Pod Insights Practical AI AI search at You.com About this episode Neural search and chat-based search are all the rage right now. However, You.com has been innovating in these topics long before ChatGPT. In this episode, Bryan McCann from You.com shares insights related to our mental model of Large Language Model (LLM) interactions and practical tips related to integrating LLMs into production systems.
Sponsors:
Fastly https://fastly.com/ – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com https://www.fastly.com/?utm_source=changelog&utm_medium=podcast&utm_campaign=changelog-sponsorshipFly.io https://fly.io/changelog – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog https://fly.io/changelog and check out the speedrun in their docs https://fly.io/docs/speedrun/. Featuring:
Bryan McCann – GitHub https://github.com/bmccann, LinkedIn https://www.linkedin.com/in/bmarcusmccann, X https://x.com/BMarcusMcCannChris Benson – Website https://chrisbenson.com, GitHub https://github.com/chrisbenson, LinkedIn https://www.linkedin.com/in/chrisbenson, X https://x.com/chrisbensonDaniel Whitenack – Website https://www.datadan.io/, GitHub https://github.com/dwhitena, X https://x.com/dwhitenaShow Notes:
You.com https://you.comOpen Platform for developers https://you.com/developersJoin the You.com Discord server https://discord.gg/gbH6XaQdBQUpcoming Events:
Register for upcoming webinars here https://practicalai.fm/webinars!
Transcript Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.
0:07 Speaker 00 Welcome to Practical AI. If you work in artificial intelligence, aspire to, or are curious how AI-related technologies are changing the world, this is the show for you. Thank you to our partners at Fastly for shipping all of our pods super fast to wherever you listen. Check them out at fastly.com. And to our friends at Fly, deploy your app servers and database close to your users. No ops required. Learn more at fly.io.
0:43 Daniel Whitenack? Welcome to another episode of Practical AI. This is Daniel Whitenack. I'm a data scientist with S I L International, and I'm joined as always by my co-host, Chris Benson, who is a tech strategist at Lockheed Martin. How are you doing, Chris?
0:58 Chris Benson? Doing well, Daniel. What are we in search of today? What's the topic coming up?
1:03 Daniel Whitenack? That's a good one. Well, I mean, we've, we've been talking about Chat G P T and, people using it for search and other things, but we've got the real, the real powerhouse with us today, Brian McCann, who's co-founder and C T O at you.com, which is an AI search engine. How are you doing, Brian?
1:24 Speaker 03 I'm fantastic. I'm so excited to be here.
1:27 Daniel Whitenack? Yeah.
1:27 Speaker 03 Just got finished watching an old episode last night with Dimitri and laughed about all the M L O P stuff I've learned myself at you.com over the last couple of years.
1:37 Daniel Whitenack? Yeah, there's no shortage of cringe moments in the M L Ops journey, but yeah, that was, that was a good one for sure. Maybe just taking like an initial step back at like AI, you.com, AI search engine. How did you come upon like this idea that like there needed to be? A new type of search engine and in particular like one that involves some type of AI within it. How did this idea come to shape and like what is you.com? Maybe we can start there.
2:12 Speaker 03 Great. Yeah, I can tell you all about it. Depends on how far back you really want to go, but you know, I'll start back when my co-founder and I were at Salesforce doing research in natural language processing. My co-founder and our CEO, Richard Socher, was the chief scientist there. And we worked for quite a few years on exactly the kind of technologies that are getting kind of more met adoption today, like these large language models. When I started out, it was a challenge to get them to do anything. And oftentimes, people would question why anybody worked on language models. It was starting to almost become hard to get any publications about
2:54 Speaker 03 them because they were supposed to be just a theoretical exercise of some kind. But then over the course of several years in our research and first transfer learning and contextualized word vectors, and then pushing multitask learning and unified approaches to natural language processing, we saw what was happening. And eventually we ran some pretty fun experiments, even with authors and writers around collaborations with generative AI like GPT tools today. And the first moment was that it was just kind of fun and inspiring. You know, it was starting to work. And seeing that, I think both of us started thinking about what was really gonna happen
3:37 Speaker 03 in the next few years. And there's two ways you go. All this NLP stuff becomes as good as it is today, and it just goes into making Facebook ads better, or something like that, or Instagram ads. And all that understanding that we work on doesn't really go into something that I was super stoked about at the time. You know, I came from a philosophy background, got into all the natural language stuff because I was interested in meaning and understanding what meaning was, which took me into the analytic philosophy direction and focusing on language. So for all of that to then just channel into like, Selling my little sisters something better on Instagram was not really what I was hoping for.
4:19 Speaker 03 That was the first thing there. And then the second was, I think, after we had both seen much of the research community adopt this direction, which was really not popular when I was just starting out. You know, this was controversial. It was even against software engineering principles. Engineers at various research groups and companies would would actually decry some of what we were advocating for because, well, how can you disentangle and understand where problems are in the model if you're training on all this data? It was not exactly neat and tidy from a software engineering principle perspective. But after four or five years, everybody was doing it.
4:59 Speaker 03 And so we felt like it was time to start looking at an area where maybe people felt similarly about the likelihood of it changing much. And search was one of those areas where it was very much like the original time in LP where like, oh, you know, we should do it this way. And there was a lot of people saying, no, that sounds like a bad idea. And they come around to it eventually. Now with search, I can tell you over the last couple of years, yeah, lots of people asked me like, why the heck would you start a search engine? But we saw a lot of these technological advances coming, you know, and we saw that there was this inflection point coming.
5:37 Speaker 03 We wanted to be on the other side of research and kind of directing and channeling that into a better way to do it. And search was really the gateway to the internet for that. It's for so many people, the place they go that they then find the rest of the internet. They find information and it becomes like a key point for people where this technology in understanding them can then help them in different ways. So with you.com, we wanted to really found the company on three values of like trust, facts and kindness. And leverage this technology to make search more about serving you and using understanding rather than, you know, just monetizing your attention more or less.
6:20 Daniel Whitenack? And from your perspective, I mean, people probably think that at least algorithms like have played a role like maybe generally people think like, oh, there's sophisticated algorithms behind search. Now people are talking about like AI-driven search, neural search, semantic search. Could you help us kind of like parse out like what's fundamentally different about like the things people are talking about now when they're referring to that sort of like AI and neural search? As opposed to like what might have been going on like all along with what isn't like dumb algorithms, but like they're not in the same sort of class as this other type.
7:05 Speaker 03 Yeah, for sure. I mean, I think, you know, five years ago before generative AI was really on the radar. Now we still thought there was AI involved in search. It just wasn't the kind that we're seeing today. So AI has been trying to understand this for a long time. What's happening now is the algorithms or the kind of AI we're using, the neural networks we're using are much better at understanding the context of what we're trying to say. I think this is one of the key underlying features of what we're seeing. So when you type to it or you're talking to it, one of the data threads has been understanding context. We started out with training word vectors in NLP.
7:48 Speaker 03 So if people are familiar with word vectors, every single word or token has a vector that's associated with it. And that was pretty much all the context we had. And we started looking at sentences as a whole to take into consideration context. And now these things are reading, you know, as much of the internet as they can get their hands on. Testing data sets, supervised training data on top of all the unsupervised training data. And with that comes this more nuanced understanding. Every parameter that we're adding as these models are getting bigger. They're recording some subtlety of how we use language, right? Just mimicking our behavior and picking up on those patterns. So the first is understanding context. And then the second is the generative aspect of it.
8:34 Speaker 03 So there's taking in a piece of text from you and understanding what that means, but then it's producing text. And I think that's been the part that's really, really exciting for people. Both have been really important for us at you.com and building a search engine differently. But now with you chat, for example, these generated responses are really opening up a different way of serving users that's totally in line with what we were planning for you.com as well. Because we really wanted to move search from being just about finding blue links to ideally replacing every blue link in as many cases as possible with the thing you'd actually want to do. Or the information you'd actually need.
9:18 Speaker 03 And these generative models have essentially memorized a lot of the information on the other side of those links. So it makes it a lot easier for you to act and they can spit it back out at you.
9:27 Chris Benson? No, I was just gonna say, as kind of a follow up to that, I'm kind of talking about the world before and the world after. I mean, obviously, kind of the, the big news thing that's changed the public's perception lately was chat GPT. And the public kind of becoming aware of that. And you guys have been out there leading the way all along, you know, for years at this point. How does that public perception change? How has that changed you.com and you chat and things like what? What, aside from the, just the technology considerations? How has that changed the way you guys are approaching, you know, your business in the marketplace? Would that public perception change at large? It's a different world from six months ago.
10:10 Speaker 03 Oh, it's fantastic. It is, it absolutely is. I think so many of the things that we had started to build into you.com. You know, we had some generator writing tools. We had image generation tools. We call them apps inside you.com as they have a platform for developers to build these apps into it. And what we saw happen was the door kind of opened. To do some of these newer things with more acceptance from a much wider portion of the population. I think like a lot of people had expectations about what search was and what search should do for them. And even though we were at the forefront of that, releasing
10:51 Speaker 03 these things, that kind of moment last fall, really, when it started going viral, is when everybody kind of dropped those expectations and said, hey, what is this new technology that could be doing something like search for us in a very different way? And so with that, you know, UChat has been super popular and it's becoming more and more popular as part of u.com. Right now, we have more default, normal search experience, but then you can also use the conversational approach. And that's really picking up a ton of traction. And it's clear, there's a lot of use cases that it just serves users better for.
11:27 Daniel Whitenack? So while you all were talking, I was asking you, chat, how can AI be integrated into search? And at least you're consistent with UChat. The answer is AI can be integrated into search in a variety of ways. For example, AI can be used to provide more accurate search results by understanding user intent and the context of their search query. So there you go.
11:51 Speaker 03 There you go.
11:53 Daniel Whitenack? I mean, I just mentioned I have, you know, I have UChat on my phone. I've been playing with it. And really, I don't even know if I would consider playing it, but using it. And I think one of the things like people are realizing, yeah, it's fun to like generate like a new like Eminem rap song about like AI or something in ChatGPT. But people are starting to think about these like interfaces as like tools that can, like you said, give them the content that they're really after without them having to follow a bunch of links. Now, like the search industry in general, I think has been like, there's
12:32 Daniel Whitenack? money to be made by pointing people to links, right? And ads, like promoting links. From your perspective, like, how does this shift in people thinking now about like a chat interface, which isn't driven by these links, influence maybe like the industry at large? And maybe some responses that we'll see across the industry? Because like, that's kind of the bread and butter of how everything works in search, right?
13:00 Speaker 03 Absolutely. Yeah. It's a big question right now, and I think it's one that's exciting to see evolve over the next however long. But from our perspective, what we've been trying to set up with you.com from pretty much the start, that we released it publicly last fall as well, is this more open platform approach to search, where partners, content creators, developers, whoever it is that owns what's on the other side of the link, has an active role and a clear way to monetize and benefit from anything that these language models are generating.
13:42 Speaker 03 So, for example, you know, a partner can come into you.com and create an app in a couple hours. If they've got an API or they can just give us the data and we'll create a search API for them, support the infrastructure. And then we'll show an app that either allows people to interact with their product, kind of like a try before you buy way, or the information from their site, but they own that space. So it's not like more traditional search engines where, you know, any monetization that happens on their website is their monetization and traffic has to get to that other place for those people to monetize. At you.com, the app itself is considered theirs.
14:25 Speaker 03 And any monetization that happens is theirs at that point. So it's kind of flipping the script in a way. Like you said, that's the biggest shift that we can see happen. And we can also see a lot more people moving towards paying for some of these tools as productivity tools and kind of tools that empower them more, rather than just a tool that connects them to different things, which they're very used to having free. I imagine what's going to come out of it will be some combination of the two, but there will be more and more of a shift towards providers being closely linked to that content, even if the content is less clearly attributable through a language model.
15:08 Speaker 03 But it's something that's, it's going to be interesting to see how all the different industries adapt or try not to adapt and, you know, try to keep things the way they are.
15:18 Chris Benson? So you were talking a little bit about the idea of using it for tooling and some of the things and that got me as you were kind of describing that before the break, it got me wondering, can you talk about some examples of of how you chat and the technologies underlying that and the algorithms might be used to enhance tooling? What are some of the things that you're thinking about, you know, when you're laying awake at night, thinking about what's next? Where do I want to go with this?
15:46 Speaker 03 Yeah, great, great question. Back in the summer before that, we'd been working mostly on what we called you code. And we were starting to bring in a lot more developer resources and generative AI specifically for generating code on behalf of developers. And now with these more conversational interfaces as well, you see people going to them a lot for writing code, even debugging code, debugging code that the AI apps or that the AI generates for them already. See a lot of people going and, you know, just saying, this is what I have in my fridge. Like, what can I make with this? And in much broader sets of questions,
16:26 Speaker 03 but then the conversational interface allows you to gather some context on over the course of conversation in a much more seamless way until you can get a satisfying answer or response. But yeah, lots of marketing, lots of students as well. We had an application called you write that's still inside you.com. And that's been really popular with students, for example, because it can come up in the chat. Sometimes like you can ask it to do some things, but getting the language model nudging in the right direction is still something that's challenging for people who don't quite understand how to do it. And so these productivity
17:05 Speaker 03 tools usually involve a little bit more of a touch from our side to make it like really useful for a particular niche.
17:15 Chris Benson? I just want to note that going to the refrigerator and saying this is what I have is going to be really, really useful for me.
17:22 Speaker 03 Yeah. For me, it's like, nothing in there. What do you do?
17:26 Daniel Whitenack? Yeah, I was gonna say like, it's pretty sparse in my fridge right now. So I don't know that there's a good answer to that regardless. Like, go to the grocery store.
17:34 Chris Benson? My wife makes fun of me. She's like, put something together. And I'm like, what? So this is gonna be, that's a good use case, actually.
17:40 Daniel Whitenack? Yeah. So you were talking about like this kind of like idea of like a thread of conversation, which people like learn about some topic or like the the thread provides context for a response or answer. But I'm also intrigued, like, some of the unique things about UChat in particular, and u.com like sort of more generally is like a little bit more holistic view of like multiple modes or multimodal like approaches to where um hey, like, I'm not always just getting a text blob, right? Sometimes I want a text blob and sometimes like I actually don't like if I'm asking about the weather, maybe I want like a little graph of like,
18:25 Daniel Whitenack? you know, a little card telling me about the weather. So could you explain a little bit, maybe how you all are thinking about multimodality? In terms of like these sorts of natural language interfaces, maybe both in terms of like the outputs, but potentially also in terms of the inputs. And like how you're thinking about merging those technologies and those inputs together?
18:50 Speaker 03 Yeah. Great question. It is the future, you know, it's so much, I think of what we're learning from language. Some of it's starting to make its way into image generation, right? With many tools that have come out. But all these other modalities as well. In u.com in particular, UChat has access to the kind of more traditional search engine underneath it. So it actually uses that more or less, a little metaphorical, but it knows how to understand your intent and it can go out and ask what kind of information it needs from different sources. And it can also interact with all of these apps that we've created in the open platform. So if you are looking for weather, it can go and say, oh, give me the chart for the weather. And over time, it's a little bit of a contrived example, but I would want it to
19:35 Speaker 03 look at that data and be able to answer any question you want about that data. You know, maybe run its own Python code, you know, doing statistics over that data. If you really wanted that, you know, it should be able to do all of these things. Same goes for finance, you know, if you ask about a particular stock. Uchat is not going to necessarily tell you in text about all the things that you would want to know. You know, the, the volume and high and all those things. It's going to show you a nice, nice application there. And then over time, we're enabling Uchat to use that data more and more, ground its responses in that data in the same way that it's currently grounding and citing search results right now to try to lessen the effect of hallucination,
20:19 Speaker 03 which has been like a really kind of widely known problem with some of these generative models, especially in the research days. That was one of the most frustrating aspects of these models, you know, and they're getting better. And they're especially better when you ground them in other kinds of data, like our open platform apps or the search engine results themselves. So we're going to use that to make it better and better. And I mentioned, you know, writing Python code for itself. You know, we want it to be able to pretty much do anything that you'd want to do on the internet. Like that's where this kind of technology can go, kind of utilizing the promise of some of those early kind of persistent like things, right?
21:00 Speaker 03 Like Siri and Cortana, you, you don't want to just say, oh, tell me about this thing. You want to be able to do things for you. And we want to keep moving more and more towards that vision of kind of what we call like a do engine instead of just a search engine.
21:15 Chris Benson? Very inspiring what you're saying. As you're looking at the world going forward and you're trying to think about like getting those capabilities out into all the places. And as you're looking at, you know, whether it be something as mundane as you're in the kitchen, as we talked about jokingly, or whether you're getting out into vehicles that are either cloud connected or on the edge or anything, or maybe even something, you know, another popular topic out there to throw buzzwords out is things like Metaverse and stuff. How do you get this capability out into all those use cases? In a, in a very practical and functional way for people to start taking advantage of it. Because you have almost unlimited potential in terms of, of this generative capability that we're,
22:00 Chris Benson? that we're on the forefront of. And so like I have a 10 year old daughter, I'm imagining, but you know, another 10 years out, she's gonna really have a tremendous college experience, very different from us, because she's gonna have all these new tools. How are you looking at trying to get this technology into all the places that really affect people's lives going forward?
22:23 Speaker 03 It's very likely that 10 years from now, you know, the way that people interact with the internet and the information that is out there, they're gonna find it hard to imagine how we did it, you know, without such strong language understanding we have at that point. Because language is this like really natural interface for us, right? Like you can talk about doing pretty much anything. So if something could be on the other side and be that other you out there, right? Kind of doing those things a little bit for you on your behalf, just the way you would. I think it's probably something we can't really conceive of yet. We can't really wrap our minds around it. But getting there, you know, there's traditional ways to do it. Like we have mobile browser apps and I think people understand how those work.
23:06 Speaker 03 Like Chrome or Safari, we have like a U browser on iOS and on Android. I think desktop browsers are another natural one. But pretty much anywhere you might type in text could eventually become an interface for you to interact with these things. And if you can type text into it, you can also speak to it and have speech to text take care of that for you if you want to do that. Any interface where you're using language or could use language to communicate with something is an opportunity, I think, for the next generation of search and chat and do engines like e.com. That's the forefront. I, you know, I have some sci-fi thoughts, you know, that possibly could go down.
23:50 Speaker 03 I don't know about you guys, but I have like an inner voice. Like I can hear what I'm thinking as text, more or less.
23:57 Chris Benson? You should definitely go there because we, this is what these conversations are all about.
24:02 Speaker 03 Yeah, yeah, yeah, it's. So you know, not everybody has this. Some people are surprised to learn that as well, but like some people can't see images in their head, for example. Some people don't have an inner monologue. I've for many years now, since I've been working on these things, referred to my inner monologue as my like own inner language model. Right? It kind of even predicts a little bit what you're going to say next. Um, that's how you complete people's sentences and anticipate things.
24:30 Speaker 03 Yeah. So I don't, I don't have any aspirations to work on this. Uh, I think there are a lot of things to think about. But in the long run, like that's kind of a language interface too. Like what if these things were hooked up to that? You know, if you're into the neural interface stuff, that's maybe a realm, we're very far from it. But you know, what if your inner monologue could also be supplemented by these things? Your own like thoughts, thought processes. Yeah, not on our roadmap, but.
24:55 Chris Benson? I, I get, I get that. I like that thought though, because we've come to a point, and I think everyone is coming to this point where things that would have been like, eh, well, you know, that's way out there. People are starting to kind of go, that's an interesting idea, you know, kind of seeing how fast things have ramped up.
25:13 Speaker 03 Yeah.
25:14 Chris Benson? Uh, in recent times, and I think it's pushing imagination out there at large, uh, in terms of what might be coming.
25:21 Speaker 03 Yeah, it's really inspiring, you know, at some point when we were making some of these early language models, we were working on our version of like a GPT two size model, we called it control. And someone I was working with read at some point a poem that this model had generated and was legitimately touched, you know, they were like, whoa, I, I actually really liked that poem. They didn't like poems before. And then we spent, you know, weeks, you know, in our off time, like talking about poetry and trying to find poets they liked and things like that. So even in the kind of simple moments, this opening, I think that you're talking about, right? This kind of dropping of expectations about search or technology can really do for us.
26:05 Speaker 03 It's changing the way people think about it. It's changing people's lives in some ways. It's like inspiring them, getting to be more creative. And going back to Daniel's really question, when you're combining different modalities and images and vision and text and just thinking about what you could do with your own thoughts, if you could actualize them and realize them more easily. Uh, that's a, it's a cool journey to be on.
26:27 Daniel Whitenack? So Brian, super interesting to think about like where this could be headed. And I've had similar experiences to what you talked about a second ago where it's like, I'm kind of have like mental block in this scenario. And like I go to one of these chat interfaces and even if it's just to like unblock myself, like I, I start chatting and like then it gets, it sort of jumpstarts my mind in a new direction or something. That's, that's very, yeah, very intriguing to me. Now you've been, you've been interacting with these models quite a bit over time and have probably dealt with like, you've already talked about things like grounding and hallucination
27:11 Daniel Whitenack? and like the sort of power of the knowledge embedded in these models that they've memorized and things that people have like talked about more recently. You've been kind of at the forefront of thinking about these things. So I'm wondering like now that like the whole world is talking about all of these things, if you have any sort of like wisdom you would like to impart in terms of like either like these topics that people are concerned about in terms of like grounding and hallucination or like harmful outputs or on the other side, like the ways that this is like, like I think people were concerned that this is like an automation of our life, but really like people
27:53 Daniel Whitenack? are getting such a benefit from it as like an assistive technology. So like the fact that you've spent a longer time thinking about these things that many of us have just been like hit in the face with, any wisdom or thoughts on that, like that you've kind of started to develop as your own kind of like mental model of these things?
28:13 Speaker 03 Oh yeah, yeah, for sure. Just remember that it wasn't very long ago that they would just repeat themselves over and over again and they did nothing useful.
28:22 Daniel Whitenack? Right.
28:23 Speaker 03 And there's two ways to remember that. One, they're probably need a lot better. As long as we keep going the way we're going, they're gonna get a lot better. And two, they're just tools. They're still just tools. And there's a lot of things we don't understand about them. But I think I would suggest trying our best as a community not to anthropomorphize them too much. You know, and think of them as like these other people. I think in the chat interface in particular, gets our mind ready to be talking to a person. Even just the UI and the layout of it and things like that, right? It looks like we're talking to a person more rather than a box where you type in keywords. And we've all been trained to do that for 20 years or something like that.
29:07 Speaker 03 And when we're texting with people, it's this way and that's people. People, AI, people, AI. Now it's like, ooh, what is this thing? And try to just keep at the forefront of your mind that this is a tool. It's an algorithm. There's like a computer out there behind the scenes somewhere doing this stuff. And keep the awareness that sometimes it might be helpful for you to let yourself slip into conversational flow with it. As if it's a person. And if that's helpful, that opens up, you know, inspiration and things like that. But then don't get too caught up in it, you know, remember that it's there for you.
29:39 Chris Benson? I got a question there that you're, you're making me think of as you say that. Because what you just said really applies to my personal experience. And so having grown up with computers, I'm in my early 50s. So decades of computers in the past year, my relationship with technology has changed. I have always used it for automation and kind of productivity and very, whether it be code or whether it be other tools that are out there. The thing that's changed dramatically is that I place a very high premium on creativity. And, uh, and creativity is something that has historically, prior to the last few years, been the domain of humans, uh, and we always expected creativity to continue to kind of be the more human thing and, and computers.
30:24 Chris Benson? But that's kind of been flipped around. And so we're seeing a tremendous capability, uh, assistive, you know, techniques, to use the word assistive that Daniel did a moment ago in other non- Parts of my life, I'm using these AI tools for creative purposes. And so where do you see that going? Because that surprised me to be able to go to chat and get inspiration and bring my own creativity to it. And then have it in turn, an extra creativity that is algorithmic based, enhancing that. So we end up with a product that is creativity, that is both human and automation together, that are generating this thing, which is really cool.
31:06 Chris Benson? And I'm using it like to teach children and stuff like that in other parts of my life. And so how do you see that kind of relationship going forward? You know, when you were kind of talking a little bit about, you know, the sci fi influences and stuff like that. And as we're looking at these models, which are most definitely, as you said, not entities of themselves, you know, not, not people. But they're going to get much more powerful in the fairly near future. Where does that go? What does that mean? How does the relationship look going forward between us and those, and those systems?
31:38 Speaker 03 Yeah, I mean, I fully intend to just get more creative myself, you know? I think I've, I've not, over the years, been playing with it. And I think it might help to have been playing with it for so long and seen them get better and better. And still see all the places that they still fail me, I suppose. But for me, it's fully incorporated as just like, you think of it as this different thing, right? That's like almost competitive with you on your creativity. But going 10 years in the future, like the next generation, like we were talking about before, I doubt they're going to think about it that way. They're going to think about it like you think about a normal search engine.
32:19 Speaker 03 I know there are studies, right, on people who think they know things, but really they just know how to search for it. And then they, then they feel like they knew the thing.
32:27 Chris Benson? Yeah.
32:28 Speaker 03 There's like this appendage experience that we like merge with it somehow subconsciously. Something like that will probably happen where this will just feel like. Part of your creativity. And I would encourage us to also develop the technology that way, too, so that it continues. The narrative is such that it's built for us to enhance us so that we're more creative. I feel more creative using it. I don't feel like it's creative and I'm not.
32:55 Daniel Whitenack? Me too.
32:56 Speaker 03 I feel like it's giving me access to data and the data distribution in like a really night condensed way, more or less. And I can kind of test the waters, right? I see what all the other people are doing in some way, some portion of the population, whatever the data representing. And then I can choose to either do that or do something else and change it. And that's actually really cool from a creative perspective, because sometimes you might be in your own little vacuum or echo chamber, or whatever it is, you think you're doing something really novel and cool. It turns out a million other people have done that kind of thing. Now you see, it doesn't look like it, but what you're seeing with the language model is what
33:37 Speaker 03 everybody else said. Not everybody else. A lot of people, enough people for the language model say that. So you're getting a little bit of a measurement of what's going on out there that you couldn't get before. And if you use that as another input for yourself, I think the way that, you know, humans and chess algorithms are better together, we'll continue being better together with these creativity tools, these productivity tools. And we'll just learn to be better at whatever we want to do. Hopefully it'll just free us up to think about the things that we want to think about.
34:11 Daniel Whitenack? Yeah, and I'm also kind of wondering selfishly. So we've been talking about kind of like, you've had the benefit of like, working with these models for a very long time and kind of getting an intuition of some of these things and how to think about them. In the capacity that they play, how to think about like the UIs around them. But also you've been on the technology side and kind of like at the forefront of integrating these things into your systems and also like, hey, there's output from this model. Do you know, should we show this to a user? Hey, there's output from this model like, or there's like these references that we could inject as context into this model. Like, do we do that?
34:55 Daniel Whitenack? A lot of people as practitioners are wrestling with those things too. Now that like, oh, I can go get LangChain and like pull it down and like integrate a bunch of things together and create this workflow. I can go like, so on the practitioner level, I guess more so than like the perception level, on the practitioner level, for all of those listeners out there that are like jumping into this and starting to deal with some of these issues around integrating language models into their own applications. Do you have any wisdom that you'd like to impart in terms of like that practical side of things and like how to go from this concept of integrating generative AI for this particular
35:39 Daniel Whitenack? domain and this particular problem to actually realizing that in an application that's useful for people?
35:46 Speaker 03 Yeah. And this goes back to some of the other tips I'd provide for people interacting with them too. I think for developers of these things and practitioners, do try to ground their responses as much as you can, unless your product that you're giving people is specifically, you know, say whatever you want, language model and do whatever. If people are actually looking for real information from you, just know that your users, there's, your users are also seeing that conversation interface and everything I just described that is making them feel a little bit like it's more human than it is. And it might even be their first time seeing one of these things, how well it works. So keep that stuff in mind and try to anticipate the hallucinations, try to ground things,
36:30 Speaker 03 try to provide clear attribution as much as possible. And then I would say, switch back and forth as much as you can between those moments of surprise and wonder in yourself and let your expectations drop a little bit so you can think about what you can do with these things. But then, once you implement something, be very skeptical and critical of it. You know, as much as you possibly can, like you would any other engineering system, any other like research project or experiment you're running, like, go get some numbers, like get close to the data, um, because it's very foreign to a lot of people right now. And the only way to do that is to go use it a lot, not as just a user, but as a practitioner.
37:13 Speaker 03 So you're going to see that prompts matter a lot and in ways that you probably won't anticipate sometimes, and you will anticipate sometimes. So just like, start getting your hands dirty, embrace that whole process. It's quite fun because it feels like you get a lot farther, a lot more quickly than you're used to. You know, you can kind of dream up a use case and it just kind of works. And so celebrate that, right? Like, like I love in that moment, you're, oh my gosh, this kind of works. But then immediately go back like, okay, wait a second, like, what if we evaluated this properly? What if we put all these conditions around it? Like, let's find all the places where it doesn't work, where it's going to let people down.
37:55 Speaker 03 And, you know, with you.com as a search engine, turning to do engine, like the goal is to make it impossible for you to fail in what you're trying to do, more or less. So, you know, try to embrace that mindset here, too. It's a new tool, you have to use it, like, I don't know, if you've been a Kubernetes person or home trial person, like you're not going to just know all the things. This is familiar looking because it's your language, but treat it almost as if it's foreign, you know? And take a little bit of that perspective.
38:24 Daniel Whitenack? Yeah, I love that. That's a really good perspective to bring into this. Um, as we wrap up and get to the end here, I'm wondering, like, we've talked a lot about you.com. We've talked a lot about you chat. If you were to encourage listeners, like, maybe they haven't interacted with you.com yet or you chat. Like, what are like a few things that they can do, a few places that they can visit to like, get and kind of understand the you.com experience and like, maybe a few things to try, um, that would kind of highlight some of the things that we've talked about.
38:57 Speaker 03 Yeah, so. There's you.com. It's you.com. You can go there. If you're on mobile, we do have our app. And I do recommend that because they provide a better experience on mobile, especially for the chat. Now, if you go to you.com, I'd also encourage you to look for the chat tab or go to you.com/chat because that's where a lot of this new exciting stuff is showing up. I'd also love to just chat with people directly. We have a Discord. And so if you go to you.com, it should be pretty easy to find and join the community. There's a link to it. And yeah, come talk to us about your use cases. So far, people love it for writing essays and
39:38 Speaker 03 emails to professors and code and recipes. Lots of people just like asking about themselves, even though the model doesn't always know, you know, exactly. That's like a fun use case that blends hallucination with truth. But look for those citations. You know, like I said, treat it like any other thing. Look for the citations for grounding and follow up with us on our Discord. We're pretty much there all the time that you can talk to us directly about it.
40:05 Daniel Whitenack? Yeah, that's awesome. Well, I'm, I have been enjoying interacting with you chat and other things. And I'm just really happy that we had the chance to have you on the show, Brian, and learn a little bit more about what you're doing. And also, your really insightful perspective from working with these large language models for so long. So, thank you for taking time and joining us and would love to have you back on the show in a year to think about like, I'm sure next year, AI search is going to look way different than we expect. Because, you know, six months down the road, it always looks different. But yeah, thank you for your innovation and your insights.
40:44 Speaker 03 Thank you so much for having me. It was a real pleasure to meet you. And yes, I intend to make it very different in a year. So I'll be stoked to come back and see how much of what we said holds true and whether we all think of these things as ourselves at that point. I don't know. We'll see what happens.
41:02 Daniel Whitenack? Sounds good.
41:03 Speaker 03 Yeah, thank you.
41:04 Daniel Whitenack? Yeah. Thanks, Brian. Bye.
41:14 Speaker 00 Thank you for listening to Practical AI. Your next step is to subscribe now if you haven't already. And if you're a longtime listener of the show, help us reach more people by sharing Practical AI with your friends and colleagues. Thanks once again to Fastly and Fly for partnering with us to bring you all Chang Talk podcasts. Check out what they're up to at fastly.com and fly.io. And to our beat freak in residence, Breakmaster Cylinder, for continuously cranking out the best beats in the biz. That's all for now. We'll talk to you again next time.
Previous End-to-end cloud compute for AI/ML Next Explainable AI that is accessible for all humans Page updated October 26, 2026 · transcript and summary are machine-generated