Google DeepMind CEO Predicts AGI by 2030, Showcases Advanced AI Projects

Watch: Google DeepMind CEO and AI Nobel winner Demis Hassabis on CBS' '60 Minutes'

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More A segment on CBS weekly in-depth TV news program 60 Minutes last night (also shared on YouTube here) offered an inside look at Google's DeepMind and the vision of its co-founder and Nobel Prize-winning CEO, legendary AI researcher Demis Hassabis. The interview traced DeepMind's rapid progress in artificial intelligence and its ambition to achieve artificial general intelligence (AGI) -- a machine intelligence with human-like versatility and superhuman scale. Hassabis described today's AI trajectory as being on an "exponential curve of improvement," fueled by growing interest, talent, and resources entering the field. Two years after a prior 60 Minutes interview heralded the chatbot era, Hassabis and DeepMind are now pursuing more capable systems designed not only to understand language, but also the physical world around them. The interview came after Google's Cloud Next 2025 conference earlier this month, in which the search giant introduced a host of new AI models and features centered around its Gemini 2.5 multimodal AI model family. Google came out of that conference appearing to have taken a lead compared to other tech companies at providing powerful AI for enterprise use cases at the most affordable price points, surpassing OpenAI. More details on Google DeepMind's 'Project Astra' One of the segment's focal points was Project Astra, DeepMind's next-generation chatbot that goes beyond text. Astra is designed to interpret the visual world in real time. In one demo, it identified paintings, inferred emotional states, and created a story around a Hopper painting with the line: "Only the flow of ideas moving onward." When asked if it was growing bored, Astra replied thoughtfully, revealing a degree of sensitivity to tone and interpersonal nuance. Product manager Bibbo Shu underscored Astra's unique design: an AI that can "see, hear, and chat about anything" -- a marked step toward embodied AI systems. Gemini: Toward actionable AI The broadcast also featured Gemini, DeepMind's AI system being trained not only to interpret the world but also to act in it -- completing tasks like booking tickets and shopping online. Hassabis said Gemini is a step toward AGI: an AI with a human-like ability to navigate and operate in complex environments. The 60 Minutes team tried out a prototype embedded in glasses, demonstrating real-time visual recognition and audio responses. Could it also hint at an upcoming return of the pioneering yet ultimately off-putting early augmented reality glasses known as Google Glass, which debuted in 2012 before being retired in 2015? While specific Gemini model versions like Gemini 2.5 Pro or Flash were not mentioned in the segment, Google's broader AI ecosystem has recently introduced those models for enterprise use, which may reflect parallel development efforts. These integrations support Google's growing ambitions in applied AI, though they fall outside the scope of what was directly covered in the interview. AGI as soon as 2030? When asked for a timeline, Hassabis projected AGI could arrive as soon as 2030, with systems that understand their environments "in very nuanced and deep ways." He suggested that such systems could be seamlessly embedded into everyday life, from wearables to home assistants. The interview also addressed the possibility of self-awareness in AI. Hassabis said current systems are not conscious, but that future models could exhibit signs of self-understanding. Still, he emphasized the philosophical and biological divide: even if machines mimic conscious behavior, they are not made of the same "squishy carbon matter" as humans. Hassabis also predicted major developments in robotics, saying breakthroughs could come in the next few years. The segment featured robots completing tasks with vague instructions -- like identifying a green block formed by mixing yellow and blue -- suggesting rising reasoning abilities in physical systems. Accomplishments and safety concerns The segment revisited DeepMind's landmark achievement with AlphaFold, the AI model that predicted the structure of over 200 million proteins. Hassabis and colleague John Jumper were awarded the 2024 Nobel Prize in Chemistry for this work. Hassabis emphasized that this advance could accelerate drug development, potentially shrinking timelines from a decade to just weeks. "I think one day maybe we can cure all disease with the help of AI," he said. Despite the optimism, Hassabis voiced clear concerns. He cited two major risks: the misuse of AI by bad actors and the growing autonomy of systems beyond human control. He emphasized the importance of building in guardrails and value systems -- teaching AI as one might teach a child. He also called for international cooperation, noting that AI's influence will touch every country and culture. "One of my big worries," he said, "is that the race for AI dominance could become a race to the bottom for safety." He stressed the need for leading players and nation-states to coordinate on ethical development and oversight. The segment ended with a meditation on the future: a world where AI tools could transform almost every human endeavor -- and eventually reshape how we think about knowledge, consciousness, and even the meaning of life. As Hassabis put it, "We need new great philosophers to come about... to understand the implications of this system."

What's next in artificial intelligence according to a tech visionary who may hold the cards to our future

Aliza Chasan is a Digital Content Producer for "60 Minutes" and CBSNews.com. She has previously written for outlets including PIX11 News, The New York Daily News, Inside Edition and DNAinfo. Aliza covers trending news, often focusing on crime and politics. Artificial general intelligence, in which computers have human-level cognitive abilities, is just five to 10 years away, Google DeepMind CEO Demis Hassabis predicted in an interview with 60 Minutes. AI is on track to understand the world in nuanced ways, to be embedded in everyday lives and to not just solve important problems, but also develop a sense of imagination as companies race to advance the technology, Hassabis said. "It's moving incredibly fast," Hassabis said. "I think we are on some kind of exponential curve of improvement. Of course, the success of the field in the last few years has attracted even more attention, more resources, more talent. So that's adding to the, to this exponential progress." Hassabis, who co-founded DeepMind, is one of the early pioneers of AI. Google acquired DeepMind in 2014. "What's always guided me and, and the passion I've always had is understanding the world around us," Hassabis said. "That's what's driven me in my career. I've always been, since I was a kid, fascinated by the biggest questions. You know, the meaning of life, the nature of consciousness, the nature of reality itself." To find answers to those questions, Hassabis studied at Cambridge, MIT and Harvard. He's a computer scientist with a doctorate in neuroscience. "I've loved reading about all the great scientists who worked on these problems and the philosophers, and I wanted to see if we could advance human knowledge," Hassabis said. "And for me, my expression of doing that was to build what I think is the ultimate tool for advancing human knowledge, which is AI." His work on AI led to a Nobel Prize. The 48-year-old British scientist had worked with colleague John Jumper to create an AI model that predicted the structure of proteins. Mapping one protein could take years.. DeepMind's AI model predicted the structure of 200 million proteins in one year. AI has progressed incredibly quickly in recent years, Hassabis said. It's challenging to keep up with the advances, even for people in the field. Part of that progress includes DeepMind's Project Astra, an AI companion of sorts that can see, hear and chat about anything known to humanity. Astra is part of a new generation of chatbots, able to interpret the world with its own "eyes." Correspondent Scott Pelley tested Astra by showing the AI app artworks selected by 60 Minutes. Astra identified the paintings and answered questions about them. The AI even created a story about "Automat" by Edward Hopper. "It's a chilly evening in the city. A Tuesday, perhaps. The woman, perhaps named Eleanor, sits alone in the diner," Astra said. "She is feeling melancholy due to the uncertainty of her future and the weight of unfulfilled dreams." Hassabis said he's often surprised by what AI systems can do and say because the programs are sent out onto the internet for months to learn for themselves, then can return with unexpected skills. "We have theories about what kinds of capabilities these systems will have. That's obviously what we try to build into the architectures," he said. "But at the end of the day, how it learns, what it picks up from the data, is part of the training of these systems. We don't program that in. It learns like a human being would learn. So new capabilities or properties can emerge from that training situation." Now Google DeepMind is training its AI model "Gemini" to act in the world, like booking tickets or ordering online. Robotics will also be part of advancing AI, leading to machines that can understand the world around them, reason through instructions and follow them to completion. "I think it will have a breakthrough moment in the next couple of years where we'll have demonstrations of maybe humanoid robots or other types of robots that can start really doing useful things," Hassabis said. None of the AI systems out there today feel self-aware or conscious in any way, Hassabis said. Self-awareness is a possibility down the line, but it's not an explicit goal for Hassabis. "My advice would be to build intelligent tools first and then use them to help us advance neuroscience before we cross the threshold of thinking about things like self-awareness," he said. Hassabis also says AI is lacking in imagination. "I think that's getting at the idea of what's still missing from these systems," Hassabis said. "They're still the kind of, you can still think of them as the average of all the human knowledge that's out there. That's what they've learned on. They still can't really yet go beyond asking a new novel question or a new novel conjecture or coming up with a new hypothesis that has not been thought of before." While the technology rapidly develops, Hassabis sees the potential for enormous benefits. With the help of AI, Hassabis said he believes the end of disease could be within reach in the next decade. Hassabis has AI blazing through solutions to drug development. "So on average, it takes, you know, 10 years and billions of dollars to design just one drug," Hassabis said. "We can maybe reduce that down from years to maybe months or maybe even weeks." He also believes AI could lead to "radical abundance," the elimination of scarcity. Hassabis also feels AI needs guardrails- safety limits built into the system. One of his main fears is that bad actors may use AI for harmful ends, something that's already happening with some AI systems. Another concern is ensuring control of AI as the systems become more autonomous and more powerful. As technology companies compete for AI dominance, there's also a concern that safety may not be a priority. Making sure safety limits are built into AI requires leading players and countries to coordinate, he said. AI systems can also, Hassabis believes, be taught morality. "They learn by demonstration. They learn by teaching," Hassabis said. "And I think that's one of the things we have to do with these systems, is to give them a value system and a guidance, and some guardrails around that, much in the way that you would teach a child."

Google DeepMind CEO demonstrates Genie 2, world-building AI model that could train robots

This week, 60 Minutes correspondent Scott Pelley reported on a massive leap forward in artificial intelligence technology led by Google DeepMind, the company's AI research hub. Pelley took Astra, Google DeepMind's AI assistant that can see and hear with cameras and microphones, for a test drive on the streets of London, near DeepMind's headquarters in the United Kingdom. "What can you tell me about this building I'm looking at?" he asked, wearing a pair of black glasses equipped with Astra, microphones, and a camera. "This is the Coal Drops Yard, a shopping and dining district," the AI agent replied. In a gallery filled with artwork chosen by 60 Minutes, Pelley raised a smartphone and asked Astra what painting he was standing in front of. The AI agent recognized the painting as "Automat" by Edward Hopper. Pelley asked Astra what emotions are being expressed by the painting's subject, a woman sitting alone in a cafeteria. Astra said she "appears pensive and contemplative," and that her expression suggests "a sense of solitude." And with a little push, Astra could do even more: it created a story around the painting. "It's a chilly evening in the city. A Tuesday, perhaps. The woman, perhaps named Eleanor, sits alone in the diner, enjoying a warm cup of coffee," Astra said. "She has found herself thinking about the future, wondering if she should pursue her dreams." In an interview with Google DeepMind CEO and co-founder Demis Hassabis, Pelley asked if there were moments when an AI agent did something unexpected. "That has happened many times...since the beginning of DeepMind," he told Pelley. "[With] recent systems like Astra... being able to be that good at understanding the physical world was not something we were expecting it to be that good at that quickly." While reporting this story, 60 Minutes learned more about advancements in generative AI that produce images, video and even 3D interactive environments. Two years ago, Pelley and a 60 Minutes team saw a demo for an AI model that could produce short videos using simple text commands. After typing in a text prompt to generate a "golden retriever with wings," several images appeared on screen, showing a golden-haired puppy walking through grass with wings, the image fairly blurry and distorted. Two years later, the technology has made astounding progress. Director of product development Tom Hume showed 60 Minutes associate producer Katie Brennan a demonstration of Veo 2, a video-generating AI model. A similar prompt, but with even more text added to it, produced a photorealistic video of a golden retriever puppy with wings running through a field of grass and flowers. Sunlight shone through its birdlike wings that flapped as it ran. It looked like a live-action scene filmed with a movie camera, sharp and detailed. Hassabis and DeepMind research scientist Jack Parker-Holder showed Pelley an AI model called Genie 2. Genie 2 can create a 3D world from a single static image that can be explored by a human player or AI agent. Parker-Holder pointed to an employee's photograph on a screen: the view from the top of a waterfall in California, looking out at the horizon. "So, we prompt the model with this image, which is not game-like, and Genie converts it into a game-like world that you can then interact in," he explained. Suddenly, a video played of what looked like a first-person video game that starts at the top of the waterfall in the photograph. The avatar walked around the pool at the top of the waterfall, water droplets misting into the air. As they turned right, a landscape that wasn't in the original photograph appeared. In another example, a paper plane soared through a Western landscape. New features came into view as the plane soared ahead. "Every subsequent frame is generated by the AI," Parker-Holder explained. Hassabis and Parker-Holder told Pelley that these simulated 3D environments can also be used to train AI "agents" that can perform tasks. An image of a knight with a torch standing in front of three doorways came on the screen. The doorway on the right leads to a flight of stairs. Parker-Holder explained that they took one of their "most capable AI agents" and asked it to go up the staircase. The AI-controlled knight walked up the stairs, blue light pouring over the staircase and new walls appearing around him. "The Genie world model is creating the world around it on the fly and sort of imagining what's up there," Parker-Holder explained. Pelley asked Hassabis what the practical implication of this technology would be. "There's lots of implications for entertainment, and generating games and videos," Hassabis said. "But actually, the bigger goal... is building a world model, a model that can understand our world." Hassabis said future versions of this technology could create an infinite variety of simulated environments, where AI agents could learn new skills, perform tasks, and interact with people and objects. Hassabis said this training could also work for robots. "It's much harder to collect data in the real world, much more expensive, much slower. For example, robotics data," Hassabis explained. "You can only collect a small amount of that in the real world. But in simulated worlds, you can collect almost an unlimited amount. So, you'd learn first in simulated worlds with the robot, as a simulated robot. And then you would fine tune it at the end on a little bit of real-world data." Pelley wondered if Google's trove of geographic data, collected for Google Earth, Google Maps and Google Street View, could also be used to train AI. "That's what we're exploring at the moment actually... potentially using Street View kind of data to give real-world understanding and geographical understanding to our AI systems," Hassabis said. "On the other hand, you can imagine things like... bringing to life static images of real places, whether it's your own holiday photos or actually Street View...[and] making them interactive and 3D, so you can look around." The video above was produced by Will Croxton. It was edited by Sarah Shafer.

Artificial intelligence could end disease, lead to "radical abundance," Google DeepMind CEO Demis Hassabis says

When Demis Hassabis won the Nobel Prize last year, he celebrated by playing poker with a world champion of chess. Hassabis loves a game, which is how he became a pioneer of artificial intelligence. The 48-year-old British scientist is co-founder and CEO of Google's AI powerhouse, called DeepMind. We met two years ago when chatbots announced a new age. Now, Hassabis and others are chasing what's called artificial general intelligence -- a silicon intellect as versatile as a human but with superhuman speed and knowledge. After his Nobel and a knighthood from King Charles, we hurried back to London to see what's next from a genius who may hold the cards of our future. Demis Hassabis: What's always guided me and-- the passion I've always had is understanding the world around us. I've always been-- since I was a kid, fascinated by the biggest questions. You know, the-- meaning of-- of life, the-- nature of consciousness, the nature of reality itself. I've loved reading about all the great scientists who worked on these problems and the philosophers, and I wanted to see if we could advance human knowledge. And for me, my expression of doing that was to build what I think is the ultimate tool for advancing human knowledge, which is-- which is AI. Scott Pelley: We sat down in this room two years ago. And I wonder if AI is moving faster today than you imagined. Demis Hassabis: It's moving incredibly fast. I think we are on some kind of exponential curve of improvement. Of course, the success of the field in the last few years has attracted even more attention, more resources, more talent. So that's adding to the to this exponential progress. Scott Pelley: Exponential curve, in other words straight up? Demis Hassabis: Yep, straight up and increasing speed of progress. ...in an artificial companion that can see and hear and chat about anything. Early chatbots learned only the internet, an app called Astra also takes in the world. Scott Pelley: Do we call her she? Bibo Xu: Um, that's a good question. I'm not sure, I'm not sure we all know the answer yet... Bibo Xu, is product manager for Project Astra, an app in a new generation of chatbots that interpret the world with their own eyes. We challenged Astra with virtual paintings we chose and showed to Astra for the first time. Scott Pelley:That painting is "Automat" by Edward Hopper. Scott Pelley: The person in the painting, what emotion is she exhibiting? Astra: The subject in the painting appears pensive and contemplative, her expression suggesting a sense of solitude. Scott Pelley: Can you create a story around this picture? Astra: It's a chilly evening in the city. A Tuesday, perhaps. The woman, perhaps named Eleanor, sits alone in the diner. She is feeling melancholy due to the uncertainty of her future, and the weight of unfulfilled dreams.The scene freezes in time. Only the flow of ideas moving onward. That line, "only the flow of ideas moving onward?" I wish I'd written that. And did we hear a limit to Astra's patience? Scott Pelley: What was that fictional conversation about? Astra: Ahhh, in the story I imagined, Eleanor and her friend talked about their shared dreams and the challenges of pursuing them. Scott Pelley: Something about the way you said "Ahh" made me wonder if you were getting bored. Astra: I apologize if my tone came across that way. My aim is always to engage thoughtfully. Scott Pelley: And she said, "Well, I'm sorry if you don't like my tone." Demis Hassabis: Well, that's interesting. That's, again a challenge with these systems. As they act in the moment with the context that's around them. And that may have never been tested before. He's often surprised because AI programs are sent out on the internet to learn for themselves. They can return later with unexpected skills. Demis Hassabis: So we have theories about what kinds of capabilities these systems will have. That's obviously what we try to build into the architectures. But at the end of the day, how it learns what it picks up from the data is part of the training of these systems. We don't program that in. It learns like a human being would learn. So new capabilities or properties can emerge from that training situation. Scott Pelley: You understand how that would worry people? Demis Hassabis: Of course. It's the duality of these types of systems, that they're able to do incredible things, go beyond the things that we're able to design ourselves or understand ourselves. But, of course, the challenge is, is making sure that the knowledge databases they create we understand what's in them. Now DeepMind is training its AI model called Gemini to not just reveal the world but to act in it like booking tickets and shopping online. It's a step toward "AGI" artificial general intelligence -- with the versatility of a human mind. Scott Pelley: On track for AGI in-- Demis Hassabis: In the next five to ten years, I think. Scott Pelley: And in 2030 you will have what? Demis Hassabis: Well, we'll have a system that-- really understands everything around you in very-- nuanced and deep ways-- and are kind of embedded in your everyday life. 'Embedded' like Astra in eyeglasses. Scott Pelley: What can you tell me about this building I'm looking at? Astra: This is the Coal Drops Yard, a shopping and dining district. She sees what I see. There's a speaker in the earpiece only I can hear. Scott Pelley: What was it originally before it became shops? Astra: The Coal Drops Yard was originally a set of Victorian coal warehouses used to receive and distribute coal across London. Scott Pelley: Was coal ever a problem for the environment in London? Astra: Yes. Coal was a significant source of air pollution in London, particularly during the Industrial Revolution. It occurred to us that the only thing we contributed to this relationship--were legs -- which will also soon be engineered. Demis Hassabis: I also think another big area will be robotics. I think it will have a breakthrough moment in the next couple of years where we'll have demonstrations of maybe humanoid robots or other types of robots that can start really doing useful things. For example, researchers Alex Lee and Giulia Vezzani showed us a robot that understands what it sees... Alex Lee: Put the blocks whose color is the combination of yellow and blue into the matching color bowl. Scott Pelley: The combination of yellow and blue Scott Pelley: ...is green. And it figured that out. It's reasoning. Giulia Vezzani: Yes, definitely, yes. The toys of Demis Hassabis's childhood weren't blocks but chess pieces. At 12, he was the number two champion in the world for his age. This passion led to computer chess, video games and, finally, thinking machines. He was born to a Greek Cypriot father and Singaporean mother. Cambridge, MIT, Harvard-- he's a computer scientist with a PhD in neuroscience because, he reasoned, he had to understand the human brain first. Scott Pelley: Are you working on a system today that would be self-aware? Demis Hassabis: I don't think any of today's systems to me feel self-aware or, you know, conscious in any way. Obviously, everyone needs to make their own decisions by interacting with these chatbots. I think theoretically it's possible. Scott Pelley: But is self-awareness a goal of yours? Demis Hassabis: Not explicitly. But it may happen implicitly. These systems might acquire some feeling of self-awareness. That is possible. I think it's important for these systems to understand you, self and other. And that's probably the beginning of something like self-awareness. But, he says, if a machine becomes self-aware, we may not recognize it. Demis Hassabis: I think there's two reasons we regard each other as conscious. One is that you're exhibiting the behavior of a conscious being very similar to my behavior. But the second thing is you're running on the same substrate. We're made of the same carbon matter with our squishy brains. Now obviously with machines, they're running on silicon. So even if they exhibit the same behaviors, and even if they say the same things, it doesn't necessarily mean that this sensation of consciousness that we have is the same thing they will have. Scott Pelley: Has an AI engine ever asked a question that was unanticipated? Demis Hassabis: Not so far that I've experienced, and I think that's getting at the idea of what's still missing from these systems. They still can't really yet go beyond asking a new novel question or a new novel conjecture or coming up with a new hypothesis that has not been thought of before. Scott Pelley: They don't have curiosity? Demis Hassabis: No, they don't have curiosity, and they're probably lacking a little bit in what we would call imagination and intuition. But they will have greater imagination, he says, and soon. Demis Hassabis: I think actually in the next maybe five to ten years. I think we'll have systems that are capable of not only solving an important problem or conjecture in science but coming up with it in the first place. 'Solving an important problem' won Hassabis a Nobel Prize last year. He and colleague John Jumper created an AI model that deciphered the structure of proteins. Demis Hassabis: Proteins are the basic building blocks of life. So, everything in biology, everything in your body depends on proteins. You know, your neurons firing, your muscle fibers twitching, it's all mediated by proteins. But 3D protein structures like this are so complex, less than 1% were known. Mapping each one used to take years. DeepMind's AI model did 200 million in one year. Now Hassabis has AI blazing through solutions to drug development. Demis Hassabis: So on average, it takes, you know, ten years and billions of dollars to design just one drug. We can maybe reduce that down from years to maybe months or maybe even weeks. Which sounds incredible today but that's also what people used to think about protein structures. And it would revolutionize human health, and I think one day maybe we can cure all disease with the help of AI. Scott Pelley: The end of disease? Demis Hassabis: I think that's within reach. Maybe within the next decade or so, I don't see why not. Demis Hassabis told us AI could lead to what he calls "radical abundance" -- the elimination of scarcity. But he also worries about risk. Demis Hassabis: There's two worries that I worry about. One is that bad actors, humans you know, users of these systems repurpose these systems for harmful ends. And then the second thing is the AI systems themselves as they become more autonomous and more powerful. Can we make sure that-- we can keep control of the systems? That they're aligned with our values, they-- they're doing what we want that benefits society. And they stay on guardrails. "Guardrails" are safety limits built into the system. Scott Pelley: And I wonder if the race for AI dominance is a race to the bottom for safety. Demis Hassabis: So that's one of my big worries actually, is the-- of course all of this energy, and racing, and resources is great for progress. But it might incentivize certain actors in-- in that to cut corners. And one of the corners that could be shortcut would be safety and responsibility. So the question is, is how can we-- coordinate more, you know, as leading players, but also nation-states, even. I think this is an international thing. AI's gonna affect every country-- everybody in the world. So I think it's really important that the world and the international community has a say in this. Scott Pelley: Can you teach an AI agent morality? Demis Hassabis: I think you can. They learn by demonstration. They learn by teaching. And I think that's one of the things we have to do with these systems, is to give them a value system and-- a guidance, and some guardrails around that, much in the way that you would teach a child. Google DeepMind is in a race with dozens of others striving for artificial general intelligence so human that you can't tell the difference. Which made us think about Demis Hassabis signing the Nobel Book of Laureates -- when does a machine sign for the first time? And after that, will humans ever sign it again? Demis Hassabis: I think in the next steps is going to be these amazing tools that enhance our, almost every endeavor we do as humans and then beyond that, when AGI arrives, you know, I think, it's gonna change pretty much everything about the way we do things. And its almost you know, I think we need new great philosophers to come about hopefully in the next five, ten, years to understand the implications of this.