How Does AI Actually Work?

27:46In the past, you needed about seven months to 18 months to build an application with programmers, designers, product managers, and so on and so forth. But now if you have a vision, well, you can go on BART and say, hey, this is my vision. and help me iterate on that, give me five ideas that are related to this. And then after that you can say, hey, now write a product requirement specifications for a system that may look like that. And then you can say, hey, based on all of these interactions, write a project plan. And you can iterate on that context with the chatbot, so to say. And then after that you can say, hey, considering these artifacts or considering everything that we've talked about, help me write a design document that I could use to implement this app, this solution, and it would do that.

28:34And then you can say, now I need you to help me implement this in Python. You know, design the APIs for me, write the implementation of the APIs for me, write the system designed for me. It could even help you draw some of these things. And so what you're seeing is that you're moving from a lifecycle where you had to use about 18 months with a team of 10 to even get an idea into a good shape to probably a matter of hours to weeks working with prompts and being very creative in the way you interact with that bot or as a smaller group you interact with that bot to come up with a solution that is pretty, pretty good.

29:13And so what I see is that many industries, many startups and enterprises have really, really taken advantage of that. I've seen good examples in media. I've seen good examples in healthcare and life sciences. I've seen good examples in financial services. But in all things, essentially, I'm seeing a lot of movement. Do you use these kind of systems in your own work to build your own APIs and stuff? You use BARD for your own work? Yeah, I use BARD. I use BARD every day. Every time I have an idea, every time I want to process something, I use BARD to iterate on the idea. Wow. I use BARD for outlines.

29:51If I need to give a talk, for example, at a conference, usually for me, the process of creating content would be based on the work that, it depends on the topic, but based on the work that I do and based on some research, I try to come up with a specific outline that really touches on the points that I would like to talk about. And so I use Bard to help me create that outline. And then I may fill the outline myself and give it back to Bard and say, hey, help me summarize this, and or help me extract specific talking points out of this. And then I can say, hey, make this a bit more creative and make this a bit more in different types of tones.

30:26So that's one mode of interaction. The other mode of interaction is the one that I spoke about earlier, which is when I have an idea, rough idea, say I want to create a system that helps you determine what coffee you're going to drink in the morning based on prior, whatever. Just a toy example like that. And so I can formulate specific questions and interact with Bard in that way. and I could have a prototype before the end of the day. That works. That is implementing Python full stack. That's crazy. And back end. Yeah. That's like a productivity explosion. Exactly. I want to reel it back a little bit because we talked about AI.

31:02We talked about machine learning. We talked about deep learning. But the big thing that's on everyone's mind in the last year is generative AI, which you've talked about multiple times so far. But we didn't really define what generative AI is and what makes it different from those other forms of AI. So can you give a quick explanation of what generative AI actually is? Remember we talked about AI overall being a system, not just one thing. So, and machine learning being a set of techniques that are more mathematical in nature, deep learning being one of these techniques that focuses a bit more on neural networks.

31:38So by virtue of getting something that is a lot more fundamental, So generative AI is a deep learning technique. So it's still using the deep learning technologies, but generative AI is really focused on generating or creating a specific artifact. And so that artifact could be an image, it could be a piece of text, or it could be a piece of audio, or it could be something else. Yeah, that's a very simplistic definition of what generative AI is. And what is the foundation of generative AI? What allows that to work? because we see things like generative fill in Photoshop. We see generated music now.

32:17Like every single creative industry and non-creative industry is being sort of upended by this generated content. What is allowing systems to actually generate content instead of just classifying content? Yeah, so that's a beautiful question in the sense that there's a very, very strong common denominator among all of these things. And that's the transformer architecture I spoke about earlier. So what we've seen is that applying the same technique and then changing the question a little bit gives you exactly content that is generated that you're interested in. For example, we can say, using these lower transformer architecture, help me generate an image.

32:58You can give the generative AI problem as, given images of different artifacts, like animals, like cats and dogs and whatnot, create something that looks like some of these things using, I don't know, interpolation or extrapolation, different techniques, and make it look like the family of things that I've shown you in the past. and it would give you something that doesn't exist in real life. Maybe the image, very high fidelity image of a dog or cat that doesn't exist in real life, but really, really looks like the samples of the things that you've shown it in the past. So the ability for these models to essentially create content in different modalities is the generative ability.

33:40Yeah, so we think about large language models being fed into a transformer, right? And that's just like, give me all of the text that has ever been written on the internet and we can develop relationships between words. But when you're generating an image or you're generating audio, what is being fed into the transformer in that way? Because we see there's a lot of genetics work that's being worked on with transformers, too. What kind of data do you feed into transformers to actually make that work in a variety of different fields? Right. So in general, you would give it today. Text was very easier to acquire.

34:17That's why you hear of large language models today a lot more. And the results also from generating text were a lot more impressive and exciting to look at. That's why, in my opinion, that field somewhat took over. But you're right. So you could consider the input to be pretty much anything that could be put into a sequence. A video, for example, is a sequence of frames. So you could give multiple videos broken down into frames to a transformer-based architecture. And it gets a bit more complex in a way those sequences of process or structures maintain. There are many techniques around our tension mechanism and so on and so forth.

34:58But let's consider that to be a black box. And then it knows how to do that. Then what you give it is a set of frames, which are videos, so to say. And then you say, give me something that looks like that. So in that sense, you've given it videos or a set of frames. You could also have a mechanism through which you give it videos and text, which we do today. There is this encoding model that is called clip, essentially putting together images and videos, I mean, and text. Which is the foundations of DALI and a lot of AI image generation. At least the foundational technique of these kinds of abilities, where you teach the model to recognize images and text together as a joint entity, so to say.

35:45And the process through which you do that is by getting the images processed with what we call a tokenizer and or encoder specific to an image. And that turns that into a vector. We call that an embedding. And then you go through the same kind of process with a text where you turn the text into a vector. And then once you have these two vectors, you can then combine them with basically algebra. And then at a higher level, you have the task and or the question that you want the model to answer. In one scenario, you would want the model to say, for example, given an image, explain the content of this image for me.

36:19Or you may have the reverse problem, which is given a text, generate an image that contains the information, so to say, that I've provided in this text, which is the business of mid-journey. Yeah. So as a kind of to break that down, you're depending on the field that you're trying to use transformers on, you are turning data into numbers and you're comparing those numbers to each other and then getting an output. Correct. So because you're able to take video or images or text and vectorize them and turn them into tokens, you can compare them to each other, even though they're different types of media.

36:58Correct. Correct. That that is that is excellent. And one of the things that makes it really work beautifully is because once you take the images or video or audio, you encode that into an initial vector. That process is called tokenization. Then once you get the token, and by the way, the tokens can be a bit more complex. For example, the tokenizers could learn to not just use a word per token mapping, but it could also split words into two or three if that word has a bit more complex. Multiple meanings. Multiple meanings and complexities. or if it finds it effective. Sub-tokenization? Sub-tokenization.

37:34So you may have a situation where a five-word sentence gives you 12 or 15 tokens or maybe less. So it's a matter. The concept is more about information preservation within a substructure that is a vector rather than a one-to-one mapping between the words and the vector. Same thing with an image. An image is a two-dimensional structure which has a third dimension of red, green, blue, right? Right. So if you flatten that entire thing into a pixel intensity over that entire two times, times three, so to say, dimension, then you get a larger vector. But that's just a simplistic tokenization where you say, hey, I'm going to flatten an image, flatten that more by red, green, blue.

38:18And then after that, I'm going to have a vector representing the pixel. From there, you can have a deeper tokenization that may consider the structure. For example, the adjacency of objects or the distance between objects or even some deeper level of understanding of the objects within that image. At the end of the day, you go from a piece of artifacts like audio. And in an audio, you use a spectrogram and you turn that into a specific artifact. So you go from an asset to a vector. Now, there's this other step called embedding, which is basically doing a projection of that vector onto a vector space that is shared by every other piece of artifacts, I mean, other piece of data in that space.

39:04It's like a normalization. Like a normalization. But then by that projection, what you essentially do, especially if you have a multimodal model, like if you work with an image and if you work with text, for example, then you tokenize them each, which is a one-to-one relationship between an image and a text and a tokenizer that works for them. And once you have these two vectors, you do that projection onto that shared vector space, so to say. And the beautiful thing about that is that, and you do that through training, the beautiful thing about that is that once you land these things within the same space, they become of the same nature.

39:37Right. So you can start comparing them. Yeah. So you can start assigning relations and having statements like a car, C-A-R, written in text form. Compared to the image of a car. compared to the image of a car. So these two vectors will be closed in locations. It's almost like a Rosetta stone. You're taking one language and another language, and you're sharing them in a certain way. And then once you have this shared, say you translate them all to Latin, then you can do whatever you want from there. And the common substrate of all these different things, assumption at this, is that there's information that is preserved in these different types of artifacts.

40:14So you're almost doing an information extraction exercise. Describe that. What do you mean by information? So it may be a longer conversation, but at the end of the day, so information, and I know you had a whole video about the nature of information. Yeah. It could be contextualized to the piece of artifacts that you're working with. But in a very, very simple manner, information is this entity or this thing that could give you, it's hard to define information without using information. Yeah, you have to. It's this thing that can give you a bit of a pattern, right? And we usually base that pattern on the notion of order, disorder, symmetry, and so on and so forth.

40:58But if you have something that can give you a pattern about indifference and or disorder about a specific subsystem, then you start having information. For example, if I do this. Nothing has changed very much. So if you were on the receptive end of that pattern, you won't really get much information. But if I do,

41:25there's a difference in what I did before and what I'm doing now. Now, you may not understand why I'm doing that, but you would understand that there's a difference between the way I tapped, the frequency at which I tapped my hands before and the frequency at which I tapped it after. Then you've gained information. So it's the same way that you may understand some differences within an image, for example, looking at a contour and then something changed between this and this, then you may realize that these may be two different objects, and so on and so forth. And within text as well, you may have difference maybe between words or between paragraphs and between different structures.

42:03So you have some form of information. And a beautiful thing about information is that it could be combined. So it's the evolution of information is what that you're maintaining. So it's the extraction of information and or differences in patterns within different modalities of data artifacts. But a beautiful thing about that is that it could be combined at a certain level or compared. And that's what makes it possible for you to essentially extract information out of an image by understanding how different it is or how many different patterns exist within that image and extracting information out of a piece of text by understanding how many different patterns exist within that text.

42:37And then putting that together in a normalized space through which you can start comparing them. And then reversing that, you can now combine text to images and basically have that relation maintained. With all of that combined, would you say would that be the fundamentals of like a general AI that could do everything? We're getting into the realm of AGI. Yeah, AGI. I would love your opinion on that if you feel comfortable talking about it. Of course, of course. So what is intelligence according to you? According to me? This is such a big question. I've thought about this a lot. My personal opinion on this at this point is, well, for the listeners, we're going to define AGI really quickly.

43:23AGI is artificial general intelligence. Effectively meaning you can ask an AI to do anything that a human could be able to do or possibly even more. Right? And it could be able to help you with that. Would you agree that that's the definition or do you have an expanded definition? That's somewhat why I'm asking the question of what is intelligence? Because agreeing on AGI being artificial general intelligence assumes that we agree on what intelligence is. Sure. OK. My definition of intelligence would be. Wow. Thanks. The ability to synthesize information and create new actions based on information that you weren't explicitly told to do.

44:15That'd be probably my definition of intelligence. That's a decent definition. Would you disagree that the context in which you have to do that specific workflow that you define has to be defined? i.e. you have to do it within the context of, I don't know, literature or robotics automation in the subfield. For example, having a robot that can control a specific arm either for surgery, and it would be a different thing if that robot controlled an arm, say, in a restaurant, and so on and so forth. I think that when we talk about the generalization of intelligence or even information, we're making a bold claim that goes beyond what we understand so far about the nature of these things.

44:59Uh-huh. Sure. So if I want to break down the problem of AGI, again, I might have already expressed that I'm not a very big fan of that definition because I don't really think we know exactly what we mean when we say that. Sure. But if we want to get into a practical realm, I think that it may be possible to essentially, and which is the state in which we are now, by getting these models to progress and their ability to impact the world as well. So we discussed the software version of the AI so far, which is you give it data, it could recognize it, or at this point, it can also generate data. But what is the software real-world interaction mode at this point?

45:44So we have many systems, for example, in healthcare and life sciences, that have to deal with the real world in the way that, say, or hospital equipment functions or in the way that a robotic arm that controls cameras functions. So you get many other things about the real world that may have to do with intelligence. So I think a lot of the work that we're doing on improving the quality of these AI systems has to bring things all the way up to these definitions of AI that I mentioned earlier, which involve and include planning, scheduling, and acting and sensing as well. So when you start augmenting these systems with these additional capabilities and you start training agents that are able to plan and schedule and act in the real world, then you get that sense of AGI that's closer to the definition that you gave it.

46:36Now, the ability to do that at that level, at that scale, gets challenged by where are you sensing what kind of information and also where are you acting in which kind of world environments. And if you want to look at the real world in which we operate and you want to look at all the types of interactions and actions that can happen, the number of possibilities is larger than the number of atoms in the universe. Right. And so how would you have a generally intelligent system that knows how to act in this entire world? I find that quite a challenging thing to believe. But if you constrain the problem, if you make the problem simpler, as simple as I want to have a generally intelligent system that would learn how to use all the hospital equipments within the hospital system.

47:24then maybe you have the opportunity to have an AGI system that can essentially take in a task and execute that effectively. So that is my techno-optimist view of the possibilities of AGI by training agents that have world representations, but these are simpler worlds, representations that are constrained by the problem space in which you want these systems to operate. And then being able to plan, schedule, sense, and act, including the other type of capabilities that we can do. Okay, interesting. So Danu doesn't think that we're going to have this one omniscient AGI, artificial general intelligence, that's going to be handling everything.

48:07But he rather thinks that we're going to have these smaller, more specialized AIs that kind of handle different tasks and help us do stuff a lot faster. This is actually not that different from that whole conversation around the Tesla bot, right? like where you can have a robot that's like a human that does human tasks or you can have a bunch of really small robots that handle the tasks that we already do on a daily basis kind of the same thing pretty interesting um in the next segment we're going to get into the problem of ai hallucinating which is where it just makes up a ton of random stuff and uh that's clearly a problem i was very curious about that so that'll be a fun conversation plus we need to see how fast Venu can type.

48:48So get ready for that.

49:02Mercury knows that to an entrepreneur, every financial move means more. An international wire means working with the best contractors on any continent. A credit card on day one means creating an ad campaign on day two. And a business loan means loading up on inventory for Black Friday. That's why Mercury offers banking that does more, all in one place, so that doing just about anything with your money feels effortless. Visit mercury.com to learn more. Mercury is a financial technology company, not a bank. Banking services provided through Choice Financial Group, Column N.A., and Evolve Bank and Trust members FDIC.

49:41The pumpkin spice latte is back at Starbucks. Crafted with our signature espresso and real pumpkin sauce, then topped with whipped cream, cinnamon, and nutmeg. The PSL. Get it while it's hot or iced. Only at Starbucks. Ellis wanted to hop in and ask a question real quick. Yeah, sorry. I really liked what you said about defining intelligence as it pertains to AGI. And I thought David brought up a really important kind of intelligence, like intuition and deduction and the ability to extract not just pieces of information, but threads and systems of information from multiple kinds of contexts. But there's lots of other kinds of intelligence that people like cognitive scientists like to define and classify things like spatial reasoning, things like engaging in dialectical thinking.

50:37And these are all intelligences that we've observed in ourselves. And so when we think about sort of a general purpose Swiss army knife AI, do you think that we should be limiting that to the kinds of tasks that our brains do on a daily basis? Or do you see that there's going to be almost like new methods of thinking and new cognitive strengths that emerge as these neural networks get stronger? Sure. That's a super interesting question. In a practical sense, I'm actually with you, David, on that definition, right? Because I think that that's the form of intelligence that could be mechanistically or mechanically implemented in a piece of software, as in program, right?

51:29So by our own intuition, we can think about doing things like that by breaking that down into steps. The kind of intelligence that you're talking about, to me, is a bit more like that emergence, right? Like that emergent ability that, and I don't think we've gotten to the point where we can perceive what those are. Yeah, or intuitively. It's like a new color. Yeah, intuitively know what exactly we need to do in order for the models to have that spatial awareness or that other kind of ability. Now, we can program that by having segmentation models and having distance calculations and coming up with some mathematical heuristics through which we can claim that we've achieved that capability.

52:13but I would argue that the way we learn us is not exactly the way we teach the machines how to do that, right? So there's definitely a lot more research, and we may stumble upon, you know, we may basically strike luck and then find out that other kinds of scaling mechanisms, or the way it works in physics today is that you have smaller systems, you have a simple interaction mode like magnetization or just collision analysis or the different forces that we're working with, about four of them. And based on these simple interaction modes, you get the entire universe the way we know it, at least it's the current theory.

52:51Yeah, fundamentals of physics. Yeah, at least it's the way we know it. But it may be another way, right? We may have just sensed it in our own apparatus of sensing in that kind of form, and we're able to explain it the way we explain it, but it's still a projection on the screen that we're looking at and doing our analysis. So I'm super excited about the possibility of us finding out more cognitive routes, so to say, in the way these systems learn. And right now, the best tools that we have essentially in our laboratory of AI are these deep learning tools, the transformers, and our many other architectures that are being built around that.

53:29things like memory-aware neural network architectures or things like the ability to pull from a vector store and augment the knowledge with the retrieval augmented generation capability. So I feel like the more we add interaction mode and information retrieval and utilization capabilities within these models, the more possibilities we have to have this additional emerging capability that is a lot more cognitive than the mechanic way we've been doing things. So I think that's an open question. I think it's a beautiful question. And I hope we get lucky in our lifetime to find a way to get that done.

54:08Yeah, me too. We've stumbled upon a lot of random stuff in science. So there's definitely a possibility that we have that happen, which would be big. I think it's Richard Feynman that say that science is the belief in the ignorance of the expert. so i i think that if we if we really take it as a as a basic principle that we could stumble upon some things and then we believe that whatever we know so far is may or may not be the way then we have an opportunity to really incorporate new information and our knowledge that can get us faster and further yeah i want to pull this back uh a little bit back to some practical stuff again.

54:47A big philosophical. Yeah, no, I love the philosophical conversation. I love the philosophical. I think that one thing that people think about when they think about generative AI is the problem of hallucinations. And for people that don't know, hallucinating is basically when you generate something that just isn't right or isn't true. In large language models, you can ask a question and it will confidently lie to you sometimes. And how do you look at how we're going to solve that problem? Because it seems like part of generative AI and part of large language models in general is that it's just, it's parroting information based on probabilities.

55:29And those probabilities are not always going to be correct. So you're, I'm assuming, working on ways to make these AI is more accurate. Accuracy is obviously going to be a major problem and something that we need to solve over the next couple of years. How do you look at solving the hallucination problem? The problem of hallucination, so the way these models work now is that you give it a lot of data and the question you're really asking of it is, give me, let's simplify a token to a word and working within the text domain, give me the next word based on this word that I gave you. So if you qualify the problem as write a novel for me or write a paragraph or write a summary of something, then traditionally what would happen is that you would give it the beginning of a sentence and you would say complete this sentence for me.

56:26And so it's that sentence completion, so to say, that is based on probability. And even basing that on probability within the context of this conversation is a simplification. So there's a lot more going on, but the basic principles of how it works is that let's assume that it works off of the most probable word to follow that word that existed and then taking that longer sentence as an input, figuring out what is the most probable word that could follow and so on and so forth. What that means, if you simplify the problem just at that level, And if I say, give me a complete sentence, Dr. Something works at John Hopkins or something like that, then it would just put a name there.

57:09So the question you haven't asked is make sure that that name is an existing human being that is really a doctor at John Hopkins and whatnot. So fundamentally, it's a different question to ask off of that system. And then we're back on the reason I call these things a system in the beginning is because, yes, you may have a model that gives you the next word prediction or the next token prediction. But then you still need to do a lot more work on top of that input and that output and even that processing sometimes to make sure that the output and the response that you get out of it is a truthful one or a real one.

57:49or a less toxic one if the answer is toxic and you don't want to serve toxicity to your users. So there are many pre-processing and post-processing activities that need to happen. One, to make sure that the context, I mean, the answer of the model is grounded. We call that concept grounded in reality. And the second is to make sure that the output of that model goes by a certain set of responsible AI principles. right so those are two things but fundamentally the way the science works is that it would give you something whether that thing is true or not sure it's about it's your job to make sure that that thing becomes true and so the way that happens then now is that you need to associate that response to basically a source of truth right what is truth yeah yeah what what is truth what is reality and that's that's another thing where you another another reason why you probably want to contain and contextualize that use case, so to say, down to a source of truth.

58:54Give me Dr. Blah that works at Johns Hopkins, then you need to probably have a database of all the doctors that work in that hospital and make sure that after you get the name of a doctor, because the model will give you that, you check that against that database. And if that person doesn't exist, or you can say, fill this specific spot off of the names, the list of names on the database and constrain and constrain. So that's why BARD now has that Google button where you can ask a question and then you can double check it. That's another context. That's another mechanism for that. But that's not exactly why it has that button.

59:32Just to land on the concept of hallucination. So it was named hallucination because it could give you some answers that seem real but are not necessarily real. But this is a normal functioning mode of these technologies. The reason it took us a while to release BART, for example, was not because, well, we invented the transformers. So we've known how to do this thing for a long time. But it's all of the additional set of technologies that we had to build and principles that we had to really build around the behaviors of the model that really get us to, you know, one, the requirements of building additional technologies.

1:00:10and then two, the challenge around making these technologies deterministic in the sense that you always want a specific answer. So you have to do a lot more evaluations. You have to do a lot more checks and balances. You have to add a number of metrics, like, is this model answering a question when it doesn't know the answer? You probably want to codify that into something that gets checked and so on and so forth. So there's been a lot of work that we've done on one, really having clear and concise, responsible AI's principles. And then two, turning those into technologies and or checking mechanisms that could work in conjunction with a creation, the operation, and the operation of a model.

1:00:51And then three, making sure that these cores and outputs of checks are available so that that technology could be used on a cloud ecosystem, for example, as part of a platform. So we work with research to understand what are these responsible AI principles that could be turned into metrics and guardrails and and so on, those get turned into product capabilities that work alongside our models. And then these models are exposed or commercialized, so to say, on our cloud platform, this product called Vertex AI, and you can go find that out on cloud.google. So that's how we're essentially fighting the problem of hallucination.

1:01:29There's a lot more work going on in that space. Okay, well, I think I'm gonna close it out here soon, but I want to end with asking if you think that there's anything that we missed, anything that people would gain a lot from hearing about that they just are not hearing in popular media that's very important to the whole AI story? Two things, maybe. One is the consumer applications of AI, so BART, ChatGPT, are very popular now, which is something that I'm happy about because I think that it's really bringing the conversation closer and closer to everyone. and you and I have been working in tech for a while so we may have been aware of that coming up and coming together but I think it's a massive opportunity that today people that are news editors or writers or artists or folks that work in different domains can use some of these things to help them write better to help them generate images that they can use as part of the content that they produce and create to write better letters, to write better, to do homework and so on and so forth.

1:02:37So I really love the consumer application. But one of the things that I don't think it's talked about a lot is the developer experience and also the way the barrier of entry from creativity and product generation and product creation standpoint, it's getting really, really lower with these set of technologies. And so I really think that we are at the cusp of a new form of economy where creation of valuable items of different kinds of forms would not just be a matter of a few being able to do that because they have a high training and they spent years doing, I don't know, an undergrad in computer science and so on and so forth.

1:03:29forth. But if you bring that level of assistive creativity abilities to the masses, so to say, I've found that people have ideas. People are creative. If you sit down and you tell someone, let me take away the problem of knowing how to implement these ideas, let's talk about your ideas, you get many ideas to start emerging. So I think that we're really at the border of a transformation where the economy may take a different form if different people, without the need to really understand in details how to implement some of these ideas, are able to, one, iterate on the ideas with the assistance of generative AI, to validate some of these ideas with the ability to prototype those in a matter of hours rather than years.

1:04:18And then, three, test these ideas in the ecosystem and maybe find value for different people that they could commercialize these ideas for. So I'm very optimistic about the possibilities of this in the future. All right. Well, the last thing we're going to do, we have a little game here that we play when we bring guests on where we figure out how quickly they can type the alphabet. It's a running scoreboard. You can use either the MacBook keyboard. You can use... Oh, there's a keyboard thing. Yeah, it's a keyboard test. Now I get it. Yes. Okay, so you'll take that. So you get I'm gonna ask the AI to type this thing for So you get three chances Wait, what is the most optimized way of typing the whole alphabet if you as soon as you start typing it starts So as soon as you type the letter a it'll start and does he have to hit enter at the end?

1:05:14No, you don't have to enter as soon as you hit Z it'll finish got it and no and And no typos is allowed. So if you miss a letter, like let's say you miss B and go on to C, it will not count. You still have to hit B. You have to hit every single letter. And you'll see at the top where it says type A. Okay. That will tell you the letter you're supposed to use. Do we give people tests at all or is it just three chances? There's three total chances. Okay. Ready?

1:05:48You gotta hit G. Oh. It's harder than it looks. Definitely a lot harder than it looks. That's okay. You gotta hit J. This is why you get three chances. Don't worry about it. I was extremely slow.

1:06:09Okay. So first run, 26 seconds. Now I'm gonna just... Hit reset. Can I change the keyboard? Yeah, you can change keyboards. All right, so now I understand why there are options. Yeah. So we have... We have mechanical keyboard. We also have the butterfly keyboard that Apple sells. Let me know. I'm going to get a keyboard. All right, so I'll go mechanical. You want mechanical? Let's do it. Set us up however you want. Round two. Go for it. Nice.

1:06:48Okay. 26 to 9. Yeah, 26 to 9.8. Much better. Whoa, that's a big come up. Much better. Last try. Last try. But you guys aren't impressed. That means that I'm not... Nine is pretty good. I'm not that high. Nine is not bad. I was not far in front of that. Nine is actually really good, especially for a second attempt. We've seen some things in here that you would not believe. I'll show you the scoreboard after this and you'll be surprised. Four seconds. Okay. Okay, ready? Ready? Go.

1:07:23nice eight eight point seven three not bad honestly not bad okay where's that on the leaderboard david so here's the leaderboard fastest tom scott three point five seconds it was insane that was crazy to watch it was just um wow so let's see eight point seven three is right above Brandon. Wow. All right. Actually, no. Faster than David Blaine, too. You beat David Blaine. You beat David Blaine. He might be a magician, but you're a magician on the keyboard. Wow.

1:08:008.773. You also beat Hasan Minhaj. Hey, Hasan. So you beat Hasan Minhaj, David Blaine, and Brandon. Nice. Nice. Cool. All right. Well, thank you again. Thanks for having me. Seriously, thank you for coming. Where can people find you on the internet? Well, I'm Dean Banga on XNow. Okay. Nowadays. And I'm on LinkedIn as well. So I'm Dan Banga, essentially. Awesome. We'll link that in the description. And do you want to shout out any projects that you're finishing up right now or working on right now? That people can see at Google? So the Vertex AI platform is really the platform that I'm working on.

1:08:43Right. So that's what we put our solutions on. And I would say that look forward to many other more industries slash domain adapted capabilities around LLMs. Because I think that large models are a big thing. And I think it requires a lot of additional technologies to actually make it work in applications. and I think that this is about the time where we need to come up with things like design patterns. So if you think about A Gang of Four, for example, it's a book that was needed when programming needed some kind of structure. So I think we are at a place in time now where we need some kind of structure on how we build and deploy large models in enterprise environments.

1:09:28And that's something that I'm working on. Awesome. Sweet. Well, everyone watching and listening at home, if you were surprised that we had an episode today, don't worry, we have a normal episode coming on Friday. This was just a little extra story for you. So hope you enjoyed it. And we'll see you on Friday. Cheers. Peace.

1:10:02Most AI coding tools generate sloppy code that doesn't understand your setup. Warp is different. Warp understands your machine, stack, and code base. It's built for the entire software lifecycle, from prompt to production. With the powers of a terminal and the interactivity of an IDE, Warp gives you a tight feedback loop with agents so you can prompt, review, edit, and ship production-ready code. Trusted by over 600 ,000 developers, including 56 % of the Fortune Try Warp free or unlock Pro for just$5 at warp.dev slash top code.

1:11:01choice, which gives your members more ways to get on, stay on, and manage their meds. And that helps your business control your costs, because healthier members are better for business. Go to cmk.co slash access to learn more about helping your members stay adherent. That's cmk.co slash access.