How Artificial Intelligence Is Already Changing Sports, with Daryl Morey and Sendhil Mullainathan

Everyone is talking about A. I. now, but what we haven't heard is an updated, informed discussion of what, exactly, it will do to the sports world. So in our first on-stage episode, at the MIT Sloan Sports Analytics Conference, Pablo hosts an actual verified genius... and a pioneering NBA executive who gets to be sarcastically referred to as one. We discover how the Philadelphia 76ers already consult large language models, why artificial general intelligence is actually unambitious and much more. But rest assured: At this moment of tension between entertainment and efficiency, the forecast is Kyle Lowry with a chance of Gasol. Hosted on Acast. See acast.com/privacy https://acast.com/privacy for more information.

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Pablo Torre?

  This episode of Pablo Torre Finds Out is brought to you by McDonald's. The Quarter Pounder with Cheese with Medium Fries and a Drink is now $8. And look, I've chased down a lot of strange stories, but nothing quite like what's inside a Quarter Pounder with Cheese. It is 100% fresh beef, cooked right when you order it, with no artificial flavors, colors, fillers, or preservatives in the beef. The onions are hand-topped by someone who knows the perfect amount by memory, two slices of cheese and a star, and two pickles, side by side. So every bite gets both. And every time one's ordered, a cowbell sound rings in the kitchen. That's the grill master's cue to put a fresh patty on the grill. My move?

• 0:42Pablo Torre?

  QPC, fries and a drink after a long day of recording. That is my happy place. The Quarter Pounder with Cheese with Fries and a Drink, now $8 for a limited time only, only at McDonald's. For a limited time only. Prices and participation may vary. Prices may be higher in Hawaii, Alaska, and California. And for delivery. Fresh beef not available in Alaska and Hawaii. Offer not valid for delivery. This episode is brought to you by Apollo.io. A lot of the stories on this show start the same way. Something that looks pretty simple turns out to be a mess once you look under the hood. Well, it's no different in the sales world. Your team has a tool for finding prospects, a different tool for reaching out to them, and a third for keeping track of it all.

• 1:27Pablo Torre?

  On paper, that's a system. In practice, it's a salesperson spending the better part of the day copying names from one tab into another, and not much of it actually selling. Apollo.io is a platform that helps sales teams find the right buyers and reach out to them. It brings prospecting, outreach, and follow-up into one place instead of several separate tools. It's used by sales teams of all sizes, from small businesses to larger organizations. And it's built for teams who want less manual busywork and more time with buyers. If your marketing and sales teams are trying to work from the same view of the customer, it's worth a look. Sign up for free at Apollo.io. That's Apollo.io.

• 2:10Pablo Torre?

  Onnit's Black Friday Sale doesn't start until later this month, but listeners get in early. If you're new to Onnit, go to Onnit.com and

• 2:19Speaker 01

  Use code PABLO for 30% off your first order starting today. If you've never tried ONIT, start with AlphaBrain. It's their daily nootropic built to support focus, memory, and mental clarity on days when you need to be locked in, whether that's powering through a tough workout or staying focused during back-to-back meetings. Get early access and save 30% off your first order at onit.com. That's O-N-N-I-T dot com. And use code PABLO. Some exclusions apply.

• 2:56Pablo Torre?

  Welcome to Pablo Torre Finds Out. I am Pablo Torre, and today, we're going to find out what this sound is.

• 3:02Speaker 02

  And anger is all that drives Sixers fans, as far as I can tell.

• 3:07Speaker 01

  Right after this ad.

• 3:28Pablo Torre?

  So I need to jump in at the top of this episode to give you a warning. A couple of weeks ago, I was asked if I wanted to record a live episode of this show at the Sloan Sports Analytics Conference, which is a conference, if you did not know, that started at a lecture hall at MIT when I first attended it, 16 years ago now. But quickly, it moved into a convention center in Boston on account of the thousands and thousands of people who wanted to actually go. And many of those people annually include the most powerful people in sports. At this point, we're talking league commissioners, billionaire owners, Barack Obama one year, pretty much every data-driven team executive in American sports and beyond shows up.

• 4:10Pablo Torre?

  But the guy presiding over all of this, the conference's co-founder, is Daryl Morey. Daryl is now the president of basketball operations for the Philadelphia 76ers, and he is also, it turns out, a listener of this show. And so I do feel journalistically obligated to point out that the Sixers are now about 20 games under 500, having a truly horrible season, as we'll discuss. But the thing I really wanted to find out about at Sloan, even more pressingly, was a question I did not have a good answer to, I realized. Despite how much everybody is always talking about large language models, LLMs, like ChatGPT, and also when the robots are finally going to achieve

• 4:53Pablo Torre?

  artificial general intelligence, AGI, and, you know, think like human beings actually do. All of which is to say, what I wanted to find out about today is what AI is actually doing to sports in particular. Like, what's the signal here, as in the relevant information worth knowing? And what's just noise that we should discard? And so, the warning I need to give you is the same warning that I gave our live audience in Boston as I was introducing Daryl and my other honored guest today, a man named Sendhil Mullainathan, who is the perfect person to join us and demystify this subject.

• 5:35Pablo Torre?

  This is gonna be the nerdiest episode of my show. I'm glad to have all of you here, listening and watching. This will be on YouTube, I presume, and you will then get to see how nervous Daryl Morey is.

• 5:49Speaker 02

  I'm nervous, yes.

• 5:51Pablo Torre?

  You've been complaining about this all weekend.

• 5:53Speaker 02

  I just, Sendhil.

• 5:55Pablo Torre?

  I know.

• 5:56Speaker 02

  I hope I'm not insulting you by...

• 6:00Speaker 02

  Genius grant is very intimidating.

• 6:02Pablo Torre?

  It is legitimately fun to be here alongside an actual certified genius.

• 6:08Pablo Torre?

  And also an executive who gets to be sarcastically referred to as one.

• 6:15Speaker 02

  Is that the only way you could be labeled genius is the MacArthur?

• 6:18Pablo Torre?

  I think so. We've copyrighted it, so.

• 6:20Speaker 02

  Oh, nice. He even said "we."

• 6:24Pablo Torre?

  But he's on the MacArthur Foundation board. I mean, Sendhil's bio, we could just read his bio for a while. But just to catch you up on why Daryl and I are both incredibly excited to be sitting next to Sendhil, MIT professor, splitting his time between electrical engineering and computer science and economics, focusing on the intersection, I guess, broadly speaking, of algorithms and people, co-author of arguably the most highly cited economics paper in the 21st century on differences and differences estimation, which is a thing I definitely understand.

• 6:56Speaker 02

  You can subtract, right?

• 6:59Pablo Torre?

  And also landmark papers on algorithmic bias and poverty in the criminal justice system, and now training his brain, his human brain, on artificial intelligence. And also, Daryl's here. So, so Daryl.

• 7:11Speaker 02

  He's killing me.

• 7:12Pablo Torre?

  But the resume for Daryl is...

• 7:14Speaker 02

  Hasn't won yet.

• 7:16Pablo Torre?

  Well, historically, right, over 60% win rate as a GM. This is, though, barring, I don't know, some act of God or the devil, your first losing season that you're grappling with.

• 7:31Speaker 02

  It is my first losing season in, I think, 17 years, yeah, so.

• 7:36Pablo Torre?

  Feel vulnerable being here on stage?

• 7:37Speaker 02

  I do. I feel very vulnerable, yes, yes. Plus, you're a good interlocutor.

• 7:42Pablo Torre?

  That's right.

• 7:42Speaker 02

  Whatever they say, yeah.

• 7:43Pablo Torre?

  I do want to interlock you t with you, if that's how I betray my own diploma. How long have you been using large language models? I want to start with this first, and I want to also establish just the very basic premise of how long you've been using it, and also how are you using AI in your job as president of basketball operations currently? How does that look?

• 8:07Speaker 02

  So I've used them a little longer than the OpenAI moment, which was, what, November two years ago, three years ago now? Um, with the GPT, I believe, three, you could get some early access. I wasn't really special there, except I knew about it. I knew people who knew about it, and it seemed very cool. I, I, even I didn't realize how cool until it went public. I think that was like sort of a moment that even surprised the AI researchers that I think that they were like, yeah, this is really cool. But then, once the public got a hold of it, it was very cool. And then, in terms of my job, we use, um, we've used a version of AI for a long time. We mentioned this on an earlier panel. The AI is just forecasting.

• 8:51Speaker 02

  Uh, my job is making good decisions. It's all about forecasting. Um, we've used machine learning models for forecasting for a long time. And, and primarily, the big areas that would be most, uh, relevant would be things like forecasting draft picks. There are a whole bunch of different forecasting techniques. Traditional regression, linear regression, you know, tree models, you know, graphical models is like a whole set that have been tried. Uh, and they're all like a flavor of forecasting, of which, uh, even goes into large language models later.

• 9:30Speaker 02

  Um, and then, uh, for like pick and roll, uh, identification in, uh, computer vision. Um, turns out even humans can't agree on what a pick and roll is or isn't. The most basic one everyone can agree on, which is one guy hits another guy, which keeps him from guarding his guy, and then something happens that, but there's all these like phantom pick and rolls, and you act like you're gonna set it and you don't. You, even humans can't identify it, and computers do a pretty good job, but not a perfect job at that as well. Uh, and then on the LLM side, the traditional stuff is helpful. Coding, um, you know, speeding up writing projects, um, things like that.

• 10:12Speaker 02

  Those are ones we use, and then there's some shooting stuff as well, so.

• 10:16Pablo Torre?

  But just to be, uh, sort of. I don't know, top line here. When you're making a decision, and insert your favorite Sixers decision here, are you asking an LLM? For their input?

• 10:31Speaker 02

  So we, two answers there. We absolutely use models as a vote in any decision. And how much of that decision depends on, you know, how much the assumptions behind those models don't change, and their past success rates. So if you have a highly successful model for picking draft picks, and we think that the game, you know, Evan hasn't changed the rules yet, and so the game isn't changing.

• 10:59Pablo Torre?

  Evan Wash, who's in charge of the league office of defeating you?

• 11:03Speaker 02

  Yes. Then, then the models get a lot of weight in those decisions. It turns out LLMs do fairly well at prediction. They, they still are not beating human, like super forecasters, they're called, like in Human Judgment Project talks about it. But they do add signal over just scouts and things like that. So we'll, we'll treat them almost like one scout. Now, over time, if, if it's shown that they have a better track record than scouts, we might wait the LLMs or use multiple LLMs as one or two, two votes out of the process. So it turns out, I'm building on a lot of things that Sendhil knows. And you know that, you know, multi-model approaches can put you more on the decision frontier,

• 11:48Speaker 02

  the optimal decision frontier. And when I say that carefully, you get very similar accuracy with lower risk by using multi-model approaches. And so that's why we do that.

• 12:01Pablo Torre?

  I would just like NBA Central to aggregate what Daryl just said, which is that he asked ChatGPT for help on trades.

• 12:09Speaker 02

  Yeah, let's not, please not aggregate.

• 12:10Pablo Torre?

  Ah, I'm just trying to, you know, pay for my kid's tuition, Daryl.

• 12:16Pablo Torre?

  Sendhil, look, part of the larger conversation here, I was in San Francisco for All-Star Weekend. The word, the word cloud over All-Star Weekend was artificial intelligence, was AGI.

• 12:27Speaker 03

  Yeah.

• 12:28Pablo Torre?

  Artificial general intelligence specifically. Your view, though, on the ambition of AGI, thinking like a human, it sounds like what to you, given your, your research?

• 12:40Speaker 03

  It sounds unambitious. Yeah, I think that AGI on the surface feels like an ambitious goal, but it's a shockingly unambitious goal. Let me articulate why. We already have people who can think like people.

• 12:55Speaker 02

  People who can think like what?

• 12:56Speaker 03

  People.

• 12:57Speaker 02

  Okay.

• 12:58Speaker 03

  Like, we have that, and we have ways to make more of those people. And they're fun ways, actually.

• 13:05Pablo Torre?

  That's the next panel.

• 13:06Speaker 03

  That's the next panel. But what I think is missing, and you've done a lot of this. What I think we need is algorithms that can do things people could never do. And to me, that's the fundamental expansion that we're gonna get. We need algorithms that can see things that we can't, that can notice things that we never could. And the reason I think the AGI part is unambitious is it's also too hard in the sense that we've had algorithms, vectors along which algorithms can see things that we absolutely can't. And those were actually the easiest paths to improve performance. To exactly do what we do with very high fidelity,

• 13:49Speaker 03

  that's actually really hard and not clear there's that much gain. And so, let me see if I can give a good example. My favorite example is The Wizard of Oz. It's by far my favorite example. How many of you have seen The Wizard of Oz? Raise your hand. Okay. How many of you have read the book? All right? How many, you've read the book? How many of you have read all 30 of the books?

• 14:07Speaker 02

  No. I read one other, and it was weird.

• 14:10Pablo Torre?

  I've just found out there are 30 books.

• 14:12Speaker 03

  Exactly.

• 14:12Pablo Torre?

  The Wizard of Oz Cinematic Universe.

• 14:14Speaker 03

  And in fact, it gets even weirder. There are 30 books. 14 of them were written by Frank Baum. 15 of them was written by this woman, Ruth Plumley Johnson. And the 15th book is the source of a big literary kerfuffle. Who wrote it? Frank Baum died while that was being written. And so, amongst literary critics, they just spent a long time close-reading that book. And they couldn't get, they couldn't agree. And so in 2002, there's a article in, 2002, think of how early this is in it. An article in this magazine that says they have done NLP. And you read the analysis and it is so clear, like with 100% accuracy, that the algorithm can see that until chapter 12, it's all Baum.

• 14:58Speaker 02

  Wow.

• 14:59Speaker 03

  After chapter 12, it's all Ruth Plonky Johnson. How can it be that an algorithm can notice with so much clarity, something that humans have utterly not noticed in our own native domain? And we see that again and again, which is algorithms are fantastic at picking up signal on the kind of things we didn't even know to notice for. Cause they notice aggregates, they don't have prejudgments of where to look for signal. So to me, I think the ambitious AI goal is actually to find algorithms that can help us. Like I loved what you were saying about how you, in scouting, you have another scout. I think Pablo, you use this phrase. I would love it if there was another scout, not of the players, but as you referred to it, self scouting, something that scouted me.

• 15:42Speaker 02

  We do that, we have a self scout, you know, just to flag any, like if another team was analyzing us, what would they, what would they find?

• 15:50Speaker 03

  Wait, so this is fantastic, yeah. Explain that, yeah.

• 15:52Speaker 02

  Can I go back and then come back to that? Cause we, you mentioned something that we say all the time, which is that on a single game, humans do better than any algorithm. Uh, but similar to your L Frank Baum example, um, uh, algorithms are very good at seeing these two to 5% patterns uh, that uh, humans miss. Cause we, we see big things, we see big patterns, we see, and we, and we, we find big patterns when there aren't any, and there's all these kinds, all these kinds of things. So we have automated uh, tools that say, when I'm about to play this team, here are the kinds of things, you know, that player is very efficient. We should limit this opportunity here. So we flip that on its head and self scout and say, what?

• 16:37Speaker 02

  When they play us, what are they likely saying? We don't know for sure. That's a little different.

• 16:41Speaker 03

  Oh yeah, it's a little, what I would love is a model of Daryl that you look at. No, no, but that you look at and that says to you, hey, just to you, hey, I think this is the kind of situation where you often do this. Like something that helps you get candidate biases of yourself. And in a way, what I like about that is it doesn't need to be perfect at that. If it was 20% right at that, boy, what value add? Because it'll notice the type of things we might not notice about you. So I think once you think of algorithms as where do you deploy them to find things we cannot look for? I just think it's going to open up a huge avenue of stuff.

• 17:19Speaker 02

  Can I ask a question? Because you give an optimistic take of where we should take AI or even AGI, which left a role for humans, left humans at the center. And I know that as someone who plays a lot of chess, that was also the belief in chess, that there would be this role for humans over time. And in fact, there was a time where a human-machine combo could be the best.

• 17:42Speaker 03

  The centaur.

• 17:43Speaker 02

  A centaur, yes, yes.

• 17:44Speaker 03

  One of the great terms of art for anything. Humans plus a computer being the most dominant combination of any just humans, just computers. They were the best.

• 17:54Speaker 02

  It is called centaur chess, for example, as you say. But it was in the early 2000s where that went away. And actually, any human involvement would mess up. People would beat a, would beat a, a machine with no human involvement would beat any human involvement. And so that, that I worry that, you know, we may face that as well.

• 18:13Speaker 03

  So I, I love the chess example because it so clarifies many things. There's this, there's this term, though a bit technical, I think is very helpful, called closed world versus open world problems. Closed world problems are ones where everything is specified. Let's say chess satisfies that, but I'm going to come back in how even chess may not satisfy that in a second. But let's say chess satisfies that. All the rules are known, all the objectives are known, everything is there. We will never beat an algorithm in a closed world problem. That, the idea that we're going to beat it, conditional on rules, conditional on things, is crazy. I mean, you can just compute your way to stuff. And there's an analog to closed world problems, where closed world problems, where maybe we have enough data. Again, we're not going to beat algorithms.

• 18:58Speaker 03

  But most phenomena in the world are not really closed world problems. They're open world problems. What that means is, what are the things that you can do? The moves in chess are prescribed. The moves in life are not prescribed. And some of the most genius insights of someone realizing, "Hey, I can actually make this move." Like, this is a feasible thing to do in this situation. Similarly, the objectives are not specified. And it may seem like the objectives are specified, but if you think of some of the great innovations that people have had, it has been realizing, "Oh, that's not the problem we're trying to solve. This is the problem that we're trying to solve." Like, "I am not in the burger business. I am in the customer satisfaction business. I'm not in this business, I'm in this business." And so specifying objectives, specifying moves, specifying the rules of the game.

• 19:43Speaker 03

  Once you've done that, the algorithm will clearly win.

• 19:46Speaker 02

  So you're basically saying if we're playing centaur chess, the computer doesn't know we can still flip the board.

• 19:53Speaker 03

  Right. And another example of chess is, is chess about winning? For example, suppose you're playing with a friend. In one sense, the goal is winning. But in one sense, the goal is to really have like a fun game. Can you build an algorithm that'll have a fun game with you? Now, that suddenly that gets interesting. And there are people who do chess algorithms who have been trying to figure out, "How do we build a fun game algorithm?" And so that, suddenly, that's no longer in the realm of just computing. You've now got to actually get into it, and people get involved.

• 20:22Pablo Torre?

  But that brings us right back to sports.

• 20:24Speaker 03

  Yeah.

• 20:24Pablo Torre?

  So to me, like, the problem, the tension of our time that Daryl has had a hand, through this conference, actually, in shaping, is this tension between entertainment and efficiency. And I always think about, when I mentioned the league office trying to keep up with people who are trying to innovate, there is this push and pull of how do we stay ahead of the people who are the most clever when solving these wicked problems? These open questions? And so when it comes to how we're figuring this all out, right? Currently, we're all set up so that Daryl's over there, the players are trying to catch up and figure out, "Okay, how do we fit into this?" And then the league office is somewhere else, right? Is there a way, Sendo, to actually acknowledge that

• 21:09Pablo Torre?

  a truly optimal goal here is for everybody to be aligned on what the best outcome is, which involves entertainment?

• 21:19Speaker 03

  Yeah, and I'd be curious what you say about this. I do think part, as a fan, I'm like a big superfan. I'm a superfan of you.

• 21:27Pablo Torre?

  Sendo had an account on Real GM on the Sixers message board just to out you immediately.

• 21:34Speaker 03

  Yeah, yeah, more than an account. I was so...

• 21:36Speaker 02

  What's the account ID?

• 21:37Speaker 03

  Well, no, it gets worse, Daryl. No, no, it gets much worse. This is when I was trying to get tenure at MIT. I was so obsessed with Real GM that I then became a moderator for the Sixers message board.

• 21:48Pablo Torre?

  Which is like genuine sicko behavior, by the way.

• 21:50Speaker 03

  Yes, yes.

• 21:50Speaker 02

  Was this when Sam was there?

• 21:52Speaker 03

  No, this is 2000. This is when I was trying to get tenure. Yeah, I should not have been doing this. It was really quite...

• 21:58Speaker 02

  You seemed to have done fine.

• 21:59Speaker 03

  Yeah, yeah, I hope, yeah, yeah. I won't give away my user ID. But I do think, as a fan, one of the things...

• 22:08Speaker 02

  Well, you can just put NLP on it and figure it out.

• 22:10Speaker 03

  Exactly.

• 22:11Pablo Torre?

  Well, we're gonna find out, Daryl, don't worry.

• 22:13Speaker 02

  Natural language processing.

• 22:15Speaker 03

  Yeah, this is a Frank Baum situation all over again. What I do think, and I'm really curious your guys' opinion on this, I think as a fan, what I've noticed is that wins matter. But it's shocking to me how much of my pleasure comes from a bunch of other things. The underdog story. The person who just shouldn't be scoring this much but scores this much. Like, and I was happiest as a Sixers fan during the process years, which is a weird thing to say. I would watch every game, and I don't know what that reveals about sport, but it...

• 22:49Pablo Torre?

  It reveals that this season for the Sixers is gonna be a really enjoyable one for you.

• 22:53Speaker 03

  No, no, no offense, Daryl, but it has not been. And I'll tell you why it has not.

• 22:57Speaker 02

  Me neither.

• 22:58Speaker 03

  Yeah, and we're in the same boat. It's not been because... The storylines have not been captivating. And if I think of sports as entertainment, like I would love to know even, I would love to turn an algorithm on, what makes a captivating storyline? There are just some storylines that just keep you hooked. You want to go back for the next game, you want to know what's going on. And so is that part of the objective function? Or is that an illusion? Like, look, you guys are thinking to yourself, storylines matter, we've looked at the data, there's only one thing that matters, it's wins. I don't know, I'd love to know.

• 23:28Speaker 02

  I don't focus on wins, I focus on championship. And I would say the one, the Philly fans surprised me in this manner. So I guess it's two seasons ago now. We were up 3-2 on the Celtics. Objectively, in Vegas, we were at the highest odds to win the championship that year. Because they felt that the team out of the East would win, I guess. It wasn't like above 50. I've scraped 50 when we were up on the Warriors in 18. And we were up 3-2, obviously, you know, we then lost a close game at home, which was very frustrating. And then we had a very bad loss in game seven.

• 24:12Speaker 02

  And, you know, it's a little bit similar to the LeBron, Michael Jordan argument. Objectively, people should feel better about that. Then the next season, we had a very entertaining Knicks series, like almost famously entertaining. I think it was voted best series that year. And for me, it was just stressful, but for everyone else, I'm glad you enjoyed it. It was very stressful. And we lost in six games, you know, to a Knicks team that was not as good as the Celtics team we lost to the year before. And I was very down after the loss. And I was like, man, people are going to be so angry. And they were angry, obviously, everyone wants us to win. But they were less angry than the year before.

• 24:56Speaker 02

  And anger is all that drives Sixers fans, as far as I can tell.

• 25:01Speaker 03

  Aggregates that. Anger and irrational love.

• 25:04Speaker 02

  Yes, yes, the aggregators are going to have a field day with this, Pablo. I know you're excited.

• 25:09Pablo Torre?

  My kid's going to go to private kindergarten.

• 25:13Speaker 02

  But they were less angry was my perception. I don't know for sure. It's not like you surveyed everyone, how angry are you? And that really threw me. Because to me, I'm just trying to win the title. And so the year before, for our, the way we measure it was objectively better, even though still a zero on the Boolean scale I'm judged on. So it should all be the same, and that surprised me.

• 25:35Speaker 03

  Can I put on my behavioral sciences hat for a second? I'm just gonna speculate. I'm just gonna purely speculate.

• 25:39Speaker 02

  Well, you're a Sixers fan, so you can be... Right, you can even...

• 25:43Speaker 03

  No, which is that I even think negative emotions are fine. I think the thing that is dangerous is disinterest. And if you think about sports, it's easy to dismiss sports as entertainment. But what else in our culture can have people of very different backgrounds, different generations, talk to each other and feel they've meaningfully touched, you know, communicated, you know? Had a meaningful meeting of the minds. You know, parents and children, grandparents. It's quite a unique place as a cultural artifact. And the main thing that it does, if I think of its core contribution to society, is it provides conversation. And I think the worst thing is, anger is good, you guys haven't talked about.

• 26:27Speaker 03

  Like during that, after that Celtics thing, you meet a Sixers fan, they, like, it was easy. You knew what you would do. You would complain. And complaining with another person is its own form of like connection. It's those periods when you don't really have anything to talk, like, it's disinterest? This feeling that the story is old, it's a kind of stale, it's in that...

• 26:48Speaker 02

  But we're always interesting.

• 26:49Speaker 03

  Yeah, no, right, right.

• 26:51Speaker 02

  The curse, actually.

• 26:52Speaker 03

  Both sides, yeah.

• 26:52Speaker 02

  Both directions.

• 26:53Pablo Torre?

  Is that.

• 26:54Speaker 03

  And it is always interesting. And so I wonder to what degree one should just be maximizing engagement? I know that we've had bad experiences with that.

• 27:01Speaker 02

  This is Pablo's department.

• 27:02Pablo Torre?

  That's right. Sendhil, if you want to trash any other geniuses, feel free.

• 27:16Pablo Torre?

  This message is brought to you by Apple Card. With Apple Card, you earn unlimited daily cash back on everyday purchases like groceries, or merch, or tickets to the game. Plus, it can be used anywhere MasterCard is accepted. No matter your team, no matter where you shop, Apple Card is here to help you tackle game day. Apply in the Wallet app on your iPhone today. Subject to credit approval. Apple Card is issued by Goldman Sachs Bank USA, Salt Lake City branch. Terms and more at applecard.com. Gifts mean more when they have the power to give more. They can inspire more discovery, give more confidence, and unwrap more of who you are. This Black Friday, give a gift that goes beyond the box. The Dell XPS 13 Laptop.

• 28:01Pablo Torre?

  With a beautiful design and cutting-edge performance, it helps you unlock more possibilities. It's the thinnest, lightest XPS laptop yet, with touchscreen, a backlit keyboard, and long-lasting battery life to power you through your day. Built with a durable aluminum chassis, weighing just 2.2 pounds, and Intel Core processors, it's fast, reliable, and portable enough to keep up wherever you go. Visit dell.com to explore the possibilities with XPS. While shopping, you'll also find great perks like Dell Rewards, fast free shipping, premium support, and financing with flexible payment options. Plus, you can find great deals on monitors and accessories. That means you can score a whole new setup now for less. This Black Friday sale is one you don't want to miss.

• 28:46Pablo Torre?

  Head to dell.com/deals. That's dell.com/deals.

• 28:55Pablo Torre?

  I'm pretty sure this won't shock anyone out there, but buying a car is just a hard process. You have to figure out what you want from thousands of options, then you have to find somewhere that's offering a good deal, then you get hit with unexpected fees. But let's just break it down and think about how you'd describe your ideal car to a friend. You know, something like, good gas mileage, four-wheel drive, reliable, under 30 grand. Luckily, CarGurus makes it that easy. Just describe it to CarGurus the same way. With Guru, you search in your own words and you get listings, real listings, that match. No endless filters, just the car that fits your life. CarGurus also helps you shop with more transparent pricing,

• 29:37Pablo Torre?

  allowing you to see when dealer fees are included so you can compare listings with greater confidence. And with more than 4 million listings, CarGurus has the biggest selection of cars. So it's easier than ever to find the right car and the right deal. It is no wonder CarGurus is the number one most visited car shopping site, according to SimilarWeb's estimated traffic data. So buy or sell your next car today with CarGurus at cargurus.com. Go to cargurus.com to make sure your big deal is the best deal. That's C-A-R-G-U-R-U-S dot com. Cargurus dot com.

• 30:17Speaker 04

  With the Discover Cash Back Card, it's payback time when you earn cash back on everyday purchases. Activate and earn 5% cash back at different categories each quarter on up to $1,500 in purchases. That's 5% cash back at different places each quarter, like grocery stores, on gas, and at restaurants. It pays to discover. Terms apply. See discover.com/five for details.

• 30:48Pablo Torre?

  But I actually want to bring it back around. So like the larger picture here that we're sort of saying without explicitly saying it is that the nerds won, okay? Right? Like the whole debate about like, "Oh, when are the Lakers gonna show up at Sloan?", which is a headline for a long time. The last holdout of this conference from the basketball ops department, used to be the Lakers a dozen years ago. Then everybody, everybody shows up.

• 31:10Speaker 02

  I think Jeanie Buss came, actually, as the first Laker.

• 31:13Pablo Torre?

  Yes. But I say that because when it comes to the distribution, the wide, broad access to LLMs, and I want to get to beyond LLMs in a second here, but when it comes to that, every team, even the most caveman, old-school team, having access to ostensibly an army of robot barrels, isn't the person who should be worried the most is the guy who founded the conference? Who had, as his competitive advantage, this natural curiosity and skill and career premised on doing things that you couldn't just automate. Should Daryl be worried, I guess, Sendhil? Is that the subtext here of everybody having access to these devices?

• 31:57Speaker 03

  The short answer is definitely not. And it's worth talking through which experts should be worried and which experts shouldn't.

• 32:03Pablo Torre?

  Please.

• 32:03Speaker 03

  Some experts absolutely should be worried. There are experts where the nature of their expertise is the reliable, repeated application of some tacit knowledge. So there are, you know, a very good doctor is a reliable, repeated application of tacit knowledge about diagnostics. Now, it's not that those algorithms today can do that. I think we're far, but it is also totally plausible that we will get to the point where...

• 32:33Speaker 02

  You mean like reading an x-ray?

• 32:34Speaker 03

  Reading an x-ray, yeah. It's like, it's easy to say that's going to happen next year, but it's, that's not going to happen, but it is definitely, like, it is... Do not tell your kids to go into radiology, so. You'll be happy, since we both had moms who told us to go into medicine.

• 32:50Pablo Torre?

  That's right.

• 32:50Speaker 03

  The nerds will win over the doctors.

• 32:51Pablo Torre?

  Sendhil and I bonded over the trauma of not becoming a doctor in his office yesterday. Yeah, it's real.

• 32:58Speaker 03

  But so that repeated application of tacit knowledge. On the other hand, I think the genius of someone like Daryl and experts like that are people who can take an ill-formed problem and actually formulate it in a way that it becomes tangible and actionable. So it's easy to say, oh, the three-point shot. But it was recognizing in this ocean of stuff, let's focus on this part of the problem, is actually very, very, very hard. The reason algorithms are complementary to that, it goes back to the chess thing. Once you've formulated the problem, we can now use algorithms to bulldoze through it, which then raises the enormous returns to... Problem formulation.

• 33:43Speaker 03

  And I think people who can bridge the inchoate, underspecified, who knows what's even going on here? And bridge it back into the I've now formulated into a data set or a specific type of activity. That skill is going to go way up. And so I think the data science skills that are going to be worth less are the people who, once it's formulated, do stuff with it. But that's not your genius. And that then, does that make sense to you?

• 34:08Pablo Torre?

  Yeah, and even just like, you know, Daryl, I had the opportunity, I was at the Sixers Celtics game with you. And I was very curious, for those who remember Larry Kuhn. Larry Kuhn, a retired computer scientist who had written the seminal text for understanding the NBA's salary cap and collective bargaining agreement, the NBA Salary Cap FAQ. Larry was such a scarce resource. That body of knowledge used to be so scarce that everybody would consult this like blog spot page. And

• 34:38Speaker 02

  It was Larry and just a very few people at the league office and a few teams at the time, yeah.

• 34:42Pablo Torre?

  Yeah, but now ostensibly, why can't an LLM analyze the CBA? And take the jobs of the many humans who are currently tasked in the way that lawyers are tasked with analyzing documents?

• 34:57Speaker 02

  In fact, it can. And so he had me give it what I thought was a medium hard problem. And it answered it flawlessly. This is on 4.5, the latest from OpenAI. Then we gave it a medium plus hard problem. It also answered flawlessly. And then I was with Monty McNair from the Kings. He formulated one that he thought was hard, and it did fail the hard one. So I think we, yes, we have the same problem that law firms have, which is even though it gets the answer 98.9% right, you can't hand it to a client who's paying you that much money unless it's, well, nothing's 100, but you probably need a higher sigma on your, or at least to say there was a human who looked at it. Like, you'd be like, oh, you just took the algorithm.

• 35:42Speaker 02

  You're like, yeah, that doesn't work. That will work, though, eventually. Or, you know, where people will be like, that's a high enough sigma. I'm going to take the answer from the algorithm.

• 35:52Speaker 03

  And then I'd add one thing to that. It's the problem as LLMs they are today is not just their error rate, but the inscrutability of their errors.

• 36:02Pablo Torre?

  Explain that.

• 36:02Speaker 02

  Yeah, explain that, yeah.

• 36:03Speaker 03

  We have almost no way of knowing the form factor and where their errors are going to come from. That is, you tried some hard ones and got it to fail. I bet if we had an hour, we could find some easy ones that it fails on. And it's unclear to you why it failed on this easy one? We got this easy one.

• 36:20Speaker 02

  So this has been my test since the LLMs came out. And only 4.5 is the first one to have solved this. I would give it, I've since the OpenAI first one, I've given an artificial Monty Hall problem to the LLMs. And it's perfect because they're trained. There's been so many articles written on it. It's trained on a billion articles and the answers always switch in these articles.

• 36:43Speaker 03

  That's fantastic.

• 36:43Speaker 02

  Well, with some tiny exceptions. So I've been giving it a Monty Hall problem where, and just so folks know that, three doors. You pick a door, I'd pick door one. The host then opens another door and says, "Okay, you can either keep the door or do you want to switch?" And it turns out if you switch, you get 2 out of 3 probability. If not, most of our audience probably knows this. But the key to the whole Monty Hall problem is Monty Hall knows which door to open. So I formulated, I have to change, I put it in sacks. And then I have a person just walk by and say there's nothing in a sack, but without any knowledge of the others, and say, "Do you want to switch?" In that formulation, it's no advantage to switch. And 4.5 was the first one that got it right. All the other ones were like, "Switch."

• 37:26Speaker 03

  Yeah, yeah, fantastic.

• 37:27Speaker 02

  And so that's been my little test for how advanced they're getting. But those are the kinds of problems you're talking about, where like, change a little assumption and it changes a major part of the answer.

• 37:37Speaker 03

  Yeah.

• 37:37Speaker 02

  They will miss it because they've been trained heavily on the correct answer based on what they knew.

• 37:44Speaker 03

  Yeah, it's tempting to think that they're reasoning their way to an answer. When there's something else they're doing, we have this paper we're finishing called Patempkin Understanding, where it's very easy to generate these little Patempkins. Where it seems to get this right, then why is it getting this other thing utterly wrong? And you can start algorithmically generating and you see it's kind of like Swiss cheese, their knowledge. This thing.

• 38:07Speaker 02

  This is the New York driving.

• 38:09Speaker 03

  Oh, this is another paper we're just finishing now. So it's like, so it's like an example of this is like, you can, you can just give it a bunch of examples and say, What's an A B A B rhyme scheme? Great. And then you write a little thing. Take out a word and say, can you fill this in to rhyme it?

• 38:23Speaker 02

  And they can or cannot?

• 38:25Speaker 03

  Sometimes it gets it right, sometimes it doesn't. And when it doesn't get it right, you take that word and you say to another instance, does this word rhyme with this word? And it says, no. So it's like, there's incoherence underneath the object.

• 38:38Speaker 02

  Well, that's where the inference time comes in.

• 38:40Speaker 03

  That's where you hope.

• 38:40Speaker 02

  They just repetitively ask themselves questions before they answer the first time, right?

• 38:45Speaker 03

  So you're hoping that those type of tricks kind of get this stuff out of the system.

• 38:48Speaker 02

  But it is a kludge. The more I go into the inference time stuff, it's basically a kludge on maybe a fundamental problem, but I'm not quite sure.

• 38:57Speaker 03

  No, it's definitely a fundamental problem. It really is. I think what's happening in this space is that when you play with these L L M's, it's just so amazing. They feel like they've understood. It's hard not to get pulled in and feel like, oh, my God, this is a thinking creature.

• 39:10Pablo Torre?

  But what you're saying is that the fact that it's a language model talking to us has fooled us into thinking that there is a depth that is not actually present.

• 39:18Speaker 03

  That's exactly right.

• 39:19Speaker 02

  But that's probably true of most humans, too.

• 39:25Pablo Torre?

  Fortunately, that is.

• 39:27Speaker 02

  This is like in interviews. This is my favorite interview tactic is they, I don't care what they bring up. I sadly might know a little bit about everything and I'll just like start asking. And if they can't get past like two layers and you're like, okay, they don't really understand it.

• 39:40Pablo Torre?

  But I do want to get to just the job, right? So, okay, so there are versions of what I imagine that C B A problem is, where it's like, could you have an L L M call a play? And then you consult in the huddle, okay, this is what our robot assistant coach is proposing. You have a person check it. I can understand they're at the table in every decision. But just the job, Daryl, of what it means to be a president of basketball operations, such that Sendhil has faith in your ability to persist past the broad access of everybody having these robot assistant G M's, coaches and everything else. How much of your job is dealing with incoming, like, bad ideas, frankly?

• 40:23Speaker 02

  Yeah, we often, when I say we, I mean like me and some other GMs across sports. We feel often our job is sort of bad idea whack a mole. It was like, because ideas like form in these little narratives and they can be good or bad ideas, but part of our job is to, you know, smother the bad ideas in the crib before they, they be, you know, I, I will say, I won't say the, um, the assistant, but when I had Kyle Lowry way back early in his career, what made him a great player was, you know, his tenacity and everything, but it also made his personality somewhat challenging just to assistant coaches.

• 41:05Speaker 02

  Um, and basically he, we weren't winning, we were winning about half our games. And then Kyle went out and we won six in a row. And a narrative started forming, we might be better without Kyle Lowry, which was so absurd in the data that it wouldn't even be something anyone who looks at data would consider, but I could see how, you know, us, you know, we find patterns anywhere, could see that. And I had to like, work hard to like, to like, be like, no, like this guy, like we had an easier schedule. We had all the different things that would go into that. And so that's, but that happens like multiple times a week at least, if not more,

• 41:50Speaker 02

  where you're just trying to keep things on like, let's get the big things right and not let these narratives form that might harm us.

• 42:06Pablo Torre?

  Did you know over 75% of Americans are chronically dehydrated? And 90% don't get enough potassium, which is a key electrolyte responsible for energy, muscle function and clear thinking? Well, that's why you can be drinking water all day and still feel tired or foggy or just off. And while most hydration packs really load up on the sugar, instant hydration contains zero sugar. There's no glucose spike and no sugar crash. And that is really important to me because it not only gives me electrolytes without loading me up with sugar, but it also helps me avoid that late afternoon crash. You know, that time of day when your eyes start drooping as you reply to yet another email and you need something to get you back on track. Just mix a packet of Instant Hydration with water,

• 42:50Pablo Torre?

  and I am feeling ready to push through to the end of the day. For a better way to stay hydrated, go to instanthydration.com/ptfo and use my promo code PTFO for over 40% off your first subscription order. It's Instant Hydration's best offer available. That's instanthydration.com/ptfo, promo code PTFO. Life in 2026 is tough. We all have our struggles and we could all use some help. But trying to figure out how to get the right mental health treatment for you can feel overwhelming. Talkiatory helps you move from "I know I need help" to actually having a psychiatrist who listens and a clear, personalized treatment plan. Talkiatory is 100% online psychiatry practice

• 43:35Pablo Torre?

  that provides comprehensive evaluations, diagnoses, and ongoing medication management for conditions like ADHD, anxiety, depression, and more. With Talkiatory, you can meet with a licensed psychiatrist who takes the time to understand what's going on, builds a personalized treatment plan, and supports you over time with consistent, evidence-based care. And all 800-plus clinicians are in-network with major insurers, so you can use your existing insurance instead of paying monthly subscriptions or out-of-network costs. Head to talkiatory.com/ptfo to complete the short assessment and get matched with an in-network psychiatrist in just a few minutes. That's T-A-L-K-I-A-T-R-Y.com/ptfo

• 44:20Pablo Torre?

  to get matched in minutes. Talkiatory.com/ptfo. Cozy makes furniture for the part of life that nobody warns you about. Getting the couch into the room, making the room feel like you, then actually living on it, spills it all. With Cozy, your home can grow with you by adapting to new spaces, new styles, and every era of your life. It's modular furniture, so you can actively adjust your furniture to fit any space. It's all built around making the entire home comfortable and easy so that your stuff works with your life, not around it. The covers are washable and interchangeable, so a refresh is only one wash away, and the spill goes from panic to shrug. And it all ships to your door in easy-to-move boxes. Plus, Cozy's free one-on-one design consultations

• 45:03Pablo Torre?

  make the whole home vision a lot less intimidating. Cozy has everything you need to make your home feel like it has a plan because Cozy makes every part of the process easy. So, visit Cozy today, that's C-O-Z-E-Y dot com, and make yourself at home.

• 45:26Pablo Torre?

  Sendhil, I want to move beyond LLMs because I know so much of your research is not merely these chatbots that are, again, the talk of every conference you'll go to at this point, but it's also supervised learning and how to train these models once you now account for a more realistic version of what being an executive in sports would be like. Can you explain supervised learning and how your fandom of sports has led you to see sports through that lens?

• 45:53Speaker 03

  Yeah, so I think supervised learning differs, I'll do one thing that might be helpful to people. Supervised learning is I collect a bunch of data of various kinds and I ask the algorithm, what in this data predicts this particular outcome? And as long as you can specify an outcome and some variables to predict with it, these models can sort of really start finding signal that we never even imagined. And so I think the playbook that emerges from that is to be very creative about finding things you'd like to predict. And so across disciplines, the best work has been getting clever about that. That's why I love the Frank Baum story, which is the person who did that was super clever.

• 46:35Speaker 03

  He's like, "I'll just get some data and predict whether this was written by Baum or not. And I've got some data that tells me ones that were, ones that were written by Ruth Plumlee." And so I think for me, what makes sports so interesting is that there is so many unknowns that you could imagine collecting data on, and I'm sure you guys do a lot of this already, but even something like injury risk. What is a good predictor of whether someone's going to get a certain kind of injury? And if I just play that forward without knowing what you all do in that space, if I play that forward, it's kind of a nice toy example to start thinking about stuff. Because first, you have to be creative to say, "We're not just about wins and what happens, like injuries are big, so why can't we turn the gun on that?"

• 47:20Speaker 03

  Then you have to be creative about deciding what input variables are you going to get to do that. And that's where I think people haven't fully appreciated the biggest change that these algorithms have rendered, so that if I said that these algorithms can find a lot of signal in data... Then a logical implication of that is we ought to invest in new data collection. And there's huge returns to new data collection. So what I would do is say, oh, what would I want to predict injury risk? I don't know. What are some low-cost devices I could put on players? What are some low-cost devices I could put, not even during the game, but while people are taking free throws? Maybe if I had video of people taking free throws, I would start noticing small changes in form

• 48:05Speaker 03

  that indicate things that are wrong at a biomuscular levels. So you kind of, the creativity becomes not in finding patterns in data, but in deciding what data to give the algorithm, either as an objective or an input. And that's just a very different kind of open world creativity. And I think that path is, I think, going to take off in the next 10 years. We're starting to see it in medicine. Well, you tell me. I think we'll see it in sports. We probably already have.

• 48:31Speaker 02

  For sure, yeah. And I don't know if you read it. It sounds like you didn't. I wrote a paper years ago on you need better data, not better analysts. And I actually made a lot of people mad at the conference. But yeah, the data is going to be the unique thing, not the analysts, yeah.

• 48:51Pablo Torre?

  How much parity is there now in terms of the data teams have?

• 48:56Speaker 02

  I think it's getting pretty high. I mean, we're following baseball almost in a five-year delay. And it's pretty homogeneous in terms of how the... I mean, I think the quality varies, obviously, but we're in a tighter band, much, much, much tighter band now, which is not good. Yeah, not good. Yeah.

• 49:18Pablo Torre?

  The question, though, of, you know, if someone were to approach Sendhil and say, "You vetted your real GM posts, and yet still, we think you should be the chief intelligence officer for our NBA team." Do you have a sense of what you would want to do, given your field of study now?

• 49:39Speaker 03

  Yeah, I think, and I'd love to hear what you two think about this. I think what I would focus on is turn the camera... Since so much of it has already been focused on the game, I would turn the camera elsewhere. For example, on the decision makers. I would say, what are decisions that we think are being made all the time? And how do I start creating what you call the self... Like, how do I start creating algorithms that can help scout me and tell me where my bias is? Where are the things where I screw up? So that would be an example where I would start.

• 50:08Pablo Torre?

  No, could you explain, you had this landmark study of judges and bail. I just would like everybody to appreciate what it's like when you turn the camera on a decision maker.

• 50:18Speaker 03

  Yeah, this was, this was, this study was, basically, pre-trial judges have to decide who to release. And they're making a prediction of risk. Will the person come back for trial? Will they commit a crime? So the first part of the study was, we had an algorithm predict the defendant risk. And it turns out, that does very well, and could add a lot of value to the judge. When I say a lot of value, sometimes in sports, it's hard to know what the magnitudes are. But in this case, you could close Rikers in July, and have the same crime rate. So you could cut prison population, jail population by 40%. So there's a lot of, like, welfare left on the table. But then we did two things that were surprising even to me.

• 51:00Speaker 03

  So we didn't predict what the defendant would do. We turned the camera and predicted what the judge would do. And the first thing we found was that a predictor of the judge beats that judge. So that if an algorithm just does whatever the judge would typically do, that is better than what the judge actually does. And this is sort of a crisp way to see noise. And so many of our decisions, we found this in domain again, domain. Something that could just tell you, you seem to be doing something different than you usually do. Like, in many domains, medicine, judicial. So the predicted you does better than you is quite a, quite a scary thing.

• 51:43Speaker 03

  I find that very disturbing at some level, and it's true across all experts.

• 51:48Speaker 02

  That must mean you're just cutting off some outliers and tails, is it?

• 51:52Speaker 03

  I think it's really-

• 51:52Speaker 02

  Regressing to the mean more?

• 51:54Speaker 03

  Regressing to your own mean.

• 51:55Speaker 02

  Yes, yeah.

• 51:56Speaker 03

  It's sort of because what happens is, we are use variables we really ought not to. It's exactly to your point. It's the Kyle Lowry point all over again. I'm keying in on things in the moment that like, hey, that's not what you normally do. Why are you doing that?

• 52:10Speaker 02

  Use variables that you probably want. You have some other reason to be driving an outcome in this case.

• 52:17Pablo Torre?

  But can you mention which variables were driving the outcome in this case?

• 52:20Speaker 03

  So then we expanded the prediction to not just be the things we thought mattered, but include a bunch of stuff. And you identify about half of the variation of what judges do that they ought not to be doing comes from one variable in the data set, which is the mugshot. So you can build the predictor of who the judge will release just by using the mugshot. And it does extremely well.

• 52:43Pablo Torre?

  More than any other characteristic.

• 52:45Speaker 03

  More than whether they've committed a crime, what they're being charged for, how many times they failed to appear, just the mugshot. And in the mugshot, it's not just the variables you would imagine. It reminded me of your Marc Gasol thing, actually. It was variables that even judges and the public defenders didn't realize mattered. So for example, one of the biggest things that has about half the size of having committed a violent crime is if the person has a full or fat face. Now, what's interesting about that one is when I ask people...

• 53:12Speaker 02

  The good or bad?

• 53:13Speaker 03

  Exactly. No, but isn't that weird? We don't know.

• 53:16Speaker 02

  You don't know?

• 53:17Speaker 03

  No, no, we know. But our intuition doesn't tell us, even though in the data, it's very...

• 53:21Speaker 02

  I just, I'm looking at our mugshots.

• 53:22Speaker 03

  Yeah, I'm looking at that too. It's not a good sign, is it? Yeah, yeah, yeah.

• 53:25Pablo Torre?

  Is Daryl guilty, Sendhil, is what we're asking?

• 53:28Speaker 03

  So the good news is I think Daryl will not be going to jail.

• 53:32Speaker 02

  Oh, nice.

• 53:34Speaker 03

  You have a slightly full face.

• 53:35Speaker 02

  So I can get away with more.

• 53:35Speaker 03

  Yeah, yeah, yeah. But you're not well groomed. That's the other thing you need to... Yeah, yeah, yeah, yeah, yeah. Halfway there.

• 53:41Speaker 02

  Well groomed.

• 53:42Speaker 03

  Well groomed is good. Slightly rounder face is very good.

• 53:47Speaker 02

  But that's sad, though. It should not be effective.

• 53:50Speaker 03

  Absolutely, not the same.

• 53:52Pablo Torre?

  Frankly, it's mind blowing.

• 53:53Speaker 03

  It's mind blowing, yeah.

• 53:53Pablo Torre?

  That they were not aware of this. We would not intuit that based on our predisposition for bias.

• 53:58Speaker 02

  Or you might predict the opposite.

• 54:00Speaker 03

  You might have predicted the opposite. And so I think these ideas that when the camera turn on us and help us understand what we do and what we're doing, that would be probably the first angle I would take. Because a decision aid like that could help me understand myself.

• 54:13Speaker 02

  So eliminate mugshots might be your solution?

• 54:15Speaker 03

  Well, they see the person. Right, and so in some sense, but yes, if we could do everything behind a curtain.

• 54:21Speaker 02

  Do like orchestras.

• 54:22Speaker 03

  Yes, orchestras. Behind a curtain would be fantastic. But to me, it's also just, I think these algorithms can start ferreting things out about us that we did not know about ourselves. And that's, that's again, a very optimistic thing for me. I think it's part of the path that we've been growing on of becoming better stewards of ourselves.

• 54:50Pablo Torre?

  At the end of every episode of Pablo Torre Finds Out, a show about finding stuff out, we say what we found out today.

• 54:58Pablo Torre?

  Daryl, would you like to begin?

• 54:59Speaker 02

  Can we start with Sendhil?

• 55:01Pablo Torre?

  Sendhil, would you like to begin?

• 55:04Speaker 03

  I, oh my god, I'm in the conversation so much, I'm gonna need you to say something, Daryl.

• 55:10Speaker 03

  We're just playing hot potato here.

• 55:11Speaker 02

  Yeah, I'm always picking up something. I'm trying to pick.

• 55:14Speaker 03

  So I did find out that Daryl is very attuned to whether fans are interested, excited, not excited. I think a lot of fans would have foolishly thought Daryl doesn't care about that, but he is shockingly attuned to that thing, which X post makes sense, but I think fans would have been miscalibrated on that.

• 55:32Speaker 02

  I think everyone who says they don't read it, don't read the comments, don't whatever, it's all not true. We're all, we're all humans.

• 55:38Pablo Torre?

  LeBron James reads the comments, as does Daryl Moore. We learned that this week, absolutely.

• 55:45Speaker 02

  I think probably one of the things I took away is the judge, the decision maker, and yeah, look four times, maybe even create a decision-making unit. We wouldn't be able to make a Daryl decision algorithm because it's federated across a head coach and multiple, but we could, we could create a decision-making model. And then whenever it spits out a different answer, you should start asking questions. Yeah, so that would be my takeaway.

• 56:15Pablo Torre?

  Yeah, I found out.

• 56:17Speaker 02

  What did you find out?

• 56:17Pablo Torre?

  I found out that there's a non-zero chance that Sendhil has trashed you online.

• 56:25Pablo Torre?

  And that at the same time, he also thinks we'll probably be talking about this in 15 years. So, Sendhil, Daryl, you guys for listening, thank you for doing this. This is great.

• 56:36Speaker 03

  Thank you, Pablo. Okay.

• 56:37Speaker 02

  Thanks, that was fun. Appreciate you coming over, yeah.

• 56:47Speaker 02

  This has been Pablo Torre Finds Out, a Meadowlark Media production. And I'll talk to you next time.

• 57:15Speaker 04

  With a Discover Cash Back Card, it's payback time when you earn cash back on everyday purchases. Activate and earn 5% cash back at different categories each quarter on up to $1,500 in purchases. That's 5% cash back at different places each quarter, like grocery stores, on gas, and at restaurants. It pays to discover. Terms apply. See discover.com/five for details.

• 57:38Speaker 05

  State Fair food is getting smaller and pricier. We'll have room for fried cookies. Okay, you'd never overspend on food. What's your deal?

• 57:46Speaker 06

  What's his deal? He went to Metro and got $450 in value on the new Samsung Galaxy 837 5G for free. And no activation fees.

• 57:55Speaker 05

  Free phone? Oh, sign me up.

• 57:57Speaker 06

  Get that more for your money feeling, only on Metro by T-Mobile. Bring your number and activate $40 period plan. $450 base on device discount, waived activation fee. Not available if you look Metro T-Mobile in the past 180 days. Network freedom and flexibility, that's what you want in a healthcare plan. With a Humana Medicare Advantage PPO plan, you can see any doctor in the country who accepts Medicare, including specialists. No referrals, no kidding. Learn more at gethumana.com. See any doctor who accepts Medicare and is willing to bill Humana. Humana PPOs may not be available in all areas. Benefits and costs share may vary. Humana is a Medicare Advantage PPO organization with a Medicare contract. Enrollment in any Humana plan depends on contract renewal.