This Week in Startups - AI Demos! xAI’s Grok chatbot, OpenAI’s GPTs, & more! | E1846

Episode Date: November 14, 2023

This Week in Startups is brought to you by… LinkedIn Marketing. To redeem a $100 LinkedIn ad credit and launch your first campaign, go to linkedin.com/thisweekinstartups* Vanta. Compliance and secur...ity shouldn't be a deal-breaker for startups to win new business. Vanta makes it easy for companies to get a SOC 2 report fast. TWiST listeners can get $1,000 off for a limited time at vanta.com/twist Corient. Real wealth requires real solutions. Corient provides wealth management services centered around you. For more information, speak with an advisor today at Corient.com Today’s show: Sunny Madra joins Jason to discuss and demo xAI’s new chatbot, Grok (2:18), OpenAI’s new GPTs (31:54), and an AI designed to detect fake reviews (55:40). Then, Sunny builds a GPT live on air (36:22) * Time stamps: (0:00) Sunny Madra joins Jason (2:18) Sunny demos xAI’s Grok chatbot (14:49) LinkedIn Marketing - Get a $100 LinkedIn ad credit at https://linkedin.com/thisweekinstartups (21:33) Review and feedback for Grok chatbot (28:36) Vanta - Get $1000 off your SOC 2 at https://vanta.com/twist (31:54) Sunny demos OpenAI’s Game Time and Invest America GPTs (36:22) Sunny builds a Launch GPT live! (37:18) Corient - Speak with one of Corient's wealth management advisors today at http://corient.com (48:33) Unlocking the potential of GPTs (55:40) Sunny demos Fakespot, an AI tool for spotting fake reviews * Check out Grok: https://grok.x.ai Check out OpenAI’s GPTs: https://chat.openai.com/gpts/discovery Check out Fakespot: https://www.fakespot.com/ Check out Definitive Intelligence: https://www.definitive.io/ Follow Sunny: https://twitter.com/sundeep * Read LAUNCH Fund 4 Deal Memo: https://www.launch.co/four Apply for Funding: https://www.launch.co/apply Buy ANGEL: https://www.angelthebook.com Great 2023 interviews: Steve Huffman, Brian Chesky, Aaron Levie, Sophia Amoruso, Reid Hoffman, Frank Slootman, Billy McFarland Check out Jason’s suite of newsletters: https://substack.com/@calacanis * Follow Jason: Twitter: https://twitter.com/jason Instagram: https://www.instagram.com/jason LinkedIn: https://www.linkedin.com/in/jasoncalacanis * Follow TWiST: Substack: https://twistartups.substack.com Twitter: https://twitter.com/TWiStartups YouTube: https://www.youtube.com/thisweekin * Subscribe to the Founder University Podcast: https://www.founder.university/podcast

Transcript
Discussion (0)
Starting point is 00:00:00 Oh, Jason, what do we even begin? Your tweets are like a roller coaster ride through the Twitterverse. One moment, you're making predictions about banks. Pretty good, Paul. And the next, you're trying to convince us that a tiny covert pendant isn't the creepiest thing ever. Okay, that's pretty good. Those are good polls. Let's not forget your obsession with cold plunges.
Starting point is 00:00:23 You're like a human bopsicle. Oh, always trying to one-up your friends on Twitter. And don't even get me started on your... your AI request. You're like a kid in a candy store, except a candy store is Twitter. And Twitter is an AI-generated Renaissance painting. But hey, let's at least you're consistent in your love of roasting people. Just remember, Jason, you're a prime example of why we should never take ourselves too seriously on the Twitter. Keep the laughs coming, and maybe one day you'll find a cold plunge that can wash away the absurdity of it all. This weekend startups is brought to you by
Starting point is 00:00:56 LinkedIn Marketing. To redeem a free $100 $100 LinkedIn ad credit and launch your first campaign, go to LinkedIn.com slash this week in startups. Vanta. Compliance and security
Starting point is 00:01:09 shouldn't be a deal breaker for startups to win new business. Vanta makes it easy for companies to get a sock to report fast. Twist listeners can get $1,000 off for a limited time at vanta.com slash twist. And Coriant,
Starting point is 00:01:26 Real wealth requires real solutions. Corient provides wealth management services centered around you. For more information, speak with an advisor today at coriant.com. All right, everybody, welcome to this week in startups. It's Monday. So it's Madra Monday. Yes, my pal, Sunde, Sunny Madra is with us. He is from Definitive Intelligence and I'm an investor in that company.
Starting point is 00:01:50 Go check out definitive.io. And what we do here every Monday now in the age of AI, you can get used to it, is we just show and tell, demo or die, like the old days in the computer hacking clubs here in the valley, you would just show what you built. You'd show your work, right? You'd show up. You show up with your work, and you share your work.
Starting point is 00:02:12 And we all give it a letter grade here, and we give it some feedback and some general thoughts. So this has been a crazy week. You and I have been, for the last 10 days, playing with GROC, GROK, GROK, the new AI startup by Elon Musk and a really impressive group of talented people and they have access to the Twitter fire hose which nobody else has access to
Starting point is 00:02:39 and so let's get right into it Sonny what are your initial thoughts and maybe you can do some demos here at Grock what's working, what's not it's very early days so frame it for us where they're at yeah well very early days like first of all there's a couple of things that you know we got to get them kudos for it like you know
Starting point is 00:02:55 the company was only ideated, you know, six months ago, even last, like I think May. And then, or maybe that's six now. And then, honestly, I think they really only started building it like three months ago. And so this is version zero that we have access to. And I think they're already working on version one. Got it. They've talked about the infrastructure, which I think Elon mentioned on the Lex Pod, the number 400, which they did this with like 10,000 A100s, right?
Starting point is 00:03:23 Wow. So, yeah. So, you know, really interesting. And that is a large cluster of A1s. It is. It's, you know, it's probably, you know, like $100 plus million of capital expense. Or if you wanted to, you know, rent it from someone who probably caused you similar amounts on someone's cloud. And hard to get access to that.
Starting point is 00:03:43 So he probably knows a few people, given who he is, to get access to it and build that. I suppose if Elon falls and wants some A100s, maybe he can get the right person on the phone. Yeah, and look, like, they have the advantage that they're not new to this, right? They're obviously been building clusters for a long time within Tesla, right? And so there's some advantage to them that they understand, like, how to build it, how to get the internet connects all set up and, you know, data center space and everything else. So it just gives them the advantage of moving pretty quickly because sometimes you can get stalled there. Right.
Starting point is 00:04:16 Just infrastructure, once again, is a roadblock. It became a non-issue for the last 20. years since cloud computing came out. Every month, he gets cheaper and easier to just throw something up on the web, on the internet. Now, with AI, a little more
Starting point is 00:04:35 computer intensive, not so easy. I'm sure we will build up the resources in the next, I don't know, two years, three years for it to be easy again, do you think? Or do you think we're going to constantly be playing catch up here? Well, you know, this is what Elon I'll just kind of go up because we're going to get into
Starting point is 00:04:51 Grog here, but he mentioned on the Lex Pod that he thinks we're have an oversupply of AI-related computer resources within the next 18 months. That was my position as well. Yeah. Yeah. And I talked to them about it and I use the analogy of fiber.
Starting point is 00:05:08 Remember, we got all, got very excited about fiber in the end of the millennium, the end of the century, last century. And they just started building so much fiber everywhere. And we didn't exactly have the tools built in.
Starting point is 00:05:24 We didn't have YouTube. We didn't have HD cameras on our phones, right? So what was the use case for all that bandwidth? And a bunch of companies went out of business, and then a bunch of that got bought out. So they have it. And I'm just pulling up this tweet just to get it right. So I think so there's 8,000, not 10,000, A100,
Starting point is 00:05:43 and that he expects, you know, so he expects them to get to, right? And so 64, 64,000 by mid next year. Pretty impressive. 64,000. next year. Wow. Okay, so here we go, everybody. If you're not watching, we're going to sportscast us, so we'll describe what's on the screen
Starting point is 00:05:57 for you and the implications of it. But if you want to watch, Spotify supports This Week in Startups video. There is a This Week in Startup's video feed on iTunes if you search for it, and of course, YouTube search for This Week in Startums. Okay, here we go. So, you know, one of the things that we'll just start out with is that, you know, it has
Starting point is 00:06:14 these like two modes. And so if I kind of start a new chat and I'll flip back and forth here a bit, you're going to see Fun mode and regular mode. Got it. And, you know, the fun mode, as you'd expect, it kind of takes things, takes an edge off, makes them kind of funny. And, you know, one thing that we must do, I think, and I've got some, you know, queued up already. So, you know, we don't have to wait for it to.
Starting point is 00:06:34 And it's quite fast. It's in real time. But I said, look, one thing that everyone was doing last week, J-Cal, no one did it. And now we'll do it this way is like, write a toast, right a, write a roast of Twitter user at Jason based on his tweets. Love it. Jason, the best thing to do is for you read your own roast here. So I'm going to let you do it. Oh, Jason.
Starting point is 00:06:51 And where do we even begin? Your tweets are like a roller coaster ride through the Twitterverse. One moment, you're making predictions about banks. Pretty good, Paul. And the next, you're trying to convince us that a tiny covert pendant isn't the creepiest thing ever. Okay, that's pretty good. Those are good polls. Let's not forget your obsession with cold plunges.
Starting point is 00:07:14 You're like a human bopsicle. Oh, always trying to one-up your friends on Twitter. And don't even get me started on your AI request. You're like a kid in a candy store, except a candy store is Twitter. And Twitter is an AI-generated Renaissance painting. But hey, let's at least you're consistent in your love of roasting people. Just remember, Jason, you're a prime example of why we should never take ourselves too seriously on the Twitter. Keep the laughs coming, and maybe one day you'll find a cold plunge that can wash away the absurdity of it all.
Starting point is 00:07:45 I mean, listen, it's not ready for stage, but it's a good way. workshop. Like if you had a junior comedian in a room and they said, hey, we should do something about cold plunge and that the AI pendant that you were whaling on. And of course, your Silicon Valley Bank, all caps tweet that everybody roasted. Pretty good start. Honestly. And you can see the power of the Twitter data. And the more involved in social media you are, what you can see is AI is going to, you know, with access to the latest and greatest on social media, which Twitter has a lot of the smart people, this could be. like this can vindicate Elon's purchase of Twitter. Now he purchased it because he wanted to get
Starting point is 00:08:26 rid of the woke mind virus and because I think he, uh, you know, had a personal affinity towards it. He loved it. But he did think that, you know, uh, freedom of speech was important. This woke mind virus needed to be killed. And I think also now you can see that, hey, maybe he won't lose $20 billion on this. Maybe this is the start of something really important. And if he this data and nobody else is allowed to have it. It does. Then you're going to be using grok an awful lot, right? You can see yourself saying, go use grok, right?
Starting point is 00:09:00 Well, and, you know, especially, and like, let's just maybe kind of keep going through these examples where we can kind of highlight. So, you know, last week there was a controversy around the latest Mr. Beast video where he, you know, made a bunch of wells in Africa. And so you gave people clean drinking water. And the Mids on Twitter attacked him. I honestly, I don't think these people who are attacking him actually think this. I think it's just an engagement farming strategy.
Starting point is 00:09:30 Totally. Totally. It's just the way, like, who could be upset about giving water wells to people in various African countries? Yeah. Yeah. And what's really interesting here is like, I like the approach that Grock took. This is obviously not in fun mode. This is in regular mode where it kind of gave both sides, right?
Starting point is 00:09:49 It told, it said what the critic said. And then on the other hand, it talked about, you know, what the supporters of Mr. B said. So you said, what is the controversy with the latest Mr. Beast video? So this is something where you will see something trending and you want to work backwards to know what's going on. You hear somebody was on trial, somebody died. Yeah. A celebrity died. Somebody's trending and you're like, oh, my God, Christopher Walken's trending.
Starting point is 00:10:15 Oh, no. Christopher Walkins trending. Did he die? Wow. Yeah. And you get nervous, right? and you want to work backwards. And so here, you're just asking Grock, what is it?
Starting point is 00:10:25 And it says, the country surrounding Mr. Beast's latest video involves his philanthropic efforts in Africa. He recently built 100 water wells in various African countries, which has sparked debate about the portrayal of Africa and the impact of such actions on local communities. Oh my God. When people, when people say local communities and perpetuating stereotypes, that's when you know you're going to get snowed, right?
Starting point is 00:10:49 Like, there's not actually an issue here. there's no stereotype being perpetrated here except it's the frontier market it's an emerging market and emerging markets are further behind the developed markets and that can go for China Vietnam and then to an African country
Starting point is 00:11:04 then to you know a country run by a dictator like North Korea there's no harm being done here to say that some places need clean water or maybe they don't have access to clean water oh my God critics argue that his actions may
Starting point is 00:11:20 perpetuate the stereotype that Africa is dependent on handouts, in quotes, and could potentially shame the Kenyan government. Well, if the government's not giving people clean water, then maybe they should be shamed. I mean, I hate to point out the obvious. I hate to be pegged and obvious on the pod. They believe that this approach is charity. This approach to charity may not address the root causes of the issues faced by these communities. Okay, you know what the root is? These countries are further behind in their development because in a lot of cases, they're run by dictators who have stolen all the money and have oppressed their own people, in which case, that maybe you do want to shame them. Now, I'm not speaking about Kenya in specific here,
Starting point is 00:11:58 but I'm just talking generally about dictatorships anywhere on the globe. It could be Latin America, could be Africa, could be Asia, could be North America. On the other hand, support us to Mr. B. appreciate his efforts to provide clean drinking water to 500,000 people and believe that his actions are genuinely helping those in need. And then it gives you two tweets that this is called from. And you've got to assume that it's pulling not only the tweet, but do you think it's going to the Target news site and pulling that as well? I think, like, you know, as we go through more of the examples, it has the capability to do
Starting point is 00:12:30 that. Like when you, when you, you know, we can do some live. I just pulled these up so we don't have to kind of do them as you don't. But like, I have some fun ones here that kind of highlight it as well. So this is another place where like, you know, Twitter, sorry, GROC is really shining because of its access to Twitter data. And not having to, I guess, you know, rely on, like, web search, which is going to lead to, you know, I think problems in some regard as well with like all this, you know,
Starting point is 00:12:58 people, there's a new version of robots.t.com. That's out there, right? Where sites are saying, hey, don't crawl my data for AI bots, right? That was kind of implemented recently. And so was it? What's it called, you know? Does it have like a name? Well, I don't want to kind of misstate it.
Starting point is 00:13:14 So we'll pull up the actuals. But it's like, you know, Like robots on TXT, but for for AI's. I said that a year ago. Like they should, you should have to, there should be a license. So it should be, you know, whatever it is, New Yorktimes.com slash license. And when you read the license, it should say in the license,
Starting point is 00:13:31 in HTML readable semantic code. Yeah. Here's the license. You can use it. You can reference the New York Times in your language model with a citation. And you can summarize an article. of up to you know
Starting point is 00:13:50 for up to two sentences of summary three sentences of summary you cannot use it to train your model yeah right so training equals off exactly or it could be you know for every if you want to summarize this you have to have a paid
Starting point is 00:14:06 subscription yeah any number of issues any number of ways to handle I was just pulling it up here so I think they're just doing it within robots at TXT you can block the GPT bot user agent. So they've given it a different user agent that you can put in there and say,
Starting point is 00:14:23 hey, you're not, you're allowed to come here. Opening I did that proactively? Yeah, yeah. Oh, smart move on their part. So here comes their defense. Hey, you can just opt out. It's up to you.
Starting point is 00:14:33 So that's the opt out of defense. It doesn't work. It's just on a go forward basis, it might lower the number of people who might potentially sue you. Does it mean if you trained it on data you didn't know? that you're not in trouble.
Starting point is 00:14:48 Yeah. All right, business to business founders need to understand two very important things. B2B marketing is hard. We all know that. It's really hard. Number two, it's simple on LinkedIn ads. Why is B2B marketing so hard? Because the decision makers, hey, people like me, right?
Starting point is 00:15:02 The founder of the company. Or maybe you, you're an executive listening to the show. They're hard to identify, right? And they're really hard to target over the internet. And how do you know you're reaching them in the most respectful environment? People who are decision makers, you cannot reach them through that 19, 90s way of reaching executives. No, they need social outreach. And the way to get that social outreach dialed in is with LinkedIn. LinkedIn solved this problem. There are 70 million decision
Starting point is 00:15:27 makers hanging out on LinkedIn. And executives like me, yeah, the decision makers, we're on LinkedIn. We're deep into LinkedIn every single day. And LinkedIn ads helps you get your B2B message in front of the right people like me. And listen, when people are on LinkedIn, they want to do business. LinkedIn equals business. Business equals LinkedIn. Each social network has its vibe and the vibes at LinkedIn are business. It's business vibes only. And it's happened finally. LinkedIn has hit one billion users. The March to a billion has been achieved. Congratulations to all my friends at LinkedIn. So here's a call to action. Get started today. See why LinkedIn is the place to be for B2B. We'll even give you a hundy right now, $100 credit on your next campaign. Go to LinkedIn.com
Starting point is 00:16:09 slash this week in startups to claim your $100 credit. Why wouldn't you take the 100? Go to LinkedIn.com slash this week in startups. The links are in the show notes. Terms and conditions do apply. You know, here I'll give another, like a good sports example where you kind of want something much more real time. Remember, some people are listening, so read it, yeah. Exactly.
Starting point is 00:16:28 And I'm going to go through it. So I basically said, hey, how did Zach Wilson play last night? You know, he's been the replacement for Aaron Rogers. And it says, you know, based on his information available, Zach Wilson's performance last night was a mix of positive and negative. First player to have 250 pass yards and 50 rush yards. which is notable, but he also threw an interception late in the game, which was considered inexcusable by some.
Starting point is 00:16:50 And so, you know, really just super helpful, like for these type of things where, you know, something has happened, you're seeing about it on... And then it gives you the citations. It shows you the tweets it pulled this from. Yeah, exactly. See, that's the key. This is what I've always wanted. Yeah.
Starting point is 00:17:05 I've always wanted the ability to summarize what's on Twitter in real time. It's really powerful, you know, like tell me the sentiment of the movie the killer, which we were talking about in our group chat. Yeah. You know, some people liked it. Some people didn't. Who liked it? Who didn't?
Starting point is 00:17:21 And then you could, would be really nice as if I could say here, which of my followers, you know, who are the followers of At Chasin who like the Nix? I would like to know who follows me that likes the Nix. Can it do that? I don't think it can do that yet. Yeah. It doesn't understand followers, follower counts. Yeah.
Starting point is 00:17:41 You know, the database of tweets like, What would you call that information, like SQL information, database? I think it's just like the metadata of tweets, let's call it that, right? You know, because that's the, you know, who liked it, who's followed it, right? And metadata of users, they haven't kind of made that information available to Grock yet, which is there. And then look, like, you know, there are some other things. I'll just do one or two more and we'll go on from here. But like, you know, this is the one that's been moving around.
Starting point is 00:18:09 And I think it's been let's, we can maybe come back to this one next week where I know you were at, the first one, I really would like to go to this starship launch because you mentioned it was like one of the most incredible things you've ever felt from the... It was incredibly touching, like I say, human to see that rocket ship go up and think about the ramifications of being able to send hundreds of humans, cargo, whatever, to Mars. It was like very touching in a weird, a hard way to describe, but hope would be the overwhelming hope and joy for the people who created it. Yeah.
Starting point is 00:18:45 Okay. Yeah. And just the, I heard like, you know, from folks that you're there, including yourself, that it was just the sheer force of sound and energy was even, you know, you guys were several miles away or, you know, and you could still feel it kind of through in your bones. All right. And so, like, you know, this is one where I think it's doing a pretty good job.
Starting point is 00:19:08 And then, you know, there are some cases where, you know, we'll just go to kind of last week's pod, which was the one, the all-in pod, which is the one with Jared Kushner. And in this case, I said, hey, can you provide a summary of this week's interesting feedback? Can you provide a summary of this week's all-in podcast? It's sure, you know, can you tell me a specific episode? So that was episode 153. Oh, it did ask you for that. Yeah, it did. But you can see here, it got it way wrong, right? Oh. Yeah, it's impact on job. SVB collapsed. That was, yeah, that's super wrong. Yeah. And you can see here, the, hallucination is strong because it's like being very kind of affirmative in like it thinks that episode was about that.
Starting point is 00:19:48 It had, you know, SVB and kind of mixed a bunch of things up. I don't even think this episode exists and obviously in this format, right? I think that this is the balkanization in some ways of what we're going to see in AI, which is this would be a much better query for either. Somebody made an all in AI database, which is just the episodes. You might have seen podcast AI, a company we invested in. and then other people have started to make all-in transcript thing, you know,
Starting point is 00:20:15 AI versions where you can just only search the archive of it. Those would nail it, right? And then you have YouTube, which has it up there, but then you start thinking about Spotify and you start thinking about iTunes. If Spotify and iTunes took the transcripts and everything, I don't know if they have the legal ability to do this.
Starting point is 00:20:32 I think you would have to ask us for permission to build a derivative product, but maybe they'll just build it anyway. You know, you could be searching for that. Yeah. Yeah. We'll close out on a fun one. And so I just dropped in 420.
Starting point is 00:20:46 This number means a lot of things, a lot of different people. Yeah. And it gave a really great response here. Ah, the number 420, a true symbol of the universe's infinite wisdom. In some cultures, it represents the ultimate answer to the question of life, the universe, and everything. In other cultures, it represents a time of day when people gather to discuss the mysteries of the cosmos. Yeah, they do that too. Sort of, yeah.
Starting point is 00:21:07 Yeah. I mean, you know, it's an interesting time. It's almost quitting time. Yeah, at 420, you could do a lot of different things. Yeah. We had kids. It's a family show here, so let's keep it.
Starting point is 00:21:16 Yeah, I really like, you know, like I said, I really like its ability to have access to data outside of just its kind of training corpus and the way it answers questions. So I'm going to let you lead out, J-Cal. What's your grade on this one? Okay. So it's not perfect, so you can't give it an A. No, yeah.
Starting point is 00:21:37 But it's certainly not bad. so you can't give it a C, which means it's going to be a B. Right? Okay. So now you're going to, we argue B minus B plus or B, right? That's, I think, any logical person who's listened to us do this, and this is a 0.1 product. So based on how much work it's been into, you know, has been put into it, you could qualify it with that and say for three or four months work, this is an A plus.
Starting point is 00:22:01 You could say that. But I'm not grading it based on how much work is when I'm grading it against the market. So grading against the market. I wouldn't give it a B plus yet, but I wouldn't give it a B minus. So I think it's a solid D. Like out of the gate, it feels like you can get use out of it.
Starting point is 00:22:18 But out of the gate, it's not going to have the complete set of Twitter data that I want. Yep. And I want to be able to say, tell me who are the most credible Twitter users talking about COVID
Starting point is 00:22:39 or who thought the vaccines were overhyped before we had the data for it, right? Like something really sophisticated like that which takes into account time, the user account, how often they tweet about it, how often they get retweeted, how much engagement. So if I could just say,
Starting point is 00:22:56 hey, who are the most engaging Twitter handles for the Nix? That would be really interesting for me. And if it actually gave, and then put that on a Twitter list and follow those, you know, like, that's what I want to do. I kind of want to automate what I do on Twitter. And there was a company we had invested in called Little Bird. It was Get Little Bird.
Starting point is 00:23:19 And they got bought by another company sprinkler. And these companies did things like this with the Twitter API, not using AI, but they would just look for keywords and then they would build an index. And they could tell you these are the most followed accounts talking about the NICs. are the ones that get the most engagement. These are the most engaging replyers, you know, replying to them. So you could kind of figure out and then you could say if these were the top 100 NICs accounts, who follows the most, who of the hundred gets followed the most by the other 99? So then you can build like a meta ranking.
Starting point is 00:23:55 So these are the ones talking, getting the most engagement overall talking about the NICs. But if you take those hundred, who follows each other? You're like, oh, and this person is the goat of the goats, you know? It kind of could be very interesting. Yeah. I also like being able to do multiple searches at once. I thought that was kind of cool. Yeah, like, you know, I'm just kind of showing it here for those listening.
Starting point is 00:24:17 Side by side. Right. And you can even branch conversations, right? So you can look at the response tree of, you know, how it got there. It's got some pretty interesting features. You can regenerate the conversation. You know, like I tried what you were saying here. And, you know, it does find kind of the list of things.
Starting point is 00:24:35 but then it gives you, like, opening I or anyone else would say, like, hey, here's the way for you to kind of create a Twitter list, which is great. But you want that all integrated. Look, I'm going to take into account how quickly they've done it, access to proprietary data, and I'm going to put it at B plus. I think to do it that fast, the speed at which it runs at, and integrated kind of with the Twitter experience, and I think there's just some nice to have, but, like, you know,
Starting point is 00:25:02 as a first release, and, you know, we're getting spoiled because we see the best, of the best all the time, right? And so they've done an incredible job. Kudos to the team. They've done it really quickly. They're taking feedback into account. There is a GROC subscription plan. Part of the subscription service costing 16 per month under the X premium plus.
Starting point is 00:25:18 So on X, I think you get premium plus. Yeah. Which I think I just have premium. Yeah. But I had a friend at Twitter who got me into the GROC beta, but I think I have to go cancel my. This is what I hate about subscriptions. No, you know, I move to the premium plus. iTunes
Starting point is 00:25:35 subscribers. Even from iTunes you can do it there. Within the app, you can upgrade from premium to premium plus.
Starting point is 00:25:44 Oh, okay, that's what I used to do. Okay. And it does like all the production and everything. Because don't they charge
Starting point is 00:25:49 you the 30% extra? Like I think Twitter. I don't know if they do 30, but there's a premium you pay for going through the app store. But yeah, I guess so if you, that's an interesting just user question.
Starting point is 00:26:00 Like, do you want to go through the app store so it manages all your subscriptions you pay an extra Vig? there to have it all nice and neat and not have to manage all those Yeah Maybe I like that
Starting point is 00:26:10 It's usually a little bit easier to cancel Like if you ever want to do a downgrade Because you just do it You know through there You know the call on the phone Like the Wall Street Journal Oh my God I hate the Wall Street Journal
Starting point is 00:26:19 With those dark times Can you imagine being the sanctimonious I hate to sound like Trump Okay Sanctimonious fake news media Uses dark patterns Okay Yeah
Starting point is 00:26:30 Nasted Nasted Nasted dog No they do It's like, of one side, they're like criticizing everybody, like the New York Times and Los Chirno criticizing Big Tech, and then they're doing dark patterns. You can sign up for anything you want. You just can never leave.
Starting point is 00:26:47 And if you do want to leave, you have to call a phone number and they harangue you for 20 minutes. It's also super confusing because they have like an app subscription and they have a iPad subscription and web subscription. Apple News. Yeah. Well, no, Apple News is different because some things are included in Apple News and it's Oh, man. It's all dark patterns.
Starting point is 00:27:05 It's all dark patterns. It's shame on you. And then, you know, like, I was having this issue with Peloton as well and tonal. Just let me pause my membership when I'm not using it. I just want to. I think this is where Lena Khan could actually do something meaningful for consumers. Like, ask consumers what's frustrating for them as opposed to, like, saying to consumers, it's frustrating to have Amazon Prime.
Starting point is 00:27:27 It's not frustrating to have Amazon Prime. You know what's frustrating? Not being able to have a standard for pausing subscriptions. canceling subscriptions make a standard to protect consumers. That's it. Just like we did in banks where banks have to show you your interest rate on the top level of your statement, and they have to show you your interest paid to date or per year. You know how all of a sudden that magically showed up in all your apps?
Starting point is 00:27:50 Yeah. Did you notice that? Like when you open your app, if you have like a margin loan or you have a mortgage, it's like very clear how much you paid an interest. Oh, they got, they forced them to. That was like all Dodd-Frank, I believe, is that they were like, listen, be super clear about this. You can't bury it or make it confusing. You have to say, here's how much interest you paid this year. So, you know, people who were using their credit cards and getting charged
Starting point is 00:28:11 20%, and they had 10,000 on their card, they didn't realize they're paying like $2,000 a year, you know, to just float this $10,000. It kind of adds up. And they go, wow, I'm an idiot. I'm really paying a huge fig here, or if it was like a 25% credit card. Because they didn't have those introductory rates, then the introductory rate would go down. And just everything was confusing. six months and then it's like next thing you know it's crazy yeah this is why i don't use any of this stuff listen selling software is hard enough right now man it's hand-to-d combat out there in b2 land the last thing you need to do is slow your sales team down because you don't have your sock two dialed in so if you're sass or a services company and you store consumer data in the cloud
Starting point is 00:28:50 you know what you need to do you need to check out vanta they're going to get your sock two compliant easier and faster and vanta makes it so easy to get and renew your sock two on average Vanta customers are SOC2 compliant in just two to four weeks. Compare that to three to five months without Vanta. They're going to save you hundreds of hours of work and up to 85% on compliance costs. And Vanta does more than just SOC2. They also automate up to 90% compliance for GDPR, HIPAA and more. You can't afford to lose out on those major customers, the lighthouse customers, the big fish, the whales.
Starting point is 00:29:22 Because of silly stuff like lacking compliance. Just work with Vanta. I'm an investor in the company. It's a great company. Get your compliance automated. tight tight is right and close those big deals here's the best part vana's going to give you a thousand off because they love this weekend startups they love startups vanta.com slash twist
Starting point is 00:29:36 that's va nta com slash twist to get a thousand dollars off your stock two what did you give your grade what did you give a b plus i give a solid b okay i mean listen i don't want people to think i'm in the bag here for elon because we're besties like i honestly think nothing is fair a b out of the grade is incredible listen i would give the roadster a c as a sports car right? It was like out of the gate. And then, you know, his next thing, the Model S was an A plus.
Starting point is 00:30:03 So, you know, they have a, I, you know, Elon has a tendency to get something out there in the world, get feedback, and then nail it on the second try. That's my experience with his products. I think. Opposite of Apple, who waits and waits and waits and waits. And then you're just like, okay, great, it's, I'll be in your, like, I used to be a big proponent of tiles. Yeah. And then AirTex came out. And I was like, you know, as much as I love my tile team,
Starting point is 00:30:31 and I was team tile for a decade, I had to move to air tags because they just integrated, you know. It's like people using like Control 4 or Questron or whatever these or Savant. And you eventually rip all that stuff out. You throw it right in the garbage after you spend a quarter million dollars or $100,000 on your home automation. And then use Apple TV and Sonos like I do. Yeah.
Starting point is 00:30:55 Yeah. Why do you use that? Because. Kids, your spouse, your guests, they all know how to use Apple TV and cellos. And then they can enjoy the music in their room when they stay at your house or, you know, turn on the TV in the movie theater or turn on the TV in the guest room or whatever. Just works. It's just supposed to just work.
Starting point is 00:31:17 You're not supposed to be fighting against this technology. I feel like the GPT technology is getting there. I had a little moment internally in the company. People were writing emails that were not enthusiastic enough to founders. And I'm like, this is like very. dry and boring. I was like, can you highlight this and go into Notion AI, Grammarly AI, Claude, Bard, Chat GPD, post your email to a founder in there and say, make this more enthusiastic. Yes. And they did it and it worked. And I'm like, okay,
Starting point is 00:31:43 you are an incredibly boring writer. Yeah. Add more stoke. Add more stoke. Like Chad and JT. On that note, let's get into Chat GPT because it actually has So we now have GPTs. Last week, we quickly demoed after demo day, the assistant in the back end. And now we have access to the GPTs. And so what I'm going to do here is go into, let me get my screen share set up.
Starting point is 00:32:14 I was you in the Dolly one. The Dolly one is technically a GPT. Yeah. So these are the ones made by OpenAI. I've made some. And we'll go through this whole process. I actually made one for our bestie Brad. But just what I want to highlight first is, you know, so open AIs made a few different ones here.
Starting point is 00:32:35 One of them is actually along kind of lines, what you were saying, is like this creative writing coach, which helps you improve your writing skills, and, you know, math mentor, mixologist, laundry putty. I think there's a chef mentor, a classic GPT. But I did something with game time, which I can explain board games or card games, to play any age that the games begin. So I went in here and I already have it kind of queued up So we don't have to do it real time here So you asked it
Starting point is 00:33:04 I asked it I have Ace King Diamond suited And the flop comes Jack 109 with two diamonds What are my odds? And basically it sounds like you're playing Hold'em And the Ace King of Diamonds in your hand And the flop comes, you know, I'm just reading it out here Flot comes Jack 109 with two of those being diamonds
Starting point is 00:33:23 Your head has several potential strengths in it Talks about my flush draw my straight draw, my straight flush draw, and then combination odds, which I think is pretty awesome if you're trying to learn some of these games. Yes, you're learning outs, and it tells you here,
Starting point is 00:33:36 for the flush draw, you have four diamonds, needing one more for a flush. Okay, so flush is five diamonds. You just established that with folks. There are 13 diamonds in the deck, and you've seen four. Your two plus a two on the board.
Starting point is 00:33:48 There are nine diamonds left out of the 47 unseen cards, assuming a full table with no other diamond folds. No, like somebody didn't flip over there, diamonds. The odds of hitting a diamond on the turn or approximately 19.1%, 9 out of 47. And the way you do that, the easy way to do this back of the envelope math is to just give each of your outs times it by two. Right?
Starting point is 00:34:12 Yeah. It's actually 2.1 or something. We get 18%. Yeah, we do 18 on that, right? Yeah. But if you did 2.1%, you would round up and you'd be like 19. So you got a 1 in, essentially a 1 in 5 chance of turning it and then a 1 in 5 chance of rivering it, which means you have a 2. and five chance. She's a 40% chance of hitting. Here, a straight draw. You have a king,
Starting point is 00:34:31 and there's a jack and ten on the board, so an open and a straight draw, any queen or ace would give you a straight. Wait a second. Queen or ace would give you a straight. Why would an ace give you a straight? Oh, I said you have base 10? He got that wrong. Oh, okay. Bad advice. A queen, there are four queens. So there are four queens and three remaining aces, the aes wouldn't give you a straight. Wow. Okay, so you may not be ready for prime time. Somebody clip this and send it to Sam Altman because he plays cards. Sam. Yeah, here we go. Sam, I know Sam likes to play cards.
Starting point is 00:35:08 Yeah. This is a hallucination that could cost you a lot of money. Yeah, yeah, yeah. And the straight flesh try messes that up a little bit too now that like I had just quickly done this. Straight flush draw, specifically you were holding for the queen of diamonds. No, because I had only said. said, I had said in the original question, Jack 109 comes with two of them being diamonds, so I didn't clarify which. Oh, they didn't specify which too, right?
Starting point is 00:35:32 If it had been 10 jack of diamonds, then a straight flush row would be a possibility. Again, it should have asked you a follow-up question there, which ones are the diamonds? Combined odds, since you have both a flush right and a straight-jor, you should consider the combined probability. It involves a bit of math to avoid double-counting the queen of diamonds, right?
Starting point is 00:35:50 That's true. There are 15 total outs, nine diamonds plus six straight-outs. No, you have... three straight outs. So it's actually nine plus three is 12. So... Maybe a disclaimer.
Starting point is 00:36:04 Do not use this for your... Just yet. Okay. Just yet. If your opponent has this. Yeah. And we go all in,
Starting point is 00:36:12 what are my odds, right? And so basically, I kind of ran it through that, but now we have to take this with a grain of salt because, you know, these details could be wrong.
Starting point is 00:36:22 Our friends at Corian provide wealth management services centered around you. Coriant's goals are to exceed your expectations, simplify your life, and help you establish a legacy that lasts for generations. Coriant has been helping high achievers just like you, enjoy their lives more fully, preserve their well, and provide for the people, causes, and communities they care about. They're one of the largest integrated fee-only U.S. registered investment advisors, and Coriant has deeply experienced teams in 23 strategic locations. Each team has extensive knowledge spanning the full spectrum of planning, investing, lending, and money management disciplines. The teams at Coriant put the collective power of their expertise into building you the custom wealth, investment, and family office solutions that can help you reach your holistic financial goals, no matter how complex they may be.
Starting point is 00:37:10 Real wealth requires real solutions. For more information, speak with an advisor today at coriant.com. That's coriant.com. Can you show us how to make a GPT live on air? Yeah, so I wanted to do one for launch. Okay. And, you know, I made one for Invest America. Let me just show you that one real quickly.
Starting point is 00:37:29 Okay. And then we're going to follow the similar process. So this is the initiative that Brad is working on. Brad Gerson of the fifth best. Exactly. And, you know, you'll see here it has a URL. You can go to it. And if I send this to you, JCal, and you open it on your phone, I'll just text it to you real quickly.
Starting point is 00:37:46 Neat thing that they've done just says something interesting is if I send this to you and you open that link, it will open GPT, but as Invest America for you. Yes. Yeah. So basically, you get dropped into the Invest America app. GPTs are apps is a way to think of them. And you can make your own apps and put them in the app store. Essentially. Or you just send the URL to people. So if you wanted to do this
Starting point is 00:38:13 again for Shakespeare, put Shakespeare's combined works in there, I guess, as a PDF and you can have people do that. So here we go. Okay, hold on. I, let me get this back up. So with Invest America, how did you do it? What were the qualifiers? No, so I just went to the website because I didn't have any docs and I was just doing it for fun. And so, and I just said, hey, I clicked on tell me about Invest America and it's going to go through a process here about, you know, all the content I'd given it.
Starting point is 00:38:38 I can kind of just, we can look at it real quickly. If I, you know, click here, open it up and click Edit GPT. For some reason, it's like running super slow right now. So I don't know if it's like a popular. Yeah, okay, here we go. Let's go here. Whoa. Okay.
Starting point is 00:38:54 And so if I go into this configuration, you can see, I gave it a name, I gave it a description, I gave it some instructions, right, which is this GPT provides information about, and this is just a copy and paste from the website. Then I said, the website is this, the Twitter account is this. So you're being, with the instructions, you're being super clear that this GPT should focus on Invest America and giving it to resources so that it doesn't use its entire corpus. narrowed things down and it knows what you're talking about when you click on it. Great.
Starting point is 00:39:24 And then I screenshoted a few, you know, things from the Twitter account and gave it. So that's all that's all I did. So since we've done that. Yes. Yes. Very interesting. So why don't we do one for launch fund? Okay.
Starting point is 00:39:39 Okay. So let's just call it launch fund for. Got it. This GPD provides information about launch. Fund 4. Which you were an LPN. Yes, I am. Okay.
Starting point is 00:39:56 And, uh, all right. So let's, let's, got your first capital call, I assume. You shipped it? Uh, I have not shipped it yet, but I got the capital call. Shippie-dipid-dip-do. Okay. So I, I scraped, um, a bunch of stuff from the website.
Starting point is 00:40:11 So I just put it in this, just text document called, uh, PDF document called Launch Fund four. Great. Right. Uh, I also took a couple of screenshots here. this morning, which should be on my desktop. Let me just make sure these are okay. I think these are the two screenshots I took.
Starting point is 00:40:29 These are about the companies and the team because I didn't have it anywhere else. Awesome. All right. And so let's just give it a quick instruction. This GPT provides information about the new launch fund. Number four. Okay.
Starting point is 00:40:49 Anything else you want to put? in here. Launch 4 is an early stage venture capital fund. Early stage venture capital fund, okay. Managed by Jason Calacanis, the host of This Week in startups and the All In podcast. So I'm just trying to give it a little more context here, so that maybe it doesn't confuse us because launch is a very generic name.
Starting point is 00:41:14 So it doesn't make a mistake there. Yeah, okay. But I don't know if that's necessary or not. Yeah. Okay, the fund is right here. I'm just going to grab this. Oops. That's launch.com slash four.
Starting point is 00:41:30 Yep. Okay. And maybe the Twitter URL? Is there a Twitter URLs? We are. We're at launch. Yeah. The Twitter URL is Twitter.com slash launch.
Starting point is 00:41:40 There's an X URL is. X.com slash launch. Okay. And so we're done. So basically we do this. We're going to save, save. and I'll just say only people. Oh, we can have Dolly generate an icon for it as well.
Starting point is 00:41:56 Okay. But it'll just take a minute or two. Let's just do that. So now I do that. So it's like making it live. So I have to launch one for it. Okay. So now I'm in this.
Starting point is 00:42:04 So if I text this to you, I'm just separately here. I'm going to text it over to you, J. Calso. You have it. You can try it. Yep. But I'll do it here.
Starting point is 00:42:13 Okay. Okay. Okay. Okay. Tell me about the font strategy. The font strategy. Okay. and let's see what it comes up.
Starting point is 00:42:21 And so I just scrape the website, give it something, and so here it goes, right? Okay, number one, early stage focus. The fund is primarily target C stage startups at their inception and supports them through Series B funding rounds,
Starting point is 00:42:33 large portfolio with significant ownership. The fund aims to invest in over 400 early stage the goal of achieving 10% ownership in the top 5% of these companies, that's correct. Utilization of podcasts for reach and discovery. The fund leverages the popularity of Jason Callaghanis's podcast, correct? Founder University and Launch Accelerator, the fund operates
Starting point is 00:42:50 Founder University of Launch Accelerate, Founder University is an online course that helps Founder's ideas. Yeah, this is great. I mean, this is perfect. Micro-investments and future funding rounds for select startups, graduating for Founder University of the Fund makes friends and family-style investments of $25,000. I mean, this is just nailing it. This is A-plus. I mean, this is A-plus.
Starting point is 00:43:09 I would say, if you're asking me to rate GPTs out of the gate, I think it's an A-plus. I don't know what you think it's definitely an A so then we're debating A minus A or A plus Can it get better? Of course it's going to get much better But is this going to change the game
Starting point is 00:43:30 Of starting companies And doing information retrieval and creating services, yes So the question is Just websites and websites The question is what's the time between When you could create a GPT slash app Or you could create one that replicates what Slack does
Starting point is 00:43:49 or what I don't know create a new Uber create a a version of yeah you get the idea this is amazing
Starting point is 00:44:00 yeah I mean it's like and look it just took a you know five minutes right I had to scrape the website that's incredible about this
Starting point is 00:44:08 is how quickly you can do it yeah and imagine this incorporates your stripe account right yes in the next version Imagine it allows you to connect.
Starting point is 00:44:19 It can. You can. We made a, we made like an informational GPT. There is other features in there that allow you to, you know, so if I go back into this interface here, here, you know, if we go down below, you can add these actions and you can start basically connecting it to other services that you have. So we made a very simplistic one here. So imagine this was open table and you could book a restaurant or Yelp made one. And you could query the reviews and then have it actually make the reservation for you. So if you start thinking about these as agents that go out into the world, like baby GBT,
Starting point is 00:44:56 we talked about when we started doing this, like, that's kind of the next step is what can it do once it gives you the answer? Like, what if it had on there, would you like to book a call with Jason Calcanus to talk about this? Then it asked you three questions. Yeah. Have you invested in a venture capital firm before? Do you have any questions about venture and it tried to answer them?
Starting point is 00:45:14 You get the idea. Well, you can do that. So we'll add that in. Jason, you know, sometimes you really are the world's greatest moderator because you hit it.
Starting point is 00:45:21 So we are going to... Well, thank you for saying that. According to the YouTube comments, some people prefer other moderators who maybe don't ask us challenging of questions to certain guests. Interested in investing,
Starting point is 00:45:38 direct them to this Europe. Okay? Okay. And so we just, we added that. And I would, using Dolly to come up with an icon here, but it's taking a... This thing is a bit slow.
Starting point is 00:45:51 I don't know. It kind of takes... Dolly seems like it's really resource-intensive. Yeah. That always happens to me. Dolly takes way too long. I think it's like amongst their most intensive. And it probably cost them a ton of money to do Dolly, so they probably make it slow and put
Starting point is 00:46:07 it on like a slower framework, so... Yeah. You know, it doesn't cost as much. So I just added that, so I say, I'm interested. And investing. Let's see if it incorporated that actual piece I just put in there if it didn't. But there you go. Right?
Starting point is 00:46:33 And so we just did that real. So it's all of this is happening real time instantaneously. It doesn't require a developer. Yeah. Yeah. Yeah. And you could put in there, hey, if somebody wants to do a meeting, please ask them these five questions to qualify them.
Starting point is 00:46:49 Yes. You know, set into this calendar and give them three dates to choose from. So you don't even have to go to the type form. Like, we're sending you to type form. It could do that whole interaction with you in chat. This changes everything. It's paradigm shifting. Yeah, yeah.
Starting point is 00:47:05 It's totally paradigm shifting. And Apple and Android, you know, people who have app stores need to look at this. So this is a message to Tim Cook. This is a message to Sundar. Sundar. This is the next app store. store, you don't have it. Fire 100 people.
Starting point is 00:47:24 Bring 200 people into a room. Fire a hundred of them. And then the other 100 put in charge and do like a Darth Vader type thing. Like this has to be up and running within 120 days and it has to be better. It has to be not only feature. Just you 200 people have 120 days to make this better. And if it's not better, then fire 100 people in the room and then put the other 100 in charge. Yeah.
Starting point is 00:47:48 You got to take it like a Darth Vader approach. to this because you're not, you're moving way too slow. And imagine like, you know, so much of our interaction is on text and, you know, you, if someone asks you like, oh, Jason, tell me more about your fund and you just send them that and it opens up, like, open AI, but in, you know, the launch fund four view and like, I just chat with it, like, how powerful is that going to be? Crazy. The whole thing's going to, and then if it had a human seeing the chat and fixing it in real time,
Starting point is 00:48:17 So let's say every time it fires up one of these chats, we get a Slack room, like a thoroughway slack room, that just shows them interacting, and we're kind of watching it occur, and a human can jump in if it's wrong. And you could highlight it and say, this is the correct answer for next time. Or you could say,
Starting point is 00:48:31 human coming in to intervene. So this is going to get super interesting. Imagine it's answering questions for American Airlines, and there's an American Airlines GPT, and you just start talking to, like, why doesn't American Airlines have one of these? Well, they will. Yeah.
Starting point is 00:48:45 But, I mean, imagine it's answering questions about upgrading the lounge. And then it's got something wrong about the lounge, right? And it's like, oh, if you have a first class ticket, you can go into the lounge. That's not always true. Sometimes your business got to be, you can't use the lounge.
Starting point is 00:48:57 You've got to be international business now to get it or something. Yeah. So it's like, okay, you can't use the lounge. It's like one of the stupidest, craziest thing, right? Just make it simple. If you're in business class, you get the lounge. If you're not in business class, you don't get the lounge. What does this have to be like a game?
Starting point is 00:49:08 Every time I go up there, like I'm some pauper. Because they gave too many people access to the lounge with credit cards. Now they have to claw it back. Okay. It's not my problem. If I bought a business class ticket, let me go have a cup of bad coffee and use your slightly better Wi-Fi and sit in a less hard chair. Niceer bathroom, too.
Starting point is 00:49:28 Yeah, with a bathroom that's been cleaned more than once every three days. Okay, great. But don't make it complicated. But anyway, if you were watching that and it did have something there, it could highlight and say to check if your business class ticket is, go to the front counter. Sometimes it is, sometimes it, and then you just fix that. Or a human could jump in and say, you're at JFK, we're actually under control. it's not available until January 1st,
Starting point is 00:49:49 2024, and then it incorporates that into the next answer. So imagine I'm watching, so I'm a customer sport rep. I'm watching, Cindy, 10 of these in real time. And I'm just sitting there like this watching. That one's wrong.
Starting point is 00:50:00 Boom, I go to number two, I fix it. Boom. This one's wrong. Now imagine I'm doing that, not for customer service at American Airlines, but I'm doing that for giving advice on indigestion.
Starting point is 00:50:11 So I'm a doctor. I'm an emergency care. Yep. And I see people coming in and saying, have indigestion and they asked them this question, hey, what did you eat? When did you last eat? When did this start? Have you vomited? Have you done this? And then it says, oh, wait a second. This person says they ate some liquid soap or something and it said, oh, go to the emergency room now, you know, like call 911. And can you imagine if that was done by AI, how many lives would be
Starting point is 00:50:36 saved? Now, listen, we just did the one with doing poker odds and it was wrong. So you would want to be careful with this. You would be monitoring 9-11, calls in countries where you don't have access to a doctor. So the GPT would be by default better than nothing. And then you have some human watching it, fixing it in real time. There are emerging markets where probably people don't have access to doctors and they're looking stuff up on their phone or they're just asking people, you know, for word of mouth recommendations for an upset stomach. They don't, you know, know, know, what 20 questions ask. This, I think Vinod Costa was right. I think these things would do a better job. You tell me what you think. For the global
Starting point is 00:51:16 population, then doctors would, because they don't have access to a doctor, or if you did have access to doctor, I wonder if this would be better because it would be lower cost. I don't know. How close we are. Two examples.
Starting point is 00:51:28 I think there was a woman who put in, you know, like the latest version of chat chipped, you can, you know, especially after a dev day launch, everyone has access where you can just upload like a PDF. And it's not like code interpreter, but just analyze it for you. And then she uploaded like her blood results.
Starting point is 00:51:43 And it basically highlighted something, something and it said, you know, she had this problem for a long time and it just had a different view and she's like, oh my God, thanks for doing that because like, nobody ever did that. And then me personally, you know, my dad has Parkinson's and so he's on all these meds. And the other day is just like, I literally just took a picture of his subscription and just put it in the chat to be. Tell me what all these drugs are and it just did it for me. And so rather than typing them all out and some are generics and some are not. So it's a game changer. It's a real, real game changer.
Starting point is 00:52:14 disclaimer disclaimer disclaimer it's stuff hallucinates it gets things wrong so you want to check but as a first line in your discovery i don't see any harm to having it tell you what is in your blood test and then giving that response to your doctor and saying hey this thing thinks my iron deficiency you know i should have this treatment and this thing what do you think i don't know where it's getting this information on the open web from but i mean it sounds to me like every single time you get any kind of a doctor report or blood thing there's no down side to putting it through there and getting a third opinion and then bringing it back to your doctor and doing it in consultation with them. Well, I mean, it's amazing. It's like, I really like that idea. Like you said, you know, we always go for a second or third opinion. Why can't you get one? And I think this is the article. I just pull it up here.
Starting point is 00:53:05 And yeah, so I think it says like, woman claims that you be found correct diagnosis for her son's chronic pain. She put it in there and then basically had these meltdowns and it found out. So I think it's excellent. Yeah. Really, really good. Oh man, I'm getting these ads running on here now. Fantastic. Awesome.
Starting point is 00:53:21 This is why the internet's going to go away too, because these ads are everywhere now, and it's going to have a different model. It's much cleaner now. Now we do need to get into the discussion of copyright. And now that there's a business being built out of this, who gets paid? Because if you are giving this advice,
Starting point is 00:53:39 and it's been trained on WebMD or other commercial, enterprises data there's an argument we don't know like can I get you the other side? What if they got textbooks?
Starting point is 00:53:51 Textbooks. Those textbooks, trust me, those are some of the most insane but they could have licensed them. We don't know that.
Starting point is 00:53:58 I don't think I've not heard of Open AI paying a single license. Have you? Well, many textbooks are out of copyright, right? What's the copyright
Starting point is 00:54:06 on your book? You can keep you can keep, if you update them, you can keep them perpetually under. So if you were to like just change a sentence, you could then renew it. Oh, really?
Starting point is 00:54:17 Yeah. So it's, you're talking about artworks, like a book like Great Gatsby or something like that. And those can be, I think it's 75 years or 50 years past the life of, you just ask chat GPT. What's the copyright on a book? But I think it's 50 years after the author dies. And then it goes into public domain. But they keep increasing that. And they call it the Mickey Mouse rule.
Starting point is 00:54:39 So I think they made it 75 after the life of the thing because of when Roy did. Disney died, they wanted to get 75 years to that to protect the Disney family. So they call it the Disney rule now. But yeah, here we go. The copyright duration for textbooks. United States, for works published in 1976, it last the life of the author plus 70 years. Exactly what I said. For works created for higher anonymous or pseudonym works, the duration is 95 years in the publication, 120 years per creation, whichever shorter.
Starting point is 00:55:06 European in general is life of the author plus 70 years. Copyate laws can vary significantly. most countries' life plus 70 years rule. Okay. Interesting. So you learn something new every day on chatchap. Yeah. There you do.
Starting point is 00:55:19 We do. All right. Do we want to do one more? I think we have time for one more if you had one. Or we can just wrap up. It's up to you. Okay, we'll do one more. We'll do one more.
Starting point is 00:55:28 We'll do one more real quick. We give them what they want. We give them what they want. Okay. So this, let me get this set up. And I actually found this and we want to use it myself. And so let me go here.
Starting point is 00:55:41 This is called fake spot reviews analysis. And so this was like a historical plug-in that you could add to your Chrome. And you can see it here. I have it added in. And on any, you know, a couple of different sites,
Starting point is 00:55:55 I'm just on Amazon here for those listening. You can see here, I can say analyze reviews of the, you know, third-generation AirPods. So you click this, analyze reviews. Okay.
Starting point is 00:56:05 And, um, you know, it's like a Chrome extension. Got it. And, you know, before it would do these pros and cons,
Starting point is 00:56:11 but now it has this little chat box. here. And this chatbot lets you chat with all the reviews. I like that. And so are the AirPod pros good for large ears, let's just say. Stupid question. Basically, you know, like someone may have. And there you go, right?
Starting point is 00:56:32 So it's kind of looked through all the reviews that can give you an answer. I think that's like super helpful. No, this is super helpful because I am often trying to, being a product wizard myself, Yeah. Ask very nuanced questions. And yeah, it's very hard to get through all of the things, but I know how to search.
Starting point is 00:56:49 There is a search feature in the Amazon reviews, but I, oh, there is. Okay, I didn't even know that. They have a search feature, but they don't have a chat bot. Okay.
Starting point is 00:56:56 And so you're searching for keywords. And so you can search for battery or whatever. You're looking for, you know, if you're looking for the charging speed or whatever, you know, so. Yeah. Fantastic.
Starting point is 00:57:07 Awesome. So I give that a B. That's a B for me. Okay. All right. You know, it's nothing spectacular, nothing bad. I give it a B-mind. It's like I would have liked to see something more interesting like it. And so I encouraged people making it to make it more than I would expect.
Starting point is 00:57:26 I don't just want to chat bot. That's going to be like easy. They could turn that on in 10 seconds. Yeah. You know, really easily turn it on 10 seconds. So I would go with something more unique. What would be a unique feature to do with the reviews? Maybe tell me sentiment of the reviews over time.
Starting point is 00:57:46 Yeah. So how many months of reviews are there? And what were the major, what were the major comment by quarter? They actually, they don't have quite that, but they have like, you know, has this many reviews and it has some amount of that. I'd like to tell me if there's fake reviews too.
Starting point is 00:58:06 I mean, I think it's cool. I'll be honest. Yeah. It does. Yeah. It says it says Amazon rating is this, but fake reviews. adjusted rating is this. Oh.
Starting point is 00:58:14 Yeah. Yeah. That I like. Okay, I'm going to go B. I'm going to go B plus maybe even. Yeah. Because I, that's an acute problem I have.
Starting point is 00:58:22 I think when you're tackling this, you always got to think about, you know, you got to think about what are the unique problems or frustrations. People have in the unique problem of frustration that reviews is how fake they are. Yeah.
Starting point is 00:58:35 Or how fake they seem. And so that's something we can all use help with. Yeah. All right. I'm kind of with you, B plus, I think is good. You can always make it better.
Starting point is 00:58:43 Keep grinding. Let's do it. Yeah. Well, also, I think back to anticipating, if I, whatever question I'm asking there, you ask the question, are they good for large years? It should be asking what other AirPods competitors are good for large years. Or which, so you should, whatever query somebody does, you should have another GPT running that says, what are their questions?
Starting point is 00:59:06 Should I ask this potential purchaser in order to help them solve their problem? Correct. And then show you those three. Yeah, drive to a purchase. Yes. You should be, oh, is this for you or for a loved one? Yeah. And how large are your ears?
Starting point is 00:59:23 Have you ever tried other, do you have any ear ones currently that work well? Which brand are then? Or have you considered these three other brands? We hear that they have, you know, it turns out the ones from Google that I like the pixel buds. Yeah. I like the pixel buds because they're flat. Flat. Yeah, you said that before.
Starting point is 00:59:41 So when you lay on your pillow at night, which are AirPods, you ever get that, you ever try to lay on your pillow with AirPods? Oh, yeah, yeah, you wake up, it hurts, yeah, yeah. Okay, hey, producer John, producer court, do me favor. Will you send Mr. Sundeepe a set of Google PixelBuds from the fine folks of this week in startup? So I said, thank you. Okay, that's Mr. Sundeepe.
Starting point is 01:00:06 Sorry, Mr. Sundeep. I say thank you to Mr. Sundee. I'm trying to teach these young kids some manners here. You're just getting Mr. Sandip is here. I like referring to people by their last name. It's so jarring.
Starting point is 01:00:18 So jarring to you call Mr. Calacanus. Yeah, yeah. Did you have that happening now that people are like who work for you or who work in your orbit? Call you Mr. Calcanus?
Starting point is 01:00:27 Only when you like travel like, you know, in like certain countries and you get it, right? Oh man. I'm like, I'm like, I turn around. I'm like,
Starting point is 01:00:34 is my dad here? Do my dad come with me? Yeah. Mr. Gallaghanis. It's been another amazing episode of the Speaking of Starz with your guy, Sandeep Madra. If you would like, go to definitive.io
Starting point is 01:00:49 and you can hire definitive intelligence to do partnerships and consultations, but I think they're dance cards full. So if you're a large company and you're spending, you know, let's say mid-six figures, engagement to solve your AI problems, his team is the one that will solve them very quick.
Starting point is 01:01:04 We'll create that dashboard that you wanted, the LLMOPS dashboard. We'll do it for you. Oh, yeah? What way? What does that just remind me what we want to do that? No, so, like, you know, what you were talking about there is called LLM ops, like LLM operations. So I think a lot of businesses now are focusing on commercializing, you know, LLM applications, and you need like operations around it so that you can do those kind of things.
Starting point is 01:01:25 And so. Yeah. For sure. And shopping with a lot of that infrastructure. Ah, got it. Yeah. Just the infrastructure here and the training of teams is going to take a couple of years to get this right. And definitive.
Starting point is 01:01:36 com. We'll do it for you faster. And you're in a race, folks. so get on the horn with Sunny. He's Sundeepe on Twitter formerly known as Twitter and we'll see you all next time on this week at startups.
Starting point is 01:01:45 Hey, write a review if you like the show. Talk to you later, bye.

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