Can Gemini 1.5 Pro Beat Our Best Stock Trade? - Ep. 13 with Jesse Beyroutey

[00:00] When we bought NVIDIA in January 2019, it was $33 a share. Today, it is $800 a share. That was the trade of our lives. We want to find... [00:11] an investment that's just as good as our NVIDIA investment using Gemini. And I think we can do it. Basically, what we have done is we have downloaded earnings call transcripts from 2022 and 2023. We're going to load them into Gemini and we'll see [00:24] We'll ask some questions, see how it does. This is the stock that we came to at the end of a long journey, and I'll let you see it as I do it. [00:33] We're going to swipe up to submit. Order received. [00:39] There we go. [00:52] Hey, I want to just take a quick break from this episode to tell you about a podcast you should know about. It's hosted by Nathan LeBenz, who's actually on this show and did one of the most popular episodes we've ever had about how to use AI as a co-pilot for the mind. Nathan hosts a podcast called The Cognitive Revolution, where he interviews builders at the edge of AI and discusses the profound shifts that it will unlock over the next decade. [01:22] To listen to the show, search for Cognitive Revolution, your podcast player. All right, now let's get back to how do you use ChatGPT. Jesse, welcome to the show. Thanks, Dan. I am just delighted to do this with you. For people who don't know, you are one of my closest friends, and you are also a partner at IA Ventures.

[01:52] wise and digital ocean. Um, and you're both, uh, I think one of the smartest people I've ever met. Um, you really like have this way of digging down into an issue and like kind of figuring out the crux of it. Um, yeah. [02:09] And you're just like a very, very good person. [02:13] friend and very good person and I like just I'm so lucky to have you in my life and I'm so happy to be able to do this with you um yeah [02:21] Thanks for coming on. I didn't know that I was going to get this completely overwhelming, almost make me cry level of introduction. But thank you. I also want to say thanks for getting me out of my natural ostrich-like tendency to not appear in anything or be on the Internet. You always manage to stretch me in ways that have ultimately been so additive and productive in my life. [02:51] things out onto the internet that people regularly reference back to me like, oh, I saw you on Emory. So I'm really excited about this too. Great. I just, you know, I get to hang out with you and hear all your smart thoughts all the time. And I'm just like trying to bring more Jesse into the world. So this is our latest, our latest attempt. And you are coming on to talk about Gemini Pro 1.5, the new model from Google that has a million token context window, which is like [03:18] sort of wild and our goal is to put it through its paces and try to try to see what we can do with it.

[03:26] And the concept that we came up with is, I think, really, it's going to be really fun. And [03:36] I'm just sharing my screen because to set it up, what you realize is it would be really cool to do a good trade with Gemini and see if we can get it to identify a stock to pick. And it harkens back to this... [03:50] I think probably the best trade, at least I've ever done. I don't know about you. You're a professional investor. It's mine too. Yeah. Maybe that in a second. So in 2019, we created a little notion doc called Beirutti Times Shipper Investments because we wanted to take a bet. [04:10] on a specific company. And the company that we wanted to bet on was NVIDIA. [04:15] and [04:17] When we bought NVIDIA in January 2019, it was $33 a share. Today, it is $800 a share. And we wrote down our investment thesis. We said, you know, the price is down because of the trade war, but that's only a temporary risk. And that NVIDIA is in a position of power because of its proprietary GPUs. [04:36] because of its proprietary GPU architecture and its position in the market, should only grow as machine learning and gaming increases the need for high-powered CPUs and computers, so the price dip should be temporary. [04:47] So that was the trade of our lives. It was quite a moment. I mean, we fancied ourselves as distressed asset investors in our little long, short public market fund. I think it's important to note that we also made one of our worst investments ever at about the same time.

[05:07] So it's not like we were absolute geniuses. And we didn't have LLMs at the time. So maybe today I'll be different. [05:17] we want to find [05:18] an investment that's just as good as our NVIDIA investment using Gemini. And I think we can do it, or I hope we can do it. Yeah, I'm really excited about this in particular because I love using LLMs for role-playing type exercises as almost like a conversational participant along with me. So my favorite sort of prompts for ChatGPT and now for Gemini are, assume that you [05:48] And that elicits a different kind of perspective from the LLM than just asking it a question flat out, because it's trying to take advantage of whatever knowledge that it had about that person and things that co-occur with that person's name on the Internet. [06:18] like an analyst on our little hedge fund team. I love that. I'm curious, like, what are the names of people that you've used and found to work well so far? It really depends on the setting. Yeah. But I mean, I just generally always try to ask, like, what would the CEO of a famous company in that industry? So if I'm, you know, let's say I'm analyzing something about aggregators,

[06:48] Or what would Ben Thompson have to say about this? And it's kind of the intersection of someone who clearly would have an informed opinion about the thing, probably has talked about it before, has a lot of information about them on the Internet already. And therefore, there's like some meaningful thing that the LM might be able to draw from. And then also that whose perspective is generally a little bit contrarian or comes at things from a different angle than, you know, what the average of the Internet might have. That makes sense. That's really cool. [07:18] I love that. So I want to get us I want to get us going into our into our investment finding exercise because we've got 90 minutes. The clock is ticking. So set up for us how we're thinking about like doing the initial selection of companies. And I think we're basing it on how we thought about NVIDIA. And we're going to try to see if we can do a similar kind of filter for this this round of investment. Right. [07:48] to find companies that had been trading down suddenly recently for some reason that we could look at and think, oh, this distress situation is temporary. And so from our perspective as a more like long-term investor, it gives us the advantage of a margin of safety. Oh, if it's trading down by 20%, 30% or whatever, then we can be a little bit wrong about things and still not lose too much

[08:18] that we made around that time where it took us a little while, but we eventually recovered our principle on it and were able to live to die another day. Yeah, totally. And I will say like, yes, we went into this with this very long-term thesis, like, oh, it's only down temporarily, but then I panic sold it during the pandemic. So I look stupid, but I still feel good about identifying it originally, but I'm going to hold this one. This trade is I'm going to keep around. [08:48] do this. You shouldn't day trade. This is not a good idea. And we're doing it only with an amount of money that we're willing to lose. [08:56] So this is not investment advice. You probably buy index funds unless you really know what you're doing. But anyway. Yeah, treat this as worse than Wall Street bets because it doesn't even have the common thread. And more on that later because we might even post our bet to Wall Street bets. We are going to probably post our bet to Wall Street bets if we can. But one thing that I forgot to say is we are going to put actual money down. [09:26] Hopefully by the end of the episode, we will find a company to put $1,000 in and we'll be able to track how it does. [09:33] Cool. So, yeah, why don't you, why don't you, I think you're, I think you've set up the filter of what we're looking for appropriately. And I know you're, you've been looking through companies to, to kind of start our research with. Do you want to share your screen and, and show us what you've been looking at?

[10:03] investment, we were looking at companies that weren't massive yet, but had the potential to be the, you know, 10 bagger of the future. And so for me, that was expressed in the form of, it's a company that's between a couple billion dollars and a hundred billion in market cap. So it could become the next trillion dollar company, but it's starting from small beginnings. I think NVIDIA was like something in the 50 to a hundred billion range when we first invested. Now it's a [10:33] today, depending on the trading. I was looking for companies like that, that were in positive gross profit, which we might play around with, but just want companies that actually make a little bit of money. They're not going to die. Yeah. We're looking to avoid our total bozo risk as much as we possibly can. The way that we're trying to do that is just like, okay, the company [11:03] that I was just looking for, like really, there's so many screens that you can do, but I really just wanted to find companies that had a six-month performance that was like, they're down 20% or something like that. But then, you know, on a five-year basis in this column, you know, are also down, but, you know, we might come up with a reason for why. That was the basic screen. And we were

[11:33] Maybe we'll have something positive to say about it whatsoever. But I think we should also try to do companies that we know absolutely nothing about later. Right, totally. So I'm looking at this list, and the first thing in my mind is, like, I guess we could just throw this into Gemini and ask it to filter based on our, like, NVIDIA criteria. Yes. But I just want to confirm that that seems like a good idea to you. I think anything with LLMs is a good idea because we'll see what we get out of it. So let's just do it. [12:03] screener screen over to me. Um, sorry, throw it into Gemini. Yeah. Uh, yeah. [12:08] All right, so what we've got here is you copy-pasted the output from the trade view, and I'm going to just head into – [12:19] head into Gemini. And so again, this is, this is not ChatGBT. This is Gemini 1.5 Pro, which is this new model. It's, it's invite beta only private beta. Um, and what we're going to do is we're going to take the, um, [12:35] We're going to take the output that you gave me and we're going to try to filter it by our criteria. So let's say something like, hey, I'm trying to pick a stock. I want to find a 10-bagger. [12:51] Specifically, I'm trying to replicate a trade I did in 2019 where I bought NVIDIA. It was down temporarily. Yeah. [13:02] because of the

[13:04] trade war and now it's a $2 trillion dollar, [13:10] Now it's a $2 trillion company. Here's a list of potential starting points for trades. Does anything... [13:21] pop out to you. Any revisions there? Does that seem like a good thing? Okay, cool. So I'm going to paste it in and hit go. [13:30] See what happens. [13:33] Thank you. [13:35] One of the things I've noticed about Gemini is it's slower than ChatGPT. So it can take a million... [13:43] It can take a million tokens, but you have to wait like... [13:48] Sometimes it takes a minute for it to actually return. I mean, it's because our request just got queued behind all the things that make Google money to run on their TPUs or whatever. So I get it. [14:02] Okay, so Gemini is saying, good caveat. It's important to remember that past performance is not indicative of future results, and finding the next 10-backer is extremely difficult. While your NVIDIA trade was successful, replicating that exact scenario is unlikely. [14:18] I appreciate that. But you're saying there's a chance. Don't give up all hope to Zia. [14:26] However, I can offer some insights on the list you provided. Potential growth stocks, Bill D, Bill Holdings Incorporated. This company provides cloud-based software solutions for managing invoices and payments. It has shown strong revenue growth and has the potential to benefit from increasing adoption of digital payment solutions. Clavio, this company offers an email marketing

[14:48] and is well-positioned in a growing market. [14:50] Appian, this company provides a low-code platform for building business applications. The demand for low-code solutions is increasing, which could benefit Appian. Important considerations, high growth, potential look for companies with strong growth. Valuation, while high-growth companies often have high valuations, it's important to ensure the price is justified. Okay, so... [15:10] I think so. It's it. [15:12] identified Bill Holdings, Klaviyo, and Appian. I think we should strike Appian, 'cause I just feel like low-code is just like such a bad idea in an AI market. [15:22] But I'm curious if you have a differing opinion and or if any of the other any of its other suggestions pop out to you as something we should explore. [15:31] Yeah. So what immediately stood out to me is that it's already identified that high growth companies have potentially high valuations, which is obviously true. And here, what we're specifically looking for as a starting point is a company that's artificially depressed. Right. And so we want to figure out what reason there might be for the company to be artificially depressed and give us that that, you know, nice feeling that we can make our money back even if we're totally wrong. [16:01] I would actually even let's like try a different angle. The angle might be instead of asking about those specific stocks, let's ask it for how to construct a screener to identify companies that might be artificially depressed in their prices. Because maybe my screener idea is actually not even the right one. OK. And should we say should we use the trade view and say like in the trade view or can't hurt?

[16:31] even if it's not stock screener type filters are pretty generic. So I think it could just give us some ideas. Okay, cool. How should I construct a screener to identify companies that might be artificially depressed in a stock screener? Does that seem like a good place to start? Okay. And I will say, like, these are things that we could do with JGVT. [16:50] And hopefully once we narrow things down a little bit, we will start using more of Gemini's, like, increased capacity to analyze data. [17:02] All right. So here are some criteria you can use to construct a stock screener. Price to earnings ratio. Look for companies with P.E. ratio significantly lower than their historical average. Price to book ratio. Similar to P.E. to P.E. ratio is significantly lower than its historical average would be good. Price to cash flow ratio, debt to equity ratio, free cash flow. It's talking about technical indicators like the relative strength index. [17:32] So I don't know, any of those things spark something for you? We could also think about, you know, throwing in something like Ben Graham's intelligent investor book and see how Ben Graham might evaluate some of these stocks. But yeah, tell me what you think.

[18:02] added heavily, like, you might do this or you might do that. And I'm like, okay, great. I'm just trying to do the best version that I can with five parameters. Like, what would you use? Okay, so make it okay, make a decision, do the best you can. Yeah, okay, cool. [18:18] Thank you. [18:19] You kind of want to download the intelligent investor just to have it. [18:25] Based on the information provided, it is impossible to make specific investments. Wow. Choosing a stock. So this is, you know, I think – [18:34] It's, you know, Google's model is going to be probably pretty safe, you know? Yeah. Yeah. We're running up against some Google doesn't want to be liable for what we did with 10.9 type issues, which I get it. You know, we're like just two dumb people on Wall Street that's trying to make some some kind of new idea here. But I think I think we should try to get it to be a little bit more explicit. Yeah. We could say, like, pretend you're, I don't know, Warren Buffett or something. Yeah. And I've come to you. [19:04] to make a final decision. [19:07] Do you want to have it decide on a trading strategy or on a stock? [19:11] I think we should go with trading strategy as a starting point, a trading strategy. [19:15] And this will probably weight it towards Warren Buffett's trading strategy. But I think it'll... [19:22] Um, [19:23] I think it'll get it to make a decision, for sure. Does it work with Lynx? [19:27] I don't think so. Okay. But we can just copy and paste anything that's in the link into the... Does it work with PDFs yet or no? It works with PDFs. Okay. Got it. Sweet.

[19:35] It also works with videos. [19:39] So if you've got any videos or audio, also great. [19:45] So my instinct is I think it'd be really fun to have it try to get like people who run major hedge funds to be our analysts. I love that. So, you know, OK, since he's been in the news a lot, I'm trying to think of a good thing to feed in for Bill Ackman. OK, let's get Bill's opinion. Let's get Bill's opinion. How to find a good distressed stock. OK, so I'll say Warren Buffett in Gemini says, well, I don't advocate for frequent trading. [20:15] value-oriented approach. Look for undervalued companies using metrics like PE, PB, and PE over PCF. [20:22] Look for companies with strong fundamentals and durable competitive advantage. So these are all things that we've already kind of considered. But I think the PE, maybe a PE... [20:31] A low PE filter is an interesting one to consider. Yeah. Yeah. So let's, I'm just going to try a filter. So I broadened our industry here and I'm going to try a price to earnings filter. So basically Gemini, our simulation of Warren Buffett asked us to filter our list by price to earnings ratio below a certain number. We picked 15. And so these are the companies that are... [21:00] that are in that [21:01] And these are the companies that have a fairly low price to earnings ratio might be depressed. I have not filtered this by tech companies.

[21:10] Right. And maybe that's purposeful. I just want to make sure you're good with that. Yeah. I mean, I think we can do like a broad screen and just have it have it tell us what to do like like an analyst would. Perfect. [21:26] one thing that I'm feeling is we don't have real time data in Gemini so asking it about what is currently depressed might not [21:36] work that well? Well, we're going to use the stock screener to figure out what's currently depressed. So the way that I was thinking about doing that was... [21:45] So they have, if you search filter it by the word performance, they have ways of screening by six-month performance. Ah, okay, cool, cool, cool, cool. And so what I was thinking is, okay, we want something that's below minus 20 on the six-month. And then on a five-year basis, maybe we want something that is at or above zero. Yeah, I like that because it indicates... [22:15] Strength, but temporary dysfunction. Exactly. [22:21] That's what we're looking for. My third has told me that last week, so that's where that came from. [22:30] So, okay, so we've got 29 matches, and we could look at them individually ourselves. We could throw them into Gemini. What's your call? Yeah, so I think that now is a good time to throw them into Gemini

[22:45] Commonality or something like that. Okay, cool. Points of commonality. Tell me more about that. Well, as a starting point, I think that language models are amazing at clustering things. So if I were to ask it to group them into some relevant groups that we can consider. If you had to cluster these stocks, how would you do it? [23:06] and why. All right. So I'm just going to paste the plain text and see how that goes. Okay, cool. So it says clustering stocks involve grouping them based on similarities. Here's some potential approaches in the rationale. Clustering by sector, clustering by financial metrics, clustering by technical indicators, clustering by fundamental factors, hybrid approach. Choosing the best approach. The best approach for clustering stock depends on your specific goals and strategy. For long-term investors, focusing on fundamental strategies and financial metrics. For short-term [23:36] I would actually ask it, because obviously those things are true, but I would actually ask it to cluster them by things about the company and what it does. So that it's more possible for us to analyze it more on the basis of just the nature of the company and its position in its industry. The nature of the company and its position in the industry. So I'm just literally typing what you said and see what it does. All right, let's try it. [24:04] And I'm noticing that it's like it's a little bit hesitant for some of these queries to like really give us an answer. Yeah. I'm not sure the chat GPT would be so hesitant. All right. Well, let's let's do a side by side. We should do a side by side while this is loading. OK, so so Gemini said clustering stocks by company and industry position.

[24:25] So based on the information provided, here's a possible clustering of the stocks based on the nature of the company and its position in the industry. Cluster one, commodity-based businesses, companies like Archer Daniels, Darling Ingredients, Civitas, blah, blah, blah. These companies are primarily involved in the extraction, processing, or distribution of commodities like agricultural products. This immediately makes me think of lithium. [24:45] for batteries or anything related to chips or silicon or whatever seems like an interesting play. But I bet those are already hot. [24:55] I don't think they're depressed right now. Right. Yeah. We're going to have a hard time finding anything depressed that's around semiconductors because it's so on thesis right now. That makes sense. Okay. These companies are typically price takers with limited control over the market price of their product. Their performance is heavily influenced by supply and demand dynamics in global commodity prices. That doesn't sound like our kind of investing. [25:17] Consumer facing businesses. Companies. Davis Budget Group. Car. I f***ing hate budget. I will not invest in budget. [25:25] This is like a moral stand. Yeah, we're taking a stand here. We're only investing in a company that we actually like. Or at least one that I haven't heard of, or at least one that I haven't had a personally horrible experience with. [25:39] That's funny because out of the whole list, the one that stood out to me was GoGo. GoGo in-flight internet? I was thinking about how it's potentially artificially depressed because it's both a brand that people hate.

[25:55] reaction that you just had to budget. And also at the same time, there's like the buzzy Starlink company that's going to try to go after them. And so I wonder how much that impacts them. That's an interesting thing to look at. I love that. Okay, cool. DIN mode, which I have no idea what that is. [26:12] We could look it up. Urban and Urban One. So those are the other consumer-facing businesses aside from GoGo. Then there's technology-oriented businesses. So this is our bread and butter right here. Perion Network. [26:24] Intest Corporation, Universal Security Instruments, and Kimball Electronics. These companies develop or provide technology-based products and services, including software. [26:33] And then we've got a couple more. DaVita in healthcare. DaVita, cross-country healthcare, AMN Healthcare Services. I know you've got some investments in healthcare. I don't know if any of these pop out to you. Yeah, I mean, I think a lot of people really dislike DaVita, so that's another one. In fact, actually, what I was thinking of asking Gemini is, which of these businesses are most likely to be trading poorly because consumers dislike the brand? [26:58] Okay, so which of these businesses are mostly going to be trading poorly because consumers dislike the brand? [27:05] Because I think what you want to do is just strike them from our list. [27:08] Maybe. Or, you know, maybe that's actually worth spending some time. [27:17] Yeah. Tell me about that, though, because like if consumers dislike the brand, theoretically, that leaves a lot of room for a competitor to come along. That would like kill the company. Right. Yes and no.

[27:38] GoGo is the default and has hardware lock-in on so many planes that it's not going anywhere anytime soon, even though consumers hate it. And so that maybe is an interesting opportunity. I get it. Okay. And it said that. So from the provided list, the businesses most likely to be trading poorly are GoGo. GoGo provides in-flight internet and entertainment services. Urban One. Urban One is a media company targeting African-American and urban audiences. And Davis Budget Group. [28:08] experience as a customer service vehicle or could damage brand perception. All right. I'm getting a feeling here, which is I just think that GoGo is going to be interesting for us to analyze. Let's do it. I love it. So I want to dig straight in and start talking about GoGo. Okay. How do we do that? Yeah. So I think the key question for GoGo is whether or not their technology can be upgraded. So it's clear that they have a distribution advantage already. Right. Because they're already in all the airplanes. [28:38] And they've also integrated with all of the apps and services that the airlines use to provision the Internet and connect your payments and all that sort of stuff. So they're kind of the one to beat. And people hate the service because the service quality is low. So the question is upgradability.

[29:08] I love that. I think that's a really interesting place to start. Why didn't you think about first like airline switching costs or like how hard it is for the airlines to rip them out and move to someone else? My immediate thought was that if GoGo is incumbent, it's the one that they already have a deal with. It's the one that's already installed. And if there's some clear upgrade path for them. [29:30] that's going to be the natural first step for the airlines before bidding out completely replacing all of the hardware. And so if it's possible for there to be a low-cost upgrade path, I think that they have that default status. They have an advantage. Okay, that makes sense. Okay, cool. So should I just ask that? Yeah. Okay, cool. So how hard would it be for GoGo to produce hardware that would allow it – [29:57] to upgrade its current services. [30:01] in planes. Um... [30:04] To what? What's the to be like Starlink technology? Yeah, to to improve service quality using the latest in connectivity like Starlink. [30:15] Okay. Like Starlink. All right. Let's see. And then I think this is also a good opportunity to start integrating some of Gemini's giant processing capability. Let's do it. And my immediate thought is let's just like get the earnings transcripts. Yes. And see how much they're talking about. Okay, great. How do I do that? Just go to their website and grab the earnings transcripts, I think is the best way. But we could also ask Gemini if there's a faster

[30:45] earnings transcripts. Oh yeah. I mean, literally just like, uh, I mean the, the, the dumb and simple ways to find their IR site and go to their quarterly results. Okay, cool. Invest relations. Here we go. Yeah. We got it. Um, [31:00] Do we want annual reports, earnings reports? Yeah, earnings. And then let's get the earnings call. [31:08] Yeah, yeah, yeah, exactly. So the transcript usually has all of the conversation already transcribed. Okay. But we could also ask Gemini to listen to the audio and see how they sound. Well, what I want to do, what I'm really interested in is whether Gemini can detect the... [31:30] like the voice, oops, you guys, can detect like, [31:36] uh, [31:37] The voice tone and stuff like that to see, like, oh, are they, like, really – [31:42] nervous or whatever, you know, like how are they feeling? And I'm going to have to do some magic to see if I can actually download this file. But yeah, that doesn't seem like it's going to be super easy, but I might be able to find it somewhere else. So, okay. So do I do, Gogo announces their quarter results, Gogo earnings... [32:04] Earnings transcript? That's the one? Yeah, yeah, yeah. But also, by the way, I just found it seems like there's a company that publishes the conference calls onto YouTube. Oh, sweet. So I just tried searching YouTube for...

[32:23] Thank you. [32:24] Go, go earnings call. Great. And I can download a YouTube... [32:28] a YouTube downloader. [32:31] Yeah. [32:33] Thank you. [32:35] Oh, Gemini can't just go straight in and process the YouTube link? I see. [32:39] Got it. [32:40] Thank you. [32:41] Oh, actually, never mind. It only had a couple of random ones. I thought it was every single one. [32:47] All right. [32:48] Different strategy. [32:50] Pivot, pivot. [32:53] We've got a transcript. So I have that now. We can start with that. Or if you want to keep looking for more stuff, we can look at Q. Well, I'm thinking let's actually try to load in a bunch of the transcripts at once. You want to do the 10K? Okay. [33:09] From 2022? Sure. But I think the transcripts have some more like there's Q&A in there. And what I'm really wondering is how much that things like replacement cycle and Starlink as a competitor and whatnot are coming up and what management's sort of reactions to those are. This is so good. Okay. So I have all the earnings transcripts from 2022 and 2023. Is that enough? I think let's do that. Okay. I'll start with that. Yeah. [33:40] Cool. So I'm downloading, save. I realize that our potential bet on GoGo here has the characteristics of our worst investment more than the characteristics of our best investment. Interesting.

[33:56] Our worst investment came from the reason for a temporary dislocation being that, well, this company was being sued and there were a bunch of reasons why all of a sudden – [34:10] People were thinking negatively of it because of that sort of recency of announcement. [34:15] And it wasn't benefiting from a wave of positive momentum for the adoption of a new technology that it was already well positioned for. And so I'm wondering – [34:29] as we dig into it a little bit more as to whether we can find reasons that gogo is actually going to be a huge beneficiary of that new technology wave or if it's actually disliked for good reason. Right, right. I love that. Well, to that point. So we have a response from Gemini about, wow. [34:46] about how hard or easy it would be to upgrade its hardware. And so Gemini says, [35:16] Thank you. [35:16] So, I mean, we have to take all this with a grain of salt. It could be making it up. Of course. For all we know, GoGo has this. Well, let's go to the transcript. We should Google or go to the... Let's go to the transcript. Okay. So basically what we have done is we have downloaded all of GoGo's earnings call transcripts from 2022 and 2023. We're going to load them into Gemini and we'll see... We'll ask some questions, see how it does.

[35:40] So we're going to take this and we're going to throw it in here. [35:45] and [35:47] We'll see it's all being uploaded. What would be your first question of these transcripts? I would ask, to what extent is management already talking about upgrading? Nice. Okay. Upgrading to new technology. How's that? Let's do it. Great. So I'm just saying, to what extent is management already talking about upgrading to new technology? Okay. [36:07] And, uh... [36:10] I think we just put in about 100,000 tokens. So this is already more than ChatGPT can handle. And it's about where OpenAI's latest model, which is not yet available generally in ChatGPT, it's about what it can handle. It's about 128,000 tokens is GPT4 Turbo. So we're pushing the limits of existing technology already. Let's do it. Yeah. [36:33] Thank you. [36:33] Again, we need the waiting music. We need the already baked response to take out of the oven. Okay. So management has been actively discussing upgrading to new technology, specifically in reference to their 5G ATG network and global broadband initiative. Here's a summary of their comments from the Q1 2022 earnings call. 5G ATG network. Google remains on track for commercial launch in the second half of 2022. They have passed all development risks and are focused on a 5G chipset tracking and building towers. [37:03] selling, shipping, and installing 5G equipment that can operate on the 4G network until the 5G box is available. Customers who pre-provision with this equipment can easily upgrade to 5G later by simply swapping the box. GoGo is seeing strong demand for 5G with orders from end customers, dealers, and commitments from OEMs. Global Broadband GBB Initiative. GoGo is partnering with Hughes Network Systems to develop a small electronically steered antenna to access the OneWeb Low Earth Orbit LEO Satellite Constellation.

[37:33] significantly expanding their adjustable market. GBB is expected to launch commercially in the second half of 2024. GoGo is seeing overwhelmingly positive responses to GBB from customers, dealers, and OEMs. [37:44] For existing advanced customers, the upgrade to GBB will be simple, requiring only the installation of the ESA antenna and running two wires inside the aircraft. So that's actually a really interesting point for what you were just saying earlier, that it will be pretty easy for them. It looks like from this one search to upgrade their aircraft to satellite. Fantastic. Well, that's looking pretty positive. I could imagine people not following that specifically. [38:14] Now, let's ask, to what extent would that upcoming change already be priced into their stock, and how would we figure that out? Okay, that's a great idea. To what extent would that upcoming change already be priced into their stock, and how would we figure that out? [38:31] I think it would be worth also inquiring as to like why is the stock down right now? Yeah, like because we're assuming that it's probably because of Starlink, but maybe it's something else. Yeah, it could be. Global aviation is not doing well or, you know. Yeah, totally other reasons. [38:46] Thank you. [38:48] All right. It is difficult to say definitively to what extent the upcoming technology changes are already priced into Gogo stock. The stock price reflects a variety of factors, including current financial performance, blah, blah, blah. However, there are some indicators that the market is anticipating the positive impacts of Gogo's new technology. Strong stock performance. Gogo stock price has performed well in recent years, significantly outperforming the broader market. Is that true? Like we should probably check that.

[39:11] This suggests that investors are optimistic about the company's future growth prospects. Positive analyst sentiment. The majority of analysts covering GoGo have a buy or strong buy rating. Again, something that we should check. High trading multiples. GoGo stock trades at relatively high multiples compared to its peers. This suggests that investors are willing to pay premium. Given that we filtered by low PE ratio companies, I'm surprised that it's – [39:33] has a high trading multiple. I agree. So here are some approaches to gauge the market's expectations, analyze analyst reports, compare GoGo to its peers, and model the impact of new technologies. So what do you think we should – do you want to start with it? [39:48] analyze analyst reports or is there a follow-up question you want to ask? Yeah, well, I'm particularly trying to think about ways that we can use the advantage of a giant context window. Um, [39:59] And analyst reports would have been great if we had an easy access to them, but I don't know if we're going to be able to easily download all of them. You don't have any subscription to like... I don't. We don't do public stock, so I got as much as the average Redditor does. So I don't think that that's going to be a useful direction. [40:22] Where I'm at right now is I'm thinking about how we're trying to establish why GoGo is down. Yeah. [40:33] And... [40:34] That's because we started with a stock screener. [40:38] And just looked at things that were down. Yeah. But if I think about our original theory generation strategy, it was finding things that were down for a clear reason that we knew. And the reason being something that was sort of public and in the news.

[41:08] to artificially trade down that we can specifically find. I love that. Okay. We can totally do that. I think we would probably use ChatGPT for that. All right. Let's do it. Let's switch tools. Unless you had a sense for how you wanted to go about it. No, I didn't have any sense more than I said. Yeah, let's try it. Let's give that a shot, and we'll see... [41:28] We'll see. I don't want to lose the GoGo thread. There's something in it. There's something in it. I'm just realizing that in order for us to establish why it's down and what is or isn't priced in, we're trying to hunt for a specific reason for it being down. Yeah. And I think we could potentially establish that, but it'd be hard to feel confident about it. [41:58] 5G network for second time in 12 months. So if we had, if we had to guess connecting the dots, I'd say that's probably part of it is, and they attributed the delay to a design error made by a third party subcontractor of its solution provider in-flight internet provider. GoGo business aviation is the Lang launch of its 5G network originally slated for a fourth quarter 2022 rollout. The service was delayed to mid 2023 to a computer chip testing holdup. Now GoGo expects a design fall on its chips to push the launch back further to mid 2024. [42:28] Yes. [42:28] One of the things in the calculus is [42:32] do we think that they'll end up executing on this? Are the endless delays signs of incompetence or do we want to bet? Yeah, yeah, I definitely see that. And

[42:45] I guess the thing that feels important to me here is that delays are an internal thing. [42:52] And what we're really looking for is a stock trading down to an exogenous shock. Okay, cool, cool, cool. So a great example, you know, in video, it was the trade war. Yeah. You know, more recently, Meadow is an amazing trade because it was artificially down due to ATT and uncertainty around it. You're totally right. So I'm really hoping we can find some exogenous factors right now that might be affecting stocks. Okay. What are some stocks that are trading down because of exogenous factors? [43:22] tech stocks or just any stock. [43:24] Try any for now. I'm going to do this in chat GPT and I'm also going to do it in perplexity. All right. Because I don't know. Perplexity might work actually. [43:33] So let's see perplexity first. [43:37] Okay, Proplexity is not answering this question well. It's basically telling me why stocks might trade down rather than using stock prices. [43:47] And... [43:47] Uh, some stocks are trading down due to exotic and chat GBT says some stocks are trading down due to exogenous factors in 2024 include those affected by inflation data and the energy sector stocks and inflation data impact stocks in general have experienced downward pressure due to higher than expected inflation data.

[44:17] So what is this making you think? [44:20] Thank you. [44:21] My immediate instinct is, well, if energy stocks are artificially down because of a bunch of exogenous factors, the second thing, [44:32] the part of a thesis is that also we want companies that are going to benefit from a positive wave of adoption due to a technology that they've built being adopted rapidly. So energy strikes me as an interesting one to dig into because there's a bunch of technology shifts on the horizon for energy and like government investing in it a lot at the same time that there's maybe some reasons why the energy stocks are down. Right. [45:00] Are you thinking like... [45:03] big energy stocks like Exxon? Are you thinking like trying to find some like solar company or some wind company or nuclear or something like that? Well, I think it's important that we find a company that sits on a key bottleneck. That was the insight behind NVIDIA and Meta as two example trades was that NVIDIA had this huge advantage in CUDA in its particular case. And, you know, [45:33] for advertising for a certain type. And in both cases, they stood to take advantage of their position in that value chain. So I think we should try to find something that might be similar. Okay. And how would you suggest we go about that? Should we ask, like, what energy companies control a key bottleneck? Yeah, let's do that. Okay. And ideally, we want to frame it,

[46:01] In reference to and are positioned to ride a new technology wave. Yeah. What energy companies control a key bottleneck in the value chain? [46:11] Phrase it like that. In the value chain and are positioned to ride a new technology wave over the next five years, let's say. Does that sound good? Okay. And ChatGPT at the bed. [46:28] The best analysts do that, too. [46:31] We can't help ourselves sometimes. [46:41] we could just go back over to Gemini and throw that in as well and compare. Yeah. So I'm going to ask Gemini, what energy companies control a key bottleneck in the value chain and are positioned to ride a new technology wave over the next five years? [46:54] In the energy sector, the TGBT is saying, in the energy sector, companies that control key bottlenecks in the value chain and are positioned to ride a new technology wave over the next five years include those involved in hydrogen production and fuel cell technology, as well as those focused on building resilient supply chains for energy transition technologies. [47:11] cell technology hydrogen is emerging as a key player in the energy transition with applications from renewable energy systems to decarbonizing transportation companies involved in hydrogen production fuel cell fuel selected fuel cell technology and related infrastructure are well positioned to capitalize on this hydrogen power vehicles and fuel cell [47:28] electronic vehicles are expected to play a complementary role. Okay. Building resilient supply chains. As the energy transition accelerates, supply chain resilience is becoming increasingly important. Companies that can navigate and mitigate risks related to volume shortages, price volatility, geographical sourcing dependencies, long lead times and quality issues in the supply chain will have a competitive advantage. And then green business opportunities, companies that can scale green technologies quickly and efficiently will have an advantage. What's popping out to you?

[47:58] that might benefit in each of those categories. Okay, give us some public stocks that fit each of these categories. [48:04] Mm-hmm. [48:05] Thank you. [48:06] We'll see what Gemini said. So Gemini, by comparison, said, here are some energy companies that control key bottlenecks in the value chain and are positioned to ride a new technology over the next five years. One is midstream companies. Bottleneck. Midstream companies control the transportation and storage of oil and gas. This is actually pretty cool. [48:36] Includes pipeline leak detection, automated pipeline operations, and carbon capture and storage. Examples are Kinder Morgan and Enterprise Products Partners. Like, I like that it's giving examples. Yeah, it already went to the examples. Yeah. Clustered them in a useful way. Yeah, it's pretty cool. Renewable energy developers. Bottleneck. Renewable energy developers control the development and construction of renewable energy projects. This gives them a key role. [48:57] In the transition to low carbon energy, new technology wave renewable energy developers are constantly innovating to improve the efficiency and cost effectiveness of renewable energy technologies. [49:06] So solar panels, wind turbines, energy storage, and it's suggesting NextEra Energy, the world's largest producer of wind and solar energy. And then First Solar, a leading manufacturer of thin film solar panels, FSLR, is constantly innovating to improve the efficiency and affordability of its products. Energy storage companies. [49:24] Bottleneck. Energy storage is a critical bottleneck in the transition to a renewable future. As the grid becomes increasingly reliant on intermittent renewable energy sources, energy storage is needed to balance the supply and demand. New technology wave, lithium ion batteries, flow batteries, and hydrogen storage, and it's recommending Tesla and Fluence Energy. Yeah, what are you thinking?

[49:43] Well, I'm thinking let's find out if any of those are artificially down. Yeah, exactly. Okay, cool. I wonder what the – oh, let's compare to ChatGPT. So ChatGPT says plug and power. For hydrogen production, it says plug power, Inc., Bauer, Power Systems, and Bloom Energy. And then for building resilience of supply chains, it says Albany Corporation, Freeport, McMoran Incorporation, Rio Tinto Group, which who knows. [50:13] Green business, it recommends Beyond Meat, Tesla, and First Solar. So actually, the green business is the one sort of overlap between Gemini and ChatGPT. What I'd like to do is have it... [50:26] I'm going to have Gemini just output a clean list for us. Here's a list of other recommendations. Please... [50:34] Please print them out. [50:36] please print these and your recommendations as a bulleted. [50:45] list with just the ticker symbol just so it makes it easy to add to our stock screener. Beautiful. So, yeah. [50:53] and then I'm going to split my screen. And what was the stock screener again? [50:59] - Trading view. - Trading view, okay. I'm not ready. [51:05] And then how do you in Trading View [51:09] look at a specific set of ticker symbols, filters.

[51:14] I think you can... [51:18] I think I just type in a symbol. Yeah, I don't think there's a faster way of doing it. Okay. We've got our clean list of recommendations. [51:30] Yeah, how should we start? Just go down the list? [51:35] Yeah, I mean, I'm trying to figure out a way to... [51:37] Upload them. Okay. Oh, upload them. Or just dump a list into a product, but I can't find one. Okay. If there's any way... Okay. Well, let's just go one by one unless there's... I'm happy to copy-paste them individually because there's not that many. If we can get them all up on a screen somewhere, but I don't know what product would do that. Me neither. Okay. Cool. Well, we'll just do it this way. So let's go one by one. So we're going to start with KMI. [52:00] And we're going to just kind of do a little spot check of KMI. [52:07] Looks like it is down. [52:10] We've got a $38 billion market cap. [52:14] Where is the P.E. ratio 16? So it's like just above our threshold. [52:18] Um... [52:20] dividend yield is 6.55%. Um, [52:24] Yeah, anything sticking out to you here? Should we move on to the next one? [52:29] Uh... [52:30] Yeah, it just doesn't look like it's gotten hit by any kind of recent exogenous event. [52:35] And that's really like a key factor that we're looking for. Yeah. It's down 10% over five years and it's down only 0.29%. Okay. So yeah, over the last six months. So I think we're, I think we're good. We're good on that one. Um,

[52:49] So I'm going to just pop this out. I think it's not really working that well. [52:56] Separate. Okay, cool. So next one is EPD. So EPD... [53:03] is Enterprise Products Partners LP. This is also up 5% over the last six months, so that's not really that good. [53:14] Let's see. N-E-E. [53:17] NextEra Energy Inc. [53:21] Down 15% over the last six months and up 20% over the last five years. So we've got a strong company potentially over the last five years, but definitely hit by an exogenous shock. It's NextEra Energy. It's a utility company. It engages in the provision of renewable energy. It operates through the following segments, FPL and NEEER. I have no idea what that means. [53:47] in Florida. The nearest segment produces electricity from clean and renewable sources, including wind and solar. So we've got a 15 price to earnings ratio, so right on target for us, $116 billion market cap. So it's a little larger than I think we were thinking of. But [54:11] But there's something good there, I think. [54:14] it at least passes some initial criteria. What are you thinking? [54:18] Um, this is making me think that, uh, I just kind of keep going back to what works so well with NVIDIA. Yeah. And, um, I realized that there's the.

[54:28] trading down due to an exogenous factor. [54:31] stands to benefit from a technology wave and also [54:35] there's this last aspect, which is extremely scalable business model. And I think that the challenge I'm immediately imagining with some of these energy companies is that, yes, they're going to benefit from a technology wave, but – and we need to assess that specifically for each company. Right, right. [54:54] But then there's still the issue that they don't get this incredible scalability of the business model that a company like NVIDIA or Meta had. Okay, got it. And so now I'm a little bit stuck on how we're going to go about finding something like that in the energy industry. And my instinct is let's ask. Okay, cool. I love that. I think, so I just want to point something out, which is like, we came into this with... [55:19] an idea of a trade we made a while ago. And through the course of like using Gemini and talking about it, [55:26] We, and more specifically you, have been refining the key characteristics of the trade we already made and the trade that we want to make in the future. And I think that's such a valuable process. It's something that I think you're incredibly good at is really being able to articulate cleanly the concept or the idea or the principle behind what you're doing. And I think having that three-part trade so far, maybe it'll get larger as we go, it's such a powerful thing. And I just want to underscore that. [55:56] Yeah, yeah. It's trying to break down into what are the key components, what are the makings of a company that's going to end up doing ridiculously well and see how much they can replicate in the public market. Yeah, hopefully we can find that. It's a high bar. And I guess it's possible that we come out of this not making an investment. And sometimes that's okay because we are looking for that 10 bagger.

[56:26] Yeah, I'll put it in a high-yield savings account. Okay, cool. So, okay, so... [56:34] Help me compose a response to this. We're looking for a company that has a particularly scalable business model so that as the technology wave of, for example, solar comes to bear in the coming years, this company stands to not only benefit but also scale massively. [57:04] have a highly scalable business model. Okay. So one thing that we should think about is like defining for Gemini, like what you mean by highly scalable. I think it's actually good to keep it. Keep it, keep it out of track. Okay. Okay. Let's see. We can always refine. We can always refine. That's, that is true. I think that's a good principle to start, start simple in general, and then refine depending on what we get. Yeah. I find that using LLMs is a task of [57:34] so it's seeing what's related to the way you ask the question and then you find some nuance and you kind of keep going and keep going and keep going yeah [57:46] All right. We're waiting. We got the dots. Yeah. I mean, honestly, I think that the biggest opportunity I've learned about today is hold music for LLS.

[57:57] Immediate investment. [57:59] Okay. Here are some public companies in the energy sector with highly scalable business models that stand to benefit from the solar technology wave. First Solar is a leading manufacturer of thin film or solar panels. The company has a highly scalable manufacturing product and a global footprint. As the demand for solar energy continues to grow, First Solar is well positioned. [58:16] Enphase Energy. Enphase is a leading manufacturer of microinverters, which are used to convert direct current electricity from solar panels to alternating current. That's interesting. That can be used in homes and businesses. [58:27] End phase is microinverters are modular and easy to install, which makes the company's business model highly scalable. [58:33] Solar Edge Technologies. Solar Edge is a leading manufacturer of power optimizers and inverters for solar energy systems. Like Enphase, Solar Edge's products are modular and easy to install, which makes the company's business model highly scalable. It's really keen on modular and easy to install, which is interesting. Sunrun is a leading provider of residential solar energy systems. The company has a strong track record of growth and is well positioned to benefit from an increasing demand for residential solar energy. Sunrun's business model is scalable because it can be easily replicated in new markets. What do you think? [59:03] Well, obviously, manufacturers came out a lot here. And I think you're right that we didn't define highly scalable terribly well. But if I think about, again, I keep going back to Meta and NVIDIA. [59:19] Both of those have highly scalable business models in a different way, which is, you know, as NVIDIA is fabulous as a manufacturer. So it doesn't literally have to go and manufacture the items. It just buys capacity from TSMC.

[59:49] infrastructure thing or other thing that they would need to spend money on. I think that these companies might have kind of the opposite characteristic. And so I guess, yeah, maybe we should actually default, since we keep using it as inspiration, maybe we should actually go flip back to asking Gemini and ChatGPT what companies have characteristics similar to Meta and NVIDIA. Let's do that. [1:00:19] I like that. And I think we can, I think we can list out our list out more details of our trade and least list out details of meta and NVIDIA and see what that does. Yeah, let's try it. Okay. So you, you lead the way and I will, I will be the scribe. Uh, [1:00:34] We're trying to find a company whose business model is scalable in that, [1:00:41] it can grow a hundred times in a year and not run into any key bottleneck. [1:00:51] That characteristic is extremely rare and more common in the digital world. But we're looking for things that might have some similarity in non-Internet or software. In particular, since energy seems like a great opportunity, we're wondering about if there are any public companies in the energy sector that have this sort of extremely scalable business model

[1:01:21] That also enables that company to capture the lion's share of new market opportunity as it comes up in a tailwinded market. [1:01:35] something like that. You can give the LLM basically war a Mipsum text for a slightly better total stream of consciousness and it can just do something with it. It's one of my favorite. It's so good, right? Okay, cool. So we're trying to find a company whose business model is scalable and then it can grow 100x in a year and not run into any bottleneck. That characteristic is extremely rare and more common in the digital world, but we're looking for things in non-internet [1:02:05] Because energy seems like a big opportunity, we're wondering if any companies in the sector have this characteristic and sit in a bottleneck of the value chain that allows the company to capture the lion's share of new opportunity as it comes up in a tailwinded market. I'm going to take this exact thing and paste it into ChatGPT and see if... Yeah, let's do it. Steve, we'll go ahead. Also, we even invented the word tailwinded. [1:02:24] I know exactly what it means. It's great. It's a great word. So does ChatGPT in general. I believe in it. [1:02:35] that can scale 100x in a year without running into any key bottlenecks is indeed a challenging task. In the energy sector, physical constraints, blah, blah, blah. Energy storage solutions. Companies that provide innovative energy storage solutions such as battery technology or energy management systems might have potential to scale rapidly. Energy efficiency services. Companies that offer services to improve energy efficiency such as smart grid technology.

[1:02:56] could have scaling potential. Renewable energy trading platforms, platforms that facilitate the trading of renewable energy or carbon credits could potentially scale. [1:03:03] Electric vehicle charging networks, companies that develop and deploy EV charging infrastructure might have potential to scale quickly. Cool. Let's try to get to list some companies. List some companies, please. And then, okay. So let's see. Let's compare to what Gemini said. Gemini said it is extremely rare for a non-internet and software company to have a business model that is scalable enough to grow 100x in a year without running into any bottlenecks. However, there are a few energy companies that have the potential. First Solar is a leading manufacturer of thin film. [1:03:33] king on First Solar. The company has a highly scalable manufacturing process and a global footprint. They're more efficient and affordable. It's well positioned to scale. It also sits in a key bottleneck in the solar value chain. The company is one of the few manufacturers of thin film solar panels and has significant cost advantages. While it is unlikely that First Solar will grow 100x in a year, the company does have the potential to scale its business significantly. [1:03:54] Other companies are Enphase, which are already suggested, SolarEdge, which is suggested, and Sunrun, which is already suggested. So we're not getting anything like... [1:04:05] Totally groundbreaking here. Yeah, and I just quickly looked up Enphase. I had never heard about them before, and it would have been an awesome trade for us in 2019 if we'd found them at the same time as we found NVIDIA. And I'm not sure if today they're so unknown. So we're running into the challenge that I think a lot of these are probably pretty packed trades.

[1:04:31] Can we say, like, can you give us some more stocks that are less well-known? [1:04:33] Yeah. And also, I think at this phase, we might also switch out of the energy industry. The only reason we got down deep into energy was because it gave us shock. Exactly. Maybe one thing we could do is just start over with the three or four part trade that we have. So it's like exogenous shock sits in a key bottleneck of the value chain and is able to scale. [1:05:03] um [1:05:05] I think those are the three major ones. Yeah. Cool. So I'm going to just create a new chat prompt. [1:05:12] I don't want to, I want to save this. Cancel. Okay. Energy. Save. Okay. Okay. [1:05:22] Mm-hmm. [1:05:23] Okay, so... [1:05:26] We're looking to find public stocks that have the following... [1:05:32] characteristics. [1:05:34] are suffering some kind of exogenous shock to their business. [1:05:41] Sit in a highly valuable bottleneck in the value chain. [1:05:48] Um, and, um... [1:05:52] have a highly scalable business model such that they could scale 100x in a year. [1:06:01] Yeah.

[1:06:01] easily... [1:06:03] relatively easily. Anything else that you think we should put into this prompt? Let's try that. List them out. Okay. Same thing. We're going to do the same thing for ChatGPT. And remember, ChatGPT has access to real-time information. So I'm curious how it does relative to Gemini. Finding stocks that meet all three of these criteria can be challenging. This is ChatGPT's response. I can suggest a few industries and companies that might fit these characteristics. Cyber security companies like CrowdStrike and Pella Uthl Networks had a valuable bottleneck. [1:06:33] scalable businesses. They could face exogenous shocks from regulatory changes, major security breaches, or shifts in technology. Cloud service providers like Amazon, AWS, and Microsoft, I think we can get rid of that. Semiconductor companies like NVIDIA, I think we can get rid of that. Biotechnology and vaccine manufacturers. So companies like Moderna and BioNTech have shown that they can scale rapidly in response to global health crises. They sit in a valuable position in the value chain. [1:06:59] blah, blah, blah. Uh, fintech companies like square PayPal and Adyen. So I don't know. I think these are okay, but, um, can you, I'm just going to ask, can you dig deeper? Yeah. [1:07:08] and find less well-known companies. [1:07:13] And let's compare to... [1:07:15] Gemini. So Gemini says shockproof stocks. I don't know why... [1:07:20] So basically, it's finding stocks that are in each of the categories instead of all three categories. So it's saying shockproof stocks, Anadarko Petroleum, Carnival Corporation, Boeing. I don't know if Boeing is shockproof.

[1:07:42] All it takes is one door to fly off a 737-match or whatever. It's been pretty shocking. [1:07:50] Google, Microsoft, Visa, scalable stocks, Amazon, Netflix. So it's giving us like really kind of generic suggestions. Can you dig deeper? I'm just going to say, can you dig deeper and find some less well-known stocks? [1:08:07] So going back to ChatGPT, it says, here are some less well-known public companies that might fit your criteria. Digital Turbine, this company provides mobile advertising and app distribution solutions. The Trade Desk, that's an IA company. - That's kind of funny. - Inari Medical, this medical device company specializes in treating venous diseases. Serence specializes in creating unique moving experiences for the automotive world. Upstart Holdings, JFrog, Matterport. [1:08:33] Anything pop out to you? [1:08:35] Um... [1:08:41] Well, seeing Matterport show up just reminded me that – [1:08:47] I believe Matterport was an instance of a company that got public by being a SPACed company. And I think the SPACed companies all got pretty wrecked. Yeah. [1:09:00] And are now particularly small cap. Some of them are probably barely staying on the exchange. And so there might be an interesting opportunity lying in the list of SPACed companies. That'd be fun to analyze. That would be fun. I'm also just noticing that it doesn't feel like we're getting terribly useful responses here. Yeah. It's going to require quite a bit more digging. Yeah.

[1:09:30] And I think it's almost like the same work that you'd expect an analyst in our little hedge fund to be doing every day. We're going to get a ton of stock pitches that are no good. And so we've got to move our attention to a better opportunity. Next analyst, please. So I'm thinking about the SPAC companies. What do you think? I think we can do that. I think we can also. So we've got about 15 minutes left. [1:10:00] from this. I don't know. Are you cool to move on to that or do you want to push forward one more time? I just feel like we've got to make a bet. We've got 15 minutes left. The clock is ticking. Let's find our bet. How about this? [1:10:18] Within 15 minutes, we're going to bet on one company that has SPAC'd, gotten public, and gotten wrecked in the public market. And we're going to pick which one we should bet on. Let's do it. And do not do this at home. Absolutely. Do not do this at home. Okay. So how do we get all the SPAC companies? Unless she's asked for a list. Okay. Can you give me a list of all of the companies that SPAC'd in 2019? Was it? 2020 to 2021. 2020 to 2021. [1:10:48] He says no. [1:10:50] Okay. Well, that certainly ended that conversation, Chad Gbt. I'm trying to find some. There's a website called SPACTrack. So I'm just looking at the SPACTrack list. Let's see if I downloaded it.

[1:11:20] Overhealth, SoFi, Lucid, 23andMe, WeWork, Grab Holdings, Bark, Astrospace. Honestly, like, [1:11:27] I think Opendoor is an interesting one. All right. Like they were doing really horribly for a while, and I wonder where their stock is now. Let's go back to our trading view. [1:11:37] What's their ticker? [1:11:41] What's OpenDoors ticker? [1:11:46] Open. Classic. Okay. So looking at open door... [1:11:52] We've year to date is down 33 percent. [1:11:56] Over the year, it's up... [1:11:58] For the last year, it's 51%. Five years, it's down 73%. Market cap is 1.98 billion, so it's very small. [1:12:09] Open Door engages in the operation of buying, selling, and trading of residential properties online. The company is founded by Eric Wu and is headquartered in Tempe. [1:12:17] It has 1,000 employees. What should we look at? [1:12:22] Well, I'm starting to think about the most efficient way to cut through this because we only have 10 minutes. [1:12:30] So Open Door doesn't feel like one that I would spend much time on. Go back to the list. Okay. [1:12:37] So I'm wondering about, I think we should take a bet on a company that got public but had some pretty speculative technology. And there's a bet that we could take on their speculative technology working and if it works, the massive upside scalability of their model, et cetera, et cetera. So let's see if we can find an instance of that here. Yeah.

[1:13:07] You know, what stands out to me is actually very few of these have that characteristic. [1:13:15] But it's on a very incomplete list. I'm interested in 23andMe. I don't know if it's still public. I don't think so. There's some really bad scandal with it, right? Well, there's a bad scandal with it. So that's the exogenous shock. And I'm pretty sure that it's like- It's still public. It's trading at 58 cents. [1:13:45] of a rat's nest of regulatory issues and whatnot, but, you know, potentially, potentially interesting. It's at the same time, it's, it's also got a, the characteristic of being sued a lot, which, which we've gotten burned by in the past. But I do think like genetic data is going to be way more valuable now with transformers because you can throw it, like you can process it all and make interesting predictions from it potentially in a way that you couldn't do prior to transformers. [1:14:15] I really wonder if that data will be really valuable. Yeah. And clearly it's gotten better to such a level that there's definitely margin of safety if we end up being right. Right. If it doesn't go bankrupt. If it doesn't go bankrupt, which I think is a key question, is it going to go bankrupt? So let's see. Well, we've got under 10 minutes. We've got to figure

[1:14:45] Let's try to figure that one out with ChatGPT. Yeah, let's do that. What would you ask ChatGPT? Is 23andMe going to go bankrupt? [1:14:56] Is 23andMe going to go bankrupt? Okay. [1:15:01] Cool. And it says, as my last update in April of 2023, there are no public indicators. No, that's that's right. You're wrong. I'm going to just add a new chat is 23 and me going to go bang. [1:15:15] Go bankrupt. Make your best guess. [1:15:21] Thank you. [1:15:25] 23andMe is facing significant financial and legal challenges, but it's not clear the company will go bankrupt. The company's stock has fallen dramatically and is in danger of being delisted. Additionally, it's dealing with multiple class action lawsuits related to a data breach last year. The company's financial situation is precarious. [1:15:41] With a substantial portion of its venture funding already spent, however, its attempt to transform into a healthcare company and has some drug candidates in early stage human trials, the future of the company will likely depend on its ability to navigate its legal challenges and pivot its business model. [1:15:55] Thank you. [1:15:57] It feels like a tough bet. [1:16:00] Maybe we go back to our list. All right. Going back to our list. We've got SoFi. We've got, I don't know what QuantumScape is. We've got ChargePoint. Yeah, that's a network. [1:16:15] Oh, man.

[1:16:16] This is a tough list. Tough list. [1:16:18] What's Virgin Galactic up to? I don't know. [1:16:24] Let's ask. What is Virgin Galactic up to? Browse. [1:16:33] I'm going to go. [1:16:35] It recently completed its 11th successful space flight known as Galactic 06 on January 26, 2024. This is notable as it marked the first time all four seats aboard were occupied by private astronauts. It reached blah, blah, blah. However, Virgin Galactic plans to halt its unity suborbital flights by mid 2024 as it concentrates resources on the next generation of vehicle, the Delta class ship. The company will reduce the frequency of. [1:16:59] these flights and it's part of the transition to achieve positive cash flow by 2026. [1:17:05] Hmm. [1:17:06] Let's see what his stock price is doing. Virgin Galactic. [1:17:12] So... [1:17:14] Let's see. [1:17:17] It's down. [1:17:19] A lot. [1:17:21] but not really an exogenous shock. It's just performing poorly. [1:17:28] Yeah. [1:17:29] Man, this is tough. I'm starting to feel like that 4% interest rate is looking good on the bank account. [1:17:38] I mean, I think we've got to hold ourselves. We've got to hold ourselves, too. Yeah, we've got to make a bet.

[1:17:59] good or have been thinking about that don't necessarily fit this thesis? No, I want to do a D-SPAC or a battered stock. So I think let's go with 23andMe. And I think we should flip from analyzing the stock to becoming a promoter of it. So let's get Gemini to listen to its – to read its transcripts and construct a case for [1:18:29] be a 10 bagger for us. I love it. Okay, cool. So, so we're going to get the, um, [1:18:36] The webcast. All right. Let's try a webcast. Sorry. I don't know. This is going to be the same. Yeah, the transcript is going to be the same problem as the last time. Yeah. [1:18:46] That's the Q&A. [1:18:48] Yeah, I think that's fine. The Q&A is okay. Okay. [1:18:52] So... [1:18:55] We've got 2024 earnings call, the Q&A, and then... [1:19:01] Thank you. [1:19:02] Uh, we've got, let's keep going. [1:19:05] There's probably some investor presentation that's worth it as well as – [1:19:10] Yeah, all of these other things. Okay, cool. [1:19:13] Thank you. [1:19:13] Thank you. [1:19:15] All right. So we've got a bunch of these. [1:19:20] Oh, wow. [1:19:21] Interesting. [1:19:22] Look at this. This is like sort of a AI enabled Q&A.

[1:19:30] or maybe it's not AI enabled, but it's very organized and it's not like a, [1:19:34] Oh, it's not a transcript. I thought this was the earnings call. Got it. [1:19:38] So we've got the investor presentations, but I think... [1:19:41] Um... [1:19:43] Thank you. [1:19:44] Thank you. [1:19:44] Shit. [1:19:46] Uh... [1:19:51] Thank you. [1:19:52] Yeah, I don't see that. [1:19:54] available. [1:19:58] Earnings call transcripts. Let's see if we can find it. [1:20:02] Thank you. [1:20:03] seeking off a [1:20:06] Thank you. [1:20:07] All right, we've got it from Seeking Alpha. Thank you. So this is Q3 2024. [1:20:13] Let's see. [1:20:16] Ooh, 23andMe stock falls 20% amid earnings report breakup speculations. [1:20:22] I should probably read this before we... We YOLO into it. I can't read it because I don't have access to it. Yeah. 2023... The internet's so broken now. Break up speculation. [1:20:37] We've got three minutes. All right. I mean, it feels like if the clock is ticking, we've got to probably make a buy. 23andMe considers splitting up company to revive stock price. A day after the company reported dismal third quarter... [1:20:51] 2024 results and discussed splitting itself in two to help juice its stock. 23andMe reported $44.7 million for the quarter, down $66.9 million. And it received a deficiency letter giving the company

[1:21:03] 180 days to bring its share price back. [1:21:06] And Wojcicki said the company is considered splitting up its consumer and therapeutic business. [1:21:12] It feels like a buy to me. This is the moment of truth. [1:21:19] I mean, I think at the end of the day, we've already decided that this is going to be our buy. And now we're just talking about constructing the investment. I think you're right. I will say, like, I feel uncertain about this buy. You feel extremely uncertain about it. It has all the characteristics of all of our worst investments. [1:21:42] the content. We're doing it for the fans. We're doing it for the audience. This is what they call a YOLO trade. Okay, we're buying $1,000 worth of 23andMe. This is our stock that the AI has recommended. [1:22:12] So first of all, I'm going to press buy and I'll let you see it as I do it. [1:22:16] We're going to swipe up to submit. [1:22:20] Order received. [1:22:23] Thank you. [1:22:24] So there we go. There we go. [1:22:28] We made an investment. We made an investment. I feel horrible about it. Yep, me too. I don't think this one's going into our hall of fame. I don't think so either. But I think there is a lesson here, which is –

[1:22:41] when you have a really good strategy, and I think we have a good strategy, there's not always an opportunity that fits that strategy. And it's really easy psychologically to peer pressure yourself, as we just did, to make a horrible decision because you want to do something. And I think that that's really core to... [1:23:01] to the psychology of a good investor is you have to be really good at doing nothing, which most people are not. [1:23:10] And, like, I actually think that if we sit on this thesis, which we will because it's already always in our heads, there will be over the next, like, couple years, like, one or two opportunities that pop up that will obviously fit it and we will – [1:23:25] be able to take advantage of it. [1:23:26] Yeah, that really stands out to me. When we saw that happen to NVIDIA or Meta's stock price being depressed, those were the fat pitches. And you just have to be ready and wait for them. I should know, I regularly reference sports analogies in my life as someone who is not into sports at all. And so I actually have no idea what a fat pitch is, but I just know that it's something that I need to look out for. [1:23:56] And this was not that. This was exactly the opposite. My reflection is just since we were really trying to feature using LLMs today, was the massive context window is a huge benefit for Gemini. But the challenge with dealing with massive context windows is that you need to find enough content to load into that context window to make it useful.

[1:24:26] that the Internet today is kind of broken, and you can't really easily access lots of content, largely, I think, because no one wants to have that content indexed by LLMs. And so that's this kind of circular thing that I think is going to happen for a lot of the biggest benefits of LLMs in the near future, is that you won't be able to access the content that most takes advantage of their context window. I think that makes a lot of sense. [1:24:56] publishers and movie studios and whatever will do deals with LLMs like the same way that Reddit has just did a deal with Google to provide content so that you can like, you know, instead of maybe me buying a book for me to read, I could buy a book or like a set of books for my LLM to have access to, to ask questions about. And I think that would be [1:25:18] a world where you can have people who create content, like, benefit from using it inside of LLMs. And I think that'll be better for content creators because people, like... [1:25:29] it makes the books more useful. It makes you like, if you don't, if you don't have to read a 300 page book, like, [1:25:35] Your LLM can read it. You might get value out of it that's locked in there that would be relevant to you, but that you wouldn't know because you can't spend the time on it. I was just about to make the same observation. If you think about how many products that we ran into just during this hour of messing around with LLMs and trying to make a stock pick, every single one of those roadblocks that we hit, we would have been willing to pay a content site a bit of money like buying an app in the app store to get that content into the LLM and make our next bit of progress.

[1:26:05] opportunities like that for content companies on the internet 100 i'm like just envisioning like a one click thing that it's like take all this stuff and just like like push it into like some some vast file store that like is hooked up to gemini or chat gpt or whatever and you can just scroll around the internet like clicking and clicking and clicking and each time it's like two dollars or three dollars or whatever and then you can create this like large personal database that you can use to make decisions or find stocks or whatever yeah and i think that that information being updated is [1:26:35] really key input. So there were so many times that we ran into a roadblock that looked something like, well, we don't have the latest data or we don't have the list of stocks and all the data required against them. So anything that has a real-time data source is going to be really advantaged. That's something that stood out to me. Totally, totally. The other thing that stood out to me was, aside from the information availability, there's this issue where the LLMs are not really willing to just make a recommendation. And in fact, [1:27:05] like they're getting worse and worse over time. There's the sense of they're just getting a little bit frightened of saying anything too direct. And so I think the golden age of LLM use might be in the near future when things haven't gotten locked down too far just yet and you're able to get enough context into that context window. I think that makes a lot of sense. There's also just this

[1:27:35] to kind of milk toast, it means that there's always opportunities for people to build ones that are willing to return riskier results. Like that's the limits of the, of the models, usefulness and intelligence is not actually technology driven anymore. Like that is one limit, but like mostly it's like, what do we allow the technology to do? And I think there's a lot of opportunity for people who are willing and can take the risk to allow it to do more stuff to, [1:28:05] that [1:28:06] people will want to use. [1:28:07] Yeah. We're going to have to make another stock bet again in six months to see how it does. Let's do it. Well, thank you so much for coming on. This was amazing. I loved every second of it. And I feel terrible about like that was the worst way I've ever spent $1,000, but it was worth it to get to sit down with you. I think it's worth it too. And as someone who didn't spend $1,000 on the bet, I still feel pot committed to it. [1:28:37] 23andMe every day now. Amazing. Awesome. Well, thank you for this. Of course. See you next time.

[1:29:07] I want to exit that position. I want to take the win. And then I want to go into another stock that I think fits the thesis. And I want you to help me explain why it might fit this thesis for everyone who's listening. [1:29:22] I can't believe we made money in that trade, but let's do it. So this, kids, is how you make money on day trade. [1:29:30] We're down minus 4% on the 23andMe since we bought it last week, and we're up 9% total. So I'm just going to sell all of it. I'm going to do a sell-all trade. We're going to make some money. [1:29:46] and [1:29:48] done. Is it done? [1:29:50] It's done. We made money. Okay. Wow. Considering how little thought went into that, that's actually pretty impressive. That's pretty good. A stop clock is right twice a day or whatever. I feel pretty excited about it. So the thing that we want to do now is I actually think that Google sort of fits this thesis to some extent. [1:30:20] earnings like a month ago. But the real interesting thing that occurred to me is they've had this sort of exogenous shock where over the last week or so, there have been all these problems with Gemini. And I think that that is driving down the stock price. It's lost $70 billion in value over the last week. And I just feel like it might fit that thesis. What do you think?

[1:30:41] Thank you. [1:30:41] Yeah, I think that Google is, I mean, it's up 50% year over year. So it's hard to say that it's, you know, doing poorly. But in the last few weeks in particular, Google, [1:30:57] There was the combination of a negative perception moment, [1:31:02] which they've been affected by a couple of times before, especially on the sort of comparative chat GPT. And it was combined with their earnings disappointed because their revenue per ad impression wasn't as good, I think, as well as their CapEx was high, unusually high. [1:31:26] And I think investors are right to perceive that, well, something is changing in the Google model. They're going to have to spend more on CapEx for longer in order to serve search with Gemini and with LLM type features to serve costs more to deliver. And at the same time, it's harder to load ad units into it. [1:31:56] confirmed by the recent earnings, even though obviously they're not terribly affected by LLMs just yet. And at the same time, people's fears about Google being incredibly corporate, woke, unable to get out of its own way were confirmed by all the Twitter, ChatGPT, Dali comparisons to asking questions of Gemini.

[1:32:26] for the exogenous shock component of the thesis. [1:32:30] There's still the other parts, though, too, which are, well, does the company have a tailwind that it benefits from? And does it have an extremely scalable business model? [1:32:42] so that when that tailwind shows up, the company is able to capture a lot of the flow of demand. And I think it's worth repointing out that Google has one of the most scalable business models ever conceived. So that helps. But if we specifically analyze Google from the perspective of, well, in the future, they're going to need to deliver search results in a way that requires a lot more compute. [1:33:12] They are still advantaged in that business model because inside of Google, they've built their own, basically their own mini NVIDIA. [1:33:22] They actually design their own semiconductors, and then they have their own cloud to deploy those and deliver on AI-based search as well as cloud services. And so they're extremely scalable business model in spite of having a bit more cost in the near term. [1:33:42] is actually a huge beneficiary of this tailwind in LLM-generated search and LLM-generated experiences. So I do think that it qualifies so long as you're okay with the lower margin of safety.

[1:34:02] It's not like the stock is way, way down. You're right. That is true. [1:34:12] on Google, they're like, search is going away, blah, blah, blah, all that kind of stuff. I think it's reflected in the stock price. But I think people forget that everyone felt that way about Microsoft like five or 10 years ago. And before that, everyone felt that way about Apple like 15 years ago. And both of those companies managed to get through those periods and come back really, really strongly in the subsequent technology waves. And I just feel like Google may be going through a rocky period. It may go through a rocky period for a while longer, but I do think it's [1:34:43] I mean, the fact that they got you to start experimenting with Gemini alone, I think, is the best indicator. And so if they're able to keep your attention and you find yourself using Gemini more and more, I think that's a good reason to hold on to it. [1:35:00] I agree. Okay, so let's roll our 23andMe winnings into Google and hope that Sundar delivers. [1:35:09] So I'm going to do dollars and I'm going to put in 1,087. So we're buying $1,087 worth of Google. [1:35:24] and [1:35:26] We're heading by. [1:35:28] We did it. We're in Google. Go Gemini. Go Gemini. Go Sundar. Make us some money. Thank you, Jesse, for coming on and completing this last segment of the episode. I'm excited for it and I'm excited for our next 10 bagger.

[1:35:46] All right. So excited to see what happens here. Thanks a lot. Of course. [1:35:52] oh my gosh folks you absolutely positively have to smash that like button and subscribe to how do you use chat gpt [1:36:07] Why? Because this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard. But instead of gold, it's filled with pure, unadulterated knowledge bombs about chat GPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat. [1:36:25] craving for more it's not just a show it's a journey into the future with dan shipper as the captain of the spaceship so [1:36:32] So do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. [1:36:38] And now, without any further ado, let me just say, Dan, I'm absolutely hopelessly in love with you.