Transcript: Can Gemini 1.5 Pro Beat Our Best Stock Trade?

The transcript of How Do You Use ChatGPT? with Jesse Beyroutey is below for paying subscribers.

Timestamps

1. Introduction: 01:29
2. How Dan made the greatest trade of his life: 03:50
3. Jesse’s strategy to use LLMs to get nuanced answers 05:27
4. Gearing up to orchestrate the best trade of our lives with Gemini Pro 1.5 09:20
5. How Jesse gets AI to make great decisions 17:52
6. Using Gemini Pro 1.5 to find patterns in data 22:38
7. How AI can provide deeper insights into the stock market 26:48
8. Leveraging Gemini Pro 1.5’s huge context window to analyze data 34:41 
9. Gemini Pro 1.5 and ChatGPT go head-to-head 46:33 
10. Choosing a stock with just 15 minutes left on the clock 1:10:11
11. What Jesse thinks are the biggest new opportunities enabled by LLMs 1:24:01
12. The epilogue Jesse and Dan recorded one week after making the trade 1:28:43

Transcript

Dan Shipper (00:00:00)

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 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 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. We're going to swipe up to submit. Order received. So there we go.

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 Labenz, who was actually on this show and did one of the most popular episodes we’ve ever had about how to use AI as a copilot 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. He talks to the researchers and entrepreneurs who are shaping this moment, like Logan Kilpatrick of OpenAI, who I interviewed for this show as well, Eugenia Kuyda of Replika, and Suhail Doshi of Playground.

To listen to the show, search for Cognitive Revolution in your podcast player. Alright, now let's get back to How Do You Use ChatGPT?. 

Jesse, welcome to the show. 

Jesse Beyroutey (00:01:32)

Thanks, Dan. I am just delighted to do this with you.

Dan Shipper (00:00:36)

For people who don't know, you are one of my closest friends, and you are also a partner at IA Ventures. IA is a $600 million venture fund, and you've done seed investments in public companies like Wise and DigitalOcean. And you're both, I think, one of the smartest people I've ever met. You really have this way of digging down into an issue and kind of figuring out the crux of it. And you're just a very, very good friend and very good person. And I’m just so lucky to have you in my life. And I'm so happy to be able to do this with you. Yeah. Thanks for coming on.

Jesse Beyroutey (00:02:22)

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 managed to stretch me in ways that have ultimately been so additive and productive in my life. The last time was helping me get one of my first things out onto the internet that people regularly reference back to me like, oh, I saw you on every, so I'm really excited about this too.

Dan Shipper (00:02:59)

Great. I get to hang out with you and hear all your smart thoughts all the time. And I'm just trying to bring more Jesse into the world. So this is 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 sort of wild. And our goal is to put it through its paces and try to see what we can do with it. And the concept that we came up with, I think it's gonna be really fun. And I'm just sharing my screen, because, just 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, I think, probably the best trade, at least, I've ever done. I don't know about you. You're a professional investor.

Jesse Beyroutey (00:03:55)

It's mine too.

Dan Shipper (00:03:56)

Yeah. So, in 2019, we created a little Notion doc called Beyroutey x Shipper Investments because we wanted to take a bet on a specific company and the company that we wanted to bet on was Nvidia. And 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 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 GPU architecture, and its position in the market should only grow as machine learning and gaming increases the need for high powered GPUs and computers, so the price dip should be temporary. So, that was the trade of our lives. 

Jesse Beyroutey (00:04:50)

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. So, it's not like we were absolute geniuses, and we didn't have LLMs at the time. So, maybe today it’ll be different. 

Dan Shipper (00:05:15)

Yeah. So the concept for the show is we want to find 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.

Jesse Beyroutey (00:05:24)

Yeah. I'm really excited about this in particular because I love using LLMs for role-playing-type exercises as almost a conversational participant along with me. So my favorite sort of prompts for ChatGPT, and now for Gemini, assume that you are such a famous character. What would you have to say about X? 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. And now, today, being able to do it with like an insane context window means that we can just load in like all of the context around a person and see Gemini can take the perspective of that person as if they're like an analyst on our little hedge fund team.

Dan Shipper (00:06:19)

I love that. I'm curious, what are the names of people that you've used and found to work well so far?

Jesse Beyroutey (00:06:29)

It really depends on the setting. But I mean, I just generally always try to ask like, what would the CEO of a famous company in that industry—so, let's say I'm analyzing something about aggregators, I might ask, what would Jeff Bezos have to say about this? 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 some meaningful thing that the LLM might be able to draw from. And then also those whose perspective is generally a little bit contrarian or comes at things from a different angle than what the average of the internet might have.

Dan Shipper (00:07:16)

That makes sense. That's really cool. Yeah, I love that. So I want to get us going 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 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 round of investment.

Jesse Beyroutey (00:07:41)

Right, exactly. So back when we were doing our little hedge fund in 2019, our idea was we wanted 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 long-term investor, it gives us the advantage of a margin of safety. Oh, if it's trading down by 20 percent, 30 percent, or whatever, then we can be a little bit wrong about things and still not lose too much money as happened with our worst-case investment that we made around that time, where it took us a little while, but we eventually recovered our principal on it and we're able to live to die another day.

Dan Shipper (00:08:27)

Yeah, totally. And I will say, 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. I think we should also say for anyone who's listening, you shouldn't 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. So this is not investment advice. You should probably buy index funds unless you really know what you're doing. But, anyway—

Jesse Beyroutey (00:09:05)

Treat this as worse than WallStreetBets because it doesn't even have the common thread, and more on that later because we might even post our bet to WallStreetBets. 

Dan Shipper (00:09:13)

We are going to probably post our bet to WallStreetBets. But one thing that I forgot to say is we are going to put actual money down. So I created a Robin Hood account, which is the first time I’ve ever had a Robin Hood account. I put $1,000 in and hopefully, by the end of the episode, we will find you a company to put $1,000 in and we'll be able to track how it does. So yeah, I think you've set up the filter of what we're looking for appropriately. And I know you've been looking through companies to start our research with. Do you want to share your screen and show us what you've been looking at?

Jesse Beyroutey (00:09:47)

Yeah, let's open it up here. So I just popped open this website TradingView and it gives you a way of screening all of the available stocks against a bunch of filters and criteria. And when I thought about the context of our Nvidia investment we were looking at companies that weren't massive yet, but had the potential to be the tenbagger 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 $100 billion in market cap. It could become the next trillion-dollar company but it's starting from small beginnings. I think Nvidia was something in the $50-100 billion range when we first invested and now it's a $2 trillion company today, depending on the trading. So I was looking for companies 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 like that. We're looking to avoid our total bozo risk as much as we possibly can. And the way that we're trying to do that is just, okay, the company has to figure out how to make money somehow. And then aside from that, I was just looking for, 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 percent or something like that. But then on a five-year basis in this column is also down, but we might come up with a reason for why that was the basic screen, and we were only looking at technology companies because that was what Dan and I thought maybe we'll have something. But I think we should also try to do companies that we know absolutely nothing about later.

Dan Shipper (00:11:40)

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. But I just want to confirm that that seems like a good idea to you.

Jesse Beyroutey (00:11:54)

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.

Dan Shipper (00:11:59)

Somehow, you're going to have to get that stock screen over to me so I can throw it into Gemini. Alright. So what we've got here is you copy-pasted your output from, from the trade view.

And I'm going to just head into Gemini. And so, again, this is not ChatGPT. This is Gemini 1.5 Pro, which is this new model. It's a private beta. And what we're going to do is we're going to take the output that you gave me, and we're going to try to filter it by our criteria. Let's say something like, hey, I'm trying to pick a stock. I want to find a tenbagger specifically. I'm trying to replicate a trade I did in 2019 where I bought Nvidia. It was down temporarily because of the trade war and now it's a $2 trillion company. Here's a list of potential starting points for trades. Does anything pop out to you? Any revisions there? Does that seem like a good time? Okay, cool. So I'm going to paste it in and hit go, see what happens. One of the things I've noticed about Gemini is it's slower than ChatGPT, so it can take a million tokens, but you have to wait—I don't know. Sometimes it takes a minute for it to actually return, which is—

Jesse Beyroutey (00:13:53)

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.

Dan Shipper (00:14:02)

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 tenbagger is extremely difficult. While your Nvidia trade was successful, replicating that exact scenario is unlikely.” Thank you, Gemini. Appreciate that, but you're saying there's a chance, 

Jesse Beyroutey (00:14:24)

Don't give up all hope.

Dan Shipper (00:14:25)

“However, I can offer some insights on the list. You provided potential growth stocks, Bill Holdings Inc.: This company provides cloud invoices and payments. It has shown strong revenue growth and has the potential to benefit from the increasing adoption of visual payment solutions. Klaviyo: This company offers an email marketing platform for e-commerce businesses and has a strong track record of growth and is well positioned in a growing market. Appian: This company provides a low-code platform for building business applications to 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 is important to ensure the price is justified.” Okay, so it identified Bill Holdings, Klaviyo, and Appian. I think we should strike Appian because I just feel like low-code is just like such a bad idea in an AI market. But I'm curious if you have a differing opinion and or if any of its other suggestions pop out to you as something we should explore.

Jesse Beyroutey (00:14:24)

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 we're specifically looking for, as a starting point, a company that's artificially depressed. And so we want to figure out what reason there might be for the company to be artificially depressed and give us that. That nice feeling that we can make our money back, even if we're totally wrong. So I would actually even—let's 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.

Dan Shipper (00:16:20)

Okay. And should we use the trade view and say in the trade view or—

Jesse Beyroutey (00:16:27)

Can't hurt. I mean, it might be aware of what that is but also even if it's not, stock screener and type filters are pretty generic. So I think it could just give us some ideas.

Dan Shipper (00:16:37)

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? And I will say, these are things that we could do with ChatGPT and hopefully once we narrow things down a little bit, we will start using more of Gemini's increased capacity to analyze data. Alright. So, “Here are some criteria you can use to construct a stock screener price-to-earnings ratio. Look for companies with a P ratio significantly lower than their historical average price-to-book ratio. Similar to PE, a PB 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. I don't really want to use technical indicators. So I don't know if any of those things spark something for you. We could also think about 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.

Jesse Beyroutey (00:17:52)

My immediate instinct is to ask it to just make a decision. So every time I ever get some kind of summary from ChatGPT or Gemini, it's always like caveated 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?

Dan Shipper (00:18:09)

Okay. So, make a decision. Do the best you can. Yeah. Okay. You kind of want to download The Intelligent Investor and just to have. “Based on the information provided, it is impossible to make specific investments choosing a stock—” You know, I think Google's model is going to be pretty safe.

Jesse Beyroutey (00:18:39)

We're running up against some—Google doesn't want to be liable for what we did, which I get it we're two dumb people on WallStreetBets trying to make some kind of new idea here. But I think we should try to get it to be a little bit more explicit.

Dan Shipper (00:18:58)

Yeah. We could say, pretend you are—I don't know—Warren Buffet or something. Yeah, let's try that. And I've come to you to make a final decision on—do you want to have it decide on a trading strategy or on a stock?

Jesse Beyroutey (00:19:11)

I think we should go with a trading strategy to start with.

Dan Shipper (00:19:14)

And this will probably weight it towards Warren Buffett's trading strategy. But I think it’ll get it to make a decision, for sure. 

Jesse Beyroutey (00:19:20)

Does it work with links? 

Dan Shipper (00:19:28)

I don't think so, no. But we can just copy-paste anything that's in a link into—

Jesse Beyroutey (00:19:32)

Does it work with PDFs yet, or no?

Dan Shipper (00:19:34)

It works with PDFs. Okay, got it. Sweet.

It also works with videos. So if you've got any videos or audio—also great.

Jesse Beyroutey (00:19:44)

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, okay, since he's been in the news a lot, I'm trying to think of a good thing to feed in for Bill Ackman. Let's have, let's have, let's get Bill's opinion on how to find a good distressed stock right now. 

Dan Shipper (00:20:08)

Warren Buffett in Gemini says, well, “I don't advocate for frequent trading. If you insist on starting a strategy, consider a value-oriented approach, look for undervalued companies using metrics like P/E, P/B, and P/CF, 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 a low P/E filter is an interesting one to consider. 

Jesse Beyroutey (00:20:34)

Yeah. So 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.

Dan Shipper (00:20:44)

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 in that bucket, and these are the companies that have a fairly low price-to-earnings ratio that might be depressed. I have not filtered this by tech companies and maybe that's purposeful. I just want to make sure you're good with that.

Jesse Beyroutey (00:21:16)

Yeah, I think we can do a broad screen and just have it tell us what to do, like an analyst would.

Dan Shipper (00:21:26)

Perfect. 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 work that well.

Jesse Beyroutey (00:21:38)

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—so, if you filter it by the word performance, they have ways of screening by six-month performance, et cetera. 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.

Dan Shipper (00:22:10)

Yeah. I like that because it indicates strength, but temporary dysfunction. That's what we're looking for. My therapist told me that last week, so that's where that came from. So we've got 29 matches and we could look at them individually ourselves. We could throw them into Gemini. What's your call?

Jesse Beyroutey (00:22:38)

Yeah. So I think that now is a good time to throw them into Gemini and ask it to look for points of commonality or something like that.

Dan Shipper (00:22:46)

Okay, cool. Points of commonality. Tell me more about that.

Jesse Beyroutey (00:22:51)

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 and why?

Dan Shipper (00:23:07)

Alright. So I'm just going to paste the plain text and see how that goes. Okay, cool. So, okay. So it says, “Clustering stocks involves grouping them based on similarities. Here's some potential approaches in the rationale of 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 investors, technical indicators and price behavior might be more important.”

Jesse Beyroutey (00:23:38)

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 or the nature of the company and its position in the industry.

Dan Shipper (00:24:00)

So I'm just literally typing what you said, and see what it does. Alright, let's try it. And I'm noticing that it's a little bit hesitant for some of these queries to really give us an answer. I'm not sure that ChatGPT would be so hesitant. Alright. Well, let's do a side-by-side. We should do a side-by-side while this is loading. So Gemini said clustering stocks by company, nature, and industry position. 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 for batteries or anything related to chips or silicon or whatever seems like an interesting play, but I bet those are already hot. I don't think they're depressed right now, right? 

Jesse Beyroutey (00:24:57)

Yeah, we're going to have a hard time finding anything depressed that's around semiconductors because it's so on thesis right now.

Dan Shipper (00:25:02)

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 and global commodity prices.”

Jesse Beyroutey (00:25:13)

That doesn't sound like our kind of investing.

Dan Shipper (00:25:14)

So consumer-facing companies, Avis Budget Group. I hate Budget. I will not invest. This is like a moral stand we’re taking here.

Jesse Beyroutey (00:25:30)

We're only investing in a company that we actually like.

Dan Shipper (00:25:32)

Or at least one that I haven't heard of, or at least one that I haven't had a personally horrible experience with.

Jesse Beyroutey (00:25:39)

That’s funny because out of the whole list, the one that stood out to me was Gogo. I was thinking about how it's potentially artificially depressed because it's both a brand that people hate. Everyone has the same reaction that you just had to Budget. And also at the same time, there's the buzzy Starlink company that's going to try to go after them. And so I wonder how much that impacts them.

Dan Shipper (00:26:05)

That's an interesting thing to look at. I love that. Okay, cool. Dinmode, which I have no idea what that is. We could look it up. 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, Intest Corporation, Universal Security Instruments, and Kimball Electronics. “These companies develop a provider, technology-based products and services, including software.” And then we've got a couple more: 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.

Jesse Beyroutey (00:26:43)

Yeah. I mean, I think a lot of people really dislike DaVita. So that that's another one. And 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.

Dan Shipper (00:26:59)

Okay. So, “Which of these businesses are most likely to be trading poorly because consumers dislike the brand?” Because I think what you want to do is just strike them from our list.

Tell me about that though, because if consumers dislike the brand, theoretically, that leaves a lot of room for the competitor to come along that would kill the company, right?

Jesse Beyroutey (00:27:27)

Yes and no. So if consumers dislike a brand, but it has some crazy distribution lock-in so—Gogo being a great example. Maybe 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.

Dan Shipper (00:27:49)

I get it. Okay. So, “From the provided list, the business is 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 Avis Budget Group: While car rentals are generally more susceptible to economic fluctuation, travel demand, negative experiences, customer service vehicle, or could damage brand perception.”

Jesse Beyroutey (00:28:14)

Alright, I’m getting a feeling here, which is I just think that Gogo is going to be interesting for us to analyze.

Dan Shipper (00:28:18)

I love it. So I want to dig straight in and start talking about Gogo. How do we do that? So I think the key question for Gogo is whether or not their technology can be upgraded.

Jesse Beyroutey (00:28:30)

So it's clear that they have a distribution advantage already.

Dan Shipper (00:28:35)

‘Cause they're already in all the airplanes. 

Jesse Beyroutey (00:28:37)

They're in all the airplanes. 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. And so I think it'd be interesting to start talking through with Gemini, how Gogo might go about.

Dan Shipper (00:29:08)

I love that. I think that's a really interesting place to start. Why didn't you first think about airline switching costs or how hard it is for the airlines to rip them out and move to someone else?

Jesse Beyroutey (00:29:17)

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, 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. They have them to manage.

Dan Shipper (00:29:44)

Okay. That makes sense. Okay, cool. So should I just ask that?So, “How hard would it be for Gogo to produce hardware that would allow it to upgrade its current services in planes to”—what? To be like Starlink technology? 

Jesse Beyroutey (00:30:09)

Yeah, to improve service quality using the latest in connectivity like Starlink.

Dan Shipper (00:30:15)

Okay. “—like Starlink.” Alright. Let's see.

Jesse Beyroutey (00:30:19)

And then I think this is also a good opportunity to start integrating some of Gemini's giant processing capability. And my immediate thought is let's just get the earnings transcripts and see how much they're talking about.

Dan Shipper (00:30:34)

Okay, great. How do I do that?

Jesse Beyroutey (00:30:35)

Just go to their website and grab the earnings transcripts, I think is the best way. We could also ask Gemini if there's a faster way to load 'em all in and see.

Dan Shipper (00:30:45)

No, I just, I've never gotten anyone's earnings transcripts.

Jesse Beyroutey (00:30:46)

Oh, yeah. So they have to show me. I mean, literally, the dumb and simple way is to find their IR site and go to their quarterly results.

Dan Shipper (00:30:54)

Okay. Cool. Investor relations. Here we go. Do we want annual reports? Earnings reports? And then we want the earnings call.

Jesse Beyroutey (00:31:09)

Exactly. So the transcript usually has all of the conversation already transcribed, but we could also ask Gemini to listen to the audio and see how they sound.

Dan Shipper (00:31:21)

Well, what I want to do, what I'm really interested in is whether Gemini can detect the voice tone and stuff like that to see, oh, are they really nervous or whatever. 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 deal with Gogo and ask for their quarterly results. Gogo earnings. Earnings transcript. That's what you want? Earnings transcript.

Jesse Beyroutey (00:32:06)

Yeah, but also, by the way, I just found it seems like there's a company that publishes the conference calls on YouTube. So I just tried searching YouTube for Gogo earnings call.

Dan Shipper (00:32:26)

Great. And I can download a YouTube downloader.

Jesse Beyroutey (00:32:32)

Oh, Gemini can't just go straight in and process the YouTube link. I see. Got it. Oh, actually, nevermind. It only had a couple of random ones. I thought it was every single one. Alright. Different strategy. Pivot. 

Dan Shipper (00:32:50)

Pivot. 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—

Jesse Beyroutey (00:33:03)

Well, I'm thinking let's actually try to load in like a bunch of the transcripts at once. 

Dan Shipper (00:33:08)

You want to do the 10-K from 2022?

Jesse Beyroutey (00:33:11)

Sure, but I think the transcripts have some more—there's Q&A in there. And what I'm really wondering is how much things like replacement cycle and Starlink as a competitor and whatnot are coming up and what management's sort of reactions to those.

Dan Shipper (00:33:28)

This is so good. Okay. So I have all the earnings transcripts from 2022 and 2023. Is that enough to start with? Okay. I'll start with that. So I'm downloading. Save.

Jesse Beyroutey (00:33:45)

I realized that our potential bet on Gogo here has the characteristics of our worst investment more than the characteristics of our best investment. 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 people were thinking negatively of it because of that sort of recency of the announcement. 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, 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 actually our dislike is for good reason. Right?

Dan Shipper (00:34:41)

I love that. Well, to that point, so we have a response from Gemini about how hard or easy it would be to upgrade its hardware. And so Gemini says, “For Gogo to produce hardware that would allow it to upgrade its current services and plans to improve service quality, several factors need to be considered. Compatibility: Gogo's current systems operate on ground based cellular networks. While Starlink utilizes satellite constellations, integrating these two technologies would require significant engineering effort. Hardware development: Developing new hardware that can communicate with Starlink satellites and integrate with existing aircraft systems would be complex and expensive regulatory approval.” So, I mean, we have to take all this with a grain of salt. It could be making it up. For all we know, Gogo has this. 

Jesse Beyroutey (00:35:23)

Well, let's go to the transcript.

Dan Shipper (00:35:24)

We should Google or 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 ask some questions. See how it does. So we're going to take this and we're going to throw it in here. And we'll see it's all being uploaded. What would be your first question be of these transcripts?

Jesse Beyroutey (00:35:52)

I would ask to what extent is management already talking about upgrading?

Dan Shipper (00:35:56)

Nice. Okay. Upgrading to new technology. How's that? So I'm just saying, “To what extent is management already talking about upgrading to new technology?” And 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, GPT-4 Turbo. So we're pushing the limits of existing technology already. Let's do it. Again, we need the waiting music. We need the already baked response to take out of the oven. 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: Gogo remains on track for a 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. Gogo is already 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 one web low earth orbit, LEO satellite constellation. This will enable Gogo to offer global broadband cognitive connectivity to business aviation, 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. 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.

Jesse Beyroutey (00:38:06)

Fantastic. Well, that's looking pretty positive. I could imagine people not following that, specifically. Now let's ask to what extent would that upcoming change already be priced into their stock and how would we figure that out.

Dan Shipper (00:38:23)

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?” I think it'd be worth also inquiring as to why is the stock down right now? ‘Cause we're assuming that it's probably because of Starlink, but maybe it's something else.

Jesse Beyroutey (00:38:40)

Maybe global aviation is not doing well for totally other reasons.

Dan Shipper (00:38:48)

Alright. “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. New technology, strong stock performance: Gogo stock price has performed well in recent years, significantly outperforming the broader market.” Is that true? We should probably check that. “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, saying that we should check high trading multiples. “Gogo stock trades at relatively high multiples compared to its peers. This is just that investors are willing to pay a premium given that we filtered by low low P/E ratio companies.” I'm surprised that it's a high-trading multiple. “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 technology.” So what do you think? Do you want to start with analyzing analyst reports or is there a follow up question you want to ask?

Jesse Beyroutey (00:39:51)

Yeah, well, I'm particularly trying to think about ways that we can use the advantage of a giant context window. And analyst reports would have been great if we had easy access to them, but I don't know if we're going to be able to easily download them.

Dan Shipper (00:40:06)

You don't have any like subscription to—

Jesse Beyroutey (00:40:12)

I got as much as the average Redditor does. So I don't think that that's going to be a useful direction. Where I'm at right now is I'm thinking about how we're trying to establish why Gogo is down.

Dan Shipper (00:40:38)

And that's because we started with a stock screener and just looked at things that were down.

Jesse Beyroutey (00:40:40)

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. So now I'm starting to think that maybe a different approach would be better where we're actually starting from more like recent news events or things going on in global macro that might cause something to artificially trade down that we can specifically find.

Dan Shipper (00:41:10)

I love that. Okay. We can totally do that. I think we would probably use ChatGPT for that.

Jesse Beyroutey (00:41:17)

Alright, let's do it. 

Dan Shipper (00:41:21)

What's down, but—unless you had a sense for how you wanted to go.

Jesse Beyroutey (00:41:24)

No, I don't have any more sense than I said.

Dan Shipper (00:41:25)

Yeah, let's try it. Let's give that a shot and we'll see. I don't want to lose the Gogo thread. There's something in it. There's something in it.

Jesse Beyroutey (00:41:32)

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. And I think we could potentially establish that, but it'd be hard to feel confident about it.

Dan Shipper (00:41:50)

I just did a little search. And one thing that's coming up already. Ah, Gogo delayed its launch of an in-flight 5G network for the 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. And they attributed the delay to a design error made by a third-party subcontractor over its solution provider. “In-flight internet provider Gogo Business Aviation is delaying the 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 flaw in its chips to push the launch back further to mid-2024.” So I think one of the things in the calculus is, do we think that they'll end up executing on this? Are the endless delays signs of incompetence? Or do we want to bet—

Jesse Beyroutey (00:42:43)

Yeah. I definitely see that. And I guess the thing that feels important to me here is that delays are an internal thing. And what we're really looking for is a stock trading down to an exogenous. So, great example: Nvidia, it was the trade war, more recently Meta is an amazing trade because it was artificially down due to AT&T and uncertainty around it. So I'm really hoping we can find some exogenous factors right now that might be affecting stocks.

Dan Shipper (00:43:16)

Okay. What are some stocks that are trading down because of exogenous factors? And should we maybe say tech stocks or just any stock? I'm going to do this and I'm also going to do it in Perplexity. Alright, because I don't know. Perplexity might work actually. So let's see Perplexity first. Okay. Perplexity is not answering this question. Well, it's basically telling me why stocks might trade down rather than using stock prices. And. some stocks are trading down due to exogenous—ChatGPT says some stocks are trading down due to exogenous factors in 2024 including those affected by inflation data and the energy sector stocks. “Inflation data impact stocks in general have experienced downward pressure due to higher than expected inflation data. The CPI data for January showed a 3.1 percent year over year increase. so inflation is one big exogenous factor and then energy, energy stocks after leading the market in 2022, took a breather in 2023, losing 6.7 percent by mid December compared to a nearly 20 percent gain.” So what does this make you think?

Jesse Beyroutey (00:44:21)

My immediate instinct is well, if energy stocks are artificially down because of a bunch of exogenous factors, the second part of a thesis is that also we want companies that are going to benefit from a positive wave of adoption due to 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 government is investing in it a lot at the same time that there's maybe some reasons why the energy stocks are down.

Dan Shipper (00:45:00)

So are you thinking of big energy stocks like Exxon, or are you thinking of trying to find some like a solar company or some wind company or nuclear or something like that?

Jesse Beyroutey (00:45:10)

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. 

Dan Shipper (00:45:30)

And Meta had this advantage in being the highest at scale player for advertising for a certain type. Right? 

Jesse Beyroutey (00:45:35)

Right. 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.

Dan Shipper (00:45:46)

Okay. And how would you suggest we go about that? Should we ask what energy companies control like a key bottleneck? Yeah, let's do that. And I really want to frame it in reference to, “and are positioned to ride a new technology wave.” Yeah. “What energy companies control a key bottleneck in the value chain phrase 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, shit the bed.

Jesse Beyroutey (00:46:28)

The best analysts do that too.

Dan Shipper (00:46:33)

We can't help ourselves sometimes. Alright, let's see. We're waiting for ChatGPT generation, but I think while ChatGPT is thinking, we could just go back over to Gemini and throw that in as well and compare. So I'm going to ask Gemini what energy companies control key bottlenecks and the value chain in our position to do a new technology wave over the next five years in energy. It’s saying, “In the energy sector, companies that control key bottlenecks in the value chain and are positioned to write a new technology 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. So hydrogen production and fuel 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 technology and related infrastructure are well positioned to capitalize on this hydrogen power vehicles and fuel cell. Electric vehicles are expected to play a complementary role 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 are 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?

Jesse Beyroutey (00:47:53)

Well, we need to ask for public stocks. So let's ask it for examples of public stocks that might benefit in each of those categories.

Dan Shipper (00:47:59)

Okay. Give us some public stocks that fit each of these categories. 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 write 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. “This gives them significant leverage in the value chain as it can influence the flow and pricing of these commodities, new technology waves, and midstream companies are investing in new technology to improve the efficiency and sustainability of their operation. This includes pipeline leak detection, automated pipeline operations and carbon capture and storage. Examples are Kinder Morgan and Enterprise Products Partners.” I like that. It's giving examples. It already went to the examples.

Jesse Beyroutey (00:48:45)

Yeah. Clustered them in a useful way.

Dan Shipper (00:48:49)

Yeah. It's pretty cool. “Renewable energy developers bottleneck renewable energy developers control the development and construction for renewable energy projects. This gives them a key role 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. Solar panels, wind turbines, energy storage, and it's suggesting next era 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 bottleneck energy storage is a critical bottleneck and they 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?

Jesse Beyroutey (00:49:43)

Well, I'm thinking let's find out if any of those are artificially down.

Dan Shipper (00:49:49)

Yeah, exactly. Okay, cool. I wonder what the oh—let's compare to ChatGPT. So ChatGPT says, “Plug Power for hydrogen production. It says Plug Power, Inc. Ballard Power Systems and Bloom Energy. And then for building resilience of supply chains, it says Albany corporation, Freeport-McMoRan Corporation, Rio Tinto Group, which who knows. And then green business: It recommends Beyond Meat, Tesla, and First Solar. So actually, the green business is the one sort of overlap between Gemini and what I'd like to do is have it just output a clean list for us. Here's a list of other recommendations. Please print them out. “Please print these and your recommendations as a bulleted list with just the ticker symbol,” just so it makes it easy to add to our stock screener. Beautiful. So then I'm going to split my screen and what was the stock screener again TradingView. Okay. I'm not ready. And then how do you in TradingView, look at a specific set of tickers, symbols, filters.

Jesse Beyroutey (00:51:15)

I think you can—

Dan Shipper (00:51:20)

I think I just type in a symbol.

Jesse Beyroutey (00:51:21)

Yeah. I don't think that there's a faster way of doing it. We've got our clean list of recommendations.

Dan Shipper (00:51:20)

Yeah. How should we start? Just go down the list?

Jesse Beyroutey (00:51:36)

Yeah. I'm trying to figure out a way to upload them, 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.

Dan Shipper (00:51:53)

I mean, okay, well, we'll just do it this way. So let's go one-by-one. So we're going to start with KMI and we're going to just kind of do a little spot check of KMI. Looks like it is down. We've got a $38 billion market cap. Where is the P/E ratio? 16? So it's like just above our threshold. Dividend yield is 6.55 percent. Anything sticking out to you here? Should we move on to the next one?

Jesse Beyroutey (00:52:29)

Yeah, it just doesn't look like it's gotten hit by any kind of recent exogenous event. And that's really like a key factor that we're looking for.

Dan Shipper (00:52:37)

Yeah. It's down 10 percent over five years and it's down only 0.29 percent over the last six months. So I think we're good. We're good on that one. So I'm going to just pop this out. I think it's not really working that way. So next one is EPD. So EPD is Enterprise Products Partners LP. This is also up 5 percent over the last six months, so that's not really that good. Let’s see, NEE. NextEra Energy Inc. down 15 percent over the last six months and up 20 percent over the last five years. Okay, 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 to the following segments.” I have no idea what that means. “The segment involves the energy transmission distribution and sale of electric energy in Florida. The near 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 there's something good there. I think it at least passes some initial criteria. Yeah. What are you thinking?

Jesse Beyroutey (00:54:18)

This is making me think that I just kind of keep going back to what works so well with Nvidia. And I realized that there's the trading down due to an exogenous factor that stands to benefit from a technology wave. And also there's this last aspect, which is an 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 we need to assess that specifically for each company. 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.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.

Dan Shipper (00:55:12)

Okay, cool. I love that. So I just want to point something out, which is we came into this idea of a trade we made a while ago and through the course of like using Gemini and talking about it we, and more specifically, you have been refining the like 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. 

Jesse Beyroutey (00:55:57)

Yeah, it's trying to break down what are the key components of the makings of a company that's going to end up doing ridiculously well and seeing how much they can replicate in the public market.

Dan Shipper (00:56:08)

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're really looking for that tenbagger. I'll put it in a high yield savings account. Okay, cool. So okay. So help me compose a response to this.

Jesse Beyroutey (00:56:39)

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. which companies in the energy industry that are public companies also have a highly scalable business model.

Dan Shipper (00:57:06)

Okay. So one thing that we should think about is defining for Gemini, what you mean by highly scalable.

Jesse Beyroutey (00:57:15)

I think it's actually good to keep it abstract.

Dan Shipper (00:57:15)

Okay. We can always refine. We can always refine. That's true. I think that's a good principle to start with. Start simple in general and then refine depending on what we get.

Jesse Beyroutey (00:57:28)

I find that using LLMs is a task of continuously refining your question. 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.

Dan Shipper (00:57:50)

Alright, we're waiting. We got the dots.

Jesse Beyroutey (00:57:52)

Yeah. I mean, honestly, I think that the biggest opportunity I've learned about today is to hold music for LLMs.

Dan Shipper (00:57:57)

Immediate Investment! 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. 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. Enphase's microinverters are modular and easy to install, which makes the company's business model highly scalable. SolarEdge Technologies. SolarEdge is a leading manufacturer of power optimizers and inverters for solar energy systems. Like Enphase, SolarEdge's products are modular and easy to install, which makes the company's business model highly scalable.” 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?

Jesse Beyroutey (00:59:04)

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 it again, I keep going back to Meta and Nvidia, both of those have highly scalable business models in a different way, as Nvidia is fabulous as a manufacturer. So it doesn't literally have to go and manufacture the items that just buys capacity from TSMC and similarly meta when advertising spend is growing and they're capturing more share of people's attention, Meta doesn't have to spend all that much more on any important 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 maybe we should actually default since we keep using it as—we should actually go flip back to asking Gemini and ChatGPT, what companies have characteristics similar to meta and do that and define some of those characteristics like that.

Dan Shipper (01:00:21)

And I think we can list out more details of our trade of Meta and Nvidia and see what that does. How does that sound? So you lead the way and I will be the scribe.

Jesse Beyroutey (01:00:34)

We're trying to find a company whose business model is scalable in that it can grow 100 times in a year and not run into any key bottleneck. 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 and at the same time sit in a bottleneck in their value chain that also enables that company to capture the lion's share of new market opportunity as it comes up in a tailwinded market. Something like that. You can give the LLM basically a warmup, some text for a slightly better total stream of consciousness and it can just do something with it. 

Dan Shipper (01:01:50)

It's so good. Right? Okay, cool. So, “We're trying to find a company which is scalable and then I 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 and software, in particular. 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 Chat.

Jesse Beyroutey (01:02:19)

Let's do it. We'll go ahead. Also, we even invented the word tailwinded and—

Dan Shipper (01:02:24)

I know exactly what it means. It's great. It's a great word.

Jesse Beyroutey (01:02:26)

So does ChatGPT—or Gemini, I believe in it. 

Dan Shipper (01:02:30)

So ChatGPT says, “Finding a company in the energy sector with a business model 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 could have scaling potential. Renewable energy trading platforms, platforms that facilitate the trading of renewable energy or carbon credits, could potentially scale. Electric vehicle charging networks. Companies that develop and deploy EV charging infrastructure might have potential to scale quickly.”

Jesse Beyroutey (01:03:10)

Cool. let's try to get it to list some companies. 

Dan Shipper (01:03:12)

“Give us 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 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.” It's really keen 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 manufacturer of thin film solar panels, and it has significant cost advantages. While it is unlikely that solar will grow 100x in a year, the company does have the potential to scale its business significantly. Other companies are mPhase, which had already suggested SolarEdge, which is suggested, and Sunrun, which is already suggested. So we're not getting anything totally groundbreaking here. 

Jesse Beyroutey (01:04:07)

And you know, I just quickly looked up in mPhase. 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 you found Nvidia. 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.

Dan Shipper (01:04:31)

Can we say, can you give us some more stocks that are less well known?

Jesse Beyroutey (01:04:34)

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’s given us shock.

Dan Shipper (01:04:46)

Maybe one thing we could do is just start over with like the three- or four-part trade that we have. So its exogenous shock sits in a key bottleneck of the value chain and is able to scale. There's one other component that I'm forgetting. I think that those are the three major ones. So I'm going to just create a new Chat prompt. I want to save this. Okay, so we're looking to find public stocks that have the following characteristics: are suffering some kind of exogenous shock to their business, sit in a highly valuable bottleneck in the value chain, and have a highly scalable business model such that they could scale 100x in a year relatively easily. Anything else that you think we should put into this prompt? Alright, let's try that. List them out. 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, cybersecurity companies like CrowdStrike and Pelion Networks as an invaluable bottleneck. They have scalable businesses. They could face exogenous shocks from regulatory changes, major security breaches or shifts in technology. Cloud service providers like Amazon, AWS, Microsoft—” I think we can get rid of 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,” blah, blah, blah. “FinTech companies like Square, PayPal, and Adyen.” So I don't know. I think these are okay, but I'm just going to ask, can you dig deeper and find less-well-known companies? And let's compare it to Gemini. 

So Gemini says, “Shock-proof stocks.” I don't know why it’s basically finding stocks that are in each of the categories instead of all three categories. So it's saying, “Shock-proof stocks: Anadarko Petroleum, Carnival Corporation, Boeing. I don't know if Boeing is shock-proof. All it takes is one door to fly off of a 737 or whatever. “Bottleneck stocks: Google, Microsoft, Visa. Scalable stocks: Amazon, Netflix.” So it's giving us really kind of generic suggestions. I'm just gonna say, can you dig deeper and find some less well known stocks? 

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. Searance specializes in creating unique moving experiences for the automotive world. Upstart Holdings, JFrog, Matterport.” Does anything pop out to you?

Jesse Beyroutey (01:08:42)

Well, seeing Matterport show up just reminded me that I believe Matterport was an instance of a company that got public by being a SPAC company. And I think the SPAC companies all got pretty wrecked and are now particularly small cap, like some of them are probably barely staying on the exchange. And so there might be an interesting opportunity lying in the list of SPAC 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. It's going to require quite a bit more digging. 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?

Dan Shipper (01:04:46)

I think we can do that. I think we can also, so we've got about 15 minutes left. And I want to make sure that there's time to kind of reflect on what we have experienced and what we've learned from this. So 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.

Jesse Beyroutey (01:10:09)

So we've got 15 minutes, let's find our bet. We're going to bet—how about this: Within 15 minutes, we're going to bet on one company that has SPACed, gone public, and gotten wrecked in the public market. And we're going to pick which one we should do.

Dan Shipper (01:10:29)

Do not do this at home. Do not do this at home. Okay. So how do we get all the SPAC companies? Let's just ask for a list. Okay. Can you give me a list of all of the companies that SPACed in 2019, was it? It's 2020 to 2021?

Jesse Beyroutey (01:10:54)

No, well, that certainly ended that conversation. I'm trying to find some—there's a website called SPAC Track, so I'm just looking at the SPAC Track list. Let’s see. Downloaded. 

Dan Shipper (01:11:12)

So I'm getting a list. So, “DraftKings, Nikola Corporation. I think that's gone now. Virgin Galactic, Opendoor, QuantumScape, ChargePoint, Clover Health, SoFi, Lucid, 23andMe, WeWork, Grab Holdings, Bark, Astro Space.” Honestly, I think Opendoor is an interesting one. They were doing really horribly for a while and I wonder where their stock is now. Let's go back to our Tradingview—what's their ticker? What's Opendoor's ticker? OPEN. Classic. Okay. So, looking at Opendoor, year-to-date is down 33 percent. Over the year, it's up for the last year. It's 51 percent in five years. It's down 73 percent. Market cap is $1.98 billion. So it's very small. “Opendoor engages in the operation of buying, selling and trading of residential properties online. The company was founded by Eric Wu as headquartered in Tempe. It has 1,000 employees.” What should we look at?

Jesse Beyroutey (01:12:21)

Well I'm starting to think about the most efficient way to cut through this, ‘cause we only have 10 minutes. So Opendoor doesn't feel like one that I would spend much time on. Go back to the list. So, I'm wondering about I think we should, should take a bet on a company that got public, but had some like pretty speculative technology and there's like 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. You know what stands out to me is actually very few of these have that characteristic, but it's also a very incomplete list. I'm interested in 23andMe. I don't know if it's still public, but I think—

Dan Shipper (01:13:25)

I don't think so. Or there's some really bad scandal with it, right?

Jesse Beyroutey (01:13:29)

Well, there's a bad scandal with it. So that's the exogenous shock. And I'm pretty sure that it's—

Dan Shipper (01:13:35)

It’s trading at $0.58. There we go.

Jesse Beyroutey (01:13:39)

It's a $270 million company. And you know, it's a bit of a rat's nest of regulatory issues and whatnot. But potentially interesting. At the same time, it's also got the characteristic of being sued a lot, which we've gotten burned by in the past.

Dan Shipper (01:14:02)

But I do think 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. And I really wonder if that data will be really valuable.

Jesse Beyroutey (01:14:18)

Yeah. And clearly it's gotten battered to such a level that there's definitely a margin of safety if we end up being right.

Dan Shipper (01:14:27)

If it doesn't go bankrupt.

Jesse Beyroutey (01:14:29)

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 out if they're going to go bankrupt. And so let's try to figure that one out with ChatGPT. 

Dan Shipper (01:14:49)

Yeah, let's do that. What would you ask ChatGPT?

Jesse Beyroutey (01:14:53)

Is 23andMe going to go bankrupt?

Dan Shipper (01:14:54)

Is 23andMe going to go bankrupt? Okay. Cool. And it says, “As of my last update in April of 2023, there are no public indicators.” No, that's right. You're wrong. I'm going to just add a new chat. Is 23andMe going to go bankrupt? Make your best guess. “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, with a substantial portion of its venture funding already spent. However, it's attempting 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.”

Jesse Beyroutey (01:15:58)

Feels like a tough bet. Maybe we go back to our list.

Dan Shipper (01:16:02)

Alright, going back to our list. We've got SoFi. We've got, I don't know what QuantumScape is. We've got ChargePoint. That's a network. Oh man. This is a tough list.

Jesse Beyroutey (01:16:20)

What's Virgin Galactic up to? 

Dan Shipper (01:16:22)

I don't know. Let's ask. What's Virgin Galactic up to? Browse. “It recently completed its 11th successful spaceflight 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 these flights. And it's part of the transition to achieve positive cash flow by 2026.” Let's see what his stock price is doing. Virgin Galactic. So, let’s see. it's down a lot but not really an exogenous shock.

Jesse Beyroutey (01:17:24)

It's just, it's just performing poorly, man, This is tough. I'm starting to feel like that 4 percent interest rate is looking good on the bank.

Dan Shipper (01:17:46)

I mean, I think we've got to hold ourselves to—

Jesse Beyroutey (01:17:42)

Yeah, we’ve got to make a bet.

Dan Shipper (01:17:44)

I’ve got that $1,000 burning a hole in my Robinhood account. I think we could also broaden it if there are other stocks that you think are good or have been thinking about that don't necessarily fit this thesis.

Jesse Beyroutey (01:18:02)

No, I want to do a SPAC—or, you know, 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 why it's going to be a tenbagger for us.

Dan Shipper (01:18:30)

I love it. Okay, cool. So, we're gonna get the webcast.Oh, sorry. The transcript. This is gonna be the same. The transcript is gonna be the same problem as the last time. That’s the Q&A.

Jesse Beyroutey (01:18:48)

Yeah, I think that's fine. The Q&A is okay.

Dan Shipper (01:18:50)

Okay. So we've got 2024 earnings call, the Q&A, and then we've got—

Jesse Beyroutey (01:19:06)

Let’s keep going. There's probably some investor presentation that's worth it as well as yeah—all of these other things. Okay, cool.

Dan Shipper (01:19:16)

Alright. So we've got a bunch of these. Oh, wow. Interesting. Look at this. This is like sort of a AI-enabled Q&A, or maybe it's not AI-enabled, but it's very organized and it's not like a— 

Jesse Beyroutey (01:19:34)

Oh, it's not a transcript. I thought this was the earnings call.

Dan Shipper (01:19:37)

Got it. So we've got the investor presentations, but I think—yeah, I don’t see that available. Alright, they might not publish 23andMe earnings call transcripts. Let's see if we can find it. Seeking Alpha. Alright, we've got it from Seeking Alpha. Thank you. So this is Q3 2024. Let's see. Ooh, “23andMe stock falls 20 percent amid earnings report breakup speculation.” I can't read it because I don't have access to it. We've got three minutes.

Jesse Beyroutey (01:20:40)

Alright, I mean, it feels like the clock is ticking, we’ve gotta probably make a buy.

Dan Shipper (01:20:44)

“23andMe considers splitting up the company to revive stock price a day after the company reported dismal, third court, third-quarter 2024 results and discussed splitting itself in two to help choose its stock. 23andMe reported $44.7 million for the quarter down $66.9 million and it received a deficiency letter giving the company 180 days to bring its share price back.” And it said, the company is considering splitting up its consumer and therapeutic business. So it feels like a buy to me. This is the moment of truth.

Jesse Beyroutey (01:21:19)

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.

Dan Shipper (01:21:27)

I think you're right. I will say, I feel uncertain about this buy. You feel extremely uncertain about it.

Jesse Beyroutey (01:21:35)

It has all the characteristics of all of our worst investments.

Dan Shipper (01:21:39)

But we're doing it for the content. We're doing it for the fans. 

Jesse Beyroutey (01:21:43)

We’re doing it for the audience.

Dan Shipper (01:21:45)

Exactly. This is what they call a YOLO trade. Okay, we're buying $1,000 worth of 23andMe. Alright. This is our stock that the AI has recommended.

Jesse Beyroutey (01:22:01)

The funny thing is that the AI didn't recommend it at all.

Dan Shipper (01:22:05)

This is the stock that we came to at the end of a long journey of rejecting all stocks. And I think—so first of all, I'm going to press buy and I'll let you see it. As I do it, we're going to swipe up to submit. Order received. So there we go. There we go. We made an investment. I feel horrible about it.

Jesse Beyroutey (01:22:33)

I don't think this one's going into our hall.

Dan Shipper (01:22:35)

I don't think so either, but I think there's a lesson here, which is 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 the psychology of a good investor is you have to be really good at doing nothing which most people are not. And, 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 couple years, one or two opportunities that pop up that will obviously fit it and we will be able to take advantage of it.

Jesse Beyroutey (01:23:37)

Yeah, that really stands out to me when we saw that happen to Nvidia or Meta 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. And this was not exactly the opposite. My reflection is just since we were really trying to feature using LLMs today, 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. And we just ran into time and time again, over and over 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.

Dan Shipper (01:24:53)

I think that makes a lot of sense. My hope is that big book publishers and movie studios and whatever will do deals with LLMs, like the same way that Reddit just did a deal with Google to provide content. So instead of maybe 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 ask questions about. And I think that would be a world where you can have people who create content benefit from using it inside of LLMs. And I think that'll be better for content creators because it makes the books more useful. It makes you, if you don't have to read a 300-page book, 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.

Jesse Beyroutey (01:25:43)

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. And I think there's so many opportunities like that for content companies on the internet.

Dan Shipper (01:26:06)

100 percent. I'm just envisioning a one-click thing that 's like, take all this stuff and just push it into some vast file store that is hooked up to Gemini or ChatGPT or whatever. And you can just scroll around the internet, clicking and clicking and clicking and each time it's like two or three or whatever, and then you can create this large personal database that you can use to make decisions or find stocks or whatever.

Jesse Beyroutey (01:26:31)

And I think that that information being updated is another 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. 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, it feels 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 that 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.

Dan Shipper (01:27:27)

I think that makes a lot of sense. There's also just this thing where there's always opportunities. Like, if large scaled LLMs get too kind of milquetoast, it means that there's always opportunities for people to build ones that are willing to return riskier results. That's the limits of the models—usefulness and intelligence is not actually technology driven anymore. That is one limit, but 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 to make LLMs that people will want to use.

Jesse Beyroutey (01:28:08)

Yeah, we're gonna have to make another stock bet again in six months to see how it does.

Dan Shipper (01:28:12)

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, it was worth it to get to sit down with you.

Jesse Beyroutey (01:28:27)

I think it's worth it too. And you know, as someone who didn't spend $1,000 on the event, I still feel pot committed to 23andMe every day now.

Dan Shipper (01:28:39)

Amazing. Awesome. Of course. See you next time. 

After that episode—I just could not let the 23andMe buy stand. And I was thinking about it and I think you were thinking about it. And I was watching the market and I think I found something that sort of actually fits the thesis. And what I want to do with you is one—we actually made some money already on the 23andMe buy. So 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.

Jesse Beyroutey (01:29:23)

I can't believe we made money in that trade, but let's do it.

Dan Shipper (01:29:25)

So this, kids, is how you make money on day trading. We're down minus 4 percent on 23andMe since we bought it last week. And we're up 9 percent 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 and—Is it done? It's done. We made money. Okay. Wow.

Jesse Beyroutey (01:29:57)

Considering how little thought went into that—that's actually pretty impressive.

Dan Shipper (01:29:59)

That's pretty good. You know, a stop clock is right twice a day or whatever, you know. 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. To some extent it had poor earnings 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've been all these problems with Gemini. And I think that that is driving down the stock price. Like 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?

Jesse Beyroutey (01:30:42)

I think that Google is up 50 percent year over year. So it's hard to say that it’s doing poorly. But but in the last few weeks in particular, there was the combination of a negative perception moment which they've been affected by a couple of times before, especially on the sort of comparative ChatGPT and it was combined with their earnings disappointed because their revenue for ad impression wasn't as good, I think, as well as their CapEx was high—unusually high. And I think investors are right to perceive that while 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 just sort of cost more to deliver. And at the same time. It's harder to load ad units into it. So, the fears about LLMs were 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-DALL-E comparisons to asking questions of Gemini. so I do think that this past couple of weeks would qualify for the exogenous shock component of the thesis. 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? 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 re-pointing 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 they are still advantaged in that business model because inside of Google, they've built their own, basically their own mini Nvidia. 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 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 with it's not like the stock is way, way down—you're right.

Dan Shipper (01:34:04)

That is true. I am because one of the things that I feel about Google is people are really down 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 thought 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 well positioned to grow a lot in the AI wave.

Jesse Beyroutey (01:34:43)

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.

Dan Shipper (01:35:00)

I agree. Okay, so let's roll our 23andMe winnings into Google and hope that Sundar delivers. 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. 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 tenbagger. Alright. 

Jesse Beyroutey (01:35:48)

So excited to see what happens here.

Dan Shipper (01:35:50)

Thanks a lot. Of course. 

You absolutely positively have to smash that like button and subscribe to How Do You Use ChatGPT. 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 ChatGPT. Every episode is a rollercoaster of emotions, insights, and laughter that will leave you on the edge of your seat, craving more. It's not just a show, it's a journey into the future with Dan Shipper as the captain of the spaceship. So do yourself a favor, hit like, smash subscribe, and strap in for the ride of your life. And now, without any further ado, let me just say Dan, I'm absolutely hopelessly in love with you.

Dan Shipper is the cofounder and CEO of Every, where he writes the Chain of Thought column and hosts the podcast How Do You Use ChatGPT? You can follow him on X at @danshipper and on LinkedIn, and Every on X at @every and on LinkedIn.