我向你展示这个。我让它写一封信给莱娜·汗，邀请她作为嘉宾参加All in Summit。我告诉它，在信中提到我们在All in Pod节目中对莱娜·汗的正面评价。于是它写了这封信：“亲爱的汗主席，希望您一切安好。谨代表All in Pod的主持人们，邀请您在即将到来的All in Summit上演讲。”信中还提到：“在我们的对话中，我们经常强调您的出色资历和您所做的有影响力的工作。例如，在第36集节目中，我们认可了您开创性的角色。”这封信甚至引用了All in Pod的具体集数，而无需任何人去做研究、找出最合适的内容。因为我告诉它，只说正面的，不说负面的。对吧。
And then it said warm regards and it said who the four besties were. Again, we never told it who the besties are. We just said, write us a letter. So it's pretty incredible. Now, this is just an example with the All in Pod. Or think about any work context where the AI has access to your previous work documents. It's pretty amazing what it can do. Well, I mean, it is kind of in the name. Like this is glue, put you together and slack is where you slack. Makes all sense. The brands give you a little bit of a tip. We should have seen it coming with slack. Totally. We have a breaking news story. It's a free news. It's a long way to lose it. I got breaking news coming in. Friedberg, your life's work sachs did his product review. Now it's your turn, Friedberg. We got breaking news coming in.
然后它在信尾写了“致以温暖的问候”，并写出了四个最好的朋友是谁。我们从未告诉它谁是最好的朋友，仅仅是让它写一封信。所以这真的很不可思议。这只是一个关于All in Pod的例子。再想想任何工作场景，如果AI能够访问你之前的工作文档，它能做的事情真的很惊人。我的意思是，这也符合它的名字。这像粘合剂一样把你们连接在一起，而Slack是你工作的地方。这些品牌名给了你一点提示。我们应该早就能从Slack的名字上看出来。完全正确。我们有一个突发新闻。这是一个免费新闻，我们还有很长的路要走。我刚收到突发新闻消息。Friedberg，这是你一生的心血，Sachs完成了他的产品评审。现在轮到你了，Friedberg。我们刚收到突发新闻。
I did promise you that when Ohalo decides to come out of stealth and explains what we've done and what we're doing. I would do it here on the All in Pod first before the all in exclusive. So basically by the time this pod airs, we're going to be announcing. What Ohalo has been developing for the past five years and has had an incredible breakthrough in, which is basically a new technology in agriculture. And we call it boosted breeding. I'm going to take a couple of minutes just to talk through what we discovered or invented at Ohalo and why it's important and the kind of significant implications for it. But basically five years ago, we had this theory that we could change how plants reproduce.
我确实承诺过，当Ohalo决定公开我们所做的工作和正在做的事情时，我会首先在“All in Pod”上公布，而不是先在其他地方独家披露。所以基本上，当这期节目播出时，我们将会宣布Ohalo在过去五年中开发并取得重大突破的成果，这是一项关于农业的新技术，我们称之为“增强育种”。我将花几分钟时间来谈谈我们在Ohalo发现或发明的东西，为什么它很重要，以及它带来的重大影响。基本上，五年前，我们有一个理论，认为我们可以改变植物的繁殖方式。
And in doing so, we would be able to allow plants to pass a hundred percent of their genes to their offspring rather than just half their genes to their offspring. And if we could do that, then all the genes from the mother and all the genes from the father would combine in the offspring rather than just half the genes from the mother and half the genes from the father. And this would radically transform crop yield and improve the health and the size of the plants, which could have a huge impact on agriculture because yield, the size of the plants ultimately drives productivity per acre, revenue for farmers, cost of food, calorie production, sustainability, et cetera.
通过这样做，我们可以使植物将其百分之百的基因传递给后代，而不仅仅是传递一半的基因。如果我们能做到这一点，那么父亲和母亲的所有基因将会在后代中结合，而不仅仅是各自的一半。这将会极大地改变作物的产量，提升植物的健康和规模，对农业产生巨大影响，因为作物的产量和植物的规模最终决定了每英亩的生产力、农民的收入、食品的成本、热量的生产以及可持续性等等。
So this image just shows generally how reproduction works. You've got two parents. You get a random selection of half of the DNA from the mother and a random selection of half the DNA from the father. So you never know which half you're going to get from the mother or which half you're going to get from the father. That's why when people have kids, every kid looks different. And then those two halves come together and they form the offspring. So every time a new child is born, every time a plant has offspring, you end up with different genetics.
这张图片大概展示了繁殖是如何进行的。你有两个父母亲。从母亲那里随机获得一半的DNA，从父亲那里也随机获得一半的DNA。所以你永远不知道会从母亲那里得到哪一半，也不知道会从父亲那里得到哪一半。这就是为什么当人们有孩子时，每个孩子看起来都不一样。然后这两半结合在一起，形成后代。所以每次有新孩子出生，或每次植物有后代时，都会有不同的基因组合。
And this is the problem with plant breeding. Let's say that you have a bunch of genes in one plant that are disease resistant, a bunch of genes in the other plant that are drought resistant. And you want to try and get them together. Today, the way we do that in agriculture is we spend decades trying to do plant breeding, where we try and run all these different crosses, find the ones that have the good genes, find the other ones that have the good genes and try and keep combining them. And it can take forever and it may never happen that you can get all the good genes together in one plant to make it both disease resistant and drought resistant.
这就是植物育种的问题所在。假设你有一株植物带有抗病基因，而另一株植物带有抗旱基因。你想把这些基因结合在一起。现如今，我们在农业中通常用的方法是耗费数十年进行植物育种，尝试进行各种不同的杂交，找到具有优良基因的后代，再不断进行组合。然而，这个过程可能非常漫长，而且可能永远无法在一株植物中同时获得所有的优良基因，使其既抗病又抗旱。
So what we did is we came up with the theory that we could actually change the genetics of the parent plants. We would apply some proteins to the plants and those proteins would switch off the reproductive circuits that caused the plants to split its genes. And as a result, the parent plants give a hundred percent of their DNA to their offspring. So the offspring have doubled the DNA of either parent. You get all the genes from the mother, all the genes from the father. And finally, after years of toiling away at trying to get this thing to work and all these experiments and all these approaches, we finally got it to work.
所以，我们提出了一个理论，即我们实际上可以改变亲本植物的基因。我们会向植物施加一些蛋白质，这些蛋白质会关闭导致植物基因分裂的生殖回路。结果，亲本植物将其100%的DNA传给了后代。所以后代拥有了双倍于任一亲本的DNA。也就是说，后代同时继承了母本和父本的全部基因。最终，在经过多年的艰苦努力和无数实验及尝试后，我们终于成功了。
And we started collecting data on it and the data is ridiculous. Like the yield on some of these plants goes up by 50 to 100 percent or more. Just to give you a sense, like in the corn seed industry, breeders that are breeding corn are spending $3 billion a year on breeding and they're getting maybe one and a half percent yield gain per year. With our system, we are seeing 50 to 100 percent jump in the size of these plants. It's pretty incredible. Here's an example. This is a little weed that we that you do experiments with in agriculture called a rabbit doppes. So it's really easy to work with. And you can see that what we have at the top are those two parents, A and B. And then we applied our boosted technology to them and combined them.
我们开始收集数据，结果真是惊人。一些植物的产量提升了50%到100%甚至更多。举个例子，在玉米种子行业，育种专家每年花费30亿美元进行育种，每年的产量增幅可能只有1.5%。但使用我们的系统后，我们发现这些植物的大小提升了50%到100%。这真的非常不可思议。举个例子，有一种在农业实验中常用的小杂草叫做拟南芥，它非常容易处理。你可以看到，在图的顶部是两个亲本，A和B。我们使用了增强技术并将它们结合起来。
And we ended up with that offspring called boosted AD. So you can see that plant on the right is much bigger. It's got bigger leaves. It's healthier looking, et cetera. If you were to ask your question, does that mean that the boosted one has twice number of chromosomes as A and B? Exactly. Right. So is that like a new species then? Yeah. So it's called. How does it survive with twice number of chromosomes? Yeah, it's called polyploidy. So we actually see this happen from time to time in nature. For example, humans have two sets of chromosomes, right? So does corn. So to many other species. Somewhere along the evolutionary history, wheat. Doubled and then doubled again. And you end up actually in wheat having six sets of chromosomes.
于是我们得到了一个被称为"增强版AD"的后代。你可以看到右边那株植物要大得多，它的叶子更大，看上去也更健康等等。如果你问这个增强版的植物是否拥有A和B两倍数量的染色体？对，没错。那么，这算是一个新物种吗？是的，它就叫做。那么它是如何在拥有两倍数量的染色体的情况下生存的呢？这被称为"多倍体"现象。事实上，我们在自然界中偶尔能看到这种情况发生。比如，人类有两组染色体，玉米也是如此，还有许多其他物种。在某个进化历史阶段，小麦的染色体数量翻了一倍又一倍，最终小麦拥有了六组染色体。
Wheat is what's called a hexapploid. Potatoes are a tetraploid. They have four sets of chromosomes and strawberries are an octoply. They have eight and some plants have as many as 24 sets of chromosomes. So certain plant species have this really weird thing that might happen from time to time and evolution where they doubled their, their DNA naturally. And so what we've effectively done is just kind of. Applied a protein to make it happen and bring the correct two plants together when we make it happen. And so this is going to only happen for a plant, right? This can never happen with an animal. It wouldn't it wouldn't work in animals. It works in plants. OK. And one way you can think about plant genetics is all the genes are sort of like tools in a toolbox.
小麦是一种六倍体，马铃薯是四倍体，它们有四套染色体，而草莓是八倍体，有八套染色体。有些植物甚至拥有多达24套染色体。因此，某些植物物种在进化过程中偶尔会自然地使它们的DNA倍增。这是很奇特的现象。而我们所做的只是应用一种蛋白质来促使这一过程发生，并在此过程中将两种正确的植物结合起来。这个过程只能在植物中发生，不会在动物中实现，因为这在动物中是不可行的。植物遗传学可以理解为所有的基因就像工具箱中的各种工具。
The more tools you give the plant, the more it is. It has available to it to survive in any given second to deal with drought or hot weather or cold weather, etc. And so every given second, the more tools or the more genes the plant has that are beneficial, the more likely it is to keep growing and keep growing. And that plays out over the lifetime of the plant with bigger, bigger leaves and bigger, you know, gross, taller. But more importantly, if you look at the bottom, the seeds get bigger. And in most crops, what we're harvesting is the seed. That's true. And, you know, corn and many other crops. And so seeing over a 40% increase in seed in this little weed was a really big deal. But then we did it in potato and potato is a crazy result.
你给植物提供越多的工具，它就越能够在任何时刻生存下来，应对干旱、炎热或寒冷的天气等挑战。因此，每一刻，植物拥有的有益基因或工具越多，它就越有可能持续生长，不断壮大。这种趋势在整个植物的生命周期中表现为叶子越来越大、植株越来越高。而更重要的是，如果你观察植物的底部，种子也会变得更大。在大多数农作物中，我们收获的主要是种子。对于玉米和许多其他农作物来说，这都是事实。因此，看到这种小杂草的种子增加了40%以上真的很惊人。而当我们在马铃薯上进行试验时，结果更是令人难以置信。
Potato is the third largest source of calories on earth. And so we took two potatoes that you see here in the middle, A, B and C, D. We applied our boosted technology to it, to each of them and put them together. And you end up with this potato, A, B, C, D. That's the boosted potato. And as you can see, these were all planted on the same date. And the boosted potatoes, much bigger than all the other potatoes here, including a market variety that we show on the far right. That's what's typically grown in the field. Now, here's what's most important. When you look under the ground and you harvest the potatoes, you can see that that A, B potato only had 33 grams, CD had nine grams. So each parent had 33 and nine grams potato.
土豆是地球上第三大卡路里来源。所以，我们选择了两颗土豆，你可以在中间看到A, B和C, D。我们对它们分别应用了增强技术，并将它们组合在一起。结果得到了这个土豆，A, B, C, D。这就是增强版土豆。如你所见，这些土豆都是在同一天种植的，而增强版土豆比这里所有其他土豆都大，包括我们在最右边展示的市场常见品种，也就是通常在田里种植的那种。
现在，最重要的是，当你查看地面下的情况并收获土豆时，你会发现A, B土豆的重量只有33克，而C, D土豆的重量只有9克。也就是说，每个“父母”土豆的重量分别是33克和9克。
But the boosted offspring had 682 grams of potato. The yield gain was insane. And so you could see this being obviously hugely beneficial for humanity. You know, potatoes being the third largest source of calories. Indian potato farmers are growing one acre of potato. In India, they eat potato two meals a day. In Africa, potato is a food staple. So around the world, we've had a really tough time breeding potatoes and improving the yield. With our system, we've seen incredible yield gains in potato almost overnight. And the potatoes, those are normal size potatoes that you see there. Those are like, you know, table potatoes. Basically, that looks like a russet potato right there. That's like a normal size.
但是，改良后的后代产量达到了682克土豆。这个增产幅度简直疯狂。因此，你可以看到这对人类的巨大潜在益处。要知道，土豆是第三大热量来源。在印度，土豆农民种植一英亩的土豆。在印度，人们每天吃两顿土豆。在非洲，土豆是主食。因此，在世界各地，我们在培育土豆和提高产量方面一直面临巨大挑战。使用我们的系统，我们几乎一夜之间就在土豆上看到了惊人的产量提升。这些土豆是你们看到的普通大小的土豆，就像餐桌上常见的那种，基本上看起来就像个普通大小的褐皮土豆。
But it started as like a little, it started as like a little creamer potato. Basically, and you blew it up into a russet potato. Yeah. So the genetics on A, B, you can see they're like little purple, tiny, little purple potatoes, the genetics on CD or like these little white, you know, tiny, little ball potatoes. But when you put those two together with Boosted and you combine all the DNA from A, B and all the DNA from CD, you get this crazy high yielding potato, A, B, C, D, which by the way is higher yielding than the market variety that's usually grown in the field on the far right.
但它一开始就像是一个小奶油土豆。基本上，你把它变成了一个大的褐皮土豆。对，A和B的基因，你可以看到它们是像小的紫色土豆，CD的基因则像这些小的白色球形土豆。但是当你把这两者结合在一起，并且结合A、B和C、D的所有DNA，你会得到一种高产量的土豆，A、B、C、D。顺便提一下，它的产量比通常在最右边田地里生长的市场品种还要高。
So why not just grow russet potatoes then? We are. And so we're working on doing this with Russet. We're working on doing this with every major potato line. Sorry. Um, the, the improvement you'll see is actually in yield. So it's not the size of the potato. It's the number of potatoes that are being made. Um, and so you'll see. You're a hacker or something like that. Like the work. Exactly. You know, projects in the 60s or 70s. Shmoist. Yeah. You can tell freebergs onto something here. You got David's sex to pay attention during it. Yeah. Yeah. This is the, it's gonna be a deck of cord and sacks is awake. So actually like, how do I wet my big glasses? Is that you interrogating the potato lines? I've never had. What's going on? I think it's an accident.
那为什么不直接种植棕皮土豆呢？其实我们正在这么做。而且我们正在尝试将这种方法应用到所有主要的土豆品种上。抱歉，会有一个改进就是产量的提升。因此，提升的不是单个土豆的大小，而是产出的土豆数量。所以，你会看到类似于黑客的工作，就像60年代或70年代的项目一样。嗯，你能看出来Freeberg确实在研究一些东西。这期间甚至让David保持了关注。对，这将会成为一个突破性的项目。而Sacks也保持了清醒。那么，实际上，我该如何增加我的大眼镜？是这样的，你是在审问土豆品种吗？我从来没有经历过这样的情况。这有些奇怪。
But so have you tried these potatoes? They taste different. Oh, no, they're awesome. Yeah. They're, they're potatoes. And we do a lot of analysis. You want to spread it any horn, Seattle or anything like that? No, no. You got it. I mean, again, one of the other advantages of the system that we've developed. Let me go back here. And I just want to take two seconds on this. One of the other things this unlocks is creating actual seed that you can put in the ground in crops that you can't do that in today. So potatoes, the third largest source of calories. But the way we grow potatoes, you guys remember the movie, the Martian, you chop up potatoes and you put them back in the ground.
但是你试过这些土豆吗？它们味道不一样。哦，不，它们太棒了。是的，它们是土豆。我们做了很多分析。你想把这个推广到西雅图或者其他地方吗？不，不用。你明白我的意思。再说一次，这是我们开发的系统的优势之一。让我回顾一下，我只想花两秒钟在这上面。这个系统的另一个好处是，它可以创造实际的种子，你可以种在地里，而目前有些作物是无法做到这一点的。比如说，土豆——卡路里的第三大来源。但是我们现在种植土豆的方式，你们记得电影《火星救援》里那样吗？把土豆切成块，再种回地里。
Because the seed that comes out of a potato, which grows on the top and the flower, every one of those seed is genetically different because of what I just showed on this chart, right? You get half the DNA from the mother, half the DNA from the other. So every seed has different genetics. So there's no potato seed industry today. And potato is like a hundred billion dollar market. With our system, not only can we make potatoes higher yielding and make them disease resistant, what we also make is perfect seed. So farmers can now plant seed in the ground, which saves them about 20% of the revenue, takes out all the disease risk and makes things much more affordable and easier to manage for farmers.
因为生长在土豆顶部和花上的种子，每一颗种子的基因都是不同的，这就像我刚才在图表中展示的那样，对吧？你从母本那里得到一半的DNA，从另一半得到另一半的DNA。所以每颗种子的基因都是不同的。因此，今天还没有土豆种子产业。而土豆是一个千亿美元的市场。通过我们的系统，不仅可以使土豆产量更高，并具有抗病性，还能生产出完美的种子。这样农民可以直接种植这些种子，这可以为他们节省约20%的收入，消除所有的病害风险，使事情更加实惠和易于管理。
So it creates entirely new seed industries. So we're going to be applying this boosted technology that we've discovered across nearly every major crop worldwide. It'll both increase yield, but it will also have a massive impact on the ability to actually deliver seed and help farmers and make food prices lower and improve sustainability. No, it's actually cheaper. So high yield lower costs. Do you need more water? Less water, less land, less energy. Do you need more fertilizer? Fertilizer usually scales with biomass, but these sorts of systems should be more efficient.
这将会催生全新的种业。我们将把这个改进后的技术应用于全球几乎所有主要作物。这样不仅能提高产量，也会大大改善种子的供应，帮助农民，降低食品价格，并提升可持续性。其实，这种技术更便宜。高产量、低成本。需要更多的水吗？不，反而需要更少的水、更少的土地和更少的能源。需要更多的肥料吗？通常情况下，肥料的使用与生物质成正比，但这些系统应该会更高效。
So fertilizer use per pound produced should go down significantly as we get to commercial trials with all these stuff. And we're doing this across many crops. So there's a lot of work to do in terms of like, how do you scale and tell us a production in the field. Tell us about the patents and how important patents play a role in this, because isn't it like like one of Monsanto's big things, like they just go and sue everybody into the ground or whatever? Like, I'm going to answer you one second. I'm just going to switch my head to it. Just died. Wow.
所以，当我们在所有这些方面进入商业试验阶段时，每磅生产中的化肥用量应该会大幅减少。我们在许多作物上都在进行这种尝试，所以在如何扩大规模和实现田间生产方面，还有很多工作要做。请告诉我们专利的情况，以及专利在这其中的重要性。是不是像孟山都那样，会用专利来起诉很多人？等一下，我马上回答你，我的耳机刚刚没电了。哇。
We went from sacks as bots to freebergs crops. I'm glad we're doing him second because all of a sudden, like group chat doesn't seem very important. Yeah. Wow. He just, he just saw the whole Ukraine crisis here. I would be able to grow wheat in the desert and in the race, solve the world food problem. Yeah, Saks. What did you do for the last six months? Yeah, we made enterprise chat a little better, but we added AI to enterprise chat. We cleaned up your slack. So yeah, when you invest, we've invested a ton of money. This was stealth for five years. We put a ton of money into this business. So when you invest, like, um, I mean, north of 50 north, north of 50, yeah, 50 million five years and you don't have a product in market yet. Wow. That's a we actually have some product. Yeah.
我们从Saks的聊天机器人变成了Freeberg的农作物。我很高兴我们第二个讨论他，因为突然间，群聊似乎变得不那么重要了。哇，他刚刚看到了整个乌克兰危机。我能够在沙漠里种植小麦，并在竞赛中解决全球粮食问题。是的，Saks，你过去六个月做了什么？嗯，我们让企业聊天好了一些，但我们在企业聊天中加入了AI，我们清理了你的Slack。所以，是的，我们投资了大量资金。这五年是秘密进行的。我们投入了大量资金到这个业务中。所以当你投资时，比如说，超过5000万，是的，五年5000万，而你还没有一款上市的产品。哇，其实我们有一些产品。
So I haven't talked about the way we've been making money in some of the business. We've been doing. Okay. Let me just make sure this is like clear. So that last photo you showed with the different types of potatoes, you had created the super huge ones, but you're saying that the, the yield benefit here is just you create a much bigger, hardier plant that's capable of producing many more potatoes, but the size of potatoes doesn't change. You can control for that when you breed. So the selection of what plants you put together in the boosted system allows you to decide, do you want small, medium, large, that's all part of the, the design of which plants do you want to combine? Okay.
我还没有谈到我们在一些业务中的赚钱方法。我们做得还不错。好的，让我确保这点清楚明白。你上次展示的那张照片里展示了不同类型的土豆，你培育出了超级大的土豆，但你是说，这里的产量提升其实是你培育了一个更大、更强壮的植株，能够生产更多的土豆，但土豆的大小并没有改变。你可以在培育时进行控制。因此，在增强系统中选择要组合的植物，可以决定你想要小、中、大哪种大小，这就是你想要组合哪些植物的设计的一部分。好的。
Cause your goal is not to turn like a russet potato into like a watermelon or something like that. No, no, the goal is to make more russet potato per acre so that we use less water. We use less land farmers can make more money. People pay less for food. That's the goal. And so it's all about yield. It's not about changing the characteristics. There are some crops where you want to change the characteristics. Like you might want to make bigger corn kernels and bigger cobs on the corn, which is another thing that we've done. And that's actually been published in our patent. And the reason, by the way, I'm talking about all this is some of our patents started to get published last week. And so when that came out, the word started to get out. And that's why we decided to get public with what we've done because it's now coming out in the open.
因为你的目标不是把一个红褐色的土豆变成西瓜之类的东西，不是的。目标是每英亩种出更多红褐色土豆，这样我们就能用更少的水和土地。农民可以赚更多的钱，人们可以花更少的钱买到食品。这就是目标。所以关键在于产量，而不是改变作物的特性。当然，有些作物是需要改变特性的，比如我们可能想让玉米的颗粒更大，玉米棒更大，这些也是我们已经实现的，并已在我们的专利中公开。顺便说一下，我提到这些是因为我们的一些专利上周开始公开了。随着专利的公布，消息也开始传播开来，这就是为什么我们决定公开我们所做的事情，因为现在一切都在明面上了。
You mentioned something briefly there about where different crops can be planted. You know, we had these big talks about wheat and corn. They're only available in very specific parts. You know, north of the equator, the champion jungles, camping, obviously polar or desert extremes. So if you're successful, what would this do for on a global basis, where these crops are made? Because there are a whole discussion about you. Also, totally. Wheat belly of Europe, the cradle of wheat. It's a great question. I'm so glad you asked it because that's one of the key drivers for the business is that we can now make crops adapted to all sorts of new environments that you otherwise can't grow food.
你刚才简单提到了一下关于不同作物的种植区域。你知道，我们之前有过关于小麦和玉米的大讨论。这些作物只能种植在非常特定的地区。比如，北纬的某些地区，热带丛林，露营场所，显然还有极地或沙漠极端环境。所以如果你成功的话，这将对全球范围内的作物生产带来什么影响？因为围绕这个话题，有很多讨论。还有，完全对，欧洲的小麦腹地，小麦的发源地。这是一个很好的问题，我很高兴你问到了，因为这是我们业务的关键驱动力之一，现在我们能够让作物适应各种新的环境，在那些原本无法种植粮食的地方也能种植。
Today, there's close to somewhere between 800 million and a billion people that are malnourished. That means they are living on less than 1200 calories a day for more than a year. But on average, we're producing 3500 calories per person worldwide in our ag systems. The problem is we just can't grow crops where we need them. And so by being able to do this sort of system where we can take crops that are very drought resistant or can grow in sandy soil or very hot weather and adapt cooler climate crops to those regions, but through the system, we can actually move significantly where things are grown and improve food access in regions of how free.
今天，全球有接近8亿到10亿人营养不良。这意味着他们每天摄入的热量不足1200卡路里，且这种情况已持续一年以上。但平均而言，我们的农业系统每人每天生产的食物可以提供3500卡路里的热量。问题在于我们无法在需要的地方种植作物。因此，通过这种系统，我们可以种植具有抗旱能力强、能在沙土或高温环境下生长的作物，或者将适应较凉爽气候的作物引入这些区域。通过这个系统，我们可以极大地调整作物的种植地点，提高食物在贫困地区的可获得性。
But when you look at a potato, how do you figure out what part of their DNA is the drought resistant part? Yeah. And then how do you make sure that that's turned on? So even if you inherit that chromosome, is there some potential interaction with the generally if we can. So these are what are called markers, genetic markers. And so there are known markers associated with known phenotypes. A phenotype is a physical trait of a plant. And so we know lots of markers for every crop that we grow, markers for disease resistance, drought resistance, markers for big plants, short plants, etc.
但是，当你观察一个土豆时，如何确定它的DNA中哪个部分是抗旱基因呢？是的，那你又如何确保这个基因被激活呢？即使你继承了那个染色体，是不是还会有一些潜在的相互作用呢？ 一般来说，如果可以的话，这些被称为标记，基因标记。因此，有已知的标记与已知的表型（即植物的物理特征）相关联。我们已经为我们种植的每种作物找到了很多标记，比如抗病标记、抗旱标记、大型植物标记、矮小植物标记等等。
And so what we do is we look at the genetics of different plants that we might want to combine into the boosted system and we say, these ones have these markers, these ones have these markers. Let's put them together. And then that that'll drive the results. One of the other interesting things we're seeing, which I didn't get too much into in the slides, it's not just about combining traits, but it turns out when you add more genes together, biology figures out a way to create gene networks. These are all these genes that interact with each other in ways that are not super well understood, but it makes the organism healthier and bigger and live longer.
所以，我们的做法是研究我们想要组合成增强系统的不同植物的基因，我们会说，这些植物有这些标记，那些植物有那些标记。然后我们把它们放在一起，这样就会驱动结果。我们还发现了另一个有趣的现象，这在幻灯片里没有详细介绍，不仅仅是组合不同的性状，实际上，当你把更多的基因组合在一起的时候，生物会找到一种方法来创建基因网络。这些基因相互作用的方式尚不完全清楚，但它使得生物体更健康、更大并且寿命更长。
This is like when you bring like why mutts are healthier and live longer than purebred dogs because they have more genetic diversity. So there's a lot of work now in what's called quantitative genomics, where you actually look at the statistics across all the genes, you use a model and the model predicts which two crosses you want to make out of hundreds of thousands or millions of potential crosses that the AI predicts. Here's the two best ones to cross because you'll get this growth or this healthiness.
这有点像为什么混种狗比纯种狗更健康、寿命更长，因为它们有更多的基因多样性。因此，现在有很多人在研究所谓的数量基因组学。在这个领域，你会通过模型分析所有基因的统计数据，然后模型会预测出，在成千上万甚至数百万种可能的交配组合中，哪两种是最好的，因为这样可以获得更好的生长或健康状况。
So how do you want to make money, Freeburg, are you going to sell the seeds? Are you going to become the direct farmer? Are you going to become food as a service? Like how do you make the most money from this? We're not going to farm. Farmers are our customers. And so there are different ways to partner with people in the industry who already have seed businesses or already have genetics and help them improve the quality of their business. And then there's other industries like in potato where we're building our own business of making potato seed, for example. So every crop and every region is actually quite different. So it becomes a pretty complicated business to scale. We're in the earlier days. We're already revenue generating.
那么，Freeburg，你打算怎么赚钱？你会卖种子吗？你会直接成为农民吗？还是会把食物作为一种服务来做？你打算通过哪种方式赚最多的钱？我们不会去种地。农民是我们的客户。所以，有不同的方法可以与那些已经有种子业务或基因研究业务的人在行业内合作，帮助他们提高业务质量。除此之外，还有其他行业，比如我们在马铃薯领域正在建立自己的马铃薯种子业务。所以每种作物和每个地区的情况其实都很不同，这使得业务扩展变得相当复杂。我们现在还处于早期阶段，但是已经在产生收入。
I would like a sweeter blueberry. No comment, no comment. Yeah. I get tilted by the quality of the Driscoll's blueberries. Let me tell you something about the Driscoll's blueberries. Also the Driscoll, I've had only one batch of a Driscoll's strawberry that was just off the charts and every 19,847 other batches I bought have been total. Yeah. Now you want the European small ones or the Japanese ones from Hokkaido? Because they're rich and sweet and they're not these like monstrosity of giant flavorless strawberries. What's that about? A seedless? Could you do a seedless mango? Yes, no, cut it. She just cut it. Oh my God. How great would that be? Smooted out work for a bite on a mango is like the worst ratio. Yeah.
我想要更甜的蓝莓。没有更多评论了。是的。我对Driscoll's蓝莓的质量很不满意。让我告诉你一些关于Driscoll's蓝莓的事情。另外，我只遇到过一批Driscoll's草莓是特别好的，其他我买的19,847批都是完全不行的。对了，你想要欧洲的小蓝莓还是日本北海道的蓝莓？因为它们又甜又美味，而不像那些巨大但无味的草莓。无籽的？你能做无籽芒果吗？是的，不，切了。她直接切了。哦天哪，这太棒了。吃芒果时总是觉得那比例最差。是的。
Well, somehow we made it about us. Yeah. No, no, look, I think that's it. It is all about you guys. Now tell us about the blueberries. Sorry. Well, not every year Driscoll's puts out a special labeled package called sweetest batch and they just had the sweetest batch of strawberry and blueberries. I don't know if they're still in the stores, but they only last for like a week or two. And that's the best genetics only grown on a small number of acres. What? Really? I'm going to go in as soon as this is the see if they have it. So I got it a few weeks ago. It's quite delicious.
好吧，我们不知怎么回事把话题转到了我们自己身上。嗯，对，不，不，听着，我认为就是这样。这完全是关于你们的。现在告诉我们关于蓝莓的事情。抱歉。每年Driscoll's（德瑞斯科尔公司）都会推出一个特别标签包装，叫做“最甜批次”（sweetest batch），他们刚刚推出了最甜批次的草莓和蓝莓。我不知道它们是否还在店里，但这种包装只会持续一两个星期。这些是最好的品种，只种在少量的土地上。什么？真的吗？一会儿我就去看看他们有没有。我几周前买到了，很美味。
Anyway, we know let's just say we know the Berry market very well. Mike co-founder, CTO, Judd Ward, who's who's brilliant idea of boosted breeding was many years ago, who I met because they had a New Yorker article on Judd. I cold called him and said, Hey, will you come in and give us a tech talk? We started talking and Judd came up with this idea for boosted breeding. And so we started the business with Judd and Judd ran molecular breeding at Driscoll. So we have a lot of Driscoll's people that work at O'Hollow. We know that the market really well.
总之，我们非常了解浆果市场。Mike 是我们的联合创始人兼首席技术官，Judd Ward 是多年前提出“增强育种”这一绝妙创意的人。我是通过看到《纽约客》上关于 Judd 的文章才认识他的。我给他打了一个冷call，请他来给我们做了一次技术分享。我们开始交流，Judd 提出了“增强育种”的这个想法。于是，我们和 Judd 一起创办了这家公司。Judd 之前在 Driscoll 负责分子育种，所以我们有很多曾在 Driscoll 工作过的人加入了 O'Hollow。我们非常了解这个市场。
Can you go back to the patent stuff like are you? Oh, yeah. Sorry. That was the question. Some seed person. So we spent we spent 50 million bucks on, you know, plus on this business today. So we have filed for IP protections that people can't just rip us off. But I would say I think that the real advantage for the business arises from what we call trade secrets, which is not just about taking patents and going out and suing people. That's not a great business. The business is how do you build a moat and then how do you extend that moat? The great thing about plant breeding and genetics is that once you make an amazing variety, the next year, the variety gets better. And the next year, the variety gets better. And so it's hard for anyone to catch up. That's why seed companies generally get monopolies in the markets. Cause farmers will keep buying that seed every year, provided it delivers the best genetics. And so our business model is really predicated on how do we build advantages and moats and then keep extending them rather than try to leverage IP. So I'm a big fan of like building business model advantages.
你能继续讲专利的部分吗？哦，对不起，刚刚的问题是一些关于种子的事情。我们已经在这个业务上花了超过5000万美元。所以我们申请了知识产权保护，这样别人就不能随便抄袭我们。但我想说的是，我认为这个业务的真正优势在于我们所谓的商业秘密，而不仅仅是申请专利然后去起诉别人。那不是一个好的商业模式。真正的业务模式是如何建立一个竞争壁垒，然后如何扩大这个壁垒。植物育种和遗传学的一个伟大之处在于，一旦你培育出一种出色的品种，第二年这个品种会变得更好，第三年品种又会变得更好。因此，别人很难追赶上来。这就是为什么种子公司通常能在市场上形成垄断，因为只要能提供最好的基因，农民们每年都会继续购买这种种子。我们的商业模式真正的基础在于如何建立优势和壁垒，并不断扩大它们，而不是尝试依靠知识产权。因此，我非常推崇建立商业模式的优势。
This is going to be a credible sax. If you'd think about, you know, geopolitically, what's going on in Somalia, Sudan, Yemen, Afghanistan, those places have tens of millions of people. I think hundreds of millions collectively who are at risk for starvation. If you could actually make crops that could be farm there, Friedberg, you would change humanity. And then all these people buying a farmland in America that could devalue that farmland. If that wasn't as limited of a resource, you have Friedberg, like, no, I think, um, so first of all, like farmland in America is mostly family owned. That's 60% rented actually. So a lot of families own it and then they rent it out because they stop farming it. But the great thing that we've seen in agriculture historically is that the more calories we produce, the more food we produce, the more there seems to be a market. It's like any other economic system, wheat and rice.
这将会是一个值得信赖的萨克斯。如果你从地缘政治的角度考虑，比如索马里、苏丹、也门、阿富汗，那些地方有数千万人。有的可能是上亿人，他们面临饥饿的风险。如果你真能在那里种植作物，弗里德博格，你将会改变人类的命运。而在美国购买农田的这些人，那些农田的价值可能会因此贬值。如果农田资源不再那么有限的话。弗里德博格回答说，不，我觉得，首先美国的大部分农田是家庭拥有的。实际上，60%的农田是租出去的，所以很多家庭拥有农田但不再自己耕种。不过在农业历史上，我们看到的好的一面是，我们生产的卡路里越多，生产的食物越多，市场的需求也就越大。这就像任何其他经济系统一样，小麦和大米也是如此。
Yeah. So those are calorie sources one and two. And there's certainly opportunity for us to apply our boosted systems there. The big breakthrough with potato is we can make potato seed using our boosted system in addition to making better potatoes. McDonald's is the largest buyer of potatoes. Yeah. So in the US, 60% of the potatoes go to French fries and potato chips. McDonald's buys most of the fries. PepsiCo under Frito lay buys most of the potato chip potatoes. 40% or table potatoes. In India, 95% of the potatoes are table potatoes. They're eating at home and the Indian potato markets three to four times as big as the US potato market in Brazil. It's 90% table potato. So all around the world, potatoes, different the US is, you know, unusually large consumers of French fries and potatoes.
好的。这些是热量来源一和二。我们当然有机会在这些方面应用我们的强化系统。土豆的重大突破在于我们不仅能用我们的强化系统生产更好的土豆，还能生产土豆种子。麦当劳是最大的土豆买家。在美国，60%的土豆被用来做薯条和薯片。麦当劳买走了大部分的薯条，百事公司旗下的菲多利买走了大部分用来做薯片的土豆。剩下的40%是食用土豆。在印度，95%的土豆是食用土豆，主要在家里吃，印度的土豆市场是美国土豆市场的三到四倍。在巴西，有90%的土豆是食用土豆。全球各地对土豆的需求有所不同，美国对薯条和薯片的消费量尤其大。
I speak on behalf of Jay Kalan. I said, we will gladly invest a million out of 10 cap in both of your businesses. Absolutely. Yes. We will point our way into a cow. Jay Kalan. I will do the deal or wire the money. A little million to each of you guys at a 10 cap. Thank you. Absolutely. You're in. It may not be a 10 cap though, but yes. You're in. And Jay Kalan has secured the bag. It's a ranking news. I'm out to Jay Kalan have secured the bag from the besties actually doing work. Yeah. Well, I appreciate you guys letting me talk about it. Yeah. Congratulations. I'm excited. I'm excited to share it. You're in the both of you. I love it. It's been a, yeah, building stuff is hard. There's always risk. It's a lot of work and a lot of setbacks. But man, when you get stuff working, it's great. We're doing the things we do best. Freiberg is solving the world's hunger problem and I'm making, I'm cleaning up your slack. Yeah. I'm making your enterprise chat a little better. Or progress couch.
我代表Jay Kalan发言。我说过，我们很乐意在你们两家企业中，每家投资一百万，占总资本的10%。绝对没问题。我们会一步步走向成功，Jay Kalan。我会完成交易或汇款。每家给你们一百万，占总资本的10%。谢谢。完全没问题。你们加入进来了。虽然可能不是10%的份额，但你们确实加入了。Jay Kalan已经搞定了。这是一个重要消息，我特意出来宣布，因为Jay Kalan完全搞定了，都是因为最好的伙伴们一起努力。是的，我很感谢你们让我分享这个消息。祝贺你们。我很激动，很高兴分享这个成果。你们两家都加入进来了。我很爱这个项目。这一路走来不容易，建造东西总是充满风险，需要很多工作和承受很多挫折。但当你让事情顺利推进时，那感觉太棒了。我们在做我们最擅长的事。Freiberg在解决全球饥饿问题，而我在整理你的Slack，让你的企业聊天环境更好。或者说在优化你的工作流程。
All right. Stanley Druckenmiller has got a new boyfriend. Druckenmiller's got a boyfriend and his name is Javier. And they've a low to Argentina. Druckenmiller professed his love. Tom Cruise on Oprah's couch in a CNBC interview this week. The only free market quote leader in the world right now, bizarrely, is an Argentina of all places. He cut social security at 35% if he came to office. They've gone from a primary deficit of like four or 5% to a 3% surplus. They've taken a massive hit in GDP, basically a depression four quarter and his approval rating has not gone down. Druckenmiller has explained how he invested in Argentina after seeing Malay's speech at Davos, which we covered.
好的。斯坦利·德鲁肯米勒有了一个新伙伴。德鲁肯米勒有了一个伙伴，他的名字叫哈维尔。并且他们对阿根廷表示支持。德鲁肯米勒在本周的CNBC采访中表达了他的爱，就像汤姆·克鲁斯在奥普拉的沙发上那样。现在唯一的自由市场领导者，奇怪的是，居然是阿根廷。如果他上任，他会将社会保障削减35%。他们从大约4%或5%的财政赤字变成了3%的盈余。他们的国内生产总值（GDP）大幅下降，几乎是持续四个季度的经济萧条，但他的支持率并没有下降。德鲁肯米勒解释了他在看到迈莱在达沃斯演讲后，如何投资于阿根廷的经过，这我们之前也提到过。
Here's a 30 second clip. Play the clip. Nick, by the way, do you want to hear how I invest in Argentina? It's a funny story. I wasn't at Davos, but I saw the speech in Davos and it was about one o'clock in the afternoon in my office. I dialed up perplexity and I said, give me the five most liquid ADRs in Argentina. It gave me enough of a description that I follow the old Soros rule, invest and then investigate. I bought all of them. We did some work on them. I increased my positions. So far it's been great, but we'll see. Yeah, that's quite interesting. He, quick note, you hear Druckenmiller mention ADRs. For those of you who don't know it, I was one of them. They stand for American depository receipts, basically a global stock offered on a US exchange to simplify things for investors.
这是一个30秒的片段。播放这个片段。顺便问一下，尼克，你想听听我在阿根廷投资的趣事吗？话说我那时候没去达沃斯，但我看了在达沃斯的演讲，那时是办公室下午一点左右。我上了Perplexity网站，问它给我五个阿根廷流动性最强的ADR。它提供的信息对我来说已经足够了，我遵循索罗斯的老规矩，先投资再调查。我把它们都买了，然后做了一些研究，增加了持仓。到目前为止还不错，但还是得看看后续发展。真有意思。顺便提一句，你听到德拉肯米勒提到ADR。对于那些不知道的人，我曾经也是其中之一，ADR代表美国存托凭证，基本上就是在美国交易所上市的全球股票，简化投资者操作。
==========
Yeah, I mean, he didn't sign a prenup here. He just went all in and he bought the stock chamois and then he's going to figure it out later. Tell us your thoughts on this love affair, this bromance. There's a great clip of Malay. He goes on this talk show in Argentina and the talk show host. She's just so excited and greets him and then they start making out. Have you guys seen this? What? The full on French kissing each other. It's hilarious. Yeah, I mean, like Soros has been very famous for this invest and investigate thing. It's like a smart strategy for very, very liquid public market investors that have the curiosity that he does. I mean, I don't have much of a reaction to that.
是啊，我的意思是，他在这里没有签任何婚前协议。他就是全力以赴，直接买了股票，然后再慢慢搞清楚情况。讲讲你对这段“爱情故事”的看法，这种兄弟情谊。有一个很棒的视频，是Malay上阿根廷的一个脱口秀节目，主持人非常激动地欢迎他，然后他们就开始接吻了。你们看过这个吗？什么？他们就是在法式热吻，真的很搞笑。是的，我的意思是，索罗斯因其“投资后再调查”的策略非常有名。这种策略对那些对市场充满好奇的非常流动的公共市场投资者来说非常聪明。对此，我其实没有什么特别的反应。
I think that the thing with Argentina that's worth taking away is when you've spent decades investing about and misallocating capital and running your economy into the ground, the formula for fixing it is exactly the same. You cut entitlements and you reinvigorate the economy. And so the thing we need to take away is if we don't get our sh** together, that's probably what we're going to have to do. Saks, the influence of Malay on American politics. Will there be any? It seems like he has paralleled what Elon did at Twitter, Facebook, and Zuck did at Facebook. Do you think that this experiment he's doing down there of just cutting staff, cutting departments will ever make its way into American politics? Probably not. I mean, not until we're forced to.
我认为，阿根廷的经验值得借鉴。当你花了几十年的时间错误投资和分配资本，并将经济搞砸时，解决方法其实很简单：削减福利，重振经济。所以，我们需要明白的是，如果我们不尽快振作起来，可能也会陷入同样的境地。
至于马来西亚对美国政治的影响，会有吗？看起来他在做的事情和埃隆在推特以及扎克伯格在脸书的做法是类似的。你认为他在那里削减工作人员和部门的做法会传到美国政治中来吗？
可能不会，除非我们被逼到那个地步。
What Malay did, he comes in and they've got a huge budget deficit and they've got runaway inflation and they're debasing their currency and does practically overnight. He just slashes government spending to the point where he has a government surplus. And then as soon as he gets credibility with the markets, that allows them to reduce interest rates and inflation goes away and people start investing in the country. Magic. It's a path. It's obvious. Listen, I mean, you can't run deficits forever. You can't accumulate debt forever. It's just like a household. If you're spending exceeds your income, eventually you got to pay it back or you go broke. And the only reason we haven't gotten broke or experienced hyperinflation is because we're the world's reserve currency. So there's just a lot of room for debasement. And there's not already alternative yet.
马来西亚的做法是这样的：他上任时，国家面临着巨大的预算赤字和失控的通货膨胀，他们的货币正在贬值。几乎在一夜之间，他大幅削减政府开支，甚至达到了财政盈余的程度。一旦他获得市场的信任，就能降低利率，通货膨胀随之消失，人们开始在这个国家投资。简直如同魔法一般。这是一条明显的路径。听着，你不能永远运行赤字，你也不能永远积累债务。这就像一个家庭，如果你的支出超过收入，最终你要么偿还债务，要么破产。我们之所以没有破产或经历恶性通货膨胀，只是因为我们是世界储备货币。因此，我们有很多贬值的空间，而且还没有其他替代品出现。
I mean, everyone's trying to figure out what the alternative will be. So we've been able to accumulate more and more debt, but it's reaching a point where it's unsustainable. And what we've already seen is that the feds had to jack up interest rates from very low practically nothing to 5 and a half percent. And that has a real cost on people's well-being because now your cost of getting a mortgage goes way up. I mean, mortgage rates are over what? 7 and a half percent now? Yeah, 6%, 7%, depending on how much net worth and your credit rating. Right. And so it's much harder to get a mortgage now. It's harder to make a car payment if you need to borrow to buy a car. And if you have personal debt, the interest rates can be higher. The inflation rate actually doesn't take into account any of those things.
我的意思是，每个人都在试图搞清楚替代方案是什么。我们已经能够积累越来越多的债务，但现在已经到了无法持续的地步。我们已经看到联邦政府不得不将利率从接近零的水平提高到5.5%。这对人们的生活真的有很大影响，因为现在获取抵押贷款的成本大幅上升。我是说，现在抵押贷款利率是多少？7.5%吗？对，6%、7%，具体取决于你的净资产和信用评级。所以现在获得抵押贷款变得更难了。如果需要借钱买车，支付车款也更困难。如果你有个人债务，利率也会更高。通胀率实际上并没有考虑到这些因素。
Remember, Larry Summers did that study where he said that real inflation rate would be 18% or would have peaked at 18% if you include a cost of borrowing. That's why people don't feel as well off as the unemployment rate would normally suggest. So people are hit really hard when interest rates go up in terms of big purchases they need to make with debt. And then of course it's really bad for the investment environment because when interest rates are really high, that creates a higher hurdle rate and people don't want to invest in risk assets. Yeah. And so eventually the pace of innovation will go down. And Druckenmiller made this point. In his next set of comments, he said that Treasury is still acting like we're in a depression.
记住，拉里·萨默斯曾做过一项研究，他说如果把借贷成本考虑进去，真实的通货膨胀率会是18%或者会在18%达到顶峰。这就是为什么人们感觉没有失业率所显示的那么好。所以当利率上升时，人们在需要用债务进行的大额购买方面会受到很大打击。当然，这对投资环境也非常不利，因为当利率非常高时，就会形成更高的门槛率，人们不愿意投资于风险资产。因此，创新速度最终会下降。德鲁肯米勒在他的下一段评论中也提到了这一点，他说财政部仍然像我们在经济萧条中一样行事。
It's interesting because I've studied the depression and you had a private sector crippled with debt basically with no new ideas. So interventions policies were called for and were effective. He said the private sector could not be more different today than it was in the Great Depression. The balance sheets are fine. They're healthy. And have you ever seen more innovation ideas that the private sector could take advantage of like blockchain like AI? He says all the government needs to do is get out of the way and let them innovate. Instead they spend and spend and spend. And my new fear now is that spending and the resulting interest rates on the debt that's been created are going to crowd out some of the innovation that otherwise would have taken place.
这很有趣，因为我研究过大萧条时期。当时私营部门债台高筑，基本上没有什么新点子。因此需要进行政策干预，而且这些干预是有效的。他说现在的私营部门和大萧条时期截然不同。现在的财务状况非常健康，而我们也从未见过如此多的创新点子，如区块链和人工智能。他认为政府只需要放手让他们创新。然而，政府反而不断地花钱花钱再花钱。我现在新的担忧是，这些开支和由此产生的债务利率会挤掉本来可以进行的一些创新。
I completely endorse Druckenmiller's view of binomics and actually, I mean, this is what I said way back in 2021. Victory lap. Here we go. Well, Dave's Sacks Victory lap. We need a little graphic for that. Druckenmiller used the word binomics and said I give these guys an F because they're still printing money and spending money like we're in a depression, even though we're in a referring economy.
我完全赞同德鲁肯米勒对“拜登经济学”的看法，实际上，我在2021年早就这么说过了。可以说是胜利时刻到了。这里是戴夫·萨克斯的胜利时刻。我们需要一个小图标来庆祝这个时刻。德鲁肯米勒用了“拜登经济学”这个词, 并表示给这些人打个不及格，因为即使我们处于复苏中的经济，他们还在像处于经济萧条时一样印钞和花钱。
==========
当然，请提供您需要翻译的内容。
And when they started doing this back in 2021, you know, I tweeted it, by an omics equals pumping trillions of dollars of stimulus into a reporting economy. I'm not going to pretend like I know what's going to happen next, but never tried this before. What happened next was a lot of inflation and that jacked up interest rates. According to even Keynesian economics, the reason why you have deficit spending is because you're in a recession or depression. And so use the government to stimulate and balance things out. You don't do deficit. Yeah. You don't do deficit spending when the economy is already doing well. So this spending, there's no reason for it. Yeah.
当他们在2021年开始这样做时，我发推特说，拜登经济学等于向一个正在增长的经济体注入数万亿的刺激资金。我不会假装自己知道接下来会发生什么，因为我们以前从未尝试过这种做法。随后发生的事情是大量的通货膨胀，这推高了利率。根据凯恩斯经济学理论，财政赤字是为了应对经济衰退或萧条，你可以利用政府的刺激措施来平衡经济。当经济状况已经良好时，你不应该进行赤字支出。因此，这种支出是没有理由的。
==========
好的，请提供您需要翻译的英文文本。这将帮助我为您提供准确且易读的中文翻译。
It's like showing up to like a party that's going crazy and being like putting gasoline on the fire. And more importantly, it should limit the approval or action of certain programs that you might otherwise want to do in a normal environment, but in an inflationary environment, you don't have the flexibility to do them. Student loan forgiveness is a really good example is now the time, of course not, to do student loan forgiveness, or do we wait for inflation to temper a bit is now the time. You know, so there's just a lot of these examples that it actually, the opposite should be true. But none of all of those things get you votes.
这就像你参加一个已经疯狂的派对，还往火上浇油。更重要的是，这应该限制你在正常环境下可能会想做的某些项目的批准或实施，但在通货膨胀的环境下，你没有灵活性去做这些事情。学生贷款豁免就是一个很好的例子，现在是进行学生贷款豁免的时机吗？当然不是，还是等通货膨胀稍微缓和一些再做更合适。所以，有很多这样的例子，实际上正确的做法应当是反其道而行，但这些都不会给你带来选票。
==========
请提供需要翻译的具体文本内容。
Before we move on from this, look, what we have coming out of Washington here is a contradictory and therefore self-defeating policy. You've got the Fed jacking up rates to control inflation. You move across town and you've got Capitol Hill on the White House spending like there's no tomorrow, which is inflationary. Why would you do both those things? Choose what your policy is going to be. It's like driving with your foot on the brake and the gas at the same time. It's not a great idea for the car.
在我们继续讨论这个问题之前，请看一下，目前华盛顿出台的政策是自相矛盾的，从而注定会失败。美联储不断提高利率来控制通货膨胀。与此同时，国会和白宫却在大肆挥霍金钱，这本身就是通胀的做法。为什么要同时执行这两种相互抵消的政策？应该明确选择一种政策方向。这就像一边踩刹车一边踩油门，对车子来说可不是个好主意。
==========
当然，请提供要翻译的文本内容。
Let me just make one comment, Jake, how before we move on about the Drucken Miller investment statement? Of course. And I just wanted to say like, I think what it highlights about Drucken Miller and call it a rift in investing philosophy or a skill is the difference between precision and accuracy. What I mean by that is precision really references that you do a lot of detailed analysis to try and make sure you understand every specific thing that is going right or could go wrong. But the problem, and so that means you, for example, might do a ton of diligence on a company and make sure you understand every dollar, every point of margin, all the specifics of the maturation of that business and where they are in their cycle. But you could be very precise, but be very inaccurate.
杰克，在我们继续讨论前，我先发表一个关于德鲁肯米勒投资声明的评论，可以吗？当然可以。我想说的是，这其实突显了德鲁肯米勒在投资哲学或技能上的一个分歧，那就是精准与准确之间的区别。
我的意思是，精准指的是你做了大量详细的分析，确保你了解每一个具体的细节，包括什么是做对的，什么有可能出错。这意味着，你可能会对一家公司进行大量的尽职调查，确保你理解每一美元、每一个利润点，以及公司发展周期中的所有具体细节。但问题是，你可以非常精准，但却非常不准确。
==========
请提供您希望翻译成中文的具体文本内容。这样我才能帮助您进行翻译。
For example, if you miss an entire trend, someone could invest in Macy's back when Amazon was taking off and have done a lot of precise analysis on Macy's margin structure and performance and said, this is a great business. But they missed the bigger trend, which is that e-commerce was going to sweep away Macy's and consumers were simply that's not possible in the analysis, but they were doing it. Let's be honest, Freeburg, nobody could make that stupid of a trade to say Macy's versus Amazon over the next 10 years. Oh, yeah. And so like, and then, and Jacob. Do you want to show that? No, no, no, no. Do not hope the tiger. Let's not get into it. The other five guys. The worst spread trade in history. Yeah, let me just finish the statement.
举个例子，如果你错过了一个大趋势，有人可能在亚马逊刚起步时投资梅西百货，并对梅西百货的利润结构和业绩做了很多精确的分析，认为这是一门好生意。但他们忽视了一个更大的趋势，即电子商务将席卷梅西百货，消费者将改变购物习惯。坦白说，Freeburg，没有人会愚蠢到在未来十年内选择梅西百货而不是亚马逊。是的，而且，Jacob，你要展示一下吗？不，不，不。不要激怒老虎。不要讨论这个问题。还有其他五个人。这历史上最差的交易。让我把话说完。
No, but the other one is being accurate and accurate means you get the, yeah, the right bet, the right sentence, the right friend, the problem with being accurate, you could have said in the year 2000, hey, the internet's going to take off and you could have put a bunch of money in, but the problem was you were right. You just had to have the necessary patience. And so accuracy generally yields better returns, but it requires more patience because you can't necessarily time how long it will take for you to be right. So a guy like Druckenmiller is making an accurate bet. He bets correctly on the trend on where things are headed. He doesn't necessarily need to be precise, but he has the capital and his capital structure that allows him to be patient to make sure that he eventually gets the return.
不，但是另一个人是准确的，而准确意味着你得到了对的赌注，对的答案，对的朋友。然而，准确的问题在于，你可能在2000年说互联网将会兴起，并且投入大量金钱，但是问题是你是对的，你只是需要足够的耐心。因此，准确通常会带来更好的回报，但它需要更多的耐心，因为你无法确切知道你需要多长时间才能被证明是对的。比如德鲁肯米勒这样的人，他在趋势和未来的发展方向上做出了准确的判断。他不一定需要非常精确，但他拥有足够的资本和资本结构，可以保持耐心，确保最终获得回报。
And to build on your thoughts, having watched this movie a couple of times, and I overthought the Twitter investment as about one example, I had the opportunity to invest in Twitter when it was like a single digit millions company. And I just thought, you know what, this thing is only like the headline. And I told that like it's the headline. It's not like the entire blog post, Nick, a co-opany of idiots, this thing is going to be chaos. And I was right, but I was wrong, right? Great bet, but my wrong analysis. And so you can add precision to other aspects, like when you sell your shares or when you double down, but you have to get the trend, right? Which is Evan Williams, great entrepreneur, Jack great entrepreneur, Twitter taking off like a weed, just make the bet. Right? And I think as you knew too much about journalism, you knew too much about the space they were trying to disrupt and that can be a mistake. Correct.
让我来补充一下你的想法，之前看过几次这部电影，我也曾经对投资推特这件事情想得太多。我当时有机会投资推特，当时这个公司市值只有几百万美元。我当时认为这东西只是个头条新闻而已，不算是整个博客文章的重要内容。我还说过，像联合体一样愚蠢，这东西会变成一团糟。事实证明我对了一部分，但也错了一部分。可以说这是一个很好的赌注，但我对它的分析是错的。
因此，你可以在卖出股票或加码投资等其他方面更加精准，但必须掌握大趋势，即：埃文·威廉姆斯是个很棒的企业家，杰克也是，推特如野草般迅速崛起，只需要下注就好。而如果你对新闻业的了解太多，对它们试图颠覆的领域了解太多，这反而可能成为一个错误。正确的。
We did PayPal, no, it's not anything about payments. That was one of the reasons we were successful. All the payments experts told us it couldn't be done. Right. So that happens a lot. I had never even know, I didn't even know what a Facebook was when I joined Facebook. It's an American college phenomenon. No serious? You don't have that. Yeah, Canada. But you knew Zach and you saw some growth charts and you saw some precision in his ability to build product and that's the way to go. The great thing about network effect business is there's a trend line that sustains because it builds if it's an appropriate network effect. So you can be accurate about buying into the right network effect business. You don't need to use all of this diligence to be perfectly sound around the maturation of the revenue and the margin structure and all that stuff as long as the trend line is right and you're willing to be patient to hold your investment.
我们做过PayPal，不，不是和支付有关。这正是我们成功的原因之一。所有支付专家都告诉我们这是不可能的。对，这种情况经常发生。在加入Facebook之前，我甚至不知道Facebook是什么。这是美国大学里的一种现象。真的吗？你们加拿大没有这个。但你认识扎克（指Mark Zuckerberg），你看到了增长图表，也看到了他在产品开发方面的精确能力，这就是成功的方向。网络效应业务的伟大之处在于，它有一条可以持续的趋势线，因为如果网络效应适当，它会不断增长。所以你可以准确地选择合适的网络效应业务。只要趋势线正确，你愿意耐心持有投资，你就不需要通过所有这些尽职调查来完全确认营收和利润结构的成熟度。
I think Drucken Miller's point is incredible. He took a look. He very quickly made a macro assessment from a macro perspective. What Millay is doing is significantly different than what we're seeing in any other emerging market, let alone mature market with respect to fiscal austerity and appropriateness in this sort of inflationary global inflationary environment. And he said, you know what, I don't see any other leader doing this. This is a no brainer bet. Let me make the bet. And as long as he's willing to hold this thing for long enough, eventually the markets will get there and call it a spread trade against anything, he'll be proven right.
我认为德鲁肯米勒的观点非常了不起。他进行了观察，并迅速从宏观角度进行了评估。米莱的做法在任何新兴市场甚至成熟市场中都是显著不同的，尤其是在当前这种全球通胀的环境下，涉及财政紧缩和适当性。他说，你知道吗，我没看到其他任何领导人这么做。这是个无需动脑的赌注。让我来下注。只要他愿意长期持有这个东西，市场最终会认可他，并且无论和什么进行比较交易，他都会被证明是正确的。
Well, speaking of bets, Jay-Kal, you told me this week that you just met your largest investment ever. Tell us about that. Yeah. So I've gotten very lucky now because a lot of my founders from the first couple of cohorts of investing I did when I was a sequoia scout have come back and created second and third companies. So that happened with TK, Uber and the Cloud kitchens that happened with Raul from a report of then superhuman. And then it happened recently just in the past year, my friend Jonathan, who's the co-founder of Thumbtack, asked me to come to dinner and he said, hey, you were the first investor in Thumbtack. Well, you'd be the first investor in our next company, Athena. And I said, sure, what do you do? And he explained it to me. And we put a seven figure bet in, which is rare for us as a seed fund, right? Normally our bet sizes are 100k, 250, it's a $50 million fund.
好的，说到赌注，Jay-Kal，你这周告诉我你刚刚完成了你有史以来最大的投资。能跟我们讲讲吗？
是的。我现在非常幸运，因为在我早期作为红杉资本侦察员进行投资的几个批次中的许多创始人，现在回来创建了第二、第三家公司。比如说，当时的TK、Uber和Cloud Kitchens，还有Raul，从A Report of到Superhuman。这些都发生过。
最近就在过去的一年，我的朋友乔纳森，他是Thumbtack的联合创始人，邀请我去吃晚饭。他说，嘿，你是Thumbtack的第一位投资者。你愿意成为我们下一家公司Athena的第一位投资者吗？我说，当然，能介绍一下你们在做什么吗？他向我解释了一下。于是我们进行了一笔七位数的投资，这对我们的种子基金来说很罕见。通常我们的投资规模是10万到25万美元，因为我们有一个5000万美元的基金。
Why did you do it? Yeah, it's very simple. It's the fastest growing company I've ever seen and I'm including Uber in that. It has been growing at a rate that I'll just say is faster than Uber and Robinhood when we were investing in intensive millions of dollars. It's a very simple concept. When Thumbtack was building their marketplace, they used researchers in places like Manila, etc., in the Philippines knowledge workers. And what they realized was the point 1% of those knowledge workers were as good or better than say Americans at doing certain jobs. And so they've created this virtual EA service. You can go see it at AthenaWow.com. And we now have two of them inside of our company. It turns out Americans don't want to do the operations role.
为什么你要这么做？很简单。这是我见过增长最快的公司，我甚至将Uber也包括在内。它的增长速度比我们投资几百万美元时的Uber和Robinhood还要快。这是一个非常简单的概念。当Thumbtack构建他们的市场时，他们在马尼拉等菲律宾的地方使用了知识工作者进行研究。他们发现，这些知识工作者中有0.1%的人在某些工作上与美国人一样好，甚至更好。因此，他们创建了这个虚拟的行政助理服务。你可以在AthenaWow.com上看到这个服务。我们公司现在也有两个这样的助理。事实证明，美国人不愿意做运营类的工作。
So it's kind of like AWS. You just give them $36,000 a year. They give you essentially an operations or an EA. And they have ones that are kind of chief of staffish and this company is growing like a weed. So I am working with them on the product design as well. So imagine having two or three of these incredibly hard working people who are trained with MBA class level curriculum. They spend months training these people up. They pay them two or three times what they would make at any other company and then they pair them with executives here. And it's kind of an underground secret in Silicon Valley because it's only by invitation right now because they can only train so many people.
所以这有点像亚马逊的AWS服务。你每年只需给他们36,000美元，他们就相当于给你提供一个运营专员或行政助理。他们还有一些类似于参谋长角色的人，而且这家公司发展得非常迅猛。我还在和他们一起进行产品设计的工作。想象一下，你身边有两三个如此勤奋、接受过MBA级别课程培训的人。他们花好几个月的时间来培训这些人，并支付给他们在其他公司两到三倍的薪水，然后把他们安排给这里的高管。而且这在硅谷算是个不公开的秘密，因为现在这个服务是只通过邀请才能获得的，因为他们能培训的人有限。
But if you've tried to hire an executive assistant, I don't know if anybody's tried to do that recently. You've hooked me up so I will be guinea picking the service. Yes. Soon. And I have two of them. And so it is just the greatest that you can have an operation. Are these people powered by AI tools as well? Yeah. So that's the kind of secret sauce here is they're training them and they watch you work and then they will learn how you do your job and then how quickly you can delegate and get stuff off your plate is the name of the game.
但如果你最近尝试过雇一位行政助理，我不知道有没有人做过这件事。你已经帮我联系上了，所以我会先试用这个服务。对，很快。我现在有两个助理。这让我觉得很棒，因为这样可以更好地运作。这些人也使用AI工具吗？对，这就是秘密所在。他们对助理进行培训，并观察你的工作方式，然后学习你如何完成工作。快速将任务委派出去才是关键。
So we have an investment team with researchers and analysts in it. We have a due diligence team and then you have like executive functions in our fund. They have now started shadowing, you know, you know, highly paid Americans in an investment firm ours and then train them up. And now our due diligence, our first level screening, you know, and our tracking of companies is being done by these assistants for what I'll say is a third to a fourth of the price I was paying previously. So what that does in an organization is we're just delegating away and then moving our investment team to doing in person meetings and doing higher level stuff.
我们有一个包含研究人员和分析师的投资团队。我们还有一个尽职调查团队，以及基金的管理职能团队。现在，他们开始跟随我们投资公司里那些高薪的美国员工进行学习和培训。现在，由这些助理来负责我们初步的尽职调查、第一层筛选和公司跟踪工作，成本大约是我之前支付的三分之一到四分之一。这样做的结果是，我们把这些任务委派出去，让投资团队能够专注于面对面的会议和更高层次的工作。
And so you're 80, 90. So at 80, 90, we have this funny thing where we've made it a verb whenever you see somebody doing high quality work at a quarter to a tenth of the cost, we say, oh, you just 80, 90 did. Correct. So we're ending the investment team. I'm 80 and 90 and the investment team. And you know what? It was scary as hell for them because they're like, am I going to lose my job? It's like, no, you now get to instead of doing a check and call once a month, you can do a check and call every other week or every week or instead of doing 15 first round interviews a week, you can do 25 because you have this assistant with you doing all the repetitive work.
所以你已经到了80、90年代。在80、90年代，我们有一个有趣的说法，每当看到有人以四分之一到十分之一的成本完成高质量的工作时，我们就会说，“哦，你就是80、90做到了”。对吧？因此，我们决定终结投资团队。我在80和90团队。你知道吗？这对他们来说非常可怕，因为他们会想，我会失业吗？其实不是的，你现在可以每两周或每周做一次检查和回访，而不是每月一次。或者你可以每周进行25次初轮面试，而不是15次，因为你有助理帮你做所有重复的工作。
The way that companies will work in five and 10 years, I don't think guys, any of us are going to recognize what it's going to look like. No. Yeah. Like watching Saxa's demo earlier, how much progress and how seamless that product works with the features it has enabled by the underlying models. You just get to thinking how all of these vertical software applications become completely personalized and quickly rebuilt around the eye. Totally. Totally. It's so obvious.
我认为未来五到十年企业的运作方式将会完全不同，我们现在几乎无法想象未来的样子。对，就像刚才看到了Saxa的演示，那款产品的进展和它依赖底层模型的无缝功能真的让人惊叹。你会开始思考，所有这些专业软件应用程序将变得完全个性化，并迅速围绕人工智能重新设计。完全没错，这真的太明显了。
Can you imagine how long it would have taken John to write a letter to Lena Kahn to what like if we said John invite Lena Kahn, but be sure to reference all the nice things we said about her on episodes of the pod. I mean, 10 hours of work. You got to go find the episodes. Yeah, listen to them to figure out what the best quotes are. You got it done in five seconds. It's incredible. Totally. And this is building that same sort of capability into a very specific vertical application that's specific to some business function. And you can probably spend a couple minutes or an hour building that function. And then it saves you hours a day in perpetuity.
你能想象约翰要写一封信给莱娜·卡恩需要多少时间吗？假设我们说，约翰，邀请莱娜·卡恩，但一定要提到我们在播客中的所有赞美之词。我是说，这得花上十个小时的工作。他得去找那些集数，听一听，找出最好的引用。他只用了五秒就完成了，难以置信。确实如此。这是在一个非常特定的垂直应用中建立相同类型的功能，这个应用是针对某个业务功能的。你可能需要花几分钟或几个小时来建立这个功能，但它会永久地节省你每天的几个小时。
Yeah. And I think that's why these tools companies or the tools products that Google Microsoft, Amazon, and a few others are building are actually incredible businesses because so many enterprises and so many vertical application builders are going to be able to leverage them to write their entire business functions. I got myself and my co-founders at 8090. We get this stream of emails of companies that are like, or people that are like, we have this product idea or we have this small product. One of the emails I got, this is crazy, was from a guy that's like, oh, we've 8090 Photoshop. So like we have like a much, much cheaper version of Photoshop. And the guy was doing like a few million bucks of a VAR and growing really nicely. But then it turned out that somebody saw that and then 8090 did. So that there's a lot of that thing.
是的，我认为这就是为什么谷歌、微软、亚马逊等公司正在构建的这些工具产品实际是非常棒的生意，因为许多企业和垂直应用开发人员都能够利用这些工具来编写他们的整个业务功能。我和我的联合创始人在8090公司，我们经常收到这样的邮件，有公司或个人说他们有产品创意或是一个小产品。其中一封邮件特别有意思，是一个人说他们有一个类似于8090版本的Photoshop，就是说他们有一个便宜得多的Photoshop版本，而且这个人已经通过它赚了几百万美元，并且发展得很好。但后来发现，有人也看到了这个产品并模仿了它。所以，这样的事情很多。
And so to your point, Fibri, none of these big company standard chance. Yeah. It's everything. It's not because they're not because the products aren't good, but like Jake, I was going to go off an experiment with this. Sax going to go off and build a product. You know, as every time that you're at a boundary condition, we're all going to explore, well, maybe we could do this with AI. Maybe we shouldn't hire a person, not because we're trying to be mean about it, but it's because the normal natural thing to do. And the optics of companies is just going to go down, which means the size of companies are going to shrink, which means the amount of money you need is going to go down. And that's just going to create the ability for these companies to sell those products cheaper. So it's a massive deflationary tail.
翻译如下：
“所以，Fibri，你说得对，这些大公司的标准机会是不存在的，对吧。这涵盖了一切。这不是因为他们的产品不好，而是像Jake那样，我本来打算尝试一下这个实验。Sax打算自己去开发一款产品。每当我们处于边界条件时，都会考虑，或许我们可以用AI来做这件事，也许我们不应该雇用人手，不是因为我们想要刻意苛刻，而是因为这是自然的选择。而公司的光环也会因此减弱，这意味着公司的规模会缩小，所需的资金量也会减少，这就使得这些公司能够以更低的价格出售产品。因此，这将带来巨大的通缩影响。”
We had the same thing happen with compute. And now it's happening inside of organizations. I wrote a blog post about this on my subset called ADD. This is the framework I came up with. I told my entire team, look at what you got done every week. And I want you to ask three questions. How can I automate this? How can I deprecate this? How can I delegate it? And the automate part is AI and what you're doing, David, the delegate part is AthenaWOW.com. And then the deprecate is, hey, just be thoughtful. What are you doing that you don't need to do? And that's 80, 90, something like there are things inside these products that you don't actually need. What's the core functionality of the product? Make it as affordable as possible.
我们之前在计算方面也遇到过同样的情况，现在这种情况发生在组织内部。我在我的博客上写了一篇关于这个问题的帖子，名为 ADD。这是我提出的一个框架。我告诉我的整个团队，每周回顾你们完成的工作，并且问自己三个问题：如何自动化这项工作？如何弃用这项工作？如何委托他人完成这项工作？其中，自动化部分指的是人工智能和你在做的事情，大卫；委托部分是指 AthenaWOW.com。至于弃用，就是要仔细思考，你在做的事情中哪些是不需要的？大约有80%到90%的产品功能实际上并不需要。产品的核心功能是什么？让它尽可能地实惠。
And then what's going to happen for people who think this is bad for society? You've got it completely wrong. We're going to have more people be able to create more products and solve more problems. The unemployment rate is going to stay very low. We're just going to have more companies. So the idea, like there was somebody who was working on very small software. I want to get pitched on very niche ideas. I want to create something where people can find people to play pickleball with, right? Like a pickleball marketplace. Now that wouldn't typically work because you would need $5 million a year to build that product. But if you can build it for $500,000 a year? And now you've only got to clear that number to be profitable.
那么，对于那些认为这对社会不好的人，会发生什么呢？你完全搞错了。我们将会有更多的人能够创造更多的产品并解决更多的问题。失业率将保持在非常低的水平。我们的公司数量只会增加。比如说，有人正在开发非常小众的软件。我想听到那些非常细分领域的创意。我要创建一个让人们可以找到一起打匹克球（Pickleball）伙伴的平台，对吧？类似于一个匹克球市场。一般来说，这种项目可能行不通，因为建这个产品每年需要500万美元。但是如果能以每年50万美元的成本建成呢？那么你只需要达到这个数字就能实现盈利。
So a lot more small businesses, a lot more independent. All these little niche ideas will be able to be built. And a VC who says, I'm not giving you $5 million to build that app will be like, but I will give you $500k. And that's what I'm seeing on the ground in startups. The same startups that had a request of $3 million in funding five years ago are now requesting 500 to a million. It's deflationary all the way down.
因此，会有更多的小企业和更多的独立企业。这些小众的创意都有可能被实现。一个风投可能会拒绝给你500万美元去开发一个应用，但却会说，我可以给你50万美元支持你的项目。这就是我在创业公司中看到的趋势。五年前寻求300万美元资金的创业公司，现在只需要50万到100万美元。这种现象一直在持续。
Did you guys see the Google thing? Did you guys see the Google AI Gemini stuff? Chat GPT, Omni launched at the same time, or perhaps strategically right before Google dropped its latest AI announcements at IO. The biggest announcement is that they are going to change search. This is the piece of the puzzle on the kingdom that they have been very concerned with and they're going for it. The new product and they have like 20 different products. You can see them at labs.google where they put all their different products. But this is the most important one. They call it AI overviews. Basically, it's perplexity for most users by the end of the year, they're going to have this.
你们看到谷歌的那个东西了吗？你们看到谷歌的AI Gemini的那些东西了吗？Chat GPT和Omni几乎在同一时间发布，甚至可能是为了在谷歌发布最新的AI公告之前有意赶在前面。最重要的宣布是他们要改变搜索功能。这是他们一直非常关注的领域，现在他们要大干一场了。新的产品，其实他们有大约20种不同的产品，你可以在labs.google网站上看到所有这些产品。但最重要的就是这个，他们称之为AI概览。基本上来说，对大多数用户来说，这就是perplexity（注：一个语言模型）了，预期在今年年底他们就会推出这个功能。
Here's how it works. And you can see it on your screen. If you're watching us go to YouTube here, they gave an example. How do you clean a fabric sofa? This normally would have given you 10 blue links here. It gives you step by step guide with citations and links. So they're preempting, you know, the issue of people getting upset. And as I predicted, they're going to have targeted ads. There's the things you need in order to clean your couch. You can only use this if you're using your Gmail account. If you use like a domain name on Google Docs, it won't work there. So go to labs.google, but they're doing citations.
以下是它的工作原理，您可以在屏幕上看到。如果您在 YouTube 上观看我们，您会看到一个示例：如何清洁布艺沙发？通常情况下，这会给您提供10个蓝色链接，而现在会给您逐步的指导，并附有引用和链接。他们提前解决了人们可能会不满的问题。正如我预测的那样，他们将会有针对性的广告。这些是您清洁沙发所需要的东西。您只能在使用 Gmail 帐户时使用此功能。如果您在 Google 文档中使用域名，这个功能将无法使用。所以请访问 labs.google，不过它们确实提供引用。
And I think that we're going to see a major lawsuit here. Those people who are in those boxes are going to look at the answer here and realize maybe they don't get the click through. And that this answer was built on that. And now we're going to have to have a new framework. There's going to need to be SAC a new company that clears this content. So that Google can do answers like this. The workflow stuff in Gmail also kicked ass the demo that they showed was you get a bunch of receipts and the person giving the demo, she said something the effective. Well, wouldn't it be great if like, you know, the AI assistant were able to find all the receipts and then aggregated them and put them in a folder and then also actually generated an expense report or like a spreadsheet on the fly?
我觉得我们会看到一场重大的诉讼。那些提供内容的人会发现，他们可能得不到点击量，因为答案是基于他们的内容生成的。因此，我们需要一个新的框架，可能需要成立一家新的公司来审核这些内容，以便谷歌能够提供这样的答案。Gmail中的工作流程功能也非常出色。演示中展示了你会收到一堆收据，演示的人说，如果AI助理能够找到所有收据，将它们汇总并放入一个文件夹，然后实时生成一份费用报告或电子表格，那不是很好吗？
It's crazy. I got to say, I think that it's free to change your mind. And so it's good to do that. Oh, and I think that Chama and a rare moment of reflection might do a, are we going to have a re underwriting? Is this a re underwriting? I change my mind all the time. I just, I mean, you know, because I'm the gentleman breaking news. I think the Google thing is pretty special between last week's announcement of isomorphic labs, which let's be honest, that's a, that's just a multi-hundred billion dollar company. So you're saying there might be many.
这太疯狂了。我得说，我认为改变主意是免费的。所以改变主意是好的。哦，我觉得Chama可能会有一个难得的反思时刻，我们会重新承保吗？这是重新承保吗？我经常改变主意。只是，我的意思是，你知道的，因为我是那个揭露新闻的人。我认为谷歌的事情非常特别，上周宣布的等构实验室（Isomorphic Labs），老实说，这是一家价值数千亿的公司。所以你说可能会有很多。
Think about it this way, right? Multi-billion dollar opportunities sitting there dormant inside of Google that AI unlocks. Look at a company like Royalty Pharma. So if Royalty Pharma with a pretty, it's a phenomenal business run by a phenomenal entrepreneur, Pablo La Guretta. But what is that business? That's buying two and three percent royalties of drugs that work. And you can see how much value that those guys have created, which is essentially 90 percent, a bit margin business. It's outrageous because they're in the business of analyzing and then buying small slivers.
这样想一想，对吧？谷歌内部有数十亿美元的机会原本处于休眠状态，现在被人工智能激活了。看看像Royalty Pharma这样的公司。Royalty Pharma是一家由出色企业家Pablo La Guretta管理的优秀企业。那么这家公司的业务是什么呢？它是购买那些有效药物的2%到3%的版税。你可以看到，他们创造了多么大的价值，基本上是一个90%利润率的业务。这简直太不可思议了，因为他们的业务是先分析，然后购买这些小部分。
I think something like isomorphic ends up being of that magnitude of margin scale, but at an order of magnitude or two orders of magnitude higher revenue. So if you, if you fold that back into a Google, if you think about what they're doing now on the search side, these guys may be really kicking some ass here. So I think that the reports of their death were premature and exaggerated. Absolutely. And the report of their death, Freiburg, was based upon people don't need to click on the ads. But as I said on this very bogus, my belief is that this is going to result in more searches and more knowledge engagement because once you get how to cook your steak and get the right temperature, right, for medium rare, it's going to anticipate your next three questions better.
我认为类似于同构的东西最终会达到那种量级的规模，但收入会高一个数量级或两个数量级。因此，如果你回头看看谷歌现在在搜索方面做的事情，这些家伙可能真的在这里大展身手。所以我觉得之前有关他们衰落的报道是过早且夸大的，绝对是。而那些关于他们衰落的报道是基于人们不需要点击广告的假设。但正如我在这个非常虚假的假设中所说，我相信这将会带来更多的搜索和更多的知识参与，因为一旦你了解了如何煮牛排以及如何达到适中的温度，它将能够更好地预见你接下来的三个问题。
And now to say, hey, what wine pairing would you want with that steak? Hey, do you need steak knives? And it's just going to read your mind that you need steak knives and chamois likes to buy steak knives, but maybe you like to buy mock meats, whatever it is, it's going to drive more research and more clicks. So while the monetization per search may go down, we might see many, many more searches. What do you think, Freiburg? You work there. And when we look at the, the, the future of the company and the stock price, Nick, we'll pull it up. Man. If you had held your stock, yeah, I don't know. Did you hold? I think I bought some, um, during the original stock during the war, okay. I said, Oh, no, I sold all my stock back when I started climate because I was a startup entrepreneur and needed to live. So which, you know, I, I, I did the math on it. It was pretty, it'd be worth, it'd be worth a lot. It would be worth billions or tens of billions. No, no, would it would have been a billion or no? No. Okay. You know, I was not like a soup. I was not a senior exact for anything. I think what you said is, is probably true.
好的，现在来说说你会和牛排搭配什么酒？嘿，你需要牛排刀吗？它会直接读出你需要牛排刀，而且可能你喜欢买牛排刀，但也许你喜欢买素食肉。不管是什么，这都会推动更多的研究和点击量。所以尽管每次搜索的盈利可能会下降，但我们可能会看到更多次的搜索。弗莱堡，你觉得呢？你在那里工作。我们再看看公司和股票的未来走势。尼克，拉出来看看。老天，如果你一直持有你的股票，不知道你持有了吗？我想我在最初的时候买了一些股票，战时。好吧，我卖掉了所有股票，当时我刚创业，需要生活费。所以我算了一下，本来会值很多钱的，会值数十亿。不过，也不会有那么多钱，因为我不是高级管理人员。我觉得你说的可能是对的。
So that's a creative. I think the other thing that's probably true is a big measure at Google on the search page in terms of search engine performance was the bounce back rate, meaning someone does a search. They go off to another site and then they come back because they didn't get the answer they wanted. And then the one box launched, which shows a short answer on the top, which basically keeps people from having a bad search experience because they get the result right away. So a key metric is they're going to start to discover which vertical searches, meaning like a cooking recipes, that kind of stuff, like the reference, there's lots and lots of these different types of searches that will trigger a snippet or a one box that's powered by Gemini that will provide the user a better experience than them jumping off to a third party page to get that same content.
那么，这就是一个创新之处。我认为还有一个重要的事实是，在谷歌搜索页面上衡量搜索引擎性能的一个重要指标是回跳率。回跳率的意思是有人进行搜索，进入另一个网站，但因为没有找到想要的答案又返回来的情况。而“一框”功能的推出，就是在顶部显示一个简短的答案，基本上能防止用户在搜索中有不好的体验，因为他们可以立即得到结果。所以，一个关键指标是他们将开始发现哪些垂直搜索，例如烹饪食谱类型的搜索（还有很多很多这类不同类型的搜索），会触发由Gemini提供支持的片段或“一框”显示，从而为用户提供比跳转到第三方页面更好的体验。
And then they'll be able to monetize that content that they otherwise were not participating in the monetization of. So I think the real victim in all this is that long tail of content on the internet that probably gets cannibalized by the snippet one box experience within the search function. And then I do think that the revenue per search query in some of those categories actually has the potential to go up, knocked out. Explain. Explain. Give me an example. You keep people on the page so you get more search volume there. You get more searches because of the examples you gave. And then when people do stay, you now have the ability to better monetize that particular search query because you otherwise would have lost it to the third party content page.
然后他们就能够通过那些原本不参与变现的内容来赚钱了。因此我认为，真正受害的是互联网上的长尾内容——这些内容可能被搜索功能中的片段式体验所吞噬。而且我确实认为，在某些类别中，每次搜索的收入实际上有可能会增加。解释一下。解释一下。给我举个例子。你把用户留在页面上，就能增加搜索量。由于你提到的例子，你会有更多的搜索。而当人们确实留在页面上的时候，你现在有能力更好地对那个特定的搜索查询进行变现，因为否则你会把它输给第三方内容页面。
So for example, selling the steak knives is another is, you know, it's kind of a good example or booking the travel directly and so on. So by keeping more of the experience integrated, they can monetize the search per query higher and they're going to have more queries and then they're going to have the quality of the queries go up. So I think it's all in. There's a case to be made. I haven't done a spreadsheet analysis on this, but I guarantee you going back to our earlier point about precision versus accuracy, my guess is there's a lot of hedge fund type folks doing a lot of this precision type analysis, trying to break apart search queries by vertical and trying to figure out what the net effect will be of having better AI driven one box and snippets. And my guess is that's why there's a lot of buying activity happening in the stock right now.
举个例子，卖牛排刀或者直接预订旅行，这些都是很好的例子。通过让更多的体验集成在一起，他们可以在每次搜索中赚取更多的收入，并且会有更多的搜索查询，同时搜索的质量也会提高。所以我认为这是一笔值得的投资。虽然我没有做过具体的数据分析，但我可以保证，回到我们之前关于精确性与准确性的讨论，我猜有很多对冲基金的人正在进行这类精细分析，尝试根据不同领域来分解搜索查询，并弄清楚提高由AI驱动的一站式搜索和摘要功能的净效果。我猜这也是最近股票购买活跃的原因。
And it's actually all missing. To my point, a lot of these call options like isomorphic labs. I can tell you meta and Amazon. What meta and Amazon do not have an isomorphics lab and Waymo sitting inside their business that suddenly pops to a couple hundred billion of market cap and Google does have a few of those. So other bets could actually pay off these are maybe I look, I mean, there's Calico. No one talks about Calico. I don't know what's going on over there. My extension. Yeah. Let me get sacks involved in discussion sacks. Then we show that example. It's obvious. Google is telling you where they got these citations from and how they built their how to clean your couch, how to make your steak. Those they were in a very delicate balance with content creators over the past two decades, which is, Hey, we're going to use a little bit of your content, but we're going to send you traffic. This is going to take away the need to send traffic to these places. They're going to benefit from it.
其实这一切都缺失了。我的观点是，很多这些期权，比如同构实验室。我可以告诉你，Meta和亚马逊没有一个同构实验室和Waymo存在他们的业务中，突然间市场估值就会飙升到几千亿，而谷歌确实有几个这样的业务。所以其他的投资可能真的会有回报。比如，Calico，没人谈论Calico。我不知道那里发生了什么。如果我的扩展，嗯，让我把Sacks拉进来讨论这个问题。我们展示了那个例子，很明显谷歌会告诉你，他们从哪里获取这些引用以及如何构建的，比如如何清洁你的沙发，如何烹饪牛排。在过去的二十年里，他们与内容创作者之间有一种非常微妙的平衡：嘿，我们会使用你的一些内容，但我们会给你带来流量。而这种做法将消除发送流量的需求，最终使他们受益。
To me, this is the mother of all class action lawsuits because they're putting it right up there. Hey, we're using your content to make this answer. Here's the citations. We didn't get your permission to do this, but we're doing it anyway. What do you think is the resolution here? Does all of these content go away because there's no model? Does Google try to make peace with the content creators and cut them in or license their data? What's going to happen to content creation when somebody like Google is just going to take wire cutter or these other sources that are not behind a payroll and just give you the goddamn answer.
对我来说，这简直是所有集体诉讼之母，因为他们将它摆明了：嘿，我们在用你的内容来给出这个答案。这是引用来源。我们没有得到你的许可，但我们还是这么做了。你认为解决办法是什么？所有这些内容会消失，因为没有模型了吗？还是Google试图和内容创作者和解，给他们分成或许可他们的数据？当像Google这样的大公司直接取用Wirecutter或其他不需要付费的来源并直接给出答案时，内容创作将会变成什么样？
Well, like this is the same conversation we've had two or three times. We're going to need the courts to figure out what fair use is. And depending on what they come up with, it may be the case that Google has to cut them in by licensing deals. We don't know the answer to that yet. By the way, I do know a founder who is already skating to where the puck is going and creating a rights marketplace so that content owners can license their AI rights to whoever wants to use them. I think that could be very interesting. I had a call with him yesterday and you and I will be on that cap table together once again. Good night. Yeah.
嗯，这就是我们已经讨论过两三次的同样话题。我们需要通过法院来确定什么是合理使用。而且根据法院的决定，可能谷歌需要通过许可交易来分一部分收益给他们。我们目前还不知道答案。不过，我认识一个创始人，他已经在为未来做准备，创建了一个权利市场，这样内容所有者可以将他们的AI权利授权给想要使用的人。我觉得这会很有意思。昨天我和他通了电话，你我将再次一起出现在那张股东名单上。晚安。
So I don't want to say who it is because we can't let him announce his own round, but I'm only participating in the seed round. Look, stepping back here, it's interesting. If you go back to the very beginning of Google, the OG Google search bar had two buttons on it, right? Search and I feel lucky. I feel lucky was just tell me the answer. Just take me to the best result. And no one ever did that because it kind of sucked. Then they started inching towards with one box, but it wasn't you didn't get the one box very often. It's very clear now that Gemini powered one box is the future of Google search. People just want the answer.
所以，我不想透露具体是谁，因为我们不能让他自己宣布融资轮次，但我只参与了种子轮。退一步来看，这很有趣。如果你回到Google的早期，最初的Google搜索栏上有两个按钮，对吧？一个是搜索按钮，另一个是“手气不错”。“手气不错”就是直接给我答案，带我去最好的结果。但没有人用这个按钮，因为效果不怎么样。后来他们开始尝试用单一搜索框，但你并不总能得到直接的答案。现在很明显，由Gemini驱动的直接答案框是Google搜索的未来。人们只想要直接的答案。
I think that this feature is going to eat the rest of Google search. Now it's a little bit unclear what the financial impact of that will be. I think like you guys are saying there'll be probably be more searches because search gets more useful. There's fewer blue links to click on, but maybe they'll get, you know, compensated through those like relevant ads. Just say you're probably right that Google ultimately benefits here, but let's not pretend this was a deliberate strategy on their point. They got drag kicking and screaming into this by innovation and perplexing other companies. They had no idea. They got caught completely flat footed and they've now I guess caught up by copying perplexity and sex or perplexity.
我认为这个功能将会主导谷歌搜索的其余部分。现在还不太清楚它将带来什么样的经济影响。我觉得，就像你们说的，可能会有更多的搜索，因为搜索变得更有用了。点击蓝色链接的次数会减少，但也许他们会通过相关广告获得补偿。我同意你们的看法，谷歌最终会从中受益，但不要假装这是他们有意为之的策略。他们是被创新和其他公司的困惑逼得不得不这么做的。他们完全没有预料到这种情况，完全措手不及，现在他们通过模仿Perplexity等公司才赶上来。
I think they're kind of screwed now unless they get it's over an acquisition deal. But perplexity came up with the idea of having citations in your comprehensive search results. Yeah, which was something search results with citations and related questions. And they did it extremely well. And quite frankly, all Google had to do was copy them. Now they've done that. Yeah. I think it does look like a killer. And by the way, this was all something that I saw 15 years ago when I did Mahalo, which was my human powered search engine and which I had copied or been inspired by neighbor and down in Korea.
我认为他们现在有点麻烦了，除非通过收购交易来解决。但Perplexity提出了一个在全面搜索结果中加入引用的想法。对，搜索结果中会有引用和相关问题。他们做得非常好。坦率地说，谷歌只需要抄袭他们的模式就好了。现在谷歌已经这么做了，我认为这看起来确实像是一个杀手级应用。顺便说一句，这一切让我想起了15年前我做Mahalo的时候，这是我的一个由人工驱动的搜索引擎，我当时是借鉴或受到了韩国Neighbor的启发。
They were the first ones to do this. You know, a chamap, because there were only three or four markets where Google couldn't displace the number one. Korea, Russia, Japan, Russia had was a Russian search engine. God, I can't remember it now. Japan had Yahoo Japan, which Masayoshi San had carved out. It was never part of it. And they were loyal to that and very nationalistic Koreans and very innovative folks had down in neighbor just made search that was so amazing. You do a search and you'd be like, here's music, here's images, here's answers, here's Q&A. It was awesome.
他们是第一个做到这一点的人。你知道的，一个先驱者，因为在只有三四个市场中谷歌没有取代第一的位置。韩国、俄罗斯、日本，俄罗斯有一个本地的搜索引擎。天啊，我现在记不起它的名字了。日本有雅虎日本，这是孙正义特意划分出来的，跟雅虎无关。日本人对此非常忠诚，也非常具有民族主义精神。韩国人非常创新，他们在Naver上做了一个很棒的搜索引擎。你一搜索，就会出现音乐、图片、答案、问答等，非常厉害。
But you know, it just shows you like you need to have a lot of wherewithal and timing is everything as an entrepreneur. My timing was 10 years too early. And the wrong technology I used to humans not AI because AI didn't work 15 years ago. One thing I would say about big companies like Google or Microsoft is that the power of your monopoly determines how many mistakes you get to make. So think about Microsoft completely missed iPhone. Remember and they like they screwed up the whole smartphone mobile phone era. And it didn't matter. Didn't matter. Satcha comes in blows this thing up to a $3 trillion public company.
但你知道，这只是表明，作为一个企业家，你需要有足够的应变能力和把握时机的能力。而我的时机提前了10年，并且我使用了错误的技术。我当时选择了人类而不是人工智能，因为15年前人工智能并不好用。关于像谷歌或微软这样的大公司，我想说的是，你的垄断能力决定了你可以犯多少错误。想想看，微软完全错过了iPhone的机会，他们搞砸了整个智能手机市场。但这并没有关系。后来萨提亚（微软现任CEO）来了，把公司做到了3万亿美元的市值。
Same thing here with Google. They completely screwed up AI. They invented the transformer completely missed LLMs. Then they had that fiasco where you know, they had. Black George Washington. Black George Washington. Doesn't matter. They can make 10 mistakes, but their monopoly is so strong that they can finally get it right by copying the innovator and they're probably going to become a $5 billion company now. Sorry, $5 trillion company.
谷歌在这里也是一样。他们在AI方面彻底搞砸了。他们发明了Transformer模型，但完全错过了大语言模型（LLMs）。然后，他们还闹出了那个黑色华盛顿的问题。黑色华盛顿。不管怎样，他们可以犯10个错误，但由于他们的垄断地位太强，到最后可以通过复制创新者的成果来做到正确，现在他们可能会成为一家5万亿美元的公司。
It reminds me, you know, the greatest product creation company in history. I think we all know who that was and take a look down memory lane. Here are the 20 biggest felt Apple products of all time. The police, Mac and Thomas portable. We all remember the Newton, which was their PDA, the 20th anniversary, Macintosh, super sexy. People don't remember. They had their own video game.
这让我想起了历史上最伟大的产品创作公司。我想我们都知道那是谁。让我们一起回顾一下。这里是苹果历史上最受欢迎的20款产品。苹果电脑，Mac，还有当时的可携带设备。我们都记得牛顿，这是他们的个人数字助理（PDA）；还有20周年纪念款Macintosh，超级炫酷。人们可能已经不记得，他们曾经还有自己的电子游戏。
I was at a conference a couple of years ago that Jeff Bezos spoke at. I think he's given this talk in a couple other places. You could probably find it on the internet, but he talks about Amazon's legacy of failure and how they had the fire phone and the fire this and the fire that and he's like, our job is to fail. Big swings. He's blunders. But what makes us successful is that we learn from the failures and, you know, we make the right next decision.
几年前我参加了一个会议，杰夫·贝佐斯在会上发言。我记得他在其他地方也做过类似的演讲，你可能可以在网上找到。他谈到了亚马逊的失败史，比如Fire手机、Fire系列产品等。他说，我们的工作就是去尝试，即使会失败，而且往往会有大错误。但让我们成功的原因是，我们从失败中学习，并做出正确的下一个决定。
Yeah. But I say, if you're a startup and you make big failures, you usually squat a business. One and done. Yeah. But this is how you say this, but this is how you stay competitive. If you're a big founder led tech company, the only way you're going to have a shot at staying relevant is to take big shots that you're going to fail at. I just don't. I just, you can't just hide.
是的。但我的意思是，如果你是一家初创公司，犯了大错，通常就会毁掉生意，一次失败就倒闭了。是的。但是，这是你要这样说的，不过这也是保持竞争力的方法。如果你是一家由创始人领导的大型科技公司，唯一保持竞争力的方法是大胆尝试，即使这些尝试可能会失败。我只是认为，你不能躲避，不能袖手旁观。
You have to do things that you're going to fail at. Right. Remember this boom. This is one of the huge different stream startups and big companies is that big companies can afford to have a portfolio of products. They have a portfolio of bets. Some of them will work and that keeps the company going. Startup really has to go all in on their best idea.
你必须去做那些你可能会失败的事情。对的，记住这一点。这是初创公司和大公司之间的一个巨大区别： 大公司可以拥有一系列的产品组合。他们有一系列的赌注，其中一些会成功，而这些成功的产品能够维持公司的运营。而初创公司则必须全力投入到他们最好的想法中。
Totally. I always tell founders, just go all in on your best idea. They're always asking me for permission to pivot. And I always tell them, do go for the best idea. Don't, don't hedge. Don't try to do five things at once. Just go all in on your best idea. Yeah. Yeah. And if it doesn't look at you reboot and start with a new. You're going to go all in.
完全没错。我总是告诉创业者们，全力以赴专注在他们最好的点子上。他们总是问我是否可以转型，而我总说，去做最好的点子。不，不要犹豫，不要同时尝试做五件事。只要全力以赴在你最好的点子上。对，如果不行，就重新开始，换个新点子。你得全力以赴。
So to speak, another amazing episode is in the can. The boys are in a good mood. You got your great episode. No guesses week. Just all bestie all the time. And very important. The March to a million continues halfway there. You got us there fans. We hit 500,000 subbies on YouTube, which means you all learned a live Q&A with your besties coming at you in the next couple of weeks.
可以这么翻译：
可以这么说，又一集精彩的节目完成了。小伙子们心情都很好。你们得到了你们喜欢的精彩节目。这周没有嘉宾，全程都是好朋友的互动。还有非常重要的一点，“百万订阅”计划已经走到一半了。感谢粉丝们的支持，我们在YouTube上达到了50万订阅。这意味着在接下来的几周内，你们将会迎来一次和好朋友们的直播问答环节。
We're going to do it live on YouTube. So if you're not one of the first 500, get in there now. So you get the alert. We're going to take your questions live. It's going to be dangerous. Any questions? No questions. Who knows what could happen on a live show. And by the way, I just want to let you know that Phil Hellmuth breaking news. Phil Hellmuth and Dre Monghre and just resigned from open AI.
我们将在YouTube上直播。所以如果你不是前500名之一，赶快加入吧，这样你能收到提醒。我们会现场回答你的问题。这次会很刺激。有什么问题吗？没有问题？谁知道直播时会发生什么。顺便说一下，我还有个最新消息，Phil Hellmuth和Dre Monghre刚刚从OpenAI辞职了。
We didn't get into that, but the open AI resignations continue. Phil Hellmuth has tweeted. He's no longer with open AI. You guys like my baby cashmere pink sweater. That's pretty great. Are we going to get summer chamatsu? Now the buttons coming down. Are you going to go out and linen? The when is linen chamat show up? The unbuttoning is about to happen in the next two or three weeks.
我们没深入讨论那个话题，但开放 AI 的辞职潮还在继续。Phil Hellmuth 发推文说他已经不再和开放 AI 合作了。你们觉得我这件粉色的羊绒毛衣怎么样？挺不错的吧。我们会有夏季的Chamatsu吗？现在纽扣开始解开了。你接下来会穿亚麻布衣服吗？几周内就会看到我解开纽扣的造型了。
The great unbuttoning. The great unbuttoning. It's kind of like Groundhog Day. You know that summer's here. When almost your voice. Almost your most memorial day. When after Memorial Day, the button can come down. Yeah, we're going to go three buttons down. I'll still wear my black tea. Sax will still be blue blazer, blue shirt, red tie. And freeburg in fields of gold.
大解放。大解放。这有点像土拨鼠日，你知道夏天已经来了。几乎是在你有纪念意义的一天，就像阵亡将士纪念日之后，纽扣可以解开了。对，我们要解开三个纽扣。我仍然会穿我的黑色T恤。萨克斯仍然会穿蓝色西装外套、蓝色衬衫和红色领带。而弗里堡则置身于金色的田野中。
Look at freeburg in fields of gold. Taking us out, staying in fields of gold. Coming at you two for Tuesday. See all the next all the pod for the Sultan of Science. The rain man did socks and chairman dictator. I am the Z 100 morning zoo DJ. We'll see you next time. Love you, boys. Bye. Bye. Bye. Bye. We'll let your winners ride. Rain man, David. Sax. I'm going all the way. And it said we open source it to the fans. And they've just gone crazy with it.
看看弗里堡，金色田野中的风景。带我们出去，留在金色的田野里。周二特别献给你们两人。下次见，我们所有节目的科学苏丹。雨人做了袜子，还有董事长独裁者。我是Z100晨间动物园主播。下次再见。爱你们，伙计们，再见，再见，再见。我们让赢家们尽情发挥。雨人，戴维德，我全力以赴。然后我们说把它开源给粉丝，他们简直疯了。
Love you, guys. I'm the queen of Kinwah. I'm going all the way. What? What? I want to ride. I want to ride. I want to ride. Besties are gone. Go 30. That is my dog taking a nice, near driveway. Sax, wait it on. Oh, man. My husband, Jasher, we meet me at Wood and Sun. We should all just get a room and just have one big huge org because they're all just like this like sexual tension. But we just need to release it out there. What? You're the beat. What? You're the beat. You're the beat. What? We need to get merges.
爱你们，伙计们。我是金华女王，我要一路前行。什么？什么？我想骑。我想骑。我想骑。闺蜜们都走了。走吧，三十。那是我家的狗在车道上好好休息。萨克斯，等一下。哦，天啊。我的丈夫，贾舍尔，我们在伍德和太阳会合。我们应该都找个房间来个大聚会，因为大家都有这种性张力。我们需要释放出来。什么？你是节拍。什么？你是节拍。你是节拍。什么？我们需要合并。
I'm going all the way. I'm going all the way. And now the plugs be all in summit is taking place in Los Angeles on September 8th through the 10th. You can apply for a ticket at summit.allinpodcast.co. Scholarships will be coming soon. You can actually see the video of this podcast on YouTube, youtube.com slash at all in which search all in podcast and hit the alert bell and you'll get updates when we post and we're going to do a party in Vegas. My understanding when we hit a million subscribers. So look for that as well.
我要全力以赴。我要全力以赴。现在，All In峰会将于9月8日至10日在洛杉矶举行。你可以在 summit.allinpodcast.co 申请门票。奖学金也即将开放。如果你想看这个播客的视频，可以去YouTube，搜索“all in podcast”，然后点击通知铃，这样我们每次发布内容时你都会收到更新。当我们的订阅用户达到一百万时，我们还将在拉斯维加斯举办一个派对，所以也期待一下吧。
You can follow us on x x.com slash the all in pod. Chiktok is all underscore in underscore talk Instagram, the all in pod and on LinkedIn just search for the all in podcast. You can follow chamat at x.com slash chamat and you can sign up for a sub stack at chamat.substack.com. I do free bird can be followed at x.com slash free bird and oh, hollow is hiring. Click on the careers page at oh, hollow genetics.com and you can follow sacks at x.com slash David sacks. Sacks recently spoke at the American moment conference and people are going crazy for it.
你可以在 x.com 上关注我们，网址是 xx.com/theallinpod。我们的 Chiktok 账号是 all_in_talk，Instagram 账号是 theallinpod，在 LinkedIn 上你只需搜索 the all in podcast 即可找到我们。你可以在 x.com/chamat 上关注 Chamat，并可在 chamat.substack.com 注册订阅。你可以在 x.com/freebird 上关注 Free Bird，另外 Oh Hollow 正在招聘，点击 ohhollowgenetics.com 的职业页面查看详情。你可以在 x.com/davidsacks 上关注 Sacks。最近，Sacks 在 American Moment 会议上发表了演讲，获得了广泛好评。
It's pinned to his tweet on his ex profile. I'm Jason Calicannis. I am x.com slash Jason. And if you want to see pictures of my bulldogs and the food I'm eating, go to Instagram.com slash Jason in the first name club. You can listen to my other podcast this week and startups to search for it on YouTube or your favorite podcast player. We are hiring a researcher. Apply to be a researcher doing primary research and working with me and producer Nick working in data and science and being able to do great research, finance, et cetera.
这段话翻译成中文，尽量易读：
“这条推文被置顶在他的前社交平台账号上。我是 Jason Calicannis，我的账号是 x.com/Jason。如果你想看我的斗牛犬和我吃的食物照片，请访问 Instagram.com/Jason。在 YouTube 或你喜欢的播客播放器上，你可以找到我的另一个播客，名叫‘本周创业’。我们正在招聘一名研究员。如果你对从事初级研究、与我和制作人 Nick 一起工作、处理数据和科学研究、金融等感兴趣，可以申请这个职位。”
All in podcast.co slash research. It's a full time job. I'm working with us the besties and really excited about my investment in Athena. Go to Athena. Wow. See you in a while dot com and get yourself a bit of a discount from your boy, Jake Al. You know, while dot com. We'll see you all next time on the all in podcast.
在 podcast.co 斜杠 research 上的全职工作。我和我们的团队 Besties 一起工作，对我在 Athena 的投资感到非常兴奋。前往 Athena 哇哦，看一下 while dot com，从你的小伙伴 Jake Al 那里获得一些折扣。再见 while dot com。我们下次在 All In 播客上见。