Bee AI: The Wearable Ambient Agent

Bundle tickets for AIE Summit NYC https://www.ai.engineer/summit/2025 have now sold out. You can now sign up for the https://www.ai.engineer/summit/2025#buytixhttps://www.ai.engineer/summit/2025#buytixlivestream https://www.ai.engineer/summit/2025#buytix — where we will be making a big announcement soon. NYC-based readers and Summit attendees should check out the meetups happening around the Summit https://www.ai.engineer/summit/2025#meetups. 2024 was a very challenging year for AI Hardware. After the buzz of CES last January, 2024 was marked by the meteoric rise and even harder fall of AI Wearables companies like Rabbit and Humane, with an assist from a pre-wallpaper-app MKBHD. Even Friend.com https://www.theverge.com/2024/7/30/24207029/friend-ai-companion-gadget, the first to launch in the AI pendant category, and which spurred Rewind AI to rebrand to Limitless and follow in their footsteps, ended up delaying their wearable ship date and launching an experimental website chatbot version. We have been cautiously excited about this category, keeping tabs on most of the top entrants, including Omi https://www.youtube.com/watch?v=Y5PTRVZ_k4g and Compass https://shop.compasswearable.com/products/compass. However, to date the biggest winner still standing from the AI Wearable wars is Bee AI, founded by today's guests Maria and Ethan. Bee is an always on hardware device with beamforming microphones, 7 day battery life and a mute button, that can be worn as a wristwatch or a clip-on pin, backed by an incredible transcription, diarization and very long context memory processing pipeline that helps you to remember your day, your todos, and even perform actions by operating a virtual cloud phone. This is one of the most advanced, production ready, personal AI agents we've ever seen, so we were excited to be their first podcast appearance. We met Bee when we ran the world's first Personal AI meetup in April last year. As a user of Bee (and not an investor! just a friend!) it’s genuinely been a joy to use, and we were glad to take advantage of the opportunity to ask hard questions about the privacy and legal/ethical side of things as much as the AI and Hardware engineering side of Bee. We hope you enjoy the episode and tune in next Friday https://www.youtube.com/@aiDotEngineer/streams for Bee’s first conference talk: Building Perfect Memory. Full YouTube Video Version Watch this for the live demo https://youtu.be/opiZTavNrA4! Show Notes * Bee Website https://www.bee.computer/ * Ethan Sutin https://twitter.com/EthanSutin/status/1874163029094654144, Maria de Lourdes Zollo https://x.com/mariadlzollo * Bee @ Personal AI Meetup https://www.latent.space/p/weekend-special-5-chats?utm_source=publication-search * Buy Bee with Listener Discount Code https://shop.bee.computer/products/the-bee-band! Timestamps * 00:00:00 Introductions and overview of Bee Computer * 00:01:58 Personal context and use cases for Bee * 00:03:02 Origin story of Bee and the founders' background * 00:06:56 Evolution from app to hardware device * 00:09:54 Short-term value proposition for users * 00:12:17 Demo of Bee's functionality * 00:17:54 Hardware form factor considerations * 00:22:22 Privacy concerns and legal considerations * 00:30:57 User adoption and reactions to wearing Bee * 00:35:56 CES experience and hardware manufacturing challenges * 00:41:40 Software pipeline and inference costs * 00:53:38 Technical challenges in real-time processing * 00:57:46 Memory and personal context modeling * 01:02:45 Social aspects and agent-to-agent interactions * 01:04:34 Location sharing and personal data exchange * 01:05:11 Personality analysis capabilities * 01:06:29 Hiring and future of always-on AI Transcript Alessio [00:00:04]: Hey everyone, welcome to the Latent Space podcast. This is Alessio, partner and CTO at Decibel Partners, and I'm joined by my co-host Swyx, founder of SmallAI. swyx [00:00:12]: Hey, and today we are very honored to have in the studio Maria and Ethan from Bee. Maria [00:00:16]: Hi, thank you for having us. swyx [00:00:20]: And you are, I think, the first hardware founders we've had on the podcast. I've been looking to have had a hardware founder, like a wearable hardware, like a wearable hardware founder for a while. I think we're going to have two or three of them this year. And you're the ones that I wear every day. So thank you for making Bee. Thank you for all the feedback and the usage. Yeah, you know, I've been a big fan. You are the speaker gift for the Engineering World's Fair. And let's start from the beginning. What is Bee Computer? Ethan [00:00:52]: Bee Computer is a personal AI system. So you can think of it as AI living alongside you in first person. So it can kind of capture your in real life. So with that understanding can help you in significant ways. You know, the obvious one is memory, but that's that's really just the base kind of use case. So recalling and reflective. I know, Swyx, that you you like the idea of journaling, but you don't but still have some some kind of reflective summary of what you experienced in real life. But it's also about just having like the whole context of a human being and understanding, you know, giving the machine the ability to understand, like, what's going on in your life. Your attitudes, your desires, specifics about your preferences, so that not only can it help you with recall, but then anything that you need it to do, it already knows, like, if you think about like somebody who you've worked with or lived with for a long time, they just know kind of without having to ask you what you would want, it's clear that like, that is the future that personal AI, like, it's just going to be very, you know, the AI is just so much more valuable with personal context. Maria [00:01:58]: I will say that one of the things that we are really passionate is really understanding this. Personal context, because we'll make the AI more useful. Think about like a best friend that know you so well. That's one of the things that we are seeing from the user. They're using from a companion standpoint or professional use cases. There are many ways to use B, but companionship and professional are the ones that we are seeing now more. swyx [00:02:22]: Yeah. It feels so dry to talk about use cases. Yeah. Yeah. Maria [00:02:26]: It's like really like investor question. Like, what kind of use case? Ethan [00:02:28]: We're just like, we've been so broken and trained. But I mean, on the base case, it's just like, don't you want your AI to know everything you've said and like everywhere you've been, like, wouldn't you want that? Maria [00:02:40]: Yeah. And don't stay there and repeat every time, like, oh, this is what I like. You already know that. And you do things for me based on that. That's I think is really cool. swyx [00:02:50]: Great. Do you want to jump into a demo? Do you have any other questions? Alessio [00:02:54]: I want to maybe just cover the origin story. Just how did you two meet? What was the was this the first idea you started working on? Was there something else before? Maria [00:03:02]: I can start. So Ethan and I, we know each other from six years now. He had a company called Squad. And before that was called Olabot and was a personal AI. Yeah, I should. So maybe you should start this one. But yeah, that's how I know Ethan. Like he was pivoting from personal AI to Squad. And there was a co-watching with friends product. I had experience working with TikTok and video content. So I had the pivoting and we launched Squad and was really successful. And at the end. The founders decided to sell that to Twitter, now X. So both of us, we joined X. We launched Twitter Spaces. We launched many other products. And yeah, till then, we basically continue to work together to the start of B. Ethan [00:03:46]: The interesting thing is like this isn't the first attempt at personal AI. In 2016, when I started my first company, it started out as a personal AI company. This is before Transformers, no BERT even like just RNNs. You couldn't really do any convincing dialogue at all. I met Esther, who was my previous co-founder. We both really interested in the idea of like having a machine kind of model or understand a dynamic human. We wanted to make personal AI. This was like more geared towards because we had obviously much limited tools, more geared towards like younger people. So I don't know if you remember in 2016, there was like a brief chatbot boom. It was way premature, but it was when Zuckerberg went up on F8 and yeah, M and like. Yeah. The messenger platform, people like, oh, bots are going to replace apps. It was like for about six months. And then everybody realized, man, these things are terrible and like they're not replacing apps. But it was at that time that we got excited and we're like, we tried to make this like, oh, teach the AI about you. So it was just an app that you kind of chatted with and it would ask you questions and then like give you some feedback. Maria [00:04:53]: But Hugging Face first version was launched at the same time. Yeah, we started it. Ethan [00:04:56]: We started out the same office as Hugging Face because Betaworks was our investor. So they had to think. They had a thing called Bot Camp. Betaworks is like a really cool VC because they invest in out there things. They're like way ahead of everybody else. And like back then it was they had something called Bot Camp. They took six companies and it was us and Hugging Face. And then I think the other four, I'm pretty sure, are dead. But and Hugging Face was the one that really got, you know, I mean, 30% success rate is pretty good. Yeah. But yeah, when we it was, it was like it was just the two founders. Yeah, they were kind of like an AI company in the beginning. It was a chat app for teenagers. A lot of people don't know that Hugging Face was like, hey, friend, how was school? Let's trade selfies. But then, you know, they built the Transformers library, I believe, to help them make their chat app better. And then they open sourced and it was like it blew up. And like they're like, oh, maybe this is the opportunity. And now they're Hugging Face. But anyway, like we were obsessed with it at that time. But then it was clear that there's some people who really love chatting and like answering questions. But it's like a lot of work, like just to kind of manually. Maria [00:06:00]: Yeah. Ethan [00:06:01]: Teach like all these things about you to an AI. Maria [00:06:04]: Yeah, there were some people that were super passionate, for example, teenagers. They really like, for example, to speak about themselves a lot. So they will reply to a lot of questions and speak about them. But most of the people, they don't really want to spend time. Ethan [00:06:18]: And, you know, it's hard to like really bring the value with it. We had like sentence similarity and stuff and could try and do, but it was like it was premature with the technology at the time. And so we pivoted. We went to YC and the long story, but like we pivoted to consumer video and that kind of went really viral and got a lot of usage quickly. And then we ended up selling it to Twitter, worked there and left before Elon, not related to Elon, but left Twitter. swyx [00:06:46]: And then I should mention this is the famous time when well, when when Elon was just came in, this was like Esther was the famous product manager who slept there. Ethan [00:06:56]: My co-founder, my former co-founder, she sleeping bag. She was the sleep where you were. Yeah, yeah, she stayed. We had left by that point. swyx [00:07:03]: She very stayed, she's famous for staying. Ethan [00:07:06]: Yeah, but later, later left or got, I think, laid off, laid off. Yeah, I think the whole product team got laid off. She was a product manager, director. But yeah, like we left before that. And then we're like, oh, my God, things are different now. You know, I think this is we really started working on again right before ChatGPT came out. But we had an app version and we kind of were trying different things around it. And then, you know, ultimately, it was clear that, like, there were some limitations we can go on, like a good question to ask any wearable company is like, why isn't this an app? Yes. Yeah. Because like. Maria [00:07:40]: Because we tried the app at the beginning. Ethan [00:07:43]: Yeah. Like the idea that it could be more of a and B comes from ambient. So like if it was more kind of just around you all the time and less about you having to go open the app and do the effort to, like, enter in data that led us down the path of hardware. Yeah. Because the sensors on this are microphones. So it's capturing and understanding audio. We started actually our first hardware with a vision component, too. And we can talk about why we're not doing that right now. But if you wanted to, like, have a continuous understanding of audio with your phone, it would monopolize your microphone. It would get interrupted by calls and you'd have to remember to turn it on. And like that little bit of friction is actually like a substantial barrier to, like, get your phone. It's like the experience of it just being with you all the time and like living alongside you. And so I think that that's like the key reason it's not an app. And in fact, we do have Apple Watch support. So anybody who has a watch, Apple Watch can use it right away without buying any hardware. Because we worked really hard to make a version for the watch that can run in the background, not super drain your battery. But even with the watch, there's still friction because you have to remember to turn it on and it still gets interrupted if somebody calls you. And you have to remember to. We send a notification, but you still have to go back and turn it on because it's just the way watchOS works. Maria [00:09:04]: One of the things that we are seeing from our Apple Watch users, like I love the Apple Watch integration. One of the things that we are seeing is that people, they start using it from Apple Watch and after a couple of days they buy the B because they just like to wear it. Ethan [00:09:17]: Yeah, we're seeing. Maria [00:09:18]: That's something that like they're learning and it's really cool. Yeah. Ethan [00:09:21]: I mean, I think like fundamentally we like to think that like a personal AI is like the mission. And it's more about like the understanding. Connecting the dots, making use of the data to provide some value. And the hardware is like the ears of the AI. It's not like integrating like the incoming sensor data. And that's really what we focus on. And like the hardware is, you know, if we can do it well and have a great experience on the Apple Watch like that, that's just great. I mean, but there's just some platform restrictions that like existing hardware makes it hard to provide that experience. Yeah. Alessio [00:09:54]: What do people do in like two or three days that then convinces them to buy it? They buy the product. This feels like a product where like after you use it for a while, you have enough data to start to get a lot of insights. But it sounds like maybe there's also like a short term. Maria [00:10:07]: From the Apple Watch users, I believe that because every time that you receive a call after, they need to go back to B and open it again. Or for example, every day they need to charge Apple Watch and reminds them to open the app every day. They feel like, okay, maybe this is too much work. I just want to wear the B and just keep it open and that's it. And I don't need to think about it. Ethan [00:10:27]: I think they see the kind of potential of it just from the watch. Because even if you wear it a day, like we send a summary notification at the end of the day about like just key things that happened to you in your day. And like I didn't even think like I'm not like a journaling type person or like because like, oh, I just live the day. Why do I need to like think about it? But like it's actually pretty sometimes I'm surprised how interesting it is to me just to kind of be like, oh, yeah, that and how it kind of fits together. And I think that's like just something people get immediately with the watch. But they're like, oh, I'd like an easier watch. I'd like a better way to do this. swyx [00:10:58]: It's surprising because I only know about the hardware. But I use the watch as like a backup for when I don't have the hardware. I feel like because now you're beamforming and all that, this is significantly better. Yeah, that's the other thing. Ethan [00:11:11]: We have way more control over like the Apple Watch. You're limited in like you can't set the gain. You can't change the sample rate. There's just very limited framework support for doing anything with audio. Whereas if you control it. Then you can kind of optimize it for your use case. The Apple Watch isn't meant to be kind of recording this. And we can talk when we get to the part about audio, why it's so hard. This is like audio on the hardest level because you don't know it has to work in all environments or you try and make it work as best as it can. Like this environment is very great. We're in a studio. But, you know, afterwards at dinner in a restaurant, it's totally different audio environment. And there's a lot of challenges with that. And having really good source audio helps. But then there's a lot more. But with the machine learning that still is, you know, has to be done to try and account because like you can tune something for one environment or another. But it'll make one good and one bad. And like making something that's flexible enough is really challenging. Alessio [00:12:10]: Do we want to do a demo just to set the stage? And then we kind of talk about. Maria [00:12:14]: Yeah, I think we can go like a walkthrough and the prod. Alessio [00:12:17]: Yeah, sure. swyx [00:12:17]: So I think we said I should. So for listeners, we'll be switching to video. That was superimposed on. And to this video, if you want to see it, go to our YouTube, like and subscribe as always. Yeah. Maria [00:12:31]: And by the bee. Yes. swyx [00:12:33]: And by the bee. While you wait. While you wait. Exactly. It doesn't take long. Maria [00:12:39]: Maybe you should have a discount code just for the listeners. Sure. swyx [00:12:43]: If you want to offer it, I'll take it. All right. Yeah. Well, discount code Swyx. Oh s**t. Okay. Yeah. There you go. Ethan [00:12:49]: An important thing to mention also is that the hardware is meant to work with the phone. And like, I think, you know, if you, if you look at rabbit or, or humane, they're trying to create like a new hardware platform. We think that the phone's just so dominant and it will be until we have the next generation, which is not going to be for five, you know, maybe some Orion type glasses that are cheap enough and like light enough. Like that's going to take a long time before with the phone rather than trying to just like replace it. So in the app, we have a summary of your days, but at the top, it's kind of what's going on now. And that's updating your phone. It's updating continuously. So right now it's saying, I'm discussing, you know, the development of, you know, personal AI, and that's just kind of the ongoing conversation. And then we give you a readable form. That's like little kind of segments of what's the important parts of the conversations. We do speaker identification, which is really important because you don't want your personal AI thinking you said something and attributing it to you when it was just somebody else in the conversation. So you can also teach it other people's voices. So like if some, you know, somebody close to you, so it can start to understand your relationships a little better. And then we do conversation end pointing, which is kind of like a task that didn't even exist before, like, cause nobody needed to do this. But like if you had somebody's whole day, how do you like break it into logical pieces? And so we use like not just voice activity, but other signals to try and split up because conversations are a little fuzzy. They can like lead into one, can start to the next. So also like the semantic content of it. When a conversation ends, we run it through larger models to try and get a better, you know, sense of the actual, what was said and then summarize it, provide key points. What was the general atmosphere and tone of the conversation and potential action items that might've come of that. But then at the end of the day, we give you like a summary of all your day and where you were and just kind of like a step-by-step walkthrough of what happened and what were the key points. That's kind of just like the base capture layer. So like if you just want to get a kind of glimpse or recall or reflect that's there. But really the key is like all of this is now like being influenced on to generate personal context about you. So we generate key items known to be true about you and that you can, you know, there's a human in the loop aspect is like you can, you have visibility. Right. Into that. And you can, you know, I have a lot of facts about technology because that's basically what I talk about all the time. Right. But I do have some hobbies that show up and then like, how do you put use to this context? So I kind of like measure my day now and just like, what is my token output of the day? You know, like, like as a human, how much information do I produce? And it's kind of measured in tokens and it turns out it's like around 200,000 or so a day. But so in the recall case, we have, um. A chat interface, but the key here is on the recall of it. Like, you know, how do you, you know, I probably have 50 million tokens of personal context and like how to make sense of that, make it useful. So I can ask simple, like, uh, recall questions, like details about the trip I was on to Taiwan, where recently we're with our manufacturer and, um, in real time, like it will, you know, it has various capabilities such as searching through your, your memories, but then also being able to search the web or look at my calendar, we have integrations with Gmail and calendars. So like connecting the dots between the in real life and the digital life. And, you know, I just asked it about my Taiwan trip and it kind of gives me the, the breakdown of the details, what happened, the issues we had around, you know, certain manufacturing problems and it, and it goes back and references the conversation so I can, I can go back to the source. Yeah. Maria [00:16:46]: Not just the conversation as well, the integrations. So we have as well Gmail and Google calendar. So if there is something there that was useful to have more context, we can see that. Ethan [00:16:56]: So like, and it can, I never use the word agentic cause it's, it's cringe, but like it can search through, you know, if I, if I'm brainstorming about something that spans across, like search through my conversation, search the email, look at the calendar and then depending on what's needed. Then synthesize, you know, something with all that context. Maria [00:17:18]: I love that you did the Spotify wrapped. That was pretty cool. Yeah. Ethan [00:17:22]: Like one thing I did was just like make a Spotify wrap for my 2024, like of my life. You can do that. Yeah, you can. Maria [00:17:28]: Wait. Yeah. I like those crazy. Ethan [00:17:31]: Make a Spotify wrapped for my life in 2024. Yeah. So it's like surprisingly good. Um, it like kind of like game metrics. So it was like you visited three countries, you shipped, you know, XMini, beta. Devices. Maria [00:17:46]: And that's kind of more personal insights and reflection points. Yeah. swyx [00:17:51]: That's fascinating. So that's the demo. Ethan [00:17:54]: Well, we have, we can show something that's in beta. I don't know if we want to do it. I don't know. Maria [00:17:58]: We want to show something. Do it. Ethan [00:18:00]: And then we can kind of fit. Yeah. Maria [00:18:01]: Yeah. Ethan [00:18:02]: So like the, the, the, the vision is also like, not just about like AI being with you in like just passively understanding you through living your experience, but also then like it proactively suggesting things to you. Yeah. Like at the appropriate time. So like not just pool, but, but kind of, it can step in and suggest things to you. So, you know, one integration we have that, uh, is in beta is with WhatsApp. Maria is asking for a recommendation for an Italian restaurant. Would you like me to look up some highly rated Italian restaurants nearby and send her a suggestion? Maria [00:18:34]: So what I did, I just sent to Ethan a message through WhatsApp in his own personal phone. Yeah. Ethan [00:18:41]: So, so basically. B is like watching all my incoming notifications. And if it meets two criteria, like, is it important enough for me to raise a suggestion to the user? And then is there something I could potentially help with? So this is where the actions come into place. So because Maria is my co-founder and because it was like a restaurant recommendation, something that it could probably help with, it proposed that to me. And then I can, through either the chat and we have another kind of push to talk walkie talkie style button. It's actually a multi-purpose button to like toggle it on or off, but also if you push to hold, you can talk. So I can say, yes, uh, find one and send it to her on WhatsApp is, uh, an Android cloud phone. So it's, uh, going to be able to, you know, that has access to all my accounts. So we're going to abstract this away and the execution environment is not really important, but like we can go into technically why Android is actually a pretty good one right now. But, you know, it's searching for Italian restaurants, you know, and we don't have to watch this. I could be, you know, have my ear AirPods in and in my pocket, you know, it's going to go to WhatsApp, going to find Maria's thread, send her the response and then, and then let us know. Oh my God. Alessio [00:19:56]: But what's the, I mean, an Italian restaurant. Yeah. What did it choose? What did it choose? It's easy to say. Real Italian is hard to play. Exactly. Ethan [00:20:04]: It's easy to say. So I doubt it. I don't know. swyx [00:20:06]: For the record, since you have the Italians, uh, best Italian restaurant in SF. Maria [00:20:09]: Oh my God. I still don't have one. What? No. Ethan [00:20:14]: I don't know. Successfully found and shared. Alessio [00:20:16]: Let's see. Let's see what the AI says. Bottega. Bottega? I think it's Bottega. Maria [00:20:21]: Have you been to Bottega? How is it? Alessio [00:20:24]: It's fine. Maria [00:20:25]: I've been to one called like Norcina, I think it was good. Alessio [00:20:29]: Bottega is on Valencia Street. It's fine. The pizza is not good. Maria [00:20:32]: It's not good. Alessio [00:20:33]: Some of the pastas are good. Maria [00:20:34]: You know, the people I'm sorry to interrupt. Sorry. But there is like this Delfina. Yeah. That here everybody's like, oh, Pizzeria Delfina is amazing. I'm overrated. This is not. I don't know. That's great. That's great. swyx [00:20:46]: The North Beach Cafe. That place you took us with Michele last time. Vega. Oh. Alessio [00:20:52]: The guy at Vega, Giuseppe, he's Italian. Which one is that? It's in Bernal Heights. Ugh. He's nice. He's not nice. I don't know that one. What's the name of the place? Vega. Vega. Vega. Cool. We got the name. Vega. But it's not Vega. Maria [00:21:02]: It's Italian. What swyx [00:21:10]: Vega. Vega. swyx [00:21:16]: Vega. Vega. Vega. Vega. Vega. Vega. Vega. Vega. Vega. Ethan [00:21:29]: Vega. Vega. Vega. Vega. Vega. Ethan [00:21:40]: We're going to see a lot of innovation around hardware and stuff, but I think the real core is being able to do something useful with the personal context. You always had the ability to capture everything, right? We've always had recorders, camcorders, body cameras, stuff like that. But what's different now is we can actually make sense and find the important parts in all of that context. swyx [00:22:04]: Yeah. So, and then one last thing, I'm just doing this for you, is you also have an API, which I think I'm the first developer against. Because I had to build my own. We need to hire a developer advocate. Or just hire AI engineers. The point is that you should be able to program your own assistant. And I tried OMI, the former friend, the knockoff friend, and then real friend doesn't have an API. And then Limitless also doesn't have an API. So I think it's very important to own your data. To be able to reprocess your audio, maybe. Although, by default, you do not store audio. And then also just to do any corrections. There's no way that my needs can be fully met by you. So I think the API is very important. Ethan [00:22:47]: Yeah. And I mean, I've always been a consumer of APIs in all my products. swyx [00:22:53]: We are API enjoyers in this house. Ethan [00:22:55]: Yeah. It's very frustrating when you have to go build a scraper. But yeah, it's for sure. Yeah. swyx [00:23:03]: So this whole combination of you have my location, my calendar, my inbox. It really is, for me, the sort of personal API. Alessio [00:23:10]: And is the API just to write into it or to have it take action on external systems? Ethan [00:23:16]: Yeah, we're expanding it. It's right now read-only. In the future, very soon, when the actions are more generally available, it'll be fully supported in the API. Alessio [00:23:27]: Nice. I'll buy one after the episode. Ethan [00:23:30]: The API thing, to me, is the most interesting. Yeah. We do have real-time APIs, so you can even connect a socket and connect it to whatever you want it to take actions with. Yeah. It's too smart for me. Alessio [00:23:43]: Yeah. I think when I look at these apps, and I mean, there's so many of these products, we launch, it's great that I can go on this app and do things. But most of my work and personal life is managed somewhere else. Yeah. So being able to plug into it. Integrate that. It's nice. I have a bunch of more, maybe, human questions. Sure. I think maybe people might have. One, is it good to have instant replay for any argument that you have? I can imagine arguing with my wife about something. And, you know, there's these commercials now where it's basically like two people arguing, and they're like, they can throw a flag, like in football, and have an instant replay of the conversation. I feel like this is similar, where it's almost like people cannot really argue anymore or, like, lie to each other. Because in a world in which everybody adopts this, I don't know if you thought about it. And also, like, how the lies. You know, all of us tell lies, right? How do you distinguish between when I'm, there's going to be sometimes things that contradict each other, because I might say something publicly, and I might think something, really, that I tell someone else. How do you handle that when you think about building a product like this? Maria [00:24:48]: I would say that I like the fact that B is an objective point of view. So I don't care too much about the lies, but I care more about the fact that can help me to understand what happened. Mm-hmm. And the emotions in a really objective way, like, really, like, critical and objective way. And if you think about humans, they have so many emotions. And sometimes something that happened to me, like, I don't know, I would feel, like, really upset about it or really angry or really emotional. But the AI doesn't have those emotions. It can read the conversation, understand what happened, and be objective. And I think the level of support is the one that I really like more. Instead of, like, oh, did this guy tell me a lie? I feel like that's not exactly, like, what I feel. I find it curious for me in terms of opportunity. Alessio [00:25:35]: Is the B going to interject in real time? Say I'm arguing with somebody. The B is like, hey, look, no, you're wrong. What? That person actually said. Ethan [00:25:43]: The proactivity is something we're very interested in. Maybe not for, like, specifically for, like, selling arguments, but more for, like, and I think that a lot of the challenge here is, you know, you need really good reasoning to kind of pull that off. Because you don't want it just constantly interjecting, because that would be super annoying. And you don't want it to miss things that it should be interjecting. So, like, it would be kind of a hard task even for a human to be, like, just come in at the right times when it's appropriate. Like, it would take the, you know, with the personal context, it's going to be a lot better. Because, like, if somebody knows about you, but even still, it requires really good reasoning to, like, not be too much or too little and just right. Maria [00:26:20]: And the second part about, well, like, some things, you know, you say something to somebody else, but after I change my mind, I send something. Like, it's every time I have, like, different type of conversation. And I'm like, oh, I want to know more about you. And I'm like, oh, I want to know more about you. I think that's something that I found really fascinating. One of the things that we are learning is that, indeed, humans, they evolve over time. So, for us, one of the challenges is actually understand, like, is this a real fact? Right. And so far, what we do is we give, you know, to the, we have the human in the loop that can say, like, yes, this is true, this is not. Or they can edit their own fact. For sure, in the future, we want to have all of that automatized inside of the product. Ethan [00:26:57]: But, I mean, I think your question kind of hits on, and I know that we'll talk about privacy, but also just, like, if you have some memory and you want to confirm it with somebody else, that's one thing. But it's for sure going to be true that in the future, like, not even that far into the future, that it's just going to be kind of normalized. And we're kind of in a transitional period now. And I think it's, like, one of the key things that is for us to kind of navigate that and make sure we're, like, thinking of all the consequences. And how to, you know, make the right choices in the way that everything's designed. And so, like, it's more beneficial than it could be harmful. But it's just too valuable for your AI to understand you. And so if it's, like, MetaRay bands or the Google Astra, I think it's just people are going to be more used to it. So people's behaviors and expectations will change. Whether that's, like, you know, something that is going to happen now or in five years, it's probably in that range. And so, like, I think we... We kind of adapt to new technologies all the time. Like, when the Ring cameras came out, that was kind of quite controversial. It's like... But now it's kind of... People just understand that a lot of people have cameras on their doors. And so I think that... Maria [00:28:09]: Yeah, we're in a transitional period for sure. swyx [00:28:12]: I will press on the privacy thing because that is the number one thing that everyone talks about. Obviously, I think in Silicon Valley, people are a little bit more tech-forward, experimental, whatever. But you want to go mainstream. You want to sell to consumers. And we have to worry about this stuff. Baseline question. The hardest version of this is law. There are one-party consent states where this is perfectly legal. Then there are two-party consent states where they're not. What have you come around to this on? Ethan [00:28:38]: Yeah, so the EU is a totally different regulatory environment. But in the U. S., it's basically on a state-by-state level. Like, in Nevada, it's single-party. In California, it's two-party. But it's kind of untested. You know, it's different laws, whether it's a phone call, whether it's in person. In a state like California, it's two-party. Like, anytime you're in public, there's no consent comes into play because the expectation of privacy is that you're in public. But we process the audio and nothing is persisted. And then it's summarized with the speaker identification focusing on the user. Now, it's kind of untested on a legal, and I'm not a lawyer, but does that constitute the same as, like, a recording? So, you know, it's kind of a gray area and untested in law right now. I think that the bigger question is, you know, because, like, if you had your Ray-Ban on and were recording, then you have a video of something that happened. And that's different than kind of having, like, an AI give you a summary that's focused on you that's not really capturing anybody's voice. You know, I think the bigger question is, regardless of the legal status, like, what is the ethical kind of situation with that? Because even in Nevada that we're—or many other U. S. states where you can record. Everything. And you don't have to have consent. Is it still, like, the right thing to do? The way we think about it is, is that, you know, we take a lot of precautions to kind of not capture personal information of people around. Both through the speaker identification, through the pipeline, and then the prompts, and the way we store the information to be kind of really focused on the user. Now, we know that's not going to, like, satisfy a lot of people. But I think if you do try it and wear it again. It's very hard for me to see anything, like, if somebody was wearing a bee around me that I would ever object that it captured about me as, like, a third party to it. And like I said, like, we're in this transitional period where the expectation will just be more normalized. That it's, like, an AI. It's not capturing, you know, a full audio recording of what you said. And it's—everything is fully geared towards helping the person kind of understand their state and providing valuable information to them. Not about, like, logging details about people they encounter. Alessio [00:30:57]: You know, I've had the same question also with the Zoom meeting transcribers thing. I think there's kind of, like, the personal impact that there's a Firefly's AI recorder. Yeah. I just know that it's being recorded. It's not like a—I don't know if I'm going to say anything different. But, like, intrinsically, you kind of feel—because it's not pervasive. And I'm curious, especially, like, in your investor meetings. Do people feel differently? Like, have you had people ask you to, like, turn it off? Like, in a business meeting, to not record? I'm curious if you've run into any of these behaviors. Maria [00:31:29]: You know what's funny? On my end, I wear it all the time. I take my coffee, a blue bottle with it. Or I work with it. Like, obviously, I work on it. So, I wear it all the time. And so far, I don't think anybody asked me to turn it off. I'm not sure if because they were really friendly with me that they know that I'm working on it. But nobody really cared. swyx [00:31:48]: It's because you live in SF. Maria [00:31:49]: Actually, I've been in Italy as well. Uh-huh. And in Italy, it's a super privacy concern. Like, Europe is a super privacy concern. And again, they're nothing. Like, it's—I don't know. Yeah. That, for me, was interesting. Ethan [00:32:01]: I think—yeah, nobody's ever asked me to turn it off, even after giving them full demos and disclosing. I think that some people have said, well, my—you know, in a personal relationship, my partner initially was, like, kind of uncomfortable about it. We heard that from a few users. And that was, like, more in just, like— It's not like a personal relationship situation. And the other big one is people are like, I do like it, but I cannot wear this at work. I guess. Yeah. Yeah. Because, like, I think I will get in trouble based on policies or, like, you know, if you're wearing it inside a research lab or something where you're working on things that are kind of sensitive that, like—you know, so we're adding certain features like geofencing, just, like, at this location. It's just never active. swyx [00:32:50]: I mean, I've often actually explained to it the other way, where maybe you only want it at work, so you never take it from work. And it's just a work device, just like your Zoom meeting recorder is a work device. Ethan [00:33:09]: Yeah, professionals have been a big early adopter segment. And you say in San Francisco, but we have out there our daily shipment of over 100. If you go look at the addresses, Texas, I think, is our biggest state, and Florida, just the biggest states. A lot of professionals who talk for, and we didn't go out to build it for that use case, but I think there is a lot of demand for white-collar people who talk for a living. And I think we're just starting to talk with them. I think they just want to be able to improve their performance around, understand what they were doing. Alessio [00:33:47]: How do you think about Gong.io? Some of these, for example, sales training thing, where you put on a sales call and then it coaches you. They're more verticalized versus having more horizontal platform. Ethan [00:33:58]: I am not super familiar with those things, because like I said, it was kind of a surprise to us. But I think that those are interesting. I've seen there's a bunch of them now, right? Yeah. It kind of makes sense. I'm terrible at sales, so I could probably use one. But it's not my job, fundamentally. But yeah, I think maybe it's, you know, we heard also people with restaurants, if they're able to understand, if they're doing well. Maria [00:34:26]: Yeah, but in general, I think a lot of people, they like to have the double check of, did I do this well? Or can you suggest me how I can do better? We had a user that was saying to us that he used for interviews. Yeah, he used job interviews. So he used B and after asked to the B, oh, actually, how do you think my interview went? What I should do better? And I like that. And like, oh, that's actually like a personal coach in a way. Alessio [00:34:50]: Yeah. But I guess the question is like, do you want to build all of those use cases? Or do you see B as more like a platform where somebody is going to build like, you know, the sales coach that connects to B so that you're kind of the data feed into it? Ethan [00:35:02]: I don't think this is like a data feed, more like an understanding kind of engine and like definitely. In the future, having third parties to the API and building out for all the different use cases is something that we want to do. But the like initial case we're trying to do is like build that layer for all that to work. And, you know, we're not trying to build all those verticals because no startup could do that well. But I think that it's really been quite fascinating to see, like, you know, I've done consumer for a long time. Consumer is very hard to predict, like, what's going to be. It's going to be like the thing that's the killer feature. And so, I mean, we really believe that it's the future, but we don't know like what exactly like process it will take to really gain mass adoption. swyx [00:35:50]: The killer consumer feature is whatever Nikita Beer does. Yeah. Social app for teens. Ethan [00:35:56]: Yeah, well, I like Nikita, but, you know, he's good at building bootstrap companies and getting them very viral. And then selling them and then they shut down. swyx [00:36:05]: Okay, so you just came back from CES. Maria [00:36:07]: Yeah, crazy. Yeah, tell us. It was my first time in Vegas and first time CES, both of them were overwhelming. swyx [00:36:15]: First of all, did you feel like you had to do it because you're in consumer hardware? Maria [00:36:19]: Then we decided to be there and to have a lot of partners and media meetings, but we didn't have our own booth. So we decided to just keep that. But we decided to be there and have a presence there, even just us and speak with people. It's very hard to stand out. Yeah, I think, you know, it depends what type of booth you have. I think if you can prepare like a really cool booth. Ethan [00:36:41]: Have you been to CES? Maria [00:36:42]: I think it can be pretty cool. Ethan [00:36:43]: It's massive. It's huge. It's like 80,000, 90,000 people across the Venetian and the convention center. And it's, to me, I always wanted to go just like... Maria [00:36:53]: Yeah, you were the one who was like... swyx [00:36:55]: I thought it was your idea. Ethan [00:36:57]: I always wanted to go just as a, like, just as a fan of... Maria [00:37:01]: Yeah, you wanted to go anyways. Ethan [00:37:02]: Because like, growing up, I think CES like kind of peaked for a while and it was like, oh, I want to go. That's where all the cool, like... gadgets, everything. Yeah, now it's like SmartBitch and like, you know, vacuuming the picks up socks. Exactly. Maria [00:37:13]: There are a lot of cool vacuums. Oh, they love it. swyx [00:37:15]: They love the Roombas, the pick up socks. Maria [00:37:16]: And pet tech. Yeah, yeah. And dog stuff. swyx [00:37:20]: Yeah, there's a lot of like robot stuff. New TVs, new cars that never ship. Yeah. Yeah. I'm thinking like last year, this time last year was when Rabbit and Humane launched at CES and Rabbit kind of won CES. And now this year, no wearables except for you guys. Ethan [00:37:32]: It's funny because it's obviously it's AI everything. Yeah. Like every single product. Yeah. Maria [00:37:37]: Toothbrush with AI, vacuums with AI. Yeah. Yeah. Ethan [00:37:41]: We like hair blow, literally a hairdryer with AI. We saw. Maria [00:37:45]: Yeah, that was cool. Ethan [00:37:46]: But I think that like, yeah, we didn't, another kind of difference like around our, like we didn't want to do like a big overhypey promised kind of Rabbit launch. Because I mean, they did, hats off to them, like on the presentation and everything, obviously. But like, you know, we want to let the product kind of speak for itself and like get it out there. And I think we were really happy. We got some very good interest from media and some of the partners there. So like it was, I think it was definitely worth going. I would say like if you're in hardware, it's just kind of how you make use of it. Like I think to do it like a big Rabbit style or to have a huge show on there, like you need to plan that six months in advance. And it's very expensive. But like if you, you know, go there, there's everybody's there. All the media is there. There's a lot of some pre-show events that it's just great to talk to people. And the industry also, all the manufacturers, suppliers are there. So we learned about some really cool stuff that we might like. We met with somebody. They have like thermal energy capture. And it's like, oh, could you maybe not need to charge it? Because they have like a thermal that can capture your body heat. And what? Yeah, they're here. They're actually here. And in Palo Alto, they have like a Fitbit thing that you don't have to charge. swyx [00:39:01]: Like on paper, that's the power you can get from that. What's the power draw for this thing? Ethan [00:39:05]: It's more than you could get from the body heat, it turns out. But it's quite small. I don't want to disclose technically. But I think that solar is still, they also have one where it's like this thing could be like the face of it. It's just a solar cell. And like that is more realistic. Or kinetic. Kinetic, apparently, I'm not an expert in this, but they seem to think it wouldn't be enough. Kinetic is quite small, I guess, on the capture. swyx [00:39:33]: Well, I mean, watch. Watchmakers have been powering with kinetic for a long time. Yeah. We don't have to talk about that. I just want to get a sense of CES. Would you do it again? I definitely would not. Okay. You're just a fan of CES. Business point of view doesn't make sense. I happen to be in the conference business, right? So I'm kind of just curious. Yeah. Maria [00:39:49]: So I would say as we did, so without the booth and really like straightforward conversations that were already planned. Three days. That's okay. I think it was okay. Okay. But if you need to invest for a booth that is not. Okay. A good one. Which is how much? I think. Ethan [00:40:06]: 10 by 10 is 5,000. But on top of that, you need to. And then they go like 10 by 10 is like super small. Yeah. And like some companies have, I think would probably be more in like the six figure range to get. And I mean, I think that, yeah, it's very noisy. We heard this, that it's very, very noisy. Like obviously if you're, everything is being launched there and like everything from cars to cell phones are being launched. Yeah. So it's hard to stand out. But like, I think going in with a plan of who you want to talk to, I feel like. Maria [00:40:36]: That was worth it. Ethan [00:40:37]: Worth it. We had a lot of really positive media coverage from it and we got the word out and like, so I think we accomplished what we wanted to do. swyx [00:40:46]: I mean, there's some world in which my conference is kind of the CES of whatever AI becomes. Yeah. I think that. Maria [00:40:52]: Don't do it in Vegas. Don't do it in Vegas. Yeah. Don't do it in Vegas. That's the only thing. I didn't really like Vegas. That's great. Amazing. Those are my favorite ones. Alessio [00:41:02]: You can not fit 90,000 people in SF. That's really duh. Ethan [00:41:05]: You need to do like multiple locations so you can do Moscone and then have one in. swyx [00:41:09]: I mean, that's what Salesforce conferences. Well, GDC is how many? That might be 50,000, right? Okay. Form factor, right? Like my way to introduce this idea was that I was at the launch in Solaris. What was the old name of it? Newton. Newton. Of Tab when Avi first launched it. He was like, I thought through everything. Every form factor, pendant is the thing. And then we got the pendants for this original. The first one was just pendants and I took it off and I forgot to put it back on. So you went through pendants, pin, bracelet now, and maybe there's sort of earphones in the future, but what was your iterations? Maria [00:41:49]: So we had, I believe now three or four iterations. And one of the things that we learned is indeed that people don't like the pendant. In particular, woman, you don't want to have like anything here on the chest because it's maybe you have like other necklace or any other stuff. Ethan [00:42:03]: You just ship a premium one that's gold. Yeah. We're talking some fashion reached out to us. Maria [00:42:11]: Some big fashion. There is something there. swyx [00:42:13]: This is where it helps to have an Italian on the team. Maria [00:42:15]: There is like some big Italian luxury. I can't say anything. So yeah, bracelet actually came from the community because they were like, oh, I don't want to wear anything like as necklace or as a pendant. Like it's. And also like the one that we had, I don't know if you remember, like it was like circle, like it was like this and was like really bulky. Like people didn't like it. And also, I mean, I actually, I don't dislike, like we were running fast when we did that. Like our, our thing was like, we wanted to ship them as soon as possible. So we're not overthinking the form factor or the material. We were just want to be out. But after the community organically, basically all of them were like, well, why you don't just don't do the bracelet? Like he's way better. I will just wear it. And that's it. So that's how we ended up with the bracelet, but it's still modular. So I still want to play around the father is modular and you can, you know, take it off and wear it as a clip or in the future, maybe we will bring back the pendant. But I like the fact that there is some personalization and right now we have two colors, yellow and black. Soon we will have other ones. So yeah, we can play a lot around that. Ethan [00:43:25]: I think the form factor. Like the goal is for it to be not super invasive. Right. And something that's easy. So I think in the future, smaller, thinner, not like apple type obsession with thinness, but it does matter like the, the size and weight. And we would love to have more context because that will help, but to make it work, I think it really needs to have good power consumption, good battery life. And, you know, like with the humane swapping the batteries, I have one, I mean, I'm, I'm, I think we've made, and there's like pretty incredible, some of the engineering they did, but like, it wasn't kind of geared towards solving the problem. It was just, it's too heavy. The swappable batteries is too much to man, like the heat, the thermals is like too much to light interface thing. Yeah. Like that. That's cool. It's cool. It's cool. But it's like, if, if you have your handout here, you want to use your phone, like it's not really solving a problem. Cause you know how to use your phone. It's got a brilliant display. You have to kind of learn how to gesture this low range. Yeah. It's like a resolution laser, but the laser is cool that the fact they got it working in that thing, even though if it did overheat, but like too heavy, too cumbersome, too complicated with the multiple batteries. So something that's power efficient, kind of thin, both in the physical sense and also in the edge compute kind of way so that it can be as unobtrusive as possible. Yeah. Maria [00:44:47]: Users really like, like, I like when they say yes, I like to wear it and forget about it because I don't need to charge it every single day. On the other version, I believe we had like 35 hours or something, which was okay. But people, they just prefer the seven days battery life and- swyx [00:45:03]: Oh, this is seven days? Yeah. Oh, I've been charging every three days. Maria [00:45:07]: Oh, no, you can like keep it like, yeah, it's like almost seven days. swyx [00:45:11]: The other thing that occurs to me, maybe there's an Apple watch strap so that I don't have to double watch. Yeah. Maria [00:45:17]: That's the other one that, yeah, I thought about it. I saw as well the ones that like, you can like put it like back on the phone. Like, you know- Plog. There is a lot. swyx [00:45:27]: So yeah, there's a competitor called Plog. Yeah. It's not really a competitor. They only transcribe, right? Yeah, they only transcribe. But they're very good at it. Yeah. Ethan [00:45:33]: No, they're great. Their hardware is really good too. swyx [00:45:36]: And they just launched the pin too. Yeah. Ethan [00:45:38]: I think that the MagSafe kind of form factor has a lot of advantages, but some disadvantages. You can definitely put a very huge battery on that, you know? And so like the battery life's not, the power consumption's not so much of a concern, but you know, downside the phone's like in your pocket. And so I think that, you know, form factors will continue to evolve, but, and you know, more sensors, less obtrusive and- Maria [00:46:02]: Yeah. We have a new version. Ethan [00:46:04]: Easier to use. Maria [00:46:05]: Okay. swyx [00:46:05]: Looking forward to that. Yeah. I mean, we'll, whenever we launch this, we'll try to show whatever, but I'm sure you're going to keep iterating. Last thing on hardware, and then we'll go on to the software side, because I think that's where you guys are also really, really strong. Vision. You wanted to talk about why no vision? Yeah. Ethan [00:46:20]: I think it comes down to like when you're, when you're a startup, especially in hardware, you're just, you work within the constraints, right? And so like vision is super useful and super interesting. And what we actually started with, there's two issues with vision that make it like not the place we decided to start. One is power consumption. So you know, you kind of have to trade off your power budget, like capturing even at a low frame rate and transmitting the radio is actually the thing that takes up the majority of the power. So. Yeah. So you would really have to have quite a, like unacceptably, like large and heavy battery to do it continuously all day. We have, I think, novel kind of alternative ways that might allow us to do that. And we have some prototypes. The other issue is form factor. So like even with like a wide field of view, if you're wearing something on your chest, it's going, you know, obviously the wrist is not really that much of an option. And if you're wearing it on your chest, it's, it's often gone. You're going to probably be not capturing like the field of view of what's interesting to you. So that leaves you kind of with your head and face. And then anything that goes on, on the face has to look cool. Like I don't know if you remember the spectacles, it was kind of like the first, yeah, but they kind of, they didn't, they were not very successful. And I think one of the reasons is they were, they're so weird looking. Yeah. The camera was so big on the side. And if you look at them at array bands where they're way more successful, they, they look almost indistinguishable from array bands. And they invested a lot into that and they, they have a partnership with Qualcomm to develop custom Silicon. They have a stake in Luxottica now. So like they coming from all the angles, like to make glasses, I think like, you know, I don't know if you know, Brilliant Labs, they're cool company, they make frames, which is kind of like a cool hackable glasses and, and, and like, they're really good, like on hardware, they're really good. But even if you look at the frames, which I would say is like the most advanced kind of startup. Yeah. Yeah. Yeah. There was one that launched at CES, but it's not shipping yet. Like one that you can buy now, it's still not something you'd wear every day and the battery life is super short. So I think just the challenge of doing vision right, like off the bat, like would require quite a bit more resources. And so like audio is such a good entry point and it's also the privacy around audio. If you, if you had images, that's like another huge challenge to overcome. So I think that. Ideally the personal AI would have, you know, all the senses and you know, we'll, we'll get there. Yeah. Okay. swyx [00:48:57]: One last hardware thing. I have to ask this because then we'll move to the software. Were either of you electrical engineering? Ethan [00:49:04]: No, I'm CES. And so I have a, I've taken some EE courses, but I, I had done prior to working on, on the hardware here, like I had done a little bit of like embedded systems, like very little firmware, but we have luckily on the team, somebody with deep experience. Yeah. swyx [00:49:21]: I'm just like, you know, like you have to become hardware people. Yeah. Ethan [00:49:25]: Yeah. I mean, I learned to worry about supply chain power. I think this is like radio. Maria [00:49:30]: There's so many things to learn. Ethan [00:49:32]: I would tell this about hardware, like, and I know it's been said before, but building a prototype and like learning how the electronics work and learning about firmware and developing, this is like, I think fun for a lot of engineers and it's, it's all totally like achievable, especially now, like with, with the tools we have, like stuff you might've been intimidated about. Like, how do I like write this firmware now? With Sonnet, like you can, you can get going and actually see results quickly. But I think going from prototype to actually making something manufactured is a enormous jump. And it's not all about technology, the supply chain, the procurement, the regulations, the cost, the tooling. The thing about software that I'm used to is it's funny that you can make changes all along the way and ship it. But like when you have to buy tooling for an enclosure that's expensive. swyx [00:50:24]: Do you buy your own tooling? You have to. Ethan [00:50:25]: Don't you just subcontract out to someone in China? Oh, no. Do we make the tooling? No, no. You have to have CNC and like a bunch of machines. Maria [00:50:31]: Like nobody makes their own tooling, but like you have to design this design and you submit Ethan [00:50:36]: it and then they go four to six weeks later. Yeah. And then if there's a problem with it, well, then you're not, you're not making any, any of your enclosures. And so you have to really plan ahead. And like. swyx [00:50:48]: I just want to leave tips for other hardware founders. Like what resources or websites are most helpful in your sort of manufacturing journey? Ethan [00:50:55]: You know, I think it's different depending on like it's hardware so specialized in different ways. Maria [00:51:00]: I will say that, for example, I should choose a manufacturer company. I speak with other founders and like we can give you like some, you know, some tips of who is good and who is not, or like who's specialized in something versus somebody else. Yeah. Ethan [00:51:15]: Like some people are good in plastics. Some people are good. Maria [00:51:18]: I think like for us, it really helped at the beginning to speak with others and understand. Okay. Like who is around. I work in Shenzhen. I lived almost two years in China. I have an idea about like different hardware manufacturer and all of that. Soon I will go back to Shenzhen to check out. So I think it's good also to go in place and check. Ethan [00:51:40]: Yeah, you have to like once you, if you, so we did some stuff domestically and like if you have that ability. The reason I say ability is very expensive, but like to build out some proof of concepts and do field testing before you take it to a manufacturer, despite what people say, there's really good domestic manufacturing for small quantities at extremely high prices. So we got our first PCB and the assembly done in LA. So there's a lot of good because of the defense industry that can do quick churn. So it's like, we need this board. We need to find out if it's working. We have this deadline we want to start, but you need to go through this. And like if you want to have it done and fabricated in a week, they can do it for a price. But I think, you know, everybody's kind of trending even for prototyping now moving that offshore because in China you can do prototyping and get it within almost the same timeline. But the thing is with manufacturing, like it really helps to go there and kind of establish the relationship. Yeah. Alessio [00:52:38]: My first company was a hardware company and we did our PCBs in China and took a long time. Now things are better. But this was, yeah, I don't know, 10 years ago, something like that. Yeah. Ethan [00:52:47]: I think that like the, and I've heard this too, we didn't run into this problem, but like, you know, if it's something where you don't have the relationship, they don't see you, they don't know you, you know, you might get subcontracted out or like they're not paying attention. But like if you're, you know, you have the relationship and a priority, like, yeah, it's really good. We ended up doing the fabrication assembly in Taiwan for various reasons. Maria [00:53:11]: And I think it really helped the fact that you went there at some point. Yeah. Ethan [00:53:15]: We're really happy with the process and, but I mean the whole process of just Choosing the right people. Choosing the right people, but also just sourcing the bill materials and all of that stuff. Like, I guess like if you have time, it's not that bad, but if you're trying to like really push the speed at that, it's incredibly stressful. Okay. We got to move to the software. Yeah. Alessio [00:53:38]: Yeah. So the hardware, maybe it's hard for people to understand, but what software people can understand is that running. Transcription and summarization, all of these things in real time every day for 24 hours a day. It's not easy. So you mentioned 200,000 tokens for a day. Yeah. How do you make it basically free to run all of this for the consumer? Ethan [00:53:59]: Well, I think that the pipeline and the inference, like people think about all of these tokens, but as you know, the price of tokens is like dramatically dropping. You guys probably have some charts somewhere that you've posted. We do. And like, if you see that trend in like 250,000 input tokens, it's not really that much, right? Like the output. swyx [00:54:21]: You do several layers. You do live. Yeah. Ethan [00:54:23]: Yeah. So the speech to text is like the most challenging part actually, because you know, it requires like real time processing and then like later processing with a larger model. And one thing that is fairly obvious is that like, you don't need to transcribe things that don't have any voice in it. Right? So good voice activity is key, right? Because like the majority of most people's day is not spent with voice activity. Right? So that is the first step to cutting down the amount of compute you have to do. And voice activity is a fairly cheap thing to do. Very, very cheap thing to do. The models that need to summarize, you don't need a Sonnet level kind of model to summarize. You do need a Sonnet level model to like execute things like the agent. And we will be having a subscription for like features like that because it's, you know, although now with the R1, like we'll see, we haven't evaluated it. A deep seek? Yeah. I mean, not that one in particular, but like, you know, they're already there that can kind of perform at that level. I was like, it's going to stay in six months, but like, yeah. So self-hosted models help in the things where you can. So you are self-hosting models. Yes. You are fine tuning your own ASR. Yes. I will say that I see in the future that everything's trending down. Although like, I think there might be an intermediary step with things to become expensive, which is like, we're really interested because like the pipeline is very tedious and like a lot of tuning. Right. Which is brutal because it's just a lot of trial and error. Whereas like, well, wouldn't it be nice if an end to end model could just do all of this and learn it? If we could do transcription with like an LLM, there's so many advantages to that, but it's going to be a larger model and hence like more compute, you know, we're optimistic. Maybe we could distill something down and like, we kind of more than focus on reducing the cost of the existing pipeline or trying to the next generation. Cause it's very clear that like all ASR, all speech to the text is going to be pretty obsolete pretty soon. So like investing into that is probably kind of a dead end. Cause it's just going to be. It's going to be obsolete. swyx [00:56:39]: It's interesting. Like I think when I initially invested in tab this is, this shows you how wrong I was. I was like, oh, this is a sort of razor blades, blade razors and blades model where you sell a cheap hardware and you make up a subscription, like a monthly subscription. And now I just checked friend is a one-time sale, $99 limitless one-time sale, $99. These guys one-time sale, $49 and inference is free. What? Wow. It's crazy. Ethan [00:57:09]: I think when you probably invested, like how much was a million input tokens at that time and what is it now? swyx [00:57:15]: It's a fascinating business and like, you know, there's a lot to dig into there, but just getting that perspective out there is, I think it's not something that people think about a lot. Alessio [00:57:24]: And you obviously have thought a lot about. What about memory? I think this is something we go back and forth on about memory as in you're just memorizing facts and then understanding implicit preference and adjusting facts that you think are important. Have you ever done something about a person? Any learnings from that? I know there's a lot of open source frameworks now that do it that you build all of your own infrastructure internally. Ethan [00:57:46]: Yeah, we did. I mean I evaluated used a lot in other projects. I think that there's a few different tasks or things that revolve around memory. Like one is like retrieval obviously. And like when you need to find like even if you have a large corpus of how do you find? And so like I think existing kind of rag pipelines also will probably be the most helpful. The frameworks, I have not found one, like, there's no general way to do RAG that works, like, it's really highly dependent on the data. So, like, if you're going to be customizing something that much, it's just, you get kind of more bang from the buck from designing it all yourself. You know, a lot of those frameworks are great for getting going quickly. But I think it's really interesting memory when you're trying to do, for a person, because memory is decay, right? Like, I'm going to London, you know, then I come back, I'm not going to London anymore. What we've learned is, like, doing the traditional, like, embedding and RAG is suboptimal. We kind of built our own using small models to do really massively parallel retrieval. Which I think is going to be maybe more common in the future. And then, like, how to represent a person. We still require some human loop. And I mean, this is an ongoing project. And, you know, we're learning every day. Like, how do you correct the model when it gets something wrong about you? Right now, we have, like, things that are, like, super confirmed that are, like, ground truth about you because the human accepted it. But ideally, like, that step wouldn't be necessary. And then we have things that are fuzzier. And, like, the more... Stuff that we know is true, the more accurate we are when we're trying to decide, is this fuzzy stuff? Because it's probably, like, if you have the context, it's probably not true. So I think it's one of the most core challenges is how to handle both retrieval and then modeling and, like, especially when you're dealing with noisy source data. Because, like, even if, in an ideal world, even if you just had perfect transcription and you're going off that, that's still not enough information, right? And even if you had visual, it's still not enough. Like, there's still going to be... Alessio [00:59:55]: Yeah, one way I think about it is I usually like to order the same thing from the same restaurant if I like it. But I'm not saying that out loud. And it's kind of like, are these type of behaviors? Like, when you ask about a favorite restaurant, I would just want it to give me restaurants that I've already been to that I like. Or, like, if I'm like, hey, just order something. from this place, I should just reorder the same thing. Because it knows that I like to redo the same thing. But I feel like today, most agent memory things that I see people publish, it's like, you know, just write down the data thing. Ethan [01:00:39]: Yeah, I mean, I think that's why the reasoning, like, in our case, like, giving it time to consider all of the sources it has. So, like, look at the email, see, like, the receipts, and then look at the conversations to see, like, what I've mentioned. And then be able to then take enough time to search through all the contexts and connect the dots is, I think, really important. And, like, I don't know, like, some of the agent memory stuff is, like, the key value with RAG on top. Like, and the results there are just not complete enough when you have, like, growing corpus and, like, managing decay and hallucinations that might be in the source material. So, this is where people usually bring in knowledge graphs. Yes. And do you do it? We don't extensively use knowledge graphs. It's something, you know, we didn't talk also about the kind of potential future social aspects. Maria [01:01:33]: Yeah, I wanted to speak about it. Ethan [01:01:35]: But the problem with knowledge graphs that we found is, like, and I don't know if you can tell me what your experience has been, but they're great for representing the data, but then, like, using it at inference time is kind of challenging. swyx [01:01:49]: For speed or what other issues? Ethan [01:01:51]: Just, like, the LLM understanding. Like, the graph. Yeah. The input. Yeah, it's not in the training data, for sure. I think that the graph is the right kind of way to store the data, but, like, then you need to have the right retrieval and then just kind of formatting in a way that, like, doesn't just overwhelm or confuse what you're trying to do. Should we ask about social? Yeah, I thought you were going to go into it. Yeah. Like, not directly related. We did some experimentation. Not directly related to, like, graph retrieval or graph knowledge races. Yeah. Yeah. Yeah. Yeah. The idea that having, like, your personal context, but then, like, other people can query it, you know, it can divulge some things that you would have full control over. Then Maria and I are trying to negotiate, like, where we're going to dinner, like, there can be an exchange. We exactly did this experiment. Yeah. There can be an exchange between the agents and, like, oh. Maria [01:02:45]: So how, like, my agent can speak with Ethan's agent. Both of them, they know our location, what we like, where we went in the past. Yeah. And even, you know, if we have our calendar integrated, they know when we're free. So they can interact with each other and have a conversation and decide a place to go for us. Wow. And we did that. And it was, for me, really cool because they suggested to us a nice French restaurant that we went at the end. swyx [01:03:11]: That you've never been to? Maria [01:03:12]: That we've never been to. Okay. But both of us, they said that we like French food. Both of us, we were in Pacific Heights. And, yeah, this was really trivial. Yeah. Ethan [01:03:23]: It's a trivial, like, toy use. But I guess, like, in terms of you've been using it for a while, like, if I wanted to buy you a gift. Maria [01:03:30]: Oh, my God. You bought me a bunch of candles now that I think about it. Ethan [01:03:35]: This is another use case. I was like, yeah. When we were testing the agent, like, a bunch of candles from Amazon showed up at her door. Maria [01:03:43]: Yeah, because I love candles, but I didn't expect 20. Yeah. Ethan [01:03:47]: It was a lot of experimenting. But, like, how to manage that where it's like, what's okay for your B to divulge to him? Who? Yeah. Like, shouldn't you get an authorization request every time? Yeah, yeah, yeah. swyx [01:03:58]: For personal context. Yeah, yeah, yeah. Ethan [01:04:00]: So, like, you know, you would have to, human would have to sign off on it. But I think then, like, then I wouldn't have to guess. I could just. swyx [01:04:10]: Yeah, yeah. You know, there's this culture that, like, is very alien to everyone else outside of SF and outside the Gen Z bubble in SF, which is sharing, location sharing. Yeah. I can tell my close friends where they are exactly right now in the city. Yeah. And it's opt-in. And, like, it's. Dude. Dude. You know, and, like, it's normal and, like, it freaks out everyone who's not here. Yeah. Yeah. And so maybe we can share preference, like, who we like. Absolutely. Maria [01:04:34]: I really believe in it, for sure. We will. Ethan [01:04:36]: Or even, like, small updates about your day. My parents would love that because I don't do that. Yeah. now there's no friction. It can just be more or less automatic. Yeah. Dating? I was trained always to avoid dating. Really? As a startup founder. Yeah, you can hate that. Yeah. Everyone hates it? Maria [01:04:55]: We thought about it. Like, sometimes some people, they ask to us because it's like, oh, you know so much about me. Like, can you measure compatibility with somebody else or something like that? Yeah. Probably there is a future. Maybe somebody should build that. I think on our end, we were like, no, this is. We don't want to. Ethan [01:05:11]: I will build on your API. My sister is actually a personality psychology professor and she studies personality. And we were at Thanksgiving because my parents wear one. And I was like, ask it. Like, give me my big five. Yeah. Which is like the personality type. And it's like. Does it know my big five? Just ask it to consider everything and give your big five. And my sister said it was pretty. I didn't agree with it because it said I was disagreeable. I agree with that. But she seemed to think it was agreeable. And so. swyx [01:05:41]: You disagree that you're disagreeable? Yeah. Yeah. What other proof do we need then? Ethan [01:05:47]: Yeah. I think I'm very agreeable. Ethan [01:05:51]: But I think that we do. I did get some users are like, oh, if like we're a couple. Yeah. Maria [01:05:56]: We had like couples. Actually. They bought the product together. Yeah. Like both. Like couple. They bought the hardware. So there is something there. Another test is like the Myers-Briggs. I know that you don't like that one. No. No. swyx [01:06:08]: Ocean is cooler than Myers-Briggs. Yeah. Everyone stop using my MBTI. Use my. Use Ocean. Yeah. Maria [01:06:12]: Yeah. For me, like it was on point. Like every time. Like it. Awesome. Alessio [01:06:16]: Anything else that we didn't cover? Any cool underrated things? Maria [01:06:21]: Go to b.computer. Forty nine. Ninety nine. And you buy the device. That's the. That's the call to action. swyx [01:06:28]: And you're hiring? Maria [01:06:29]: We are hiring. For sure. Ethan [01:06:32]: AI engineers. Maria [01:06:33]: AI engineers. Nice. What is an AI engineer? Ethan [01:06:35]: Yeah. But did you study? Somebody who's scrappy and willing to. Maria [01:06:42]: Work with us. Yeah. Ethan [01:06:43]: I think. I think you coined the term, right? So you can tell us. Maria [01:06:48]: Somebody that can adapt. That has resistance. Yeah. Yeah. swyx [01:06:51]: People have different perspectives and what is useful for you is different from what is useful for me. Yeah. So anyway, it's so useful. Ethan [01:06:57]: I mean, I think that always on AI is really going to explode and it's going to be a lot from both a lot of startups, but incumbents and there's going to be all kinds of new things that we're going to learn about how it's going to change all of our lives. I think that's the thing I'm most certain about. So. And being AI. swyx [01:07:15]: Well, thanks very much. Thank you guys. This is a pleasure. Thank you. Yeah. We'll see you launch whenever. Thank you. I'm sure that launch is happening. Yeah. Thanks. Thank you. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe https://www.latent.space/subscribe?utm_medium=podcast&utm_campaign=CTA_2

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

• 0:00Speaker 00

  Hello AI engineers. We're back with yet another first for the pod, covering AI wearables. 2024 was a very challenging year for AI hardware. After the buzz of CES last January, 2024 was marked by the meteoric rise and even harder fall of AI wearables companies like Rabbit and Humane. Evenfriend.com, the first to launch in the AI pendant category and which spurred Rewind AI to rebrand to Limitless and follow in their footsteps, ended up delaying their wearable ship date and launching an experimental website chatbot version. We have been cautiously excited about this category, keeping tabs on most of the top entrants, including Omi and Compass.

• 0:45Speaker 00

  However, so far, the biggest winner still standing from the AI wearable wars is BII, founded by today's guests Maria and Ethan. B is an always-on hardware device with beam-forming microphones, seven-day battery life, and a mute button that can be worn as a wristwatch or a clip-on pin, backed by an incredible transcription, diarization, and very long context memory processing pipeline that helps you to remember your day, your to-dos, and even perform actions by operating a virtual cloud phone. This is one of the most advanced, production-ready, personal AI agents we've ever seen, so we were excited to be their first podcast appearance.

• 1:28Speaker 00

  We met B when we ran the world's first personal AI meetup in April last year, and you can go back in the Latent Space show notes for a link to Ethan's first talk to the Latent Space community. Maria and Ethan will also be joining us as speakers for the Agents Engineering Track at the AI Engineer Summit in New York City on February 21st, which is unfortunately now completely sold out. However, you can sign up for the online livestream linked in the show notes or join the workshops and leadership sessions. See you next week. Watch out and take care.

• 2:06Alessio Fanelli?

  Hey everyone, welcome to the Late in Space Podcast. This is Alessio, Partner and CTO at Dacible Partners, and I'm joined by my co-host Swyx, founder of Small AI.

• 2:14Speaker 02

  Hey, and today we are very honored to have in the studio Maria and Ethan from Bee.

• 2:18Speaker 03

  Hi, hi, thank you for having us.

• 2:22Speaker 02

  And you are, I think, the first hardware founders we've had on the podcast. Been looking to have had a hardware founder, like a wearable hardware, yeah, wearable hardware founder for a while. I think we're going to have two or three of them this year. And you're the ones that I wear every day. So thank you for making Bee.

• 2:40Speaker 04

  Thank you for all the feedback and the usage.

• 2:43Speaker 02

  Yeah, you know, I've been a big fan. You are the speaker gift for the engineer World's Fair. And let's start from the beginning. What is Bee Computer?

• 2:52Speaker 04

  Bee Computer is a personal AI system. So you can think of it as AI living alongside you in first person. So it can kind of capture your in-real-life context. So with that understanding can help you in significant ways. You know, the obvious one is memory, but that's really just the base kind of use case. So recalling and reflective, I know Swyx that you you like the idea of journaling, but you don't, but still have some kind of reflective summary of what you experienced in real life. But it's also about just having like the whole context of a human being and understanding. You know, giving the machine the ability to understand like what's going on in your life, your attitudes, your desires, specifics about your preferences.

• 3:37Speaker 04

  So that not only can it help you with recall, but then anything that you need it to do, it already knows. Like if you think about like somebody who you've worked with or lived with for a long time, they just know kind of without having to ask you what you would want. It's clear that like that is the future that personal AI like is just going to be very, you know, that AI is just so much more valuable with personal context.

• 3:59Speaker 03

  I would say that one of the things that we are really passionate is really understanding this personal context, because we'll make the AI more useful. Think about like a best friend that know you so well. That's one of the things that we are seeing from the user. They're using from a companion standpoint or professional use cases. There are many ways to use Bee, but companionship and professional are the ones that we are seeing now more.

• 4:22Speaker 02

  Yeah. It feels so dry to talk about use cases.

• 4:25Speaker 04

  Yeah.

• 4:26Speaker 03

  Yeah, it's like really like investor question.

• 4:28Speaker 04

  Yeah. We've been so broken and trained.

• 4:33Speaker 04

  But I mean, on the base case, it's just like, don't you want your AI to know everything you've said? And like everywhere you've been, like, wouldn't you want that?

• 4:41Speaker 03

  Yeah, and don't stay there and repeat every time like, oh, this is what I like. You already know that and you do things for me based on that. That's I think is really cool.

• 4:51Speaker 02

  Great. Do you want to jump into a demo? Do you have any other?

• 4:54Speaker 04

  I want to maybe just cover the origin story. Because how did you two mean? What was the, was this the first idea you started working on? Was there something else before?

• 5:02Speaker 03

  I can start. So Ethan and I, we know each other from six years now. He had a company called Squad and before that was called All About and was a personal AI.

• 5:14Speaker 04

  Yeah, I should.

• 5:15Speaker 03

  So maybe you should start this one, but yeah, that's how I know Ethan. Like he was pivoting from personal AI to Squad. And there was a co-watching with friends product. I had experience working with TikTok and video content. So I had the pivoting and we launched Squad and was really successful. And at the end, the founders decided to sell that to Twitter, now X. So both of us, we joined X, we launched Twitter Spaces, we launched many other products. And yeah, till then, we basically continued to work together to the start of B.

• 5:46Speaker 04

  The interesting thing is like, this isn't the first attempt at personal AI. In 2016, when I started my first company, it started out as a personal AI company. This is before transformers, no BERT even, like just R and N's. You couldn't really do any convincing dialogue at all. I met Esther, who was my previous co-founder. We're both really interested in the idea of like having a machine kind of model or understand a dynamic human. We wanted to make personal AI. This was like more geared towards, because we had obviously much limited tools, more geared towards like younger people. So I don't know if you remember in 2016, there was like a brief chatbot boom.

• 6:25Speaker 04

  It was way premature, but it was when Zuckerberg went up on F8 and yeah, M and like the messenger platform. People like, oh, bots are going to. Replace apps. It was like for about six months. And then everybody realized, man, these things are terrible and like they're not replacing apps. But it was at that time that we got excited and we're like, we tried to make this like, oh, teach the AI about you. So it was just an app that you kind of chatted with and it would ask you questions and then like, give you some feedback.

• 6:52Speaker 03

  Hugging Face first version was launched at the same time.

• 6:55Speaker 04

  We started, we started out the same office as Hugging Face because Beta Works was our investor. So they had a thing called Bot Camp. Beta Works is like a really cool VC because they invest in out there things. They're like way ahead of everybody else. And like back then it was, they had something called Bot Camp. They took six companies and it was us and Hugging Face. And then I think the other four, I'm pretty sure are dead. But and Hugging Face was the one that really got, you know.

• 7:19Speaker 02

  I mean, 30% success rate is pretty good.

• 7:21Speaker 04

  Yeah. Yeah. When we was like, it was just the two founders.

• 7:25Speaker 03

  Yeah, they were like a company.

• 7:27Speaker 04

  Yeah, it was a chat app for teenagers. A lot of people don't know that Hugging Face was like, hey friend, how was school? Let's trade selfies. But then, you know, they built the Transformers library, I believe, to help them make their chat app better. And then they open sourced and it was like it blew up and like, they're like, oh, maybe this is the opportunity. And now they're Hugging Face. But anyway, like, we were obsessed with it at that time, but then it was clear that there's some people who really love chatting and like answering questions, but it's like a lot of work, like just to kind of manually.

• 7:56Speaker 03

  Yeah.

• 7:57Speaker 04

  Teach like all these things about you to an AI.

• 8:01Speaker 03

  Yeah, there were some people that were super passionate. For example, teenagers, they really like, for example, to speak about themselves a lot. So they will reply to a lot of questions and speak about them. But most of the people, they don't really want to spend time.

• 8:14Speaker 04

  And you know, it's hard to like really bring the value with it. We had like sentence similarity and stuff and could try and do. But it was like, it was premature with the technology at the time. And so we pivoted, we went to YC and a long story, but like, we pivoted to consumer video and that kind of went really viral and got a lot of usage quickly. And then we ended up selling it to Twitter, worked there and left before Elon, not related to Elon, but left Twitter and then.

• 8:43Speaker 02

  I should mention, this is the famous time when, well, when Elon was, just came in, this was like Esther was the famous product manager.

• 8:52Speaker 04

  My former co-founder, she.

• 8:53Speaker 02

  Steam bag.

• 8:54Speaker 04

  She was the sleep where you were. Yeah, yeah, she invested. She stayed. We had left by that.

• 8:59Speaker 02

  She very stayed. She's famous for staying.

• 9:02Speaker 04

  Yeah. Later left or got, I think. Laid off. Laid off. Yeah. I think the whole product team got laid off. She was a product manager director. But yeah, like we left before that. And then we're like, oh, my God, things are different now. You know, I think this is, we really started working on it again right before ChatGPT came out. But we had an app version and we kind of were trying different things around it. And then, you know, ultimately it was clear that like, there were some limitations. We can go on like, a good question to ask any wearable company is like, why isn't this an app? Yes. Because like.

• 9:35Speaker 03

  Because we tried the app at the beginning.

• 9:38Speaker 04

  Yeah, like the idea that it could be more of a, and B comes from ambient. So like, if it was more kind of just around you all the time and less about you having to go open the app and do the effort to like, enter in data. That led us down the path of hardware because the sensors on this are microphones. So it's capturing and understanding audio. We started actually our first hardware with a vision component too. And we can talk about why.

• 10:05Speaker 02

  That's pretty cool.

• 10:06Speaker 04

  Why we're not doing that right now. But if you wanted to like, have like continuous understanding of audio with your phone, it would monopolize your microphone. It would get interrupted by calls and you'd have to remember to turn it on. And like that little bit of friction is actually like a substantial barrier to like, the experience of it just being with you all the time and like, living alongside you. And so I think that that's like the key reason it's not an app. And in fact, we do have Apple Watch support. So anybody who has a watch, Apple Watch can use it right away without buying any hardware. Cause we worked really hard to make a version for the watch that can run in the background, not super drain your battery. But even with the watch, there's still friction because you have to remember to turn it on.

• 10:50Speaker 04

  And it still gets interrupted if somebody calls you and you have to remember to, we'd send a notification, but you still have to go back and turn it on because it's just the way WatchOS works.

• 10:59Speaker 03

  One of the things that we are seeing from our Apple Watch users, like a lot of the Apple Watch integration. One of the things that we are seeing is that people, they start using it from Apple Watch. And after a couple of days, they buy the B because they just like to wear it.

• 11:12Speaker 04

  Yeah.

• 11:13Speaker 03

  That's something that like we're learning and it's really cool.

• 11:15Speaker 04

  Yeah, I mean, we, I think like fundamentally, we like to think of like a personal AI is like the mission. And it's more about like the understanding, connecting the dots, making use of the data to provide some value. And the hardware is like the ears of the AI. It's not like integrating like the incoming sensor data. And that's really what we focus on. And like the hardware is, you know, if we can do it well and have a great experience on the Apple Watch, like that, that's just great. I mean, but there's just some platform restrictions that like existing hardware makes it hard to provide that experience.

• 11:48Alessio Fanelli?

  Yeah. What do people do in like two, three days that then convinces them to buy the product? This feels like a product where like after you use it for a while, you have enough data to start to get a lot of insights. But it sounds like maybe there's also like a short term.

• 12:01Speaker 03

  From the Apple Watch users, I believe that because every time that you receive a call after, they need to go back to be and open it again. Or for example, every day they need to charge Apple Watch and reminds them to open the app every day. They feel like, okay, maybe this is too much work. I just want to wear the B and just keep it open and that's it. And I don't need to think about it.

• 12:22Speaker 04

  I think they see the kind of potential of it just from the watch. Cause even if you wear it a day, like we sent a summary notification at the end of the day about like just key things that happened to you in your day. And like, I didn't even think like, I'm not like a journaling type person or like, cause like, oh, I just live the day. Why do I need to like, think about it? But like, it's actually pretty, sometimes I'm surprised how interesting it is to me just to kind of be like, oh yeah, that, and how it kind of fits together. And I think that's like just something people get immediately with the watch, but they're like, oh, I'd like an easier way to do this.

• 12:53Alessio Fanelli?

  It's surprising because I only know about the hardware.

• 12:56Speaker 04

  Yeah.

• 12:57Alessio Fanelli?

  But I use the watch as like a backup for when I don't have the hardware. I feel like the, because now you're beam forming and all that, this is significantly better.

• 13:04Speaker 04

  Yeah, that's the other thing. We have way, way more control over like the, the Apple Watch, you're limited in like, you don't, you can't set the gain. You can't change the sample rate. There's just a very limited framework support for doing anything with audio. Whereas if you control it, then you can kind of optimize it for your use case. The Apple Watch isn't meant to be kind of recording this. And we can talk when we get to the part about audio, why it's so hard. This is like audio on the hardest level because you don't know, it has to work in all environments or you try and make it work as best as it can. And like this environment is very great. We're in a studio, but you know, afterwards at dinner in a restaurant, it's totally different audio environment and there's a lot of challenges with that.

• 13:46Speaker 04

  And having really good source audio helps, but then there's a lot with the machine learning that still is, you know, has to be done to try and account because like you can tune something for one environment or another, but it'll make one good and one bad and like making something that's flexible enough is really challenging.

• 14:04Alessio Fanelli?

  Do we want to do a demo just to set the stage and then we kind of talk about?

• 14:09Speaker 03

  Yeah, I think we can go like a walk through the and the prod.

• 14:12Speaker 04

  Yeah, sure. So I think we said I should.

• 14:14Speaker 02

  So for listeners, we'll be switching to video that will superimpose on to this video. If you want to see, go to our YouTube, like and subscribe as always.

• 14:23Speaker 03

  Yeah. And by the B.

• 14:26Speaker 02

  Yes, and by the B.

• 14:27Alessio Fanelli?

  While you wait.

• 14:32Speaker 03

  Maybe you should have a discount code just for the listeners.

• 14:36Speaker 02

  Sure. If you want to offer it, I'll take it.

• 14:38Speaker 04

  All right. Yeah. Well, discount code SWIX.

• 14:40Speaker 02

  Oh shit. Okay. Yeah, there you go.

• 14:42Speaker 04

  An important thing to mention also is that the hardware is meant to work with the phone. And like, I think, you know, if you, if you look at Rabbit or, or Humane, they're trying to create like a new hardware platform. We think that the phone's just so dominant and it will be until we have the next generation, which is not going to be for five, you know, maybe some Orion type glasses that are cheap enough and like light enough. Like that's going to take a long time before with the phone, rather than trying to just like replace it. So in the app, we have a summary of your days, but at the top it's kind of what's going on now. And that's updating continuously. So right now it's saying I'm discussing, you know, the development of, you know, personal AI. And that's just kind of the ongoing conversation.

• 15:26Speaker 04

  And then we give you a readable form that's like little kind of segments of what's the important parts of the conversations. We do speaker identification, which is really important because you don't want your personal AI thinking you said something and attributing it to you when it was just somebody else in the conversation. So you can also teach it other people's voices. So like if some, you know, somebody close to you, so it can start to understand your relationships a little better. And then we do conversation endpointing, which is kind of like a task that didn't even exist before, like, because nobody needed to do this. But like, if you had somebody's whole day, how do you like break it into logical pieces? And so we use like, not just voice activity,

• 16:10Speaker 04

  but other signals to try and split up, because conversations are a little fuzzy. They can like lead into one, can start to the next. So also like the semantic content of it. When a conversation ends, we run it through larger models to try and get a better, you know, sense of the actual what was said, and then summarize it, provide key points. What was the general atmosphere and tone of the conversation? And potential action items that might have come in that. But then, at the end of the day, we give you like a summary of all your day and where you were, and just kind of like a step-by-step walkthrough of what happened and what were the key points. That's kind of just like the base capture layer. So like, if you just want to get a kind of glimpse

• 16:53Speaker 04

  or recall or reflect, that's there. But really, the key is like, all of this is now like being infested on to generate personal context about you. So we generate key items known to be true about you, and that you can, you know, there's a human in a loop aspect is like you can, you have visibility into that. And you can, you know, I have a lot of facts about technology, because that's basically what I talk about all the time. But I do have some hobbies that show up. And then, like, how do you put you to this context? So I kind of like, measure my day now, and just like, what is my token output of the day? You know, like, as a human, how much information do I produce? And it's kind of measured in tokens. And it turns out it's like around 200,000 or so a day.

• 17:38Speaker 04

  But, so in the recall case, we have a chat interface. But the key here is on the recall of it, like, you know, how do you, you know, I probably have 50 million tokens of personal context, and like, how to make sense of that, make it useful. So I can ask simple like recall questions, like, details about the trip I was on to Taiwan, where recently were with our manufacturer. And in real time, like, it will, you know, It has various capabilities such as searching through your memories, but then also being able to search the web or look at my calendar. We have integrations with Gmail and Calendar. So like connecting the dots between the in-real life and the digital life. And, you know, I just asked it about my Taiwan trip

• 18:22Speaker 04

  and it kind of gives me the breakdown of the details, what happened, the issues we had around, you know, certain manufacturing problems. And it goes back and references the conversation. So I can, I can go back to the source.

• 18:36Speaker 03

  Yeah, not just the conversation as well, the integrations. So we have as well Gmail and Google Calendar. So if there is something there that was useful to have more context, we can see that.

• 18:46Speaker 04

  So like, and it can, I never use the word agentic because it's, it's cringe.

• 18:52Speaker 04

  Like an agente.

• 18:55Speaker 04

  It can search through, you know, if I'm brainstorming about something that it spans across, like search through my conversations, search through the email, look at the calendar and then depending on what's needed, then synthesize, you know, something with all that context.

• 19:09Speaker 03

  I love that you did the Spotify wrapped. That was pretty cool.

• 19:12Speaker 04

  Yeah, like one thing I did was just like make a Spotify rap for my 2024, like of my life. You can do that?

• 19:18Speaker 03

  Yeah, you can.

• 19:19Speaker 04

  Wait.

• 19:19Speaker 03

  Yeah. I love that. It's crazy.

• 19:22Speaker 04

  Make a Spotify wrapped. For my life in 2024. Yeah. So it's like surprisingly good. It like kind of like Game Matrix. So it's like you visited three countries, you shipped, you know, X many beta devices and that's kind of more.

• 19:38Speaker 03

  It gives a lot of personal insights and reflection points.

• 19:41Speaker 04

  Yeah, that's fascinating. So that's the demo. Well, we have, we can show something that's in beta. I don't know if we want to do it.

• 19:47Speaker 03

  We want to show something that's better.

• 19:49Speaker 04

  Do it and then we can kind of fit.

• 19:51Speaker 03

  Yeah.

• 19:51Speaker 04

  Yeah. So like the, the, the vision is also like not just about like AI being with you and like just passively understanding you through living your experience, but also then like it proactively suggesting things to you like at the appropriate time. So like not just pool, but, but kind of it can step in and suggest things to you. So, you know, one integration we have that is in beta is with WhatsApp.

• 20:17Speaker 05

  Green is asking for a recommendation for an Italian restaurant. Would you like me to look up some highly rated Italian restaurants nearby and send her a suggestion?

• 20:25Speaker 03

  So what I did, I just sent to Ethan a message through WhatsApp in his own personal phone.

• 20:31Speaker 04

  So basically, B is like watching all my incoming notifications. And if it meets two criteria, like is it important enough for me to raise a suggestion to the user? And then is there something I could potentially help with? So this is where the actions come into place. So because Maria is my co-founder and because it was like a restaurant recommendation, something that it could probably help with, it proposed that to me. And then I can, through the chat, we have another kind of push-to-talk, walkie-talkie-style button. It's actually a multipurpose button to like toggle it on or off. But also if you push the hold, you can talk. So I can say, yes, find one and send it to her on WhatsApp. It's an Android cloud phone.

• 21:15Speaker 04

  So it's going to be able to, you know, that has access to all my accounts. So we're going to abstract this away. And the execution environment is not really important. But like, we can go into technically why Android is actually a pretty good one right now. But you know, it's searching for Italian restaurants. You know, and we don't have to watch this. I could be, you know, have my AirPods in and in my pocket. You know, it's gonna go to WhatsApp, gonna find Maria's thread, send her the response, and then let us know. Oh my god.

• 21:44Alessio Fanelli?

  But what's it gonna suggest? I mean, an Italian restaurant?

• 21:46Speaker 04

  Yeah.

• 21:47Speaker 02

  What did it choose?

• 21:49Speaker 04

  It's easy to say. Real Italian is hard to play. Exactly. It's easy to say. I doubt it's, I don't know what.

• 21:54Speaker 02

  For the record, since you have Italians, best Italian restaurant in SF?

• 21:58Speaker 03

  Oh my god, I still don't have one.

• 22:00Speaker 04

  What?

• 22:01Speaker 03

  No, I don't.

• 22:04Alessio Fanelli?

  Let's see, let's see what the AI says.

• 22:08Alessio Fanelli?

  Bottega, I think it's Bottega.

• 22:13Speaker 03

  I've been to one called like Norchina, I think, that was good.

• 22:17Alessio Fanelli?

  Bottega's on Valencia Street. It's fine. The pizza's not good.

• 22:20Speaker 03

  It's not good?

• 22:21Alessio Fanelli?

  Some of the pastas are good.

• 22:22Speaker 03

  You know, the people say. I'm sorry to interrupt.

• 22:26Alessio Fanelli?

  Sorry.

• 22:27Speaker 03

  But there is like this Delfina that here everybody is like, oh, this Serie Delfina is amazing. I'm like, this is not.

• 22:33Speaker 02

  No, that's great, that's great.

• 22:34Speaker 04

  The North Beach Cafe.

• 22:37Speaker 02

  That place you took us to, Michele, last time?

• 22:39Alessio Fanelli?

  Vega. The guy at Vega, Giuseppe, he's Italian.

• 22:42Speaker 03

  Wait, what is it?

• 22:43Alessio Fanelli?

  It's in Bernal Heights.

• 22:44Speaker 02

  Oh.

• 22:44Alessio Fanelli?

  He's nice, he's a nice.

• 22:46Speaker 02

  What's the name of the place?

• 22:47Alessio Fanelli?

  Vega.

• 22:47Speaker 03

  Vega?

• 22:48Alessio Fanelli?

  Okay, cool, cool, we got the name.

• 22:49Speaker 03

  But it's not Vega, it's Italian. What does it mean in Italian? Vega, niente.

• 22:55Alessio Fanelli?

  It doesn't need to mean.

• 22:57Speaker 02

  The last thing I'll mention is also, you have wake word detection.

• 23:01Speaker 04

  Yeah.

• 23:01Speaker 02

  So the phone can be off, you can just like, say, hey, something, mine's Alfred, say, hey Alfred, and then it just does the thing.

• 23:08Speaker 04

  Yeah.

• 23:08Speaker 02

  Just being able to have wake words like enables some form of sort of voice agent, agent features that even ChatGPT can never have because they don't have the recording layer.

• 23:17Speaker 04

  Yeah, I think we have some other ideas, like even beyond wake words, but I think that it's interesting to see how, how people use the voice side of it. And I think that, you know, we're gonna see a lot of innovation around hardware and stuff, but I think the, the real core is like being able to do something useful with the personal context, because it does like, the thing that like, you, you always had the ability to capture everything, right? Like, we've always had recorders, camcorders, body cameras, stuff like that, but like, what's different now is like, we can actually make sense and find the important parts in all of that context.

• 23:51Speaker 02

  Yeah, so, and then one last thing, I'm just doing this, this for you, is you also have an API, which I think I'm the first developer against.

• 24:00Speaker 02

  Because I had to build my own.

• 24:01Speaker 04

  We need to, we need to hire a developer advocate.

• 24:05Speaker 02

  Or just, yeah, hire AI engineers.

• 24:06Speaker 04

  Yeah.

• 24:07Speaker 02

  The point is that you should be able to program your own assistant. And I tried Omi, the former friend, the knockoff friend, and then, you know, real friend doesn't have an API, and then Limitless also doesn't have an API. So like, I think it's very important to own your data, to be able to reprocess your audio maybe, although like, by default, you do not store audio.

• 24:24Speaker 04

  Yeah.

• 24:24Speaker 02

  And then also just to like, yeah, to, to, to do any corrections, like, there, there's no way that my needs can be fully matched by you. So I think APIs are important.

• 24:33Speaker 04

  Yeah, and I mean, as we're, I've always been a consumer of APIs, you know, in all my products, and so.

• 24:39Speaker 02

  We are API enjoyers in this house.

• 24:41Speaker 04

  Yeah, it's very frustrating, like, when you have to go, like, build a scraper, or, you know, like, but yeah, it's, it's for sure.

• 24:48Speaker 02

  Yeah, so like this, this, this is all a combination of like you have my location, my calendar, my invite, like it's, it really is for me the sort of personal.

• 24:55Alessio Fanelli?

  And is the API just to write into it or to like have it take action on external systems?

• 25:01Speaker 04

  Yeah, we're expanding it. It's right now read only. In the future, very soon, when the actions are more generally available, it'll be fully supported in the API.

• 25:13Alessio Fanelli?

  Nice. I'll buy one after the episode. The API thing to me is the most interesting.

• 25:18Speaker 04

  We do have like real time APIs. So like you can even connect the socket and like connect it to whatever you want it to take actions with.

• 25:26Alessio Fanelli?

  Yeah. Yeah, I think like when I look at these apps and I mean, there's so many of these products. We launch it's like, it's great that I can go on this app and do things, but like most of my work and like personal life is like managed somewhere else.

• 25:39Speaker 04

  Yeah.

• 25:39Alessio Fanelli?

  So being able to like plug into it. It's nice. I have a bunch of more maybe human questions that I think maybe you might have. One, is it good to have instant replay for any argument that you have? I can imagine arguing with my wife about something and you know, there's these commercials now where it's basically like two people arguing and they're like they can throw a flag like in football and have an instant replay of the conversation. I feel like this is similar where it's almost like people cannot really argue anymore or like lie to each other because in a world in which everybody adopts this, I don't know if you thought about it and also like how the lies, you know, all of us tell lies, right? How do you distinguish between what I'm, there's gonna be sometimes

• 26:22Alessio Fanelli?

  things that contradict each other because I might say something publicly and I might think something really that I tell someone else. How do you handle that when you think about building a product like this?

• 26:32Speaker 03

  I would say that I like the fact that B is an objective point of view. So I don't care too much about the lies, but I care more about the fact that. Can help me to understand what happened and the emotions in a really objective way, like really like critical and objective way. And if you think about humans, they have so many emotions. And sometimes something that happened to me, like, I don't know, I will feel like really upset about it or really angry or really emotional. But the AI doesn't have those emotions. It can read the conversation, understand what happened and be objective. And I think that level of support is the one that I really like more. Instead of like, oh, did this guy told me a lie?

• 27:13Speaker 03

  I feel like that's not exactly like what I find curious for me in terms of opportunity.

• 27:19Alessio Fanelli?

  Is the bee going to interject in real time? Say I'm arguing with somebody, the bee is like, hey, look, no, you're wrong. That that person actually said.

• 27:27Speaker 04

  The proactivity is something we're very interested, maybe not for like specifically for like selling arguments, but more for like, and I think that a lot of the challenge here is, you know, you need really good reasoning to kind of pull that off because you don't want it just constantly interjecting because that would be super annoying. And you don't want it to miss things that it should be interjecting. So like, it'd be kind of a hard task even for a human to be like, just come in at the right times when it's appropriate, like it would take them. And, you know, with the personal context, it's going to be a lot better because like if somebody knows about you, but even still, it requires really good reasoning to like not be too much or too little and just right.

• 28:04Speaker 03

  And the second part about, well, like some things, you know, you say something to somebody else, but after I change my mind, I send something like it's every time I have like different type of conversation and data about me. I think that's something that I found really fascinating. One of the things that we are learning is that indeed humans, they evolve over time. So for us, one of the challenges is actually understand like, is this a real fact? And so far, what we do is we give, you know, to the, we have the human in the loop that can say like, yes, this is true, this is not, or they can edit their own fact. For sure, in the future, we want to have all of that automatized inside of the product.

• 28:41Speaker 04

  But I mean, I think your question kind of hits on, and I know that we'll talk about privacy, but also just like, if you have some memory and you want to confirm it with somebody else, that's one thing, but it's for sure going to be true that in the future, like, not even that far into the future, that it's just going to be kind of normalized. And we're kind of in a transitional period now. And I think it's like, one of the key things that is for us to kind of navigate that and make sure we're like, thinking of all the consequences and how to, you know, make the right choices in the way that everything's designed. And so like, it's more beneficial than it could be harmful. But it's just too valuable for your AI to understand you. And so if it's like Meta Ray-Bans or the Google Ask,

• 29:26Speaker 04

  I think it's just people are going to be more used to it. So people's behaviors and expectations will change, whether that's like, you know, something that is going to happen now or in five years. It's probably in that range. And so like, I think we kind of adapt to new technologies all the time. Like when the Ring cameras came out, that was kind of quite controversial. It's like, but now it's kind of, people just understand that a lot of people have cameras on their doors. And so I think that.

• 29:51Speaker 03

  Yeah, we're in a transitional period for sure.

• 29:54Speaker 02

  I will press on the privacy thing because that is the number one thing that everyone talks about. Obviously, I think in Silicon Valley, people are a little bit more tech-forward, experimental, whatever, but you want to go mainstream. You want to sell to consumers and we have to worry about this stuff. Baseline question, the hardest version of this is law. There are one-party consent states where this is perfectly legal. Then there are two-party consent states where they're not. What have you come around to this on?

• 30:20Speaker 04

  Yeah, so the EU is totally different regulatory environment. But in the US, it's basically on a state-by-state level. Like in Nevada, it's single party. In California, it's two-party. But it's kind of untested. You know, it's different laws, whether it's a phone call, whether it's in person. In a state like California, like, anytime you're in public, there's no consent comes into play because the expectation of privacy is that you're in public. But we process the. Audio and nothing has persisted. And then it's summarized with the speaker identification focusing on the user. Now, it's kind of untested on a legal and I'm not a lawyer, but does that constitute the same as like a recording?

• 31:03Speaker 04

  So, you know, it's kind of a gray area and untested in law right now. I think that the bigger question is, you know, because like if you had your Ray Band on and were recording, then you have a video of something that happened. And that's different than kind of having like an AI give you a summary that's focused on you. That's not really capturing anybody's voice. You know, I think the bigger question is regardless of the legal status, like what is the ethical kind of situation with that? Because even in Nevada that we're or many other US states where you can record everything and you don't have to have consent, is it still like the right thing to do?

• 31:44Speaker 04

  The way we think about it is is that, you know, we take a lot of precautions to kind of not capture personal information of people around, both through the speaker identification, through the pipeline and then the prompts and the way we store the information to be kind of really focused on the user. Now, we know that's not going to like satisfy a lot of people, but I think if you do try it and wear it, it's very hard for me to see anything like if somebody was wearing a bee around me that I would ever object that it captured about me as like a third party to it. And like I said, like we're in this transitional period where the expectation will just be more normalized that it's like an AI. It's not capturing, you know, a full audio recording of what you said.

• 32:27Speaker 04

  And it's, it's, everything is fully geared towards helping the person kind of understand their, their state and providing valuable information to them, not about like logging details about people they encounter.

• 32:38Alessio Fanelli?

  You know, I've had the same question also with the Zoom meeting transcribers thing. I think there's kind of like the personal impact that there's a Firefly AI recorder.

• 32:48Speaker 04

  Yeah.

• 32:48Alessio Fanelli?

  I just know that it's being recorded. It's not like I, I don't know if I'm going to say anything different, but like intrinsically you kind of feel, because it's not pervasive. And I'm curious, especially like in your investor meetings, do people feel differently? Like have you have people ask you to like turn it off like in a business meeting to not record? I'm curious if you run into any of these behaviors.

• 33:10Speaker 03

  You know what's funny? On my end, I wear it all the time. I take my coffee blue bottle with it, or I work with it. Like, obviously, I'm working on it, so I wear it all the time. And so far, I don't think anybody asked me to turn it off. Not sure if because they were really friendly with me, that they know they're working on it, but nobody really cared.

• 33:29Speaker 02

  It's because you live in SF.

• 33:31Speaker 03

  Actually, I've been in Italy as well. And Italy is super privacy concerned. Like, Europe is super privacy concerned. And again, there are nothing. Like, it's, I don't know. That, for me, was interesting.

• 33:43Speaker 04

  Yeah, nobody's ever asked me to turn it off, even after giving them full demos and disclosing. I think that some people have said, "Well, in a personal relationship, my partner initially was kind of uncomfortable about it." We heard that from a few users. And that was more in just a personal relationship situation. And the other big one is people are like, "I do like it, but I cannot wear this at work." Because I think I will get in trouble based on policies or if you're wearing it inside a research lab or something where you're working on things that are kind of sensitive.

• 34:25Speaker 04

  So we're adding certain features like geofencing, just like at dislocation, it's just never active. And even like concept fencing, so you can be like, if these topics come up, then no capturing of that.

• 34:40Speaker 02

  I mean, I've often actually explained to it the other way, where maybe you only want it at work. So you never take it from work, and it's just a work device, just like your Zoom meeting recorder is a work device.

• 34:51Speaker 04

  Yeah, professionals have been a big early adopter segment. And you say in San Francisco, but we have out there our daily shipment of like over 100. If you go look at the addresses. Like, Texas, I think, is our biggest state, and Florida, like, just the biggest states. Like, a lot of professionals who talk for... We didn't go out to build it for that use case, but I think there is a lot of demand for kind of white-collar people who talk for a living. And I think we're just starting to talk with them. I think they just want to be able to improve their... Performance around, you know, like, understand what they were doing and.

• 35:28Alessio Fanelli?

  How do you think about Gong that I owe some of these, like, for example, sales training thing where like you put on a sales call and then it coaches you through there are more verticalized versus having kind of like a more horizontal platform.

• 35:39Speaker 04

  Yeah, I I am not super familiar with this space because like I said, we weren't like

• 35:43Alessio Fanelli?

  Right, yeah, yeah.

• 35:44Speaker 04

  It's kind of a surprise to us, but I think that that those are interesting. I've seen there's, there's, there's a bunch of them now, right? Because like it kind of makes sense. I'm terrible at sales, so like I could probably use one, but like it's not my job fundamentally, but. But yeah, I think maybe it's, you know, in a little, we heard also like people with restaurants, like if they're able to understand, like if they're, they're doing well.

• 36:06Speaker 03

  Yeah, but in general, I think a lot of people, they like to have the double check of did I do this well? Or can you suggest me how I can do better? We had a user that was saying to us that used for interviews, job interviews. So use B and after us to be, oh, actually, how do you think my interview went? What I should do better? And I like that. I'm like, oh, that's actually like a personal coach in a way.

• 36:30Alessio Fanelli?

  Yeah, but I guess the question is like, do you want to build all of those use cases? Or do you see B as more like a platform where somebody's going to build like, you know, the sales coach that connects to B so that you're kind of the data feed into it?

• 36:43Speaker 04

  I don't think this is like a data feed, more like an understanding kind of engine and like definitely in the future, having third parties through the API and building out for all the different use cases is something that we we want to do, but the like initial case we're trying to do is like build that layer for all that to work. And, you know, we're not trying to build all those verticals because no startup could do that well. But I think that it's really been quite fascinating to see like, you know, I mean, I've done consumer for a long time. Consumer is very hard to predict, like what's going to be like the thing that's the killer feature. And so, I mean, we really believe that it's the future, but we don't know like what

• 37:26Speaker 04

  exactly like process it will take to really gain mass adoption.

• 37:30Alessio Fanelli?

  The killer consumer feature is whatever Nikita Beer does.

• 37:33Speaker 04

  Yeah.

• 37:34Alessio Fanelli?

  Social afridins.

• 37:35Speaker 04

  Yeah, well, I like Nikita, but you know, he's, he's good at building bootstrap companies and getting them very viral.

• 37:42Alessio Fanelli?

  And then selling them and then they shut down. Okay, so you just came back from CES?

• 37:46Speaker 03

  Yeah, crazy.

• 37:47Alessio Fanelli?

  Yeah, tell us.

• 37:48Speaker 03

  It was my first time in Vegas and first time CES. Both of them were overwhelming.

• 37:54Speaker 02

  First of all, did you feel like you had to do it because you're in consumer hardware?

• 37:58Speaker 03

  And then we decided to be there and to have a lot of partners and media meetings, but we didn't have our own booth. So we decided to skip that. But we decided to be there and have a presence there, even just us and speak with people.

• 38:12Speaker 02

  It's very hard to stand out.

• 38:14Speaker 03

  Yeah, I think, you know, it depends what type of booth you have. I think if you can prepare like a really cool booth.

• 38:20Speaker 04

  Have you been to CES?

• 38:21Speaker 03

  I think it can be pretty cool.

• 38:22Speaker 04

  It's massive. It's like eighty, ninety thousand people across the Venetian and the convention center. And it's, to me, I always wanted to go, just like even.

• 38:33Speaker 03

  Yeah, you were the one.

• 38:35Speaker 02

  I thought it's your idea.

• 38:36Speaker 04

  I always wanted to go just as a, like, just as a fan of.

• 38:40Speaker 03

  Yeah, you wanted to.

• 38:41Speaker 04

  Because like, growing up, I think CES like kind of peaked for a while and it was like, oh, I want to go. That's where all the cool like gadgets, everything is.

• 38:48Speaker 02

  Now it's like smart bitch and like, you know, vacuum the mix up socks.

• 38:51Speaker 03

  Exactly. There are a lot of cool vacuums.

• 38:53Speaker 02

  Oh, they love it. They love the Roomba as the pick of socks.

• 38:55Speaker 03

  And pet tech, so cat and dog stuff.

• 38:59Speaker 04

  Yeah, there's a lot of like robot stuff.

• 39:01Speaker 02

  New TVs, new cars that never ship. Yeah.

• 39:02Speaker 03

  Yeah.

• 39:03Speaker 02

  I think like last year, this time last year was when Rabbit and Humane launched at CES. And Rabbit kind of won CES. And now this year, no wearables, except for you guys.

• 39:11Speaker 04

  It's funny because like it's, it's obviously it's AI everything, like every single product.

• 39:16Speaker 03

  Yeah, toothbrush with AI, vacuums with AI.

• 39:19Speaker 04

  Yeah, yeah, we like hair blow, literally a hair dryer with AI. We saw.

• 39:23Speaker 03

  Yeah, that was cool.

• 39:25Speaker 04

  But I think that like, yeah, we didn't, another kind of difference like around our, like we didn't want to do like a big overhypey promised kind of rabbit launch. Because I mean, they did, hats off to them like on the presentation and everything, obviously. But like, you know, we want to let the product kind of speak for itself and like. Get it out there and I think we were really happy. We got some very good interest from media and some of the partners there. So like it was, I think it was definitely worth going. I would say like if you're in hardware, it's just kind of how you make use of it. Like I think to do like a big rabbit style or to have a huge show on there. Like you need to plan that six months in advance and it's very expensive. But like if you, you know, go there, there's, everybody's there, all the media is there.

• 40:10Speaker 04

  There's a lot of some pre-show events that it's just great to talk to people in the industry. Also, all the manufacturer suppliers are there. So we learned about some really cool stuff that we might like. We met with somebody, they have like thermal energy capture. And it's like, oh, could you maybe not need to charge it? Cause they have like a thermal that can capture your body heat. And yeah, they're here, they're actually here in Palo Alto. They have like a Fitbit thing that you don't have to charge.

• 40:37Speaker 02

  Like on paper, there's a power you can get from that. What's the power draw for this thing?

• 40:41Speaker 04

  And it's more than you could get from the body heat. It turns out, but it's, it's quite small.

• 40:48Speaker 04

  I don't disclose technically, but I think that solar is still, they have, they also have one where it's like this thing could be like the face of it. It's just a solar cell and like that is more realistic.

• 40:59Speaker 02

  Or kinetic.

• 40:59Speaker 04

  The kinetic, apparently they, I'm not an expert in this, but they, they seem to think it wouldn't be enough. Kinetic is quite small, I guess, on the capture.

• 41:07Speaker 02

  Well, I mean, watchmakers have been powering with kinetic for a long time.

• 41:11Speaker 04

  Yeah.

• 41:11Speaker 02

  We don't have to talk about that. I just wanted to get a sense of, see, would you do it again?

• 41:15Speaker 04

  I definitely would.

• 41:16Speaker 02

  Okay, you're just a fantasy, yes. As a business point of view, it doesn't make sense. I happen to be in the conference business, right? So I'm kind of just curious.

• 41:22Speaker 03

  Yeah, so I would say as we did, so without the booth and really like straightforward conversations that were already planned. Three days, that's okay. I think it was okay. But if you need to invest for a booth that is not a good one. And like, I think.

• 41:39Speaker 04

  10 by 10 is 5,000.

• 41:41Speaker 03

  But on top of that, you need to.

• 41:43Speaker 04

  Ten by ten is like super small.

• 41:46Speaker 03

  Yeah.

• 41:46Speaker 04

  And like some companies have, I think would probably be more in like the six-figure range to get. And I mean, I think that, yeah, it's very noisy. We heard this, that it's very, very noisy. Like, obviously, if you're, everything is being launched there and like, everything from cars to cellphones are being launched. So it's hard to stand out. But like, I think going in with a plan of who you want to talk to, I feel like.

• 42:09Speaker 03

  That was worth it.

• 42:10Speaker 04

  Worth it. We had a lot of really positive media coverage from it and we got the word out and like, so I think we accomplished what we wanted to do.

• 42:18Speaker 02

  I mean, there's some world in which my conference is kind of the CES of whatever AI becomes.

• 42:24Speaker 04

  Yeah, I think that.

• 42:25Speaker 03

  Don't do it in Vegas.

• 42:26Speaker 04

  Yeah, don't do it in Vegas.

• 42:29Speaker 03

  That's the only thing. I didn't really like Vegas. Okay, that's great, amazing. Those are my favorite ones.

• 42:34Alessio Fanelli?

  You cannot fit 90,000 people in SF. That's really the.

• 42:38Speaker 04

  You need to do like multiple locations. So you could do Moscone and then have one.

• 42:42Speaker 02

  I mean, that's what Salesforce conferences.

• 42:43Speaker 04

  Well, GDC is how many? That might be 50,000, right?

• 42:47Speaker 02

  Okay, form factor, right? Like, my way to introduce this idea was that I was at the launch in Solaris. What was the old name of it? Newton? Of TAB, when Alvy first launched it. He was like, I've thought through every form factor. Pendant is the thing. And then we, and we got the pendant for this, this original, the first one was just pendant. And I took it off and I forgot to put it back on. So you went through pendant, pin, bracelet now and, you know, and maybe there's AirPods. There's a sort of earphones in the future, but what was your iteration?

• 43:20Speaker 03

  Yeah, so we had, I believe now, three or four iterations. And one of the things that we learned is indeed that people don't like the pendant. In particular, women, you don't want to have like anything here on the chest because maybe you have like other necklace or any other stuff.

• 43:35Speaker 02

  You just ship a premium one that's gold.

• 43:37Speaker 03

  Yeah.

• 43:39Speaker 04

  We're talking, some fashion reached out to us.

• 43:42Speaker 03

  Some big fashion. There is something there.

• 43:44Speaker 02

  This is where it helps to have an Italian on it.

• 43:46Speaker 04

  Exactly.

• 43:47Speaker 03

  There is like some big Italian luxury. I can't say anything, sorry. So, yeah. Bracelet actually came from the community because they were like, oh, I don't want to wear anything like as necklace or as a pendant like is and also like the one that we had, I don't know if you remember, like it was like circle, like it was like this and was like really bulky, like people didn't like it.

• 44:07Speaker 04

  It's so ugly.

• 44:07Speaker 03

  And also, I mean, I actually, I don't dislike, like, we were running fast when we did that, like, our, our thing was like, we wanted to ship them as soon as possible. So we're not overthinking the form factor or the material, we were just want to be out. But after the community organically, basically, all of them were like, why, why you don't just don't do the bracelet, like, it's way better, I will just wear it and that's it. So that's how we ended up with the bracelet, but it's still modular. So I still want to play around the fact that it's modular and you can, you know, take it off and wear it as a clip. Or in the future, maybe we will bring back the pendant, but I like the fact that there is some personalization. And right now, we have two colors, yellow and black.

• 44:52Speaker 03

  Soon we will have other ones. So yeah, we can play a lot around that.

• 44:56Speaker 04

  I think the form factor, like, the goal is for it to be not super invasive, right, and something that's easy. So I think in the future, smaller, thinner, not like Apple type obsession with thinness, but it does matter, like, the, the size and weight. And we would love to have more context because that will help, but to make it work, I think it really needs to have good power consumption, good battery life, and, you know, like with the Humane swapping the batteries, I have one, I mean, I'm, I think Humane is like pretty incredible, some of the engineering they did, but like, it wasn't kind of geared towards solving the problem. It was just, it's too heavy, the swappable batteries is too much to man. The heat. The heat, the thermals, it's like too much to.

• 45:41Speaker 04

  The light interface thing. Yeah, like that. That's cool. It's cool, it's cool, but it's like, if, if you have your hand out here, you want to use your phone, like, it's not really solving a problem, because you know how to use your phone, it's got a brilliant display, you have to kind of learn how to gesture this low resolution laser, but the laser is cool, the fact they got it working in that thing, even though if it did overheat, but like, too heavy, too cumbersome, too complicated with the multiple batteries. So something that's power efficient, kind of thin, both in the physical sense and also in the edge compute kind of way, so that it can be as unobtrusive as possible.

• 46:15Speaker 03

  Yeah. Users really like, like, I like when they say, yes, I like to wear it and forget about it. Because I don't need to charge it every single day. On the other version, I believe we had like thirty-five hours or something, which was okay. But people, they just prefer the seven days battery life and...

• 46:33Speaker 02

  Oh, this is seven days?

• 46:34Speaker 03

  Yeah.

• 46:34Speaker 02

  Oh, I've been charging every three days.

• 46:36Speaker 03

  Oh, no, you can like keep it like, yeah, it's like almost seven days.

• 46:40Speaker 02

  The other thing that occurs to me, maybe there's an Apple Watch strap.

• 46:43Speaker 03

  Ah.

• 46:44Speaker 02

  So that I don't have to double watch.

• 46:46Speaker 03

  Yeah, that's the other one. The, yeah, I thought about it. Um, I, I saw as well the ones that like you can like put it like back on the phone, like, you know, there is a lot.

• 46:57Speaker 02

  So, yeah, there's a competitor called Plug. It's not really a competitor. They only transcribe.

• 47:00Speaker 03

  Yeah, they only transcribe.

• 47:02Speaker 02

  But they're very good at it.

• 47:03Speaker 03

  Yeah.

• 47:03Speaker 04

  No, they're great. Their hardware is really good, too.

• 47:06Speaker 02

  And they just watch the PIN, too.

• 47:07Speaker 04

  Yeah, I think that the MagSafe kind of form factor has a lot of advantages, but some disadvantages. You can definitely put a very huge battery on that, you know, and so like the battery life's not, the power consumption's not so much of a concern, but, you know, downside, the phone's like in your pocket. And so I think that, you know, form factors will continue to evolve, but, and, you know, more sensors, less obtrusive and...

• 47:30Speaker 03

  Yeah, we'll have a new version.

• 47:31Speaker 04

  Easier to use.

• 47:33Speaker 02

  Okay, looking forward to that. Yeah, I mean, well, whenever we launch this, we'll try to show whatever, but I'm sure you're gonna keep iterating.

• 47:39Speaker 03

  Mm-hmm.

• 47:40Speaker 02

  Last thing on hardware, and then we'll, we'll go on to the software side, because I think that's where you guys are also really, really strong. Vision, you wanted to talk about why no vision?

• 47:47Speaker 04

  Yeah, I think it comes down to like when you're, when you're a startup, especially in hardware, you, you're just, you work within the constraints, right? And so like, vision is super useful and super interesting in what we actually started with. There's two issues with vision that make it like not the place we decided to start. One is power consumption. So, you know, you kind of have to trade off your power budget, like capturing even at a low frame rate and transmitting. The radio is actually the thing that takes up the majority of the power. So you would really have to have quite a... Like an unacceptably like large and heavy battery to do it continuously all day.

• 48:28Speaker 04

  We have, I think, novel kind of alternative ways that that might allow us to do that. And we have some prototypes. The other issue is form factor. So like even with like a wide field of view, if you're wearing something on your chest, it's going, you know, you, obviously, the wrist is not really that much of an option. And if you're wearing it on your chest, it's often going to probably be not capturing like the field of view of what's interesting to you. So that leaves you kind of with your head and face. And then anything that goes on on the face has to look cool. Like, I don't know if you remember the spectacles. That was kind of like the first. Yeah. Yeah, but they kind of, they didn't, they were not very successful. And I think one of the reasons is they were, they're so weird looking. Yeah, the camera was so big on the side.

• 49:13Speaker 04

  And if you look at the meta ray bands where they're way more successful, they, they look almost indistinguishable from a ray band. And they invested a lot into that. And they, they have a partnership with Qualcomm to develop custom silicon. They have a stake in Luxottica now. So like they, coming from all the angles, like to make glasses, I think, like, you know, I don't know if you know Brilliant Labs, they're a cool company. They make frames, which is kind of like a cool hackable glasses. And, and like, they're really good, like on hardware, they're really good. But even if you look at the frames, which I would say is like the most advanced kind of startup, I mean, there was one that launched at CES, but it's not shipping yet. Like one that you can buy now. It's still not something you'd wear every day, and the battery life is super short.

• 49:57Speaker 04

  So I think just the challenge of doing vision right, like off the bat, like would require quite a bit more resources. And so like, audio is such a good entry point. And it's also the privacy around audio. If you, if you had images, that's like another huge challenge to overcome.

• 50:17Speaker 04

  So I think that ideally the person AI would have, you know, all the senses and you know, we'll get there.

• 50:23Speaker 02

  Okay, one last hardware thing I have to ask this because then we move to the software. Were either of you electrical engineering?

• 50:29Speaker 04

  No, I'm CS and so I have a, I've taken some EE courses, but I, I had done prior to working on, on the hardware here. Like I had done a little bit of like embedded systems, like very little firmware, but we have luckily on the team, somebody with deep experience.

• 50:46Speaker 02

  Yeah, I'm just like, you know, like you have to become hardware people.

• 50:49Speaker 04

  Yeah, yeah, I mean, I learned.

• 50:50Speaker 02

  You worry about supply chain, power, radio.

• 50:54Speaker 03

  There are so many things to learn.

• 50:56Speaker 04

  I would tell this about hardware, like, and I know it's been said before, but.

• 50:59Speaker 02

  Hardware is hard.

• 51:00Speaker 04

  Building a prototype and like learning how the electronics work and learning about firmware and developing, this is like, I think, fun for a lot of engineers and it's, it's all totally like achievable, especially now, like with, with the tools we have, like stuff you might've been intimidated about, like how do I like write this firmware now? With Sonnet, like you can, you can get going and actually see results quickly. But I think going from prototype to actually making something manufactured is a enormous jump. And it's not all about technology, the supply chain, the procurement, the regulations, the cost, the tooling. The thing about software that I'm used to is it's funny that you can make changes all along the way and ship it.

• 51:43Speaker 04

  But like when you have to buy tooling for an enclosure that's expensive.

• 51:48Speaker 02

  You buy your own tooling?

• 51:49Speaker 04

  You have to.

• 51:49Speaker 02

  Don't you just subcontract out to someone in China?

• 51:52Speaker 04

  Do we make the tooling? No, no, you have to have CNC and like a bunch of machines, like nobody makes their own tooling. But like you have to design, this design and you submit it and then they go four to six weeks later.

• 52:02Speaker 02

  Yeah.

• 52:03Speaker 04

  And then if there's a problem with it, well, then you're not, you're not making any, any of your enclosures.

• 52:09Speaker 02

  What?

• 52:09Speaker 04

  And so you have to really plan ahead and like.

• 52:12Speaker 02

  I just want to leave tips for other hardware founders, like what resources or websites are most helpful in your sort of manufacturing journey?

• 52:19Speaker 04

  You know, I think it's different. Depending on like the it's hardware so specialized in different ways.

• 52:24Speaker 03

  I will say that, for example, I should choose a manufacturer company, speak with other founders.

• 52:32Speaker 03

  Like, we can give you like some, you know, some tips of who is good and who is not, or like who specializes in something versus somebody else.

• 52:39Speaker 04

  Some people are good in plastics, some people are good on PCB.

• 52:43Speaker 03

  I think like for us, it really helped at the beginning to speak with others and understand, okay, like who is around. I worked in Shenzhen, I lived almost three years in China. I have an idea about like different hardware manufacturer and all of that. Soon I will go back to Shenzhen to check out. So I think it's good also to go in place and check and choose the right people.

• 53:05Speaker 04

  If you so we did some stuff domestically and like if you have that ability. The reason I say ability is very expensive, but like to build out some proof of concepts and do field testing. Before you take it to a manufacturer, despite what people say, there's really good domestic manufacturing for small quantities at extremely high prices. So we got our first PCB in the assembly done in LA. So there's a lot of good because of the defense industry that can do quick churn. So it's like, we need this board, we need to find out if it's working, we have this deadline, we want to start. But you need to to go through this and like if you want to have it done and fabricated in a week, they can do it for a price. But I think, you know, everybody's kind of trending, even for prototyping now, moving that offshore.

• 53:49Speaker 04

  Because in China, you can do prototyping and get it within almost the same timeline. But the the thing is with manufacturing, like it really helps to go there and kind of establish the relationship.

• 54:01Alessio Fanelli?

  Yeah, my first company was a hardware company and we did our PCBs in China and took a long time. Now things are better, but this was, yeah, I don't know, 10 years ago, something like that.

• 54:10Speaker 04

  Yeah, I think that like the and I've heard this too, we didn't run into this problem, but like, you know, if it's something where you don't have the relationship, they don't see you, they don't know you. You know, you might get subcontracted out or like they're not they're not paying attention. But like if you're, you know, you have the relationship in a priority, like, yeah, it's really good. We ended up doing the fabrication assembly in Taiwan for various reasons, but.

• 54:34Speaker 03

  And I think it really had the value there at some point.

• 54:37Speaker 04

  We're really happy with the process and. But I mean, the whole process of just Choosing the right people. Choosing the right people, but also just sourcing the bill materials and all of that stuff. Like, I guess like, if you have time, it's not that bad. But if you're trying to like, really push the speed at that, it's incredibly stressful.

• 54:57Speaker 02

  Okay, we gotta move to the software.

• 54:58Alessio Fanelli?

  Yeah, yeah, yeah. So the hardware, maybe it's hard for people to understand. But what software people can understand is that running transcription and summarization, all of these things in real time, every day, for 24 hours a day, is not easy. So you mentioned 200,000 tokens for a day.

• 55:14Speaker 04

  Yeah.

• 55:15Alessio Fanelli?

  How do you make it basically free to run all of this for the consumer?

• 55:20Speaker 04

  Well, I think that the pipeline and the inference, like, people think about all these tokens. But as you know, the price of tokens is like dramatically dropping. You guys probably have some chart somewhere that you've posted.

• 55:34Alessio Fanelli?

  We did.

• 55:34Speaker 04

  And like, if you see that trend, and like 250,000 input tokens is not really that much, right? Like

• 55:41Alessio Fanelli?

  You do several layers, you do live.

• 55:44Speaker 04

  Yeah, yeah. So the speech to text is like the most challenging part, actually, because, you know, it requires like real time processing and then like later processing with a larger model. And one thing that is fairly obvious is that like you don't need to transcribe things that don't have any voice in it. Right? So good voice activity is key, right? Because like, the majority of most people's day is not spent with voice activity, right? So that is the first step to cutting down the amount of compute you have to do. And voice activity is a fairly cheap thing to do, very, very cheap thing to do. The models that need to summarize, you don't need a sonnet level kind of model to summarize.

• 56:27Speaker 04

  You do need a sonnet level model to like execute things like the agent. And we will be having a subscription for like features like that. Because it's, you know, although now with the R1, like, we'll see, we haven't evaluated it.

• 56:42Alessio Fanelli?

  A deep sea?

• 56:43Speaker 04

  Yeah. I mean, or not that one in particular, but like, you know, they're already there that can kind of perform at that level. I was like, I was gonna say in six months, but like, yeah, so self-hosted. Models help in the things where you can.

• 56:57Speaker 02

  So you are self-hosting models?

• 56:59Speaker 04

  Yes.

• 56:59Speaker 02

  You are fine-tuning your own ASR?

• 57:02Speaker 04

  Yes, I will say that I see in the future that everything's trending down, although like I think there might be an intermediary step with things to become expensive, which is like we're really interested because like the pipeline is very tedious and like a lot of tuning, right? Which is brutal because it's just a lot of trial and error. Whereas like, well, wouldn't it be nice if an end-to-end model could just do all of this and learn it? If we could do transcription with like an LLM, there's so many advantages to that. But it's going to be a larger model and hence like more compute. You know, we're optimistic, maybe we could distill something down and like we kind

• 57:43Speaker 04

  of more than focus on reducing the cost of the existing pipeline or trying to the next generation, because it's very clear that like all ASR, all speech to text is going to be pretty obsolete pretty soon. So like investing into that is probably kind of a dead end because it's just going to be obsolete.

• 57:59Speaker 02

  It's interesting, like I think when I initially invested in TAB, this is, this shows you how wrong I was. I was like, oh, this is a sort of razor blades, razors and blades model where you sell a cheap hardware and you make up a subscription, like a monthly subscription. And now I just checked, Friend is a one-time sale $99. Limitless, one-time sale $99. These guys, one-time sale $49. And inference is free? What?

• 58:26Speaker 04

  Well, would you, I think when you probably invested, like how much was a million input tokens at that time and what is it now?

• 58:34Speaker 02

  It's a fascinating business and like, you know, there's a lot to dig into there. But just getting that perspective out there is, I think it's not something that people think about a lot and you obviously have thought a lot about.

• 58:44Alessio Fanelli?

  What about memory? I think this is something we go back and forth on about memory as in you're just memorizing facts and then understanding implicit preference and adjusting facts that you think about a person. Any learnings from that? I know there's a lot of open source frameworks now to do it. Did you build all of your own infrastructure internally?

• 59:04Speaker 04

  Yeah, we did. I mean, I evaluated, used a lot in other projects. I think that there's a few different tasks or things that revolve around memory. Like, one is like retrieval, obviously, and like when you need to find, like even if you have a large corpus of, ah, do you find? And so like, I think existing kind of RAG pipelines also will probably be obsoleted. The frameworks, I have not found one, like, there's no general way to do RAG that works. Like, it's really highly dependent on the data. So like, if you're gonna be customizing something that much, it's just, you get kind of more bang from the buck from designing it all yourself. You know, a lot of those frameworks are great for getting going quickly.

• 59:47Speaker 04

  But I think it's really interesting, memory, when you're trying to do for a person, because memories decay, right? Like, I'm going to London, you know, then I come back, I'm not going to London anymore. What we've learned is like, doing the traditional like embedding in RAG is suboptimal. We kind of built our own, using small models, to do really massively parallel retrieval, which I think is gonna be maybe more common in the future. And then, like, how to represent a person? We still require some human loop, and I mean, this is an ongoing project. And, you know, we're learning every day. Like, how do you correct the model when it gets something wrong about you? Right now, we have like things that are like super confirmed,

• 1:00:32Speaker 04

  that are like ground truth about you because the human accepted it. But ideally, like, that step wouldn't be necessary. And then we have things that are fuzzier. And like, the more stuff that we know is true, the more accurate we are when we're trying to decide, is this fuzzy stuff? Because it's probably like, if you have the context, it's probably not true. So I think it's one of the most core challenges, is how to handle both retrieval and then modeling. And like, especially when you're dealing with noisy source data. Because like, even if, in an ideal world, even if you just had perfect transcription, and you're going off that, that's still not enough information, right? And even if you had visual, it's still not enough. Like, there's still gonna be some misunderstandings.

• 1:01:13Speaker 04

  And so how to not let that damage the value of it, and be like recoverable and correctable?

• 1:01:21Alessio Fanelli?

  Yeah, one way I think about is, I usually like to order the same thing from the same restaurant, if I like it. But I'm not saying that out loud. And it's kind of like, are these type of behaviors? Like when you ask about a favorite restaurant, I would just want it to give me restaurants that I've already been to that I like. Or like if I'm like, hey, just order something from this place, it should just reorder the same thing because it knows that I like to redo the same thing. But I feel like today, most agent memory things that I see people publish is like, you know, just write down the data.

• 1:01:55Speaker 03

  Yeah.

• 1:01:56Speaker 04

  Yeah, I mean, I think that's why the reasoning, like in in our case, like giving it time to consider all of the sources it has. So like, look at the emails, see like the receipts, and then look at the conversations to see like what I've mentioned. And then be able to then take enough time to search through all the context and connect the dots is, I think, really important. And like, I don't know, like some of the agent memory stuff, it's like the key value with rag on top like, and the results there are just not complete enough when you have like growing corpus and like managing decay and hallucinations that might be in the source material.

• 1:02:37Alessio Fanelli?

  So this is where people usually bring in knowledge graphs?

• 1:02:40Speaker 04

  Yes.

• 1:02:42Alessio Fanelli?

  And do you do it?

• 1:02:43Speaker 04

  We don't extensively use knowledge graphs. It's something, you know, we didn't talk also about the kind of potential future social aspects.

• 1:02:50Speaker 03

  Yeah, I wanted to speak about it.

• 1:02:53Speaker 04

  But the problem with knowledge graphs that we found is like, and I don't know if you can tell me what what your experience has been, but they're great for representing the data, but then like using it at inference time is kind of challenging like.

• 1:03:06Alessio Fanelli?

  For speed or what are the issues?

• 1:03:08Speaker 04

  Just like the LLM understanding, like the the graph.

• 1:03:12Alessio Fanelli?

  Yeah.

• 1:03:13Speaker 04

  The input.

• 1:03:13Alessio Fanelli?

  Yeah, it's not in the training data for sure.

• 1:03:15Speaker 04

  I think that the graph is the right kind of way to store the data, but like then you need to have the right retrieval and then just kind of formatting in a way that like doesn't just overwhelm or confuse what you're trying to do.

• 1:03:28Speaker 02

  Should we ask about social?

• 1:03:30Speaker 04

  Yeah, I thought you were gonna go into it. Like, not directly related.

• 1:03:35Speaker 03

  We did some experimentation.

• 1:03:36Speaker 04

  Not directly related to like

• 1:03:37Speaker 03

  Interesting.

• 1:03:38Speaker 04

  graph retrieval or graph knowledge traces. But like, the idea that having like your personal context, but then like other people can query it. You know, it can divulge some things that you would have full control over. Then Maria and I are trying to negotiate like where we're going to dinner like.

• 1:03:55Speaker 03

  We exactly did this experiment.

• 1:03:57Speaker 04

  Yeah, there can be an exchange between the agents and.

• 1:04:01Speaker 03

  So how like my agent can speak with Ethan's agent. Both of them, they know our location, what we like, where we went in the past.

• 1:04:10Speaker 02

  Yeah.

• 1:04:10Speaker 03

  And even, you know, if we have our calendar integrated, they know when we're free. So they can interact with each other and have a conversation and decide a place to go for us.

• 1:04:20Speaker 02

  Wow.

• 1:04:20Speaker 03

  And we did that. And it was for me really cool because they suggested to us a nice French restaurant that we went to then.

• 1:04:27Speaker 02

  That you've never been to?

• 1:04:28Speaker 03

  That we've never been to.

• 1:04:30Speaker 02

  Okay.

• 1:04:30Speaker 03

  But both of us, they saw that we like French food. Both of us, we were in Pacific Heights. And yeah, this was really trivial.

• 1:04:39Speaker 04

  Yeah, it's a trivial like toy use case. But I guess like in terms of you've been using it for a while. Like if I wanted to buy you a gift.

• 1:04:47Speaker 03

  Oh, my God, you bought me a bunch of candles. That's not that I think about.

• 1:04:51Speaker 04

  This is another use case. I was like, when we were testing the agent, like a bunch of candles from Amazon showed up at her door.

• 1:05:00Speaker 03

  Yeah, because I really, I love candles, but I didn't expect 20.

• 1:05:04Speaker 04

  There's a lot of experience. But like, how to manage that where it's like, what's okay for your B to divulge to who?

• 1:05:11Speaker 02

  Yeah.

• 1:05:11Speaker 04

  Like, should you get an authorization request every time?

• 1:05:14Speaker 02

  For personal context.

• 1:05:16Speaker 04

  Yeah, yeah, yeah. So like, you know, you would have to, human would have to sign off on it. But I think then like, then I wouldn't have to guess. I could just.

• 1:05:26Speaker 02

  Yeah, you know, there's this culture that like is very alien to everyone else outside of SF and outside the Gen Z bubble in SF, which is sharing, location sharing.

• 1:05:34Speaker 04

  Yeah.

• 1:05:35Speaker 02

  I can tell my close friends where they are exactly right now in the city. And it's often, and like, you know, and like, it's normal. And like, it freaks out everyone who's not here.

• 1:05:44Speaker 04

  Yeah, yeah.

• 1:05:46Speaker 02

  And so maybe we can share preference, like who we'd like.

• 1:05:49Speaker 03

  Absolutely. I really believe in it for sure. We will.

• 1:05:52Speaker 04

  Or even like. Small updates about your day.

• 1:05:57Speaker 02

  My parents would love that because I don't do that.

• 1:06:00Speaker 04

  Now, now there's no friction. It can just be more or less automatic.

• 1:06:03Speaker 02

  Yeah, yeah, yeah. Dating?

• 1:06:05Speaker 04

  I was trained always to avoid dating.

• 1:06:07Speaker 02

  Really?

• 1:06:07Speaker 04

  As a startup founder.

• 1:06:09Speaker 02

  Everyone hates it?

• 1:06:10Speaker 03

  We thought about it. Like, sometimes some people, they ask you us because it's like, oh, you know so much about me. Like, can you measure compatibility with somebody else or something like that? Yeah, probably there is a future and maybe somebody should build that. I think on our end, we were like, no, this is.

• 1:06:26Speaker 02

  I will build on your API.

• 1:06:28Speaker 04

  My sister's actually a personality psychology professor and she studies personality. And we were at Thanksgiving because my parents wear one and I was like, ask it, like, give me my big five, which is like the personality type. And it's like.

• 1:06:41Speaker 02

  Does it know my big five?

• 1:06:43Speaker 04

  Just ask it to consider everything and give your big five. And my sister said it was pretty, I didn't agree with it because it said I was disagreeable.

• 1:06:51Speaker 03

  I agree with that.

• 1:06:52Speaker 04

  She said it was disagreeable.

• 1:06:55Speaker 02

  You disagree that you're disagreeable?

• 1:06:57Speaker 04

  Yeah, yeah.

• 1:06:58Speaker 02

  What other proof do you need then?

• 1:07:02Speaker 04

  I think I'm very agreeable.

• 1:07:06Speaker 04

  But I think that we did get some users are like, oh, if like we're a couple.

• 1:07:10Speaker 03

  Yeah, we had like couples, actually. They bought the product together, like both, like coupled, they bought the hardware. So there is something there. Another test is like the Myers-Briggs. I know that you don't like that one.

• 1:07:21Speaker 02

  No, no, Ocean is cooler than Myers-Briggs. Everyone stop using my MBTI. Use my, use Ocean.

• 1:07:26Speaker 03

  Yeah, yeah. For me, like it was on point, like every time, like it.

• 1:07:30Speaker 02

  Awesome.

• 1:07:30Alessio Fanelli?

  Anything else that we didn't cover? Any cool underrated things?

• 1:07:36Speaker 03

  Go to be.computer, $49.99 and you buy the device. That's the.

• 1:07:41Speaker 02

  That's the call to action. And you're hiring?

• 1:07:43Speaker 03

  We are hiring for sure.

• 1:07:45Speaker 04

  AI engineers.

• 1:07:46Speaker 03

  AI engineers.

• 1:07:47Speaker 04

  Nice.

• 1:07:47Speaker 02

  What is an AI engineer?

• 1:07:48Speaker 04

  Yeah. But you, did you study? Somebody who's scrappy and willing to.

• 1:07:56Speaker 03

  Work with us.

• 1:07:56Speaker 04

  Yeah, I think. I think you coined the term, right? So you can tell us.

• 1:08:01Speaker 03

  Somebody that can adapt.

• 1:08:03Speaker 02

  It's really like.

• 1:08:04Speaker 03

  Has resistance.

• 1:08:05Speaker 02

  People have different perspectives and what is useful for you is different from what is useful for me. So anyway, it's so useful.

• 1:08:11Speaker 04

  I think that always on AI is really gonna explode. And it's gonna be a lot from both a lot of startups, but incumbents. And there's gonna be all kinds of new things that we're gonna learn about how it's gonna change all of our lives. I think that's the thing I'm most certain about, so.

• 1:08:28Speaker 02

  And being AI, well, thanks very much.

• 1:08:30Speaker 04

  Thank you guys.

• 1:08:31Speaker 02

  This is a pleasure.

• 1:08:32Speaker 03

  Thank you.

• 1:08:32Speaker 02

  Yeah, we'll see you launch whenever that launch is happening.

• 1:08:35Speaker 03

  Yeah, thanks.

• 1:08:37Speaker 02

  Thank you.