Think in Context: Google I/O 2024 Keynote With Google CEO Sundar Pichai

Post Title Image


  • To cater to both individual (B2C) and enterprise (B2B) users, Google’s product lineup is more fragmented and scattered compared to Amazon, AWS. This isn’t necessarily a bad thing, but it’s not necessarily good either. Synchronization between products could be more challenging.
  • Google’s models Gemini and Gemma aim to handle long-form context, multimodal inputs, and information across file formats. However, maintaining technical leadership (facing developers, partners, and the ecosystem), multimodal outputs (facing customer needs), and controlling costs (facing investors) will be urgent priorities for Google as it integrates Gemini into hundreds of Google products and features.
  • Amidst this AI wave and technological iterations, the part that left the deepest impression on me from the entire keynote was this quote from DONALD GLOVER: “Everybody’s going to become a director and everybody should be a director. Because at the heart of all of this is just storytelling. The closer we are to being able to tell each other our stories, the more we will understand each other.
  • While we’re at it, can’t Google leverage Gemini’s long context advantage to allow Google Translate to properly translate “LLM” as “large language model” instead of “Master of Laws” in the appropriate context?


My Study Notes

Opening Film

  • [Cheers and Applause].
  • WOMAN: Google’s ambitions in artificial intelligence.
  • MAN: Google launches Gemini, the generative AI.
  • And it’s completely changing the way we work.
  • You know, a lot has happened in a year. There have been new beginnings. We found new ways to find new Ways to find new ideas. 
  • And new solutions to age-old problems.
  • Sorry about your shirt. We dreamt of things – Never too old for a treehouse.
  • We trained for things.
  • All right! Let’s go go go!
  • And learned about this thing. We found new paths, took the next step, and made the big leap.
  • Cannon ball! We filled days like they were weeks. And more happened in months, than has happened in years.
  • Hey, free eggs.
  • Things got bigger, like waaay bigger. And it wasn’t all just for him, or for her. It was for everyone.
  • And you know what? We’re just getting started.

1️⃣ Introduction

  • SUNDAR PICHAI: Hi, everyone. Good morning. [Cheers and Applause]. welcome to Google I/O. It’s great to have all of you with us. We have a few thousand developers with us here today at Shoreline 1. Millions more are joining virtually around the world. Thanks to everyone for being here.
  • For those of you who haven’t seen I/O before, it’s basically Google’s version of The Eras Tour 2, but with fewer costume changes. [Laughter]. 

Gemini & AI Overviews

  • At Google, though, we are fully in our Gemini era. Before we get into it, I want to reflect on this moment we’re in. We’ve been investing in AI for more than a decade, and innovating at every layer of the stack: Research, product, infrastructure We’re going to talk about it all today. Still, we are in the early days of the AI platform shift 3
  • We see so much opportunity ahead for creators, for developers, for startups, for everyone. Helping to drive those opportunities is what our Gemini era is all about. So let’s get started. A year ago on this stage, we first shared our plans for Gemini, a frontier model built to be natively multimodal from the very beginning, that could reason across text, images, video, code, and more.
  • It’s a big step in turning any input into any output. An I/O for a new generation. Since then we introduced the first Gemini models, our most capable yet. They demonstrated state-of-the-art performance on every multimodal benchmark. And that was just the beginning. Two months later, we introduced Gemini 1.5 Pro, delivering a big breakthrough in long context. 
  • It can run 1 million tokens in production, consistently. More than any other large-scale foundation model yet. We want everyone to benefit from what Gemini can do, so we’ve worked quickly to share these advances with all of you. Today, more than 1.5 million developers use Gemini models across our tools.
  • You’re using it to debug code, get new insights, and build the next generation of AI applications. We’ve also been bringing Gemini’s breakthrough capabilities across our products in powerful ways. We’ll show examples today across Search, Photos, Workspace, Android and more. Today, all of our 2-billion user products use Gemini. And we’ve introduced new experiences, too, including on Mobile, where people can interact with Gemini directly through the app.
  • Now available on Android and iOS. And through Gemini Advanced, which provides access to our most capable models. Over 1 million people have signed up to try it, in just three months. And it continues to show strong momentum. One of the most exciting transformations with Gemini has been in Google Search. In the past year, we’ve answered billions of queries as part of our Search Generative Experience. 
  • People are using it to Search in entirely new ways. And asking new types of questions, longer and more complex queries, even searching with photos, and getting back the best the web has to offer. We’ve been testing this experience outside of Labs, and we’re encouraged to see not only an increase in Search usage, but also an increase in user satisfaction.
  • I’m excited to announce that we’ll begin launching this fully revamped experience, AI Overviews, to everyone in the U.S. this week. And we’ll bring it to more countries soon. [Cheers and Applause]. There’s so much innovation happening in Search. Thanks to Gemini we can create much more powerful search experiences, including within our products. AI Overviews
  • Let me show you an example in Google Photos. We launched Google Photos almost nine years ago. Since then, people have used it to organize their most important memories. Today that amounts to more than 6 billion photos and videos uploaded every single day. And people love using Photos to search across their life.
  • With Gemini, we’re making that a whole lot easier. Say you’re at a parking station ready to pay, but you can’t recall your license plate number. Before, you could search Photos for keywords and then scroll through years’ worth of photos, looking for the right one. Now, you can simply ask Photos. It knows the cars that appear often, it triangulates which one is yours, and just tells you the license plate number. Ask Photos

Google Photos - Ask Photos

  • [Cheers and Applause]. And Ask Photos can help you search your memories in a deeper way. For example, you might be reminiscing about your daughter Lucia’s early milestones. You can ask photos, when did Lucia learn to swim? And you can follow up with up with something more complex. Show me how Lucia’s swimming has progressed.
  • Here, Gemini goes beyond a simple search, recognizing different contexts from doing laps in the pool, to snorkeling in the ocean, to the text and dates on her swimming certificates. And Photos packages it all up together in a summary, so you can really take it all in, and relive amazing memories all over again.
  • We’re rolling out Ask Photos this summer, with more capabilities to come. [Cheers and Applause]. Unlocking knowledge across formats is why we built Gemini to be multimodal from the ground up. It’s one model, with all the modalities built in. So not only does it understand each type of input, it finds connections between them. Multimodality radically expands the questions we can ask, and the answers we will get back.
  • Long context takes this a step further, enabling us to bring in even more information, hundreds of pages of text, hours of audio, a full hour of video, or entire code repos. Or, if you want, roughly 96 Cheesecake Factory 4 menus. [Laughter]. For that many menus, you’d need a one million token context window, now possible with Gemini 1.5 Pro
  • Developers have been using it in super interesting ways. Let’s take a look.

Gemini 1.5 Pro Developer Feedback

  • I remember the announcement, the 1 million token context window, and my first reaction was there’s no way they were able to achieve this.
  • I wanted to test its technical skills, so I uploaded a line chart.
  • It was temperatures between like Tokyo and Berlin and how they were across the 12 months of the year.
  • So I got in there and I threw in the Python library that was really struggling with and I just asked it a simple question. And it nailed it. It could find specific references to comments in the code and specific requests that people had made and other issues that people had had, but then suggest a fix for it that related to what I was working on.
  • I immediately tried to kind of crash it. So I took, you know, four or five research papers I had on my desktop, and it’s a mind-blowing experience when you add so much text, and then you see the kind of amount of tokens you add is not even at half the capacity.
  • It felt a little bit like Christmas because you saw things kind of peppered up to the top of your feed about, like, oh, wow, I built this thing, or oh, it’s doing this, and I would have never expected.
  • Can I shoot a video of my possessions and turn that into a searchable database? So I ran to my bookshelf, and I shot video just panning my camera along the bookshelf and I fed the video into the model. It gave me the titles and authors of the books, even though the authors weren’t visible on those book spines, and on the bookshelf there was a squirrel nut cracker sat in front of the book, truncating the title. 
  • You could just see the word “sightsee”, and it still guessed the correct book. The range of things you can do with that is almost unlimited.
  • So at that point for me was just like a click, like, this is it. I thought, like, I had like a super power in my hands.
  • It was poetry. It was beautiful. 
  • I was so happy! This is going to be amazing! This is going to help people!
  • This is kind of where the future of language models are going. Personalized to you, not because you trained it to be personal to you, but personal to you because you can give it such a vast understanding of who you are. [Applause]. 

Gemini 1.5 Pro & Gemini Advanced

  • SUNDAR PICHAI: We’ve been rolling out Gemini 1.5 Pro with long context in preview over the last few months. We’ve made a series of quality improvements across translation, coding, and reasoning. You’ll see these updates reflected in the model starting today. I’m excited to announce that we’re bringing this improved version of Gemini 1.5 Pro to all developers globally.
  • [Cheers and Applause]. In addition, today Gemini 1.5 Pro with 1 million context is now directly available for consumers in Gemini Advanced 5, and can be used across 35 languages. One million tokens is opening up entirely new possibilities. It’s exciting, but I think we can push ourselves even further. Gemini Advanced
  • So today, we are expanding the context window to 2 million Tokens. [Cheers and Applause]. We are making it available for developers in private preview. It’s amazing to look back and see just how much progress we’ve made in a few months. This represents the next step on our journey towards the ultimate goal of infinite context. 
  • Okay. So far, we’ve talked about two technical advances: multimodality and long context. Each is powerful on its own. But together, they unlock deeper capabilities, and more intelligence. Let’s see how this comes to life with Google Workspace. People are always searching their emails in Gmail.
  • We are working to make it much more powerful with Gemini. Let’s look at how. As a parent, you want to know everything that’s going on with your child’s school. Okay, maybe not everything, but you want to stay informed. Gemini can help you keep up. Now we can ask Gemini to summarize all recent emails from the school. In the background, it’s identifying relevant emails, and even analyzing attachments, like PDFs. And you get a summary of the key points and action items. So helpful. Maybe you were traveling this week and couldn’t make the PTA meeting. The recording of the meeting is an hour long. If it’s from Google Meet, you can ask Gemini to give you the highlights. [Cheers and Applause]. There’s a parents group looking for volunteers, and you’re free that day. So of course, Gemini can draft a reply. There are countless other examples of how this can make life easier.
  • Gemini 1.5 Pro is available today in Workspace Labs. Gemini 1.5 Pro - Workspace Labs
  • Aparna will share more later on. [Applause]. We just looked at an example with text outputs. 

NotebookLM - Audio Overviews

  • But with a multimodal model, we can do so much more. To show you an early demo of an audio output in NotebookLM, here’s Josh.
  • JOSH WOODWARD: Hi, everyone! Last year, at I/O, we introduced NotebookLM 6, a research and writing tool grounded in the information you give it. Since then, we’ve seen a lot of momentum with students and teachers using it. And today, Gemini 1.5 Pro is coming to NotebookLM, and it’s great. Let me show you.
  • So here we are in NotebookLM. You can load it up with all of the materials here on the left. In this notebook, I’ve been using it with my younger son, and I’ve added some of his science worksheets, a few slide decks from the teacher, and even an open source textbook full of charts and diagrams. With 1.5 Pro, it instantly creates this notebook guide with a helpful summary and can generate a study guide, an FAQ, or even quizzes. But for my son Jimmy, he really learns best when he can listen to something. So we’ve prototyped a new feature with Gemini, and it’s called Audio Overviews. NotebookLM is going to use all of the materials on the left as input and output them into a lively science discussion, personalized for him.  NotebookLM - Audio Overviews
  • Let’s take a listen.
  • So let’s dive into physics. What’s on deck for today?
  • Well, we’re starting with the basics. Force in motion.
  • Okay.
  • And that, of course, means we have to talk about Sir Isaac Newton and his three laws of motion.
  • Ah, yes, the foundation – For understanding how objects move and interact.
  • JOSH WOODWARD: Oh, yes, this is where multimodal really shines. Now, it generated this audio discussion based on that text material. And what’s amazing is that my son and I can join into the conversation. And steer it whichever direction we want. When I tap “join.”
  • Hold on. 
  • We have a question. What’s up, Josh?
  • JOSH WOODWARD: Yeah, can you give my son Jimmy a basketball example?
  • Hey, Jimmy! That’s a fantastic idea! Basketball is actually a great way to visualize force in motion. Let’s break it down.
  • Okay. So first, imagine a basketball just sitting there on the court. 
  • It’s not moving, right? That’s because all the forces acting on it are balanced. The downward pull of gravity –
  • JOSH WOODWARD: Pretty cool, right? [Cheers and Applause]. I gotta say, the first time my son heard this, you should have seen how big his eyes got! Because he was gripped. They were talking to him. 
  • He was learning science through the example of basketball. His favorite sport. Now, what’s interesting is under the hood, you saw that Gemini had used some of the concepts of gravity, Sir Isaac Newton, but nothing in there was about basketball. It connected the dots and created that age-appropriate example for him.
  • And this is what's becoming possible with the power of Gemini. You can give it lots of information in any format, and it can be transformed in a way that's personalized and interactive for you. Back to you, Sundar. [Applause].

AI Agents

  • SUNDAR PICHAI: Thanks, Josh. The demo shows the real opportunity with multimodality.
  • Soon you’ll be able to mix and match inputs and outputs. This is what we mean when we say it’s an I/O for a new generation. And I can see you all out there thinking about the possibilities. But what if we could go even further? That’s one of the opportunities we see with AI agents. Let me take a step back and explain what I mean by that.
  • I think about them as intelligent systems that show reasoning, planning, and memory. Are able to “think” multiple steps ahead, work across software and systems, all to get something done on your behalf, and most importantly, under your supervision. We are still in the early days, and you’ll see glimpses of our approach throughout the day, but let me show you the kinds of use cases we are working hard to solve. Agents
  • Let’s talk about shopping. It’s pretty fun to shop for shoes, and a lot less fun to return them when they don’t fit. Imagine if Gemini could do all the steps for you: Searching your inbox for the receipt, locating the order number from your email, filling out a return form, and even scheduling a pickup.
  • That’s much easier, right? [Applause]. Let’s take another example that’s a bit more complex. Say you just moved to Chicago. You can imagine Gemini and Chrome working together to help you do a number of things to get ready: Organizing, reasoning, synthesizing on your behalf. For example, you’ll want to explore the city and find services nearby, from dry-cleaners to dog-walkers.
  • You will have to update your new address across dozens of Web sites. Gemini can work across these tasks and will prompt you for more information when needed, so you are always in control. That part is really important. as we prototype these experiences. We are thinking hard about how to do it in a way that’s private, secure and works for everyone.
  • These are simple-use cases, but they give you a good sense of the types of problems we want to solve, by building intelligent systems that think ahead, reason, and plan, all on your behalf. The power of Gemini, with multimodality, long context and agents, brings us closer to our ultimate goal: Making AI helpful for everyone.
  • We see this as how we will make the most progress against our mission. Organizing the world’s information across every input, making it accessible via any output, and combining the world’s information with the information in your world in a way that’s truly useful for you. To fully realize the benefits of AI, we will continue to break new ground. organize world info

2️⃣ Google DeepMind

  • Google DeepMind is hard at work on this. To share more, please welcome, for the first time on the I/O stage, Sir Demis. [Applause].
  • DEMIS HASSABIS 7: Thanks, Sundar. It’s so great to be here. Ever since I was a kid, playing chess for the England Junior Team, I’ve been thinking about the nature of intelligence. Sir Demis
  • I was captivated by the idea of a computer that could think like a person. It’s ultimately why I became a programmer and studied neuroscience. I co-founded DeepMind in 2010 with the goal of one day building AGI: Artificial general intelligence, a system that has human-level cognitive capabilities. I’ve always believed that if we could build this technology responsibly, its impact would be truly profound and it could benefit humanity in incredible ways.
  • Last year, we reached a milestone on that path when we formed Google DeepMind, combining AI talent from across the company in to one super unit. Since then, we’ve built AI systems that can do an amazing range of things, from turning language and vision into action for robots, navigating complex virtual environments, involving Olympiad level math problems, and even discovering thousands of new materials. DeepMind models
  • Just last week, we announced our next generation AlphaFold 8 model. It can predict the structure and interactions of nearly all of life’s molecules, including how proteins interact with strands of DNA and RNA. This will accelerate vitally important biological and medical research from disease understanding to drug discovery. DeepMind AlphaFold 3

Gemini 1.5 Flash

  • And all of this was made possible with the best infrastructure for the AI era, including our highly optimized tensor processing units. At the center of our efforts is our Gemini model. It’s built up from the ground up to be natively multimodal because that’s how we interact with and understand the world around us. We’ve built a variety of models for different use cases. 
  • We’ve seen how powerful Gemini 1.5 Pro is, but we also know from user feedback that some applications need lower latency and a lower cost to serve. So today we’re introducing Gemini 1.5 Flash. [Cheers and Applause]. Flash is a lighter-weight model compared to Pro. It’s designed to be fast and cost-efficient to serve at scale, while still featuring multimodal reasoning capabilities and breakthrough long context.
  • Flash is optimized for tasks where low latency and efficiency matter most. Starting today, you can use 1.5 Flash and 1.5 Pro with up to one million tokens in Google AI Studio 9 and Vertex AI 10. And developers can sign up to try two million tokens. We’re so excited to see what all of you will create with it. And you’ll hear a little more about Flash later on from Josh. Gemini 1.5 Flash and Gemini 1.5 Pro with up to one million tokens in Google AI Studio and Vertex AI
  • We’re very excited by the progress we’ve made so far with our family of Gemini models. But we’re always striving to push the state-of-the-art even further. At any one time we have many different models in training. And we use our very large and powerful ones to help teach and train our production-ready models. 
  • Together with user feedback, this cutting-edge research will help us to build amazing new products for billions of people. For example, in December, we shared a glimpse into the future of how people would interact with multimodal AI, and how this would end up powering a new set of transformative experiences. 

Project Astra

  • Today, we have some exciting new progress to share about the future of AI assistants that we’re calling Project Astra 11. [Cheers and Applause]. For a long time, we’ve wanted to build a universal AI agent that can be truly helpful in everyday life. Our work making this vision a reality goes back many years.
  • It’s why we made Gemini multimodal from the very beginning. An agent like this has to understand and respond to our complex and dynamic world just like we do. It would need to take in and remember what it sees so it can understand context and take action. And it would have to be proactive, teachable and personal, so you can talk to it naturally, without lag or delay.
  • While we’ve made great strides in developing AI systems that can understand multimodal information, getting response time down to something conversational is a difficult engineering challenge. Building on our Gemini model, we’ve developed agents that can process information faster by continuously encoding video frames, combining the video and speech input into a timeline of events, and caching this for efficient recall. 
  • We’ve also enhanced how they sound, with a wider range of intonations. These agents better understand the context you’re in, and can respond quickly in conversation, making the pace and quality of interaction feel much more natural. Here’s a video of our prototype, which you’ll see has two parts.
  • Each part was captured in a single take, in real time.
  • Okay. Let’s do some tests. Tell me when you see something that makes sound.
  • I see a speaker, which makes sound.
  • What is that part of the speaker called?
  • That is the tweeter. It produces high frequency sounds.
  • Give me a creative alliteration about these.
  • Creative crayons color cheerfully. They certainly craft colorful creations.
  • What does that part of the code do?
  • This code defines encryption and decryption functions. It seems to use AES-CBC encryption to encode and decode data based on a key and an initialization vector (IV).
  • That’s right. 
  • What neighborhood do you think I’m in?
  • This appears to be the Kings Cross area of London. It is known for its railway station and transportation connections.
  • Do you remember where you saw my glasses?
  • Yes, I do. Your glasses were on the desk near a red apple. [Applause]. Cloud be Google Glasses?
  • What can I add here to make this system faster?
  • Adding a cache between the server and database could improve speed.
  • What does this remind you of?
  • Schroedinger’s cat.
  • All right. Give me a band name for thisduo.
  • Golden Stripes.
  • Nice. Thanks, Gemini. [Applause].
  • DEMIS HASSABIS: I think you’ll agree it’s amazing to see how far AI has come, especially when it comes to spatial understanding, video processing and memory. It’s easy to envisage a future where you can have an expert assistant by your side through your phone or new exciting form factors like glasses. Project Astra
  • Some of these agent capabilities will come to Google products like the Gemini app later this year. For those of you onsite today, you can try out a live demo version of this experience in the AI Sandbox area. [Cheers and Applause]. Next, let’s take a look at how our innovations are helping people bring new creative ideas to life. 
  • Today, we’re introducing a series of updates across our generative media tools with new models covering image, music and video. Over the past year, we’ve been enhancing quality, improving safety and increasing access. To help tell this story, here’s Doug. [Applause].

Generative Media - Image

  • DOUG ECK: Thanks, Demis.  Doug Eck
  • Over the past few months, we’ve been working hard to build a new image generation model from the ground up, with stronger evaluations, extensive red teaming, and state-of-the-art watermarking with SynthID. Today, I’m so excited to introduce Imagen 3. It’s our most capable image generation model yet.  gen images gen images
  • Imagen 3 is more photorealistic. You can literally count the whiskers on its snout. With richer details, like the incredible sunlight in this shot, and fewer visual artifacts or distorted images. It understands prompts written the way people write. The more creative and detailed you are, the better.  gen images
  • And Imagen 3 remembers to incorporate small details like the ‘wildflowers’ or ‘a small blue bird’ in this longer prompt. Plus, this is our best model yet for rendering text, which has been a challenge for image generation models. In side-by-side comparisons, independent evaluators preferred Imagen 3 over other popular image generation models.
  • In sum, Imagen 3 is our highest-quality image generation model so far. You can sign up today to try Imagen 3 in ImageFX, part of our suite of AI tools at 12, and it will be coming soon to developers and enterprise customers in Vertex AI.

Generative Media - Music

  • Another area, full of creative possibility, is generative music. I’ve been working in this space for over 20 years and this has by far the most exciting year of my career. gen music
  • We’re exploring ways of working with artists to expand their creativity with AI. Together with YouTube, we’ve been building Music AI Sandbox, a suite of professional music AI tools that can create new instrumental sections from scratch, transfer styles between tracks, and more. To help us design and test them, we’ve been working closely with incredible musicians, songwriters and producers.  Music AI Sandbox
  • Some of them made even entirely new songs in ways that would not have been possible without these tools. Let’s hear from some of the artists we’ve been working with.
  • I’m going to put this right back into the Music AI tool. The same Boom, boom, bam, boom, boom. What happens if Haiti meets Brazil? Dude, I have no clue what’s about to be sprat out.  Wyclef Jean
  • This is what excites me. Da da See see see. As a hip hop producer, we dug in the crates. We playin’ these vinyls, and the part where there’s no vocal, we pull it, we sample it, and we create an entire song around that. So right now we digging in the infinite crate. It’s endless. Where I found the AI really useful for me, this way to like fill in the sparser sort of elements of my loops. Okay. 
  • Let’s try bongos. We’re going to putviola. We’re going to put rhythmic clapping, and we’re going to see what happens there. Oh, and it makes it sound, ironically, at the end of the day, a little more human. So then this is entirely Google’s loops right here. These are Gloops.
  • So it’s like having, like, this weird friend that’s just like, try this, try that. And then you’re like, Oh, okay. Yeah. No, that’s pretty dope. (indistinct noises)
  • The tools are capable of speeding up the process of what’s in my head, getting it out. You’re able to move lightspeed with your creativity. This is amazing. 
  • That right there. [Applause].
  • DEMIS HASSABIS: I think this really shows what’s possible when we work with the artist community on the future of music. You can find some brand new songs from these acclaimed artists and songwriters on their YouTube channels now. new songs with AI

Generative Media - Video

  • There’s one more area I’m really excited to share with you. Our teams have made some incredible progress in generative video. Today, I’m excited to announce our newest, most capable generative video model, called Veo . [Cheers and Applause]. Veo creates high-quality, 1080P videos from text, image and video prompts. It can capture the details of your instructions in different visual and cinematic styles. Model Veo
  • You can prompt for things like aerial shots of a landscape or a time lapse, and further edit your videos using additional prompts. You can use Veo in our new experimental tool called VideoFX . We’re exploring features like storyboarding and generating longer scenes. Veo gives you unprecedented creative control. Techniques for generating static images have come a long way. 
  • But generating video is a different challenge altogether. Not only is it important to understand where an object or subject should be in space, it needs to maintain this consistency over time, just like the car in this video. Veo builds upon years of our pioneering generative video model work, including GQN, Phenaki, Walt, VideoPoet, Lumiere and much more. VideoFX
  • We combined the best of these architectures and techniques to improve consistency, quality and output resolution. To see what Veo can do, we put it in the hands of an amazing filmmaker. Let’s take a look. Veo improved
  • DONALD GLOVER: Well, I’ve been interested in AI for a couple of years now. We got in contact with some of the people at Google, and they had been working on something of their own.  Donald Glover
  • So we’re all meeting here at Gilga Farms to make a short film.
  • KORY MATHEWSON: The core technology is Google Deep Mind’s generative video model that has been trained to convert input text into output video. [Laughter]. KORY MATHEWSON
  • DONALD GLOVER: It looks good.
  • KORY MATHEWSON: We are able to bring ideas to life that were otherwise not possible. We can visualize things of time scale that’s 10 or 100 times faster than before.
  • MATTHIEU KIM LORRAIN: When you’re shooting, you can’t really iterate as much as you wish. And so we’ve been hearing the feedback that it allows for more optionality, more iteration, more improvisation. MATTHIEU KIM LORRAIN
  • DONALD GLOVER: But that’s what’s cool about it. It’s like you can make a mistake faster. That’s all you really want at the end of the day, at least in art, is just to make mistakes fast.
  • KORY MATHEWSON: So, using Gemini’s multimodal capabilities to optimize the model’s training process, Veo is better able to capture the nuance from prompts. 
  • So this includes cinematic techniques and visual effects, giving you total creative control.
  • DONALD GLOVER: Everybody's going to become a director and everybody should be a director. Because at the heart of all of this is just storytelling. The closer we are to being able to tell each other our stories, the more we will understand each other
  • KORY MATHEWSON: These models are really enabling us to be more creative and to share that creativity with each other. [Cheers and Applause].
  • DEMIS HASSABIS: Over the coming weeks some of these features will be available to select creators through VideoFX at, and the waitlist is open now. 
  • Of course, these advances in generative video go beyond the beautiful visuals you’ve seen today. By teaching future AI models how to solve problems creatively, or in effect simulate the physics of our world, we can build more useful systems that help people communicate in new ways, and thereby advance the frontiers of AI. 
  • When we first began this journey to build AI more than 15 years ago, we knew that one day it would change everything. Now that time is here. And we continue to be amazed by the progress we see and inspired by the advances still to come, on the path to AGI. Thanks, and back to you Sundar. [Applause].


Ernest Notes: This segment seems intended as a showcase of cutting-edge technologies, with many different types covering a wide range of areas. Coming off Google’s recent earnings report aimed at investors, this keynote presented an opportunity for Google to use communication language geared towards consumers and enterprise purchasing decision makers, increasing customer trust and perception of Google as a technology leader. However, from an investor’s perspective, it could also be interpreted as over-investment or premature investment, without sufficiently explaining the rationale behind it. The firepower showcase came without properly setting the context, which may have already been reflected in the stock price reaction over the past few weeks, resulting in this keynote having little impact on the stock price. For example, Sundar mentioned 200,000 miles of network infrastructure being 10 times more than the next leading cloud provider, but didn’t explain why such infrastructure deployment is needed and how it relates to customer needs and revenue. Sundar also said Google’s liquid cooling technology leads the industry by 10 years, but didn’t explain what advantages this 10-year lead created and how it ties to customer needs and revenue.

Ernest Notes: No wonder the previous summary of AWS re:Invent took five days, four sessions, and seven hours of keynote time for sufficient narrative and communication.

  • SUNDAR PICHAI: Thanks, Demis. 
  • A huge amount of innovation is happening at Google DeepMind. it’s amazing how much progress we have made in a year. Training state-of-the-art models requires a lot of computing power. Industry demand for ML compute has grown by a factor of 1 million in the last six years. And every year, it increases tenfold 13ML Compute Demand
  • Google was built for this. For 25 years, we’ve invested in world-class technical infrastructure, from the cutting-edge hardware that powers Search, to our custom tensor processing units that power our AI advances. Gemini was trained and served entirely on our fourth and fifth generation TPUs. TPU v5
  • And other leading AI companies, like Anthropic, have trained their models on TPUs as well. Today, we are excited to announce the sixth generation of TPUs called Trillium . [Cheers and Applause]. Trillium delivers a 4.7x improvement in compute performance per chip over the previous generation. So our most efficient and performant TPU to date.  Trillium TPU v6
  • We will make Trillium available to our cloud customers in late 2024. Alongside our TPUs, we are proud to offer CPUs and GPUs to support any workload. That includes the new Axion processor we announced last month, our first custom on-base CPU with industry-leading performance and energy efficiency.  Axion Processor
  • We are also proud to be one of the first cloud providers to offer Nvidia’s cutting edge Blackwell GPUs, available in early 2025. [Applause]. We’re fortunate to have a longstanding partnership with Nvidia, and are excited to bring Blackwell’s capabilities to our customers. Nvidia Blackwell

Ernest Notes: For more information about Nvidia Blackwell, you’re welcome to read my other blog post Think in Context of the keynote: Think in Context: NVIDIA GTC 2024 Keynote with NVIDIA CEO Jensen Huang

  • Chips are a foundational part of our integrated end-to-end system, from performance-optimized hardware and open software to flexible consumption models. This all comes together in our AI Hypercomputer , a groundbreaking supercomputer architecture. Businesses and developers are using it to tackle more complex challenges, with more than twice the efficiency relative to just buying the raw hardware and chips. AI Hypercomputer
  • Our AI Hypercomputer advancements are made possible in part because of our approach to liquid cooling in our data centers. We’ve been doing this for nearly a decade, long before it became state of the art for the industry. And today, our total deployed fleet capacity for liquid cooling systems is nearly 1 Giga Watt, and growing.  Liquid Cooling
  • That’s close to 70 times the capacity of any other fleet. [Applause]. Underlying this is the sheer scale of our network, which connects our infrastructure globally. Our network spans more than 2 million miles of terrestrial and subsea fiber: Over 10 times the reach of the next leading cloud provider. 
  • We will keep making the investments necessary to advance AI innovation and deliver state-of-the-art capabilities. And one of our greatest areas of investment and innovation is in our founding product, Search. 25 years ago we created Search to help people make sense of the waves of information moving online.
  • With each platform shift, we’ve delivered breakthroughs to help answer your questions better. On mobile, we unlocked new types of questions and answers, using better context, location awareness, and real-time information. With advances in natural language understanding and computer vision, we enabled new ways to search with your voice, or a hum to find your new favorite song, or an image of that flower you saw on your walk.
  • And now you can even Circle to Search those cool new shoes you might want to buy. Go for it, you can always return them later! Of course, Search in the Gemini Era will take this to a whole new level. Combining our infrastructure strengths, the latest AI capabilities, our high bar for information quality, and our decades of experience connecting you to the richness of the web. Circle to Search
  • The result is a product that does the work for you. Google Search is generative AI at the scale of human curiosity. And it’s our most exciting chapter of Search yet. To tell you more, here’s Liz. [Applause]. Google Search
  • LIZ REID 14: Thanks, Sundar! With each of these platform shifts, we haven’t just adapted, we’ve expanded what’s possible with Google Search. LIZ REID
  • And now, with generative AI, Search will do more for you than you ever imagined. So whatever’s on your mind, and whatever you need to get done, just ask. And Google will do the Googling for you. All the advancements you’ll see today are made possible by a new Gemini model, customized for Google Search.
  • What really sets this apart is our three unique strengths.
  • First, our real-time information with over a trillion facts about people, places, and things.
  • Second, our unparalleled ranking and quality systems 15, trusted for decades to get you the very best of the web.
  • And third, the power of Gemini, which unlocks new agentive capabilities, right in Search. 3 strengths of Google Search
  • By bringing these three things all together, we are able to dramatically expand what’s possible with Google Search, yet again. This is Search in the Gemini era. So let’s dig in.

AI Overviews

  • You’ve heard today about AI Overviews 16, and how helpful people are finding them. With AI Overviews, Google does the work for you. Instead of piecing together all the information yourself, you can ask your question, and as you see here, you can get an answer instantly. 
  • Complete with a range of perspectives and links to dive deeper. As Sundar shared, AI Overviews will begin rolling out to everyone in the U.S. starting today, with more countries soon. By the end of the year, AI Overviews will come to over a billion people in Google Search. But this is just the first step. AI Overviews will come to over a billion people in Google Search
  • We’re making AI Overviews even more helpful for your most complex questions, the type that are really more like ten questions in one! You can ask your entire question, with all its sub-questions, and get an AI Overview 16 in just seconds. To make this possible, we’re introducing multi-step reasoning in Google Search.
  • So Google can do the researching for you. For example, let’s say you’ve been trying to get into yoga and Pilates. Finding the right studio can take a lot of research. There are so many factors to consider! Soon you’ll be able to ask Search to: Find the best yoga or Pilates studios in Boston. And show you details on their intro offers, and walking time from Beacon Hill. 
  • As you can see here, Google gets to work for you, finding the most relevant information and bringing it together in your AI Overview. You get some studios with great ratings and their intro offers. You can see the distance for each, like this one is just a ten-minute walk away! Right below, you see where they’re located, laid out visually. 
  • And you’ve got all this from just a single search! Under the hood, our custom Gemini model acts as your AI agent, using what we call multi-step reasoning. It breaks your bigger question down into all its parts, and it figures out which problems it needs to solve and in what order. Multi-step Reasoning Multi-step Reasoning Multi-step Reasoning
  • And thanks to our real-time info and ranking expertise, it reasons using the highest-quality information out there. So since you’re asking about places, it taps into Google's index of information about the real world, with over 250 million places, and updated in real-time. Including their ratings, reviews, business hours, and more. 
  • Research that might have taken you minutes or even hours, Google can now do on your behalf in just seconds. Next, let me show you another way multi-step reasoning in Google Search can make your life that much easier. Take planning, for example. Dreaming up trips and meal plans can be fun, but doing the work of actually figuring it all out, no, thank you. 
  • With Gemini in Search, Google does the planning with you. Planning is really hard for AI to get right. It’s the type of problem that takes advanced reasoning and logic. After all, if you’re meal planning, you probably don’t want mac’n cheese for breakfast, lunch and dinner. Okay, my kids might. 
  • But say you’re looking for a bit more variety. Now, you can ask Search to: Create a three-day meal plan for a group that’s easy to prepare. And here you get a plan with a wide range of recipes from across the web. This one for overnight oats looks particularly interesting. And you can easily head over to the Web site to learn how to prepare them. 
  • If you want to get more veggies in, you can simply ask Search to swap in a vegetarian dish. And just like that, Search customizes your meal plan. And you can export your meal plan or get the ingredients as a list, just by tapping here. Looking ahead, you could imagine asking Google to add everything to your preferred shopping cart.
  • Then, we’re really cooking! These planning capabilities mean Search will be able to help plan everything from meals and trips to parties, dates, workout routines and more. So you can get all the fun of planning without any of the hassle. You’ve seen how Google Search can help with increasingly complex questions and planning. But what about all those times when you don’t know exactly what to ask and you need some help brain storming? When you come to Search for ideas, you’ll get more than an AI-generated answer.
  • You’ll get an entire AI-organized page, custom-built for you and your question. Say you’re heading to Dallas to celebrate your anniversary and you’re looking for the perfect restaurant. What you get here breaks AI out of the box and it brings it to the whole page. Our Gemini model uncovers the most interesting angles for you to explore and organizations these results into these helpful clusters. 
  • Like, you might have never considered restaurants with live music. Or ones with historic charm! Our model even uses contextual factors, like the time of year. So since it’s warm in Dallas, you can get rooftop patios as an idea. And it pulls everything together into a dynamic, whole-page experience.
  • You’ll start to see this new AI-organized search results page when you look for inspiration, starting with dining and recipes, and coming to movies, music, books, hotels, shopping, and more. [Applause]. Today, you’ve seen how you can bring any question to Search, and Google takes the work out of searching. But your questions aren’t limited to words in a text box, and sometimes, even a picture can’t tell the whole story. 
  • Earlier, Demis showed you our latest advancements in video understanding. And I’m really excited to share that soon you’ll be able to ask questions with video, right in Google Search. Let me introduce Rose to show you this in a live demo. [Applause].

Google Search Demo

  • ROSE YAO: Thank you, Liz! I have always wanted a record player, and I got this one, and some vinyls at a yard sale recently. 
  • But, umm, when I go to play a it, this thing keeps sliding off. I have no idea how to fix it or where to even start! Before, I would have pieced together a bunch of searches to try to figure this out, like, what make is this record player? What’s the model? And, what is this thing actually called? But now I can just ask with a video. So let’s try it. Google Search Demo
  • Let’s do a live demo. I’m going to take a video and ask Google, why will this not stay in place? And in a near instant, Google gives me an AI Overview. I get some reasons this might be happening, and steps I can take to troubleshoot. So it looks like first, this is called a tone arm. Very helpful.  Google Search Demo
  • And it looks like it may be unbalanced, and there’s some really helpful steps here. And I love that because I’m new to all this. I can check out this helpful link from Audio Technica to learn even more. So that was pretty quick! [Applause]. Let me walk you through what just happened.
  • Thanks to a combination of our state-of-the-art speech models, our deep visual understanding, and our custom Gemini model, Search was able to understand the question I asked out loud and break down the video frame-by-frame. Each frame was fed into Gemini’s long context window that you heard about earlier today. Search could then pinpoint the exact make and model of my record player. Google Search Demo
  • And make sense of the motion across frames to identify that the tonearm was drifting. Search fanned out and combed the web to find relevant insights from articles, forums, videos, and more. And it stitched all of this together into my AI Overview. The result was music to my ears! Back to you, Liz. [Applause]. Google Search Demo
  • LIZ REID: Everything you saw today is just a glimpse of how we’re reimagining Google Search in the Gemini era. We’re taking the very best of what makes Google, Google. All the reasons why billions of people turn to Google Search, and have relied on us for decades. And we’re bringing in the power of Gemini’s agentive capabilities. 
  • So Google will do the searching, the Researching. The planning. The brainstorming. And so much more. All you need to do, is ask. You’ll start to see these features rolling out in Search in the coming weeks. Opt in to Search Labs 17 to be among the first to try them out.
  • Now let’s take a look at how this all comes together in Google Search this year.
  • Why is the lever not moving all the way? [Applause].

3️⃣ Google Workspace

  • APARNA PAPPU 18: Since last May, we’ve been hard at work making Gemini for Workspace even more helpful for businesses and consumers across the world. Tens of thousands of customers have been using help me write, help me visualize and help me organize since we launched. And now, we’re really excited that the new Gemini powered side panel will be generally available next month. APARNA PAPPU Side Panel GA
  • [Cheers and Applause]. One of our customers is a local favorite right here in California, Sports Basement. They rolled out Gemini for Workspace to the organization. And this has helped improve the productivity of their customer support team by more than 30%. Customers love how Gemini grows participation in meetings with automatic language detection and real-time captions now expanding to 68 languages. Gemini in Meet
  • [Applause]. We are really excited about what Gemini 1.5 Pro unlocks for Workspace and AI Premium customers. Let me start by showing you three new capabilities coming to Gmail mobile. This is my Gmail account. Okay. So there’s an E-mail up top from my husband. Help me sort out the roof repair thing, please. 
  • Now, we’ve been trying to find a contractor to fix our roof, and with work travel, I have clearly dropped the ball. It looks like there’s an E-mail thread on this with lots of E-mails that I haven’t read. And luckily for me, I can simply tap the summarize option up top and skip reading this long back and forth. 
  • Now, Gemini pulls up this helpful mobile card as an overlay. And this is where I can read a nice summary of all the salient information that I need to know. So here I see that we have a quote from Jeff at Green Roofing, and he’s ready to start. Now, I know we had other bids and I don’t remember the details.
  • Previously, I would have had to do a number of searches in G-mail and then remember and compare information across different E-mails. Now, I can simply type out my question right here in the mobile card and say something like, compare my roof repair bids by price and availability. This new Q&A feature makes it so easy to get quick answers on anything in my inbox.
  • For example, when are my shoes arriving, or what time do doors open for the Knicks game, without having to first search G-mail and open an E-mail and look for the specific information in attachments and so on. Anyway, back to my roof. It looks like Gemini has found details that I got from two other contractors in completely different E-mail threads, and I have this really nicely organized summary and I can do a quick comparison.
  • So it seems like Jeff’s quote was right in the middle and he can start immediately, so Green Roofing it is. I’ll open that last E-mail from Jeff and confirm the project. And look at that. I see some suggested replies from Gemini. Now, what is really, really neat about this evolution of smart reply is that it’s contextual. Gemini understood the back-and-forth in that thread and that Jeff was ready to start.  Gmail Context
  • So offers me a few customize options based on that context. So, you know, here I see I have decline the service, suggest a new time. I’ll choose proceed and confirm time. I can even see a preview of the full reply simply by long pressing. This looks reasonable, so I’ll hit send. These new capabilities in Gemini and G-mail will start rolling out this month to labs users. Gmail Summarize
  • [Applause]. Okay. So one of the really neat things about WorkSpace apps like G-mail, Drive, Docs, Calendar, is how well they work together, and in our daily lives we often have information that flows from one app to another. Like, say, adding a calendar entry from G-mail. Or creating reminders from a spreadsheet tracker. 
  • But what if Gemini could make these journeys totally seamless? Perhaps even automate them for you entirely. Let me show you what I mean with a real life example. My sister is a self-employed photographer, and her in box is full of appointment bookings, receipts, client feedback on photos and so much more. 
  • Now, if you’re a freelancer or a small business, you really want to focus on your craft and not on bookkeeping and logistics. So let’s go to her in box and take a look. Lots of unread E-mails. Let’s click on the first one. It’s got a PDF attachment. From a hotel, there’s a receipt. 
  • And I see a suggestion in the side panel. Help me organize and track my receipts. Let’s click on this prompt. The side panel now will show me more details about what that really means, and as you can see, there’s two steps here. Step one, create a Drive folder and put this receipt and 37 others it’s found into that folder. 
  • Makes sense. Step 2, extract the relevant information from those receipts in that folder into a new spreadsheet. Now, this sounds useful. Why not? I also have the option to edit these actions or just hit okay. So let’s hit okay. Gemini will now complete the two steps described above, and this is where it gets even better. 
  • Gemini offers the option to automate this so that this particular work flow is run on all future E-mails, keeping your Drive folder and expense sheet up to date with no effort from you. [Applause]. Now, we know that creating complex spread sheets can be daunting for most people. But with this automation, Gemini does the hard work of extracting all the right information from all the files from in that folder and generates the sheet for you.  Receipt Tracker
  • So let’s take a look. Okay. It’s super well organized, and it even has a category for expense type. Now, we have this sheet. Things can get even more fun. We can ask Gemini questions. Questions like, show me where the money is spent. Gemini not only analyzes the data from the sheet, but also creates a nice visual to help me see the complete breakdown by category.
  • And you can imagine how this extends to all sorts of use cases in your in box, like travel expenses, shopping, remodeling projects, you name it. All of that information in G-mail can be put to good use and help you work, plan and play better. Now, this particular – [Applause]. I know! Category of Spend
  • This particular ability to organize your attachments in Drive and generate a sheet and do data analysis via Q&A will be rolling out to Labs users this September. 
  • And it’s just one of the many automations that we’re working on in WorkSpace. Workspace in the Gemini era will continue to unlock new ways of getting things done. We’re building advanced agentive experiences, including customizing how you use Gemini. Now, as we look to 2025 and beyond, we’re exploring entirely new ways of working with AI. AI Workflows Data Q&A
  • Now, with Gemini, you have an AI-powered assistant always at your side. But what if you could expand how you interact with AI? For example, when we work with other people, we mention them in comments and docs, so we send them E-mail. We have group chats with them, et cetera. And it’s not just how we collaborate with each other, but we each have a specific role to play in the team.  collaborate
  • And as the team works together, we build a set of collective experiences and contexts to learn from each other. We have the combined set of skills to draw from when we need help. So how could we introduce AI into this mix and build on this shared expertise? Well, here’s one way. We are prototyping a virtual Gemini powered teammate.  AI Teammate

AI Teammate

  • This teammate has an identity and a Workspace account, along with a specific role and objective. Let me bring Tony up to show you what I mean. Hey, Tony!
  • TONY VINCENT: Hi, Aparna! Hey, everyone. Okay. So let me start by showing you how we set up this virtual teammate. As you can see, the teammate has its very own account.  AI Teammate
  • And we can go ahead and give it a name. We’ll do something fun like Chip. Chip’s been given a specific And set of descriptions on how to be helpful for the team, you can see that here, and some of the jobs are to monitor and track projects, we’ve listed a few out, to organize information and provide contexts, and a few more things. 
  • Now that we’ve configured our virtual teammate, let’s go ahead and see Chip in action. To do that I’ll switch us over here to Google chat. First, when planning for an event like I/O, we have a ton of chat rooms for various purposes. Luckily for me, chip is in all of them.
  • To quickly catch up, I might ask a question like, anyone know if our I/O storyboards are approved? Because we’ve instructed Chip to track this project, Chip searches across all the conversations and knows to respond with an answer. There it is. Simple, but very helpful. Now, as the team adds Chip to more group chats, more files, more E-mail threads, Chip builds a collective memory of our work together.  Storyboard
  • Let’s look at an example. To show you I’ll switch over to a different room. How about Project Sapphire over here and here we are discussing a product release coming up and as usual, many pieces are still in flight, so I can go ahead and ask, are we on track for launch? Chip gets to work not only searching through everything it has access to, but also synthesizing what’s found and coming back with an up-to-date response. 
  • There it is. A clear time line, a nice summary and notice even in this first message here, Chip flags a potential issue the team should be aware of. Because we’re in a group space, everyone can follow along, anyone can jump in at any time, as you see someone just did.
  • Asking Chip to help create a doc to help address the issue. A task like this could take me hours, dozens of hours. Chip can get it all done in just a few minutes, sending the doc over right when it’s ready. And so much of this practical helpfulness comes from how we’ve customized Chip to our team’s needs, and how seamlessly this AI is integrated directly into where we’re already working. Back to you, Aparna.
  • APARNA PAPPU: Thank you, Tony! I can imagine a number of different types of virtual teammates configured by businesses to help them do what they need. Now, we have a lot of work to do to figure out how to bring these agentive experiences like virtual teammates into WorkSpace, including enabling third parties to make their very own versions of Chip.
  • We’re excited about where this is headed, so stay tuned. And as Gemini and its capabilities continue to evolve, we’re diligently bringing that power directly into WorkSpace to make all our users more productive and creative, both at home and at work. And now, over to Sissie to tell you more about Gemini app. [Applause]. Feature Highlights

4️⃣ Gemini App

  • SISSIE HSIAO 19: Our vision for the Gemini app is to be the most helpful, personal AI assistant by giving you direct access to Google’s latest AI models. SISSIE HSIAO
  • Gemini can help you learn, create, code, and anything else you can imagine. And over the past year, Gemini has put Google’s AI in the hands of millions of people, with experiences designed for your phone and the web. We also launched Gemini Advanced, our premium subscription for access to the latest AI innovations from Google. 
  • Today, we’ll show you how Gemini is delivering our most intelligent AI experience. Let’s start with the Gemini app, which is redefining how we interact with AI. It’s natively multimodal, so you can use text, voice or your phone’s camera to express yourself naturally. And this summer, you can have an in-depth conversation with Gemini using your voice. Gemini app
  • We’re calling this new experience “Live”. Using Google’s latest speech models, Gemini can better understand you and answer naturally. You can even interrupt while Gemini is responding, and it will adapt to your speech patterns. And this is just the beginning. We’re excited to bring the speed games and video understanding capabilities from Project Astra to the Gemini app. Gemini Live
  • When you go live, you’ll be able to open your camera so Gemini can see what you see and respond to your surroundings in real-time. Now, the way I use Gemini isn’t the way you use Gemini. So we’re rolling out a new feature that lets you customize it for your own needs. And create personal experts on any topic you want. We’re calling these “Gems.” [Applause]. Gems - Personal Experts
  • They’re really simple to set up. Just tap to create a gem, write your instructions once, and come back whenever you need it. For example, here’s a gem that I created that acts as a personal writing coach. It specializes in short stories with mysterious twists, and it even builds on the story drafts in my Google drive.  Gems - Personal Experts Gems - Personal Experts Gems - Personal Experts
  • I call it the cliff hanger curator. Now, gems are a great time saver when you have specific ways that you want to interact with Gemini again and again. Gems will roll out in the coming months, and our trusted testers are already finding so many creative ways to put them to use.
  • They can act as your yoga bestie, your personal sous chef, a brainy calculus tutor, a peer reviewer for your code, and so much more. Next, I’ll show you how Gemini is taking a step closer to being a true AI assistant by planning and taking action for you. We all know chatbots can give you ideas for your next vacation. Gems - Personal Experts

Miami Tour

  • But there’s a lot more that goes into planning a great trip. It requires reasoning that considers space-time logistics, and the intelligence to prioritize and make decisions. That reasoning and intelligence all comes together in the new trip planning experience in Gemini Advanced. Now, it all starts with a prompt. Okay. So here we go. 
  • We’re going to Miami. My son loves art, my husband loves seafood, and our flight and hotel details are already in my Gmail inbox. Now there’s a lot going on in that prompt. Everyone has their own things that they want to do. To make sense of those variables, Gemini starts by gathering all kinds of information from Search, and helpful extensions like Maps and G-mail. Miami Tour Miami Tour Keywords Miami Tour Keywords Relationship

Ernest Notes: Although this story is set in Miami, I noticed the dish Ceviche in the scene. You can also enjoy it at places like LUNA Mexican Kitchen in the Bay Area, California. <3

  • It uses that data to create a dynamic graph of possible travel options, taking into account all my priorities and constraints. The end result is a personalized vacation plan, presented in Gemini’s new dynamic UI. Now, based on my flight information, Gemini knows that I need a two and a half day itinerary. And you can see how Gemini uses spatial data to make decisions.  Miami Tour Plan
  • Our flight lands in the late afternoon, so Gemini skips a big activity that day, and finds a highly rated seafood restaurant close to our hotel. Now, on Sunday, we have a jam-packed day. I like these recommendations, but my family likes to sleep in. So I tap to change the start time, and just like that, Gemini adjusted my itinerary for the rest of the trip. Miami Tour Plan
  • It moved our walking tour to the next day and added lunch options near the street art museum to make the most of our Sunday afternoon. This looks great! It would have taken me hours of work, checking multiple sources, figuring out schedules, and Gemini did this in a fraction of the time. This new trip-planning experience will be rolling out to Gemini Advanced this summer, just in time to help you plan your own Labor Day weekend. [Applause]. 

Gemini Advanced

  • All right. We saved the best for last. You heard Sundar say earlier that starting today, Gemini Advanced subscribers get access to Gemini 1.5 Pro, with one million tokens. That is the longest context window of any chatbot in the world. [Cheers and Applause]. It unlocks incredible new potential in AI, so you can tackle complex problems that were previously unimaginable. Model Tokens longest context window
  • You can upload a PDF up to 1,500 pages long, or multiple files to get insights across a project. And soon, you can upload as much as 30,000 lines of code or even an hour-long video. Gemini Advanced is the only chatbot that lets you process this amount of information. Now, just imagine how useful this will be for students.
  • Let’s say you’ve spent months on your thesis, and you could really use a fresh perspective. You can upload your entire thesis, your sources, notes, your research, and soon interview, audio recordings and videos, too. so Gemini has all this context to give you actionable advice. It can dissect your main points, identify improvements, and even role play as your professor. multi inputs
  • So you can feel confident in your work. And check out what Gemini Advanced can do with your spreadsheets, with the new data analysis feature launching in the coming weeks. Maybe you have a side hustle selling handcrafted products. But you’re a better artist than accountant, and it’s really hard to understand which products are worth your time.
  • Simply upload all of your spreadsheets and ask Gemini to visualize your earnings and help you understand your profit. Gemini goes to work calculating your returns and pulling its analysis together into a single chart, so you can easily understand which products are really paying off. Now, behind the scenes, Gemini writes custom Python code to crunch these numbers. analysis profit
  • And of course, your files are not used to train our models. Oh, and just one more thing. Later this year, we'll be doubling the long context window to 2 million tokens. [Cheers and Applause]. We absolutely can’t wait for you to try all of this for yourself. Gemini is continuing to evolve and improve at a breakthrough pace.  2M tokens
  • We’re making Gemini more multimodal, more agentive, and more intelligent, with the capacity to process the most information of any chatbot in the world. And as you heard earlier, we’re also expanding Gemini Advanced to over 35 supported languages, available today.. [Applause].
  • But, of course, what makes Gemini so compelling is how easy it is to do just about anything you want, with a simple prompt. Let’s take a look.
  • Enter prompt here. Okay. Can’t be that hard. How about generate an image of a cat playing guitar? Is that how it works? Am I doing AI? Yeah.
  • Just does whatever you type What are last minute gift ideas you can make with arts and crafts? Plan a workout routine to get bigger calves. Help me think of titles to my tell-all memoir. What’s something smart I can say about Renoir? Generate another image of a cat playing guitar. If a girl calls me a snack, how do I reply? Yeah, that’s how it works. 
  • you’re doing AI. Make this email sound more professional before I hit send. What’s a good excuse to cancel dinner with my friends? We’re literally sitting right here. There’s no wrong way to prompt. Yeah, you’re doing AI. There’s no wrong way to prompt. It does whatever you type.
  • Just prompt your prompt in the prompt bar. Or just generate an image of a cat playing guitar. You know it can do other stuff, right? [Applause].

5️⃣ Android

  • SAMEER SAMAT 20: Hi, everyone. It’s great to be back at Google I/O. Today, you’ve seen how AI is transforming our products across Gemini, Search, Workspace and more. SAMEER SAMAT
  • We’re bringing all of these innovations right onto your Android phone. And we’re going even further, to make Android the best place to experience Google AI. This new era of AI is a profound opportunity to make smartphones truly smart. Our phones have come a long way in a short time, but if you think about it, it’s been years since the user experience has fundamentally transformed. Android
  • This is a once-in-a-generation moment to reinvent what phones can do. So we’ve embarked on a multi-year journey to reimagine Android, with AI at the core. And it starts with three breakthroughs you’ll see this year. AI at the core
  • First, we’re putting AI-powered search right at your fingertips, creating entirely new ways to get the answers you need. 
  • Second, Gemini is becoming your new AI assistant on Android, there to help you any time.
  • And third, we’re harnessing on-device AI to unlock new experiences that work as fast as you do, while keeping your sensitive data private.
  • Let’s start with AI-powered search. Earlier this year, we took an important first step at Samsung Unpacked, by introducing Circle to Search
  • It brings the best of Search directly into the user experience. So you can go deeper on anything you see on your phone, without switching apps. Fashionistas are finding the perfect shoes, home chefs are discovering new ingredients, and with our latest update, it’s never been easier to translate whatever’s on your screen, like a social post in another language. 
  • And there are even more ways Circle to Search can help. One thing we’ve heard from students is that they are doing more of their schoolwork directly on their phones and tablets. So, we thought: Could Circle to Search be your perfect study buddy? Let’s say my son needs help with a tricky physics word problem, like this one.
  • My first thought is, oh boy, it’s been a while since I’ve thought about kinematics. If he’s stumped on this question, instead of putting me on the spot, he can circle the exact part he’s stuck on and get step-by-step instructions. Right where he’s already doing the work. Ah, of course, final velocity equals initial velocity plus acceleration times elapsed time. 
  • Right. I was just about to say that. Seriously, though, I love that it shows how to solve the problem, not just the answer. This new capability is available today! And later this year, Circle to Search will be able to tackle more complex problems involving symbolic formulas, diagrams, graphs and more.  Circle to Search
  • Circle to Search is only on Android. It’s available on more than 100 million devices today, and we’re on track to double that by the end of the year. [Cheers and Applause]. Circle to Search
  • You’ve already heard from Sissie about the incredible updates coming to the Gemini app. On Android, Gemini is so much more. It’s becoming a foundational part of the Android experience.  UI, Gemini, Hardware
  • Here’s Dave to share more. [Applause].

Demo: Gemini on Android

  • DAVE BURKE 21: Hey, everyone. A couple months ago we launched Gemini on Android. Like Circle to Search, Gemini works at the system level. So instead of going to a separate app, I can bring Gemini right to what I’m doing. Now, we’re making Gemini context aware, so it can anticipate what you’re trying to do and provide more helpful situations in the moment.
  • In other words, to be a more helpful assistant. So let me show you how this works. And I’ve got my shiny new Pixel 8a here to help me. [Applause]. So my friend Pete is asking me if I want to play pickleball this weekend. And I know how to play tennis, sort of. I have to say that for the demo. pickleball
  • But I’m new to this pickleball thing, so I’m to reply and try to be funny and say is that like tennis but with pickles? This would be actually a lot funnier with a meme, so let me bring up Gemini to help with that, and I’ll say create image of tennis with pickles. Now, one new thing you’ll notice is that the Gemini window hovers in place above the app so that I stay in the flow. Okay.  pickleball
  • So I generated some pretty good images. What’s nice is I can drag and drop any of these directly into the images below. So cool, let me send that. [Applause]. All right. So Pete’s typing, and he says – he’s sending me a video on how to play pickleball. All right. Thanks, Pete. Let’s tap on that.
  • And that launches YouTube but, you know, I only have one or two burning questions about the game. I could bring up Gemini to help with that, and because it’s context-aware, Gemini knows I’m looking at a video, so it proactively shows me an ask this video chip. So let me tap on that. And now, I can ask specific questions about the video.  pickleball
  • So, for example, what is the 2 bounce rule? Because that’s something that I’ve heard about but don’t quite understand in the game. By the way, this uses signals like YouTube’s captions, which means you can use it on billions of videos. So give it a moment, and, there. I get a nice,succinct answer. 
  • The ball must bounce once on each side of the court after a serve. Okay. Cool. Let me go back to messages and Pete’s followed up, and he says, you’re an engineer, so here’s the official rule book for pickleball. Thanks, Pete. Pete is very helpful, by the way. Okay. So we tap on that. 
  • It launches a PDF, now, that’s an 84-page PDF. I don’t know how much time Pete thinks I have. Anyway, us engineers, as you all know, like to work smarter, not harder, so instead of trolling through this entire document, I can pull up Gemini to help. And again, Gemini anticipates what I need, and offers me an ask this PDF option. 
  • So if I tap on that, Gemini now ingests all of the rules to become a pickleball expert, and that means I can ask very esoteric questions, like, for example, are spin serves allowed? And let’s hit that, because I’ve heard that rule may be changing. Now, because I’m a Gemini Advanced user, this works on any PDF and takes full advantage of the long context window and there’s just lots of times where that’s useful. 
  • For example, let’s say you’re looking for a quick answer in an appliance user manual. And there you have it. It turns out, no, spin serves are not allowed. So Gemini not only gives me a clear answer to my question, it also shows me exactly where in the PDF to learn more. Awesome. Okay.
  • So that’s a few of the ways that we’re enhancing Gemini to be more context aware and helpful in the moment. And what you’ve seen here are the first of really many new ways that Gemini will unlock new experiences at the system level, and they're only available on Android. You’ll see these, and more, coming to hundreds of millions of devices over the next couple of months. Only on Android
  • Now, building Google AI directly into the OS elevates the entire smartphone experience. Android is the first mobile operating system to include a built-in, on-device foundation model. This lets us bring Gemini goodness from the data center right into your pocket. So the experience is faster, while also protecting your privacy.
  • Starting with Pixel later this year, we’ll be expanding what’s possible with our latest model, Gemini Nano with Multimodality. This means your phone can understand the world the way you understand it. So not just through text input, but also through sights, sounds, and spoken language. Gemini Nano
  • Let me give you an example. 2.2 billion people experience blindness or low vision. So several years ago, we developed TalkBack, an accessibility feature that helps people navigate their phone through touch and spoken feedback. Helping with images is especially important. In fact, my colleague Karo, who uses TalkBack, will typically come across 90 unlabeled images per day. 
  • Thankfully, TalkBack makes them accessible, and now we’re taking that to the next level with the multimodal capabilities of Gemini Nano. So when someone sends Karo a photo, she’ll get a richer and clearer description of what’s happening. Or, let’s say Karo is shopping online for an outfit.
  • Now she can get a crystal clear description of the style and cut to find the perfect look. Running Gemini Nano on-device helps minimize latency, and the model even works when there’s no network connection. These improvements to TalkBack are coming later this year. Let me show you another example of what on-device AI can unlock. 
  • People lost more than one trillion dollars to fraud last year. And as scams continue to evolve across texts, phone calls, and even videos, Android can help protect you from the bad guys, no matter how they try to reach you. So let’s say I get rudely interrupted by an unknown caller right in the middle of my presentation. [Phone ringing]. 
  • Hello!
  • Hi. I’m calling from Save More Bank Security Department. Am I speaking to Dave?
  • DAVE BURKE: Yes, this is Dave. I’m kinda in the middle of something.
  • We’ve detected some suspicious activity on your account. It appears someone is trying to make unauthorized charges.
  • DAVE BURKE: Oh, yeah? What kind of charges?
  • I can’t give you specifics over the phone, but to protect your account, I’m going to help you transfer your money to a secure account we’ve set up for you. [Laughter].
  • DAVE BURKE: And look at this, my phone gives me a warning that this call might be a scam! [Applause].
  • Gemini Nano alerts me the second it detects suspicious activity, like a bank asking me to move my money to keep it safe. And everything happens right on my phone, so the audio processing stays completely private to me and on my device. We’re currently testing this feature, and we’ll have more updates to share later in the summer. Scam Detect
  • And we’re really just scratching the surface on the kinds of fast, private experiences that on-device AI unlocks. Later this year, Gemini will be able to more deeply understand the content of your screen, without any information leaving your phone, thanks to the on-device model. So, remember that pickleball example earlier? Gemini on Android will be able to automatically understand the conversation and provide relevant suggestions, like where to find pickleball clubs near me. 
  • And this is a powerful concept that will work across many apps on your phone. In fact, later today at the developer keynote, you’ll hear about how we’re empowering our developer community with our latest AI models and tools like Gemini Nano and Gemini in Android Studio.
  • Also, stay tuned tomorrow for our upcoming Android 15 updates, which we can’t wait to share. As we said at the outset, we’re reimagining Android with Gemini at the core. From your favorite apps, to the OS itself, we’re bringing the power of AI to every aspect of the smartphone experience. And with that, let me hand over to Josh to share more on our latest news for developers. 

6️⃣ Developer Updates

Gemini & AI Studio

  • Thank you. [Applause]. Transition
  • JOSH WOODWARD 22: It’s amazing to see Gemini Nano do all of that directly on Android. That was our plan all along, to create a natively multimodal Gemini in a range of sizes so you all, as developers, can choose the one that works best for you. Throughout the morning, you’ve heard a lot about our Gemini 1.
  • 5 series, and is I want to talk about the two models you can access today. 1.5 Pro, which is getting a series of quality improvements that go out, right about now, and the brand new 1.5 Flash. Both are available globally in over 200 countries and territories. [Cheers and Applause].
  • You can go over to AI Studio or Vertex AI if you’re a Google cloud customer and you can give them a try. Now, both models are also natively multimodal. That means you can interleave text, images, audio, video as inputs, and pack that massive 1 million token context window. And if you go to today, you can sign up to try the 2 million token context window for 1.5 Pro.
  • We’re also adding a bunch of new developer features, starting with video frame extraction. That’s going to be in the Gemini API, parallel function calling, so you can return more than one function call at a time, and my favorite, context caching, so you can send all of your files to the model once and not have to re-send them over and over again.  Gemini 1.5 New API Features
  • That should make the long context even more useful, and more affordable. It ships next month. [Applause]. Now, we’re using Google’s infrastructure to serve these models, so developers like all of you can get great prices. 1.5 Pro is $7 per 1 million tokens, and I’m excited to share that for prompts up to 128K, it will be 50% less, for $3.50. 
  • And 1.5 flash will start at .35 cents for 1 million tokens. [Cheers and Applause]. Now, one thing you might be wondering is which model is best for your use case? Here’s how I think about it. We use 1.5 Pro for complex tasks, where you really want the highest quality response, and it’s okay if it takes a little bit longer to come back.  Gemini 1.5 Flash
  • We’re using 1.5 Flash for quick tasks, where the speed of the model is what matters the most. And as a developer, you can go try them both out today and see what works best for you. Now, I’m going to show you how it works here in AI Studio, the fastest way to build with Gemini. And we’ll pull it up here, and you can see this is AI studio.  Gemini Comparison
  • It’s free to use. You don’t have to configure anything to get going. You just go to, log in with your Google account, and you can just pick the model here on the right that works best for you. So one of the ways we’ve been using 1.5 Flash is to actually learn from customer feedback about some of our labs products.  Google AI Studio
  • Flash makes this possible with its low latency. So what we did here is we just took a bunch of different feedback from our customer forums. You can put it in to Flash, load up a prompt, and hit run. Now, in the background, what it’s going to do is it’s going to go through that 93,000 token pile of information and you can see here start streaming it back.
  • Now, this is really helpful because it pulls out the themes for us. It gives us all the right places where we can start to look. We can see this is from some of the benefits from NotebookLM, like we showed earlier. Now, what’s great about this is that you can take something like this in AI Studio, prototyped here in ten seconds, and with one click in the upper left, get an API key, or over here in the upper right, just tap get code, and you’ve got all the model configurations, the safety settings, ready to go, straight into your IDE. 
  • Now, over time, if you find that you need more enterprise-grade features you can use the same Gemini 1.5 models and the same configurations right in Vertex AI . That way, you can scale up with Google Cloud as your enterprise needs grow. So that’s our newly updated Gemini 1.5 Pro and the new 1.5 Flash, both of which are available today globally, and you’ll hear a lot more about them in the developer keynote later today. [Applause]. Google AI Studio


  • Now, let’s shift gears and talk about Gemma, our family of open models, which are crucial for driving AI innovation and responsibility. Gemma is being built from the same research and technology as Gemini. Gemma - Open Model
  • It offers top performance and comes in light weight 7b and 2b sizes. Since it launched less than three months ago, it’s been downloaded millions of times across all the major model hubs. Developers and researchers have been using it and customizing the base Gemma model and using some of our pre-trained variants, like RecurrentGemma, and CodeGemma, and today’s newest member, PaliGemma, our first vision-language model, and it’s available right now. Gemma - Open Model
  • [Applause]. It’s optimized for a range of image captioning, visual Q&A and other image labeling tasks, so go give it a try. I’m also excited to announce that we have Gemma 2 coming. It’s the next generation of Gemma, and it will be available in June. One of the top requests we’ve heard from developers is for a bigger Gemma model, but it’s still going to fit in the size that’s easy for all of you to use. 
  • So in a few weeks, we’ll be adding a new 27 billion parameter model to Gemma 2, and here’s what’s great about it. This size is optimized by Nvidia to run on next-gen GPUs and can run efficiently on a single TPU host in Vertex AI . So this quality to size ratio is amazing because it will outperform models more than twice its size. 
  • We can’t wait to see what you’re going to build with it. [Applause]. To wrap up, I want to share this inspiring story from India, where developers have been using Gemma and its unique tokenization to create Navrasa, a set of instruction-tuned models to expand access to 15 Indic languages.
  • This builds on our efforts to make information accessible in more than 7,000 languages and the world. Take a look.
  • AASHI: Language is an interesting problem to solve, actually, and given India has a huge variety of languages and it changes every five kilometers.
  • HARSH: When technology is developed for a particular culture, it won’t be able to solve and understand the nuances of a country like India. 
  • One of Gemma’s features is an incredibly powerful tokenizer which enables the model to use hundreds of thousands of words, symbols, and characters across so many alphabets and language systems. This large vocabulary is critical to adapting Gemma to power projects like Navarasa.
  • RAMSRI: Navarasa is a model that’s trained for Indic languages. It’s a fine-tuned model based on Google’s Gemma. We built Navarasa to make large language models culturally rooted where people can talk in their native language and get the responses in their native language. Our biggest dream is to build a model to include everyone from all corners of India.
  • GAURAV: We need a technology that will harness AI so that everyone can use it and no one is left behind.
  • HARSH: Today the language that you speak in could be the tool and the technology that you use for solving your real-world problems. And that’s the power of generative AI that we want to bring to every corner of India and the entire world.
  • [Applause]. [Cheers and Applause].

7️⃣ Responsible AI

  • JAMES MANYIKA 23: Listening to everything that’s been announced today, it’s clear that AI is already helping people, from their everyday tasks to their most ambitious, productive, and imaginative endeavors. Our AI innovations, like multimodality, long context and agents, are at the cutting-edge of what this technology can do, taking to a whole new level its capacity to help people.  James Manyika
  • Yet, as with any emerging technology, there are still risks and new questions that will arise as AI advances and its uses evolve. In navigating these complexities, we are guided by our AI Principles, and we’re learning from our users, partners, and our own research. To us, building AI responsibly means both addressing the risks and maximizing the benefits for people and society. 
  • Let me begin with what we’re doing to address risks. Here, I want to focus on how we are improving our models and protecting against their misuse. Beyond what Demis shared earlier, we are improving our models with an industry-standard practice called red-teaming, in which we test our own models and try to break them to identify weaknesses. AI Principles
  • Adding to this work, we’re developing a cutting-edge technique we call AI-assisted red teaming. This draws on Google DeepMind’s gaming breakthroughs like AlphaGo, where we train AI agents to compete against each other and improve and expand the scope of their red teaming capabilities. We are developing AI models with these capabilities to help address adversarial prompting and limit problematic outputs. 
  • We’re also improving our models with feedback from two important groups: Thousands of internal safety experts with a range of disciplines, and a range of independent experts from academia to civil society. Both groups help us identify emerging risks, from cybersecurity threats to potentially dangerous capabilities in areas like Chem-Bio. 
  • Combining human insight with our safety testing methods will help make our models and products more accurate, reliable and safer. This is particularly important as technical advances like better intonation make interactions with AI feel and sound more human-like. We’re doing a lot of research in this area, including the potential for harm and misuse. 
  • We’re also developing new tools to help prevent the misuse of our models. For example, Imagen 3 and Veo create more realistic imagery and videos, we must also consider how they might be misused to spread misinformation. To help, last year we introduced SynthID, a tool that adds imperceptible watermarks to our AI-generated images and audio so that they’re easier to identify.
  • Today, we’re expanding SynthID to two new modalities: Text and video. These launches build on our efforts to deploy state-of-the-art watermarking capabilities across modalities. Moving forward, we will keep integrating advances like watermarking and other emerging techniques, to secure our latest generations of Gemini, Imagine, Lyria, and Veo models.  SynthID SynthID
  • We’re also committed to working with the ecosystem with all of you to help others build on the advances we’re making. And in the coming months, we’ll be open-sourcing SynthID text watermarking. This will be available in our updated Responsible Generative AI Toolkit, which we created to make it easier for developers to build AI responsibly. 
  • We’re also collaborating on C2PA, and we support C2PA, collaborating with Adobe, Microsoft, startups, and many others, to build and implement a standard that improves the transparency of digital media. Now, let’s turn to the second and equally important part of our responsible AI approach: How we’re building AI to benefit people and society. 
  • Today, our AI advances are helping to solve real-world problems, like accelerating the work of 1.8 million scientists in 190 countries who are using AlphaFold to work on issues like neglected diseases. Helping to predict floods in more than 80 countries. And helping organizations, like the United Nations track progress on the world’s 17 sustainable development goals with Data Commons.
  • And now, generative AI is unlocking new ways for us to make the world’s information, and knowledge, universally accessible and useful for learning. Billions of people already use Google products to learn every day, and generative AI is opening up new possibilities, allowing us to ask questions like, what if everyone everywhere could have their own personal AI tutor, on any topic? Or, what if every educator could have their own assistant in the classroom? Today marks a new chapter for learning and education at Google. I am excited to introduce LearnLM, our new family of models, based on Gemini, and fine-tuned for learning. LearnLM is grounded in educational research, making learning experiences more personal and engaging. And it’s coming to the products you use every day. Like Search, Android, Gemini and YouTube. In fact, you’ve already seen LearnLM on stage today when it helped Sameer with his son’s homework on Android. LearnLM
  • Now, let’s see how it works in the Gemini app. Earlier, Sissie introduced Gems, custom versions of Gemini that can act as personal assistive experts on any topic. We are developing some pre-made Gems, which will be available in the Gemini app and web experience, including one called Learning Coach. With Learning Coach, you can get step-by-step study guidance, along with helpful practice and memory techniques, designed to build understanding rather than just give you the answer. 
  • Let’s say you’re a college student studying for an upcoming biology exam. If you need a tip to remember the formula for photosynthesis, Learning Coach can help. Learning Coach, along with other pre-made gems, will launch in Gemini in the coming months. And you can imagine what features like Gemini Live can unlock for learning. 
  • Another example is a new feature in YouTube that uses LearnLM to make educational videos more interactive, allowing you to ask a clarifying question, get a helpful explanation, or take a quiz. This even works for those long lectures or seminars, thanks to Gemini model’s long context capabilities. 
  • This feature in YouTube is already rolling out to select Android users. As we work to extend LearnLM beyond our own products, we are partnering with experts and institutions like Columbia Teachers College, Arizona State University and Khan Academy to test and improve the new capabilities in our models for learning. 
  • And we’ve collaborated with MIT RAISE to develop an online course to help educators better understand and use generative AI. We’re also working directly with educators to build more helpful generative AI tools with Learn LM. For example, in Google Classroom, we’re drawing on the advances you’ve heard about today to develop new ways to simplify and improve lesson planning, and enable teachers to tailor lessons and content to meet the individual needs of their students.  MIT RAISE
  • Standing here today makes me think back to my own time as an undergraduate. Then, AI was considered speculative, far from any real world uses. Today, we can see how much is already real, how much it is already helping people, from their everyday tasks to their most ambitious, productive and imaginative endeavors, and how much more is still to come. This is what motivates us. 
  • I’m excited about what’s ahead and what we’ll build with all of you. Back to you, Sundar. [Applause].


  • SUNDAR PICHAI: Thanks, James. All of this shows the important progress we’ve made, as we take a bold and responsible approach to making AI helpful for everyone. Before we wrap, I have a feeling that someone out there might be counting how many times we’ve mentioned AI today.  Makeing AI helpful for everyone
  • [Laughter]. And since a big theme today has been letting Google do the work for you, we went ahead and counted, so that you don’t have to. [Cheers and Applause]. That might be a record in how many times someone has said AI. I’m tempted to say it a few more times. But I won’t. Anyhow, this tally is more than just a punchline. 
  • It reflects something much deeper. We’ve been AI-first in our approach for a long time. Our decades of research leadership have pioneered many of the modern breakthroughs that power AI progress, for us and for the industry. On top of that, we have world-leading infrastructure built for the AI Era, cutting-edge innovation in Search, now powered by Gemini, products that help at extraordinary scale, including fifteen products with over half a billion users, and platforms that enable everyone, partners, customers, creators, and all of you, to invent the future. This progress is only possible because of our incredible developer community. You are making it real, through the experiences you build every day. So, to everyone here in Shoreline and the millions more watching around the world, here’s to the possibilities ahead and creating them together. Thank you. Wrap Up Wrap Up Wrap Up Wrap Up Wrap Up SUNDAR PICHAI
  • [Cheers and Applause].
  • What does this remind you of?
  • Cat.
  • Wow.
  • Wow!
  • Okay!
  • When all of these tools come together, it’s a powerful combination.
  • It’s amazing.
  • It’s amazing. It’s an entire suite of different kinds of possibilities.
  • Hi. 
  • I’m Gemini.
  • What neighborhood do you think I’m in?
  • This appears to be the Kings Cross area of London.
  • Together we’re creating a new era.


  1. Shoreline Amphitheatre - Wikipedia ↩︎

  2. The Eras Tour is the ongoing sixth concert tour by the American singer-songwriter Taylor Swift. The Eras Tour - Wikipedia ↩︎

  3. Think in Context: AWS re:Invent 2020 Andy Jassy Keynote ↩︎

  4. The Cheesecake Factory - Wikipedia ↩︎

  5. Gemini Advanced - get access to Google’s most capable AI model ↩︎

  6. NotebookLM: How to try Google’s experimental AI-first notebook ↩︎

  7. Demis Hassabis, CEO of DeepMind Technologies. Demis Hassabis - Wikipedia ↩︎

  8. Think in Context: NVIDIA GTC 2024 Keynote with NVIDIA CEO Jensen Huang ↩︎

  9. Google AI Studio  |  Google AI for Developers  |  Google for Developers ↩︎

  10. Vertex AI with Gemini 1.5 Pro and Gemini 1.5 Flash | Google Cloud ↩︎

  11. Project Astra - Google DeepMind ↩︎

  12. LABS.GOOGLE ↩︎

  13. Think in Context: NVIDIA GTC 2024 Keynote with NVIDIA CEO Jensen Huang ↩︎

  14. VP, Head of Google Search.

    Elizabeth Reid | LinkedIn

    Google promotes Liz Reid to head of Search

    Liz Reid is the new head of Google Search - The Verge ↩︎

  15. Scoring, Ernest PKM Workflow ↩︎

  16. Sometimes there is an “s,” and sometimes there isn’t. AI Overviews? AI Overview? I’m curious about how Google internally coordinates across departments to integrate Gemini into various product lines while maintaining consistent external communication materials. ↩︎ ↩︎

  17. Try experiments in Search Labs - Android - Google Search Help ↩︎

  18. VP & GM, Google Workspace at Google ↩︎

  19. Sissie Hsiao, VP & GM, Google Assistant at Google

    Sissie is a Vice President at Google and General Manager for Google Assistant’s business unit. She is an innovator at heart, and her areas of expertise include transforming products and businesses with cutting edge application of technology and machine learning. Prior to leading the Assistant team, Sissie was responsible for building and scaling Google’s global advertising business in Apps, Video, and Display, leading a portfolio of advertiser and publisher facing products across R&D and go-to-market. Prior to Google, Sissie was a Lead Program Manager at Microsoft, launching multiple versions of Microsoft Office PowerPoint. She has a BS in Electrical Engineering and Computer Science from University of California, Berkeley, and is a passionate lifelong gamer.

    Sissie Hsiao ↩︎

  20. Sameer Samat, President, Android Ecosystem at Google. ↩︎

  21. Dave Burke, Vice President of Engineering, Android Platform ↩︎

  22. Josh Woodward, Senior Director, Product Management, Google Labs ↩︎

  23. James Manyika, SVP, Research, Technology & Society, Google. - James Manyika - Wikipedia ↩︎

Loading comments…