Genie 3: An infinite world model | Shlomi Fruchter and Jack Parker-Holder Google DeepMind 2026-09-22 | Genie 3: An infinite world model | Shlomi Fruchter and Jack Parker-Holder
The Great Voyage - An AI generated film inspired by vintage photography Google DeepMind 2025-07-16 | Watch a short 3-minute film made with our AI models by our in-house creative team, inspired by the age of Victorian silent cinema.Here's more detail on how it was made: Inspiration & Fine-Tuning: The team found a batch of 1800s photos at a thrift store that was then used to LoRA fine-tune our image generation model Imagen to generate new images in the same vintage style. If you want to try this yourself, you can also use "Style Ingredients" in our filmmaking tool Flow. This allows you to directly fine-tune Veo with just a single imageAnimation & Writing: We used Veo 2 Image to Video to bring the stills to life and Gemini for prompts & motion ideas, helping to shape the story. Score & Editing: We used Lyria 2 to create a period music soundtrack. We then assembled the film using Final Cut Pro (video) and Logic Pro (sound). Text cards and vintage effects were added selectively, with the background for the cards created in ImagenFind out more about our our models and tools: Gemini: https://deepmind.google/models/gemini/Imagen: https://deepmind.google/models/imagen/Veo: https://deepmind.google/models/veo/Lyria: https://deepmind.google/models/lyria/Flow: https://labs.google/flow
A whistle stop tour of AI creation with Paige Bailey Google DeepMind 2025-07-10 | This week's episode is a slight departure from our usual deep dives. Join Paige Bailey, DevRel lead, as she guides Hannah Fry though some of her favorite AI tools. Having spent years understanding the 'what' of these models, Hannah finally gets to experience the 'how’ – from generating prompts and 'vibe coding', to creating her own version of the infamous spaghetti meme.Timecodes:00:00 Coming up01:16 Introduction 03:20 Veo09:57 Spaghetti contest11:00 Multimodality 17:40 Audio28:00 AI Studio35:00 Gemini Live40:20 Building apps 43:38 Spaghetti showdown47:31 Creativity 48:18 Hannah’s thoughts Learn more and try the tools yourself:Gemini: gemini.google.com Google Labs: https://labs.google/ AI Studio: aistudio.google.com Veo 3: https://deepmind.google/models/veo/ Flow: https://labs.google/flow/ Thanks to everyone who made this possible, including but not limited to: Presenter: Professor Hannah FrySeries Producer: Dan HardoonEditor: Rami TzabarCommissioner & Producer: Emma YousifMusic composition: Eleni ShawAudio engineer: Richard CourticeProduction Manager: Dan LazardStudio Manager: Nicholas DukeVideo Director: Bernardo ResendeVideo Editor: Bilal Merhi Audio Engineer: Perry RogantinCamera and Lighting Operator: Robert MessereProduction Coordination: Zoey Roberts, Sarah Ellen Morton Visual Identity and Design: Rob Ashley Commissioned by Google DeepMind___Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on Linkedin linkedin.com/company/deepmind
Could digital twins – virtual replicas of humans or organs – accelerate medical research? 🏥 Google DeepMind 2025-07-03 | @fryrsquared
The nature of AI: solving the planets data gap with Drew Purves Google DeepMind 2025-06-19 | Could we use the sound of a coral reef to determine its health? Do we know where all the world's natural forests are? And are we on the verge of using AI to decode animal communication? In this episode, Professor Hannah Fry is joined by Drew Purves, Nature Lead at Google DeepMind. They explore how AI is helping ecologists map forests and species for the first time in history and how this data can be used to better understand the root causes of deforestation.They also explore bioacoustics and how sound is playing a pivotal role in tracking species on land and underwater —providing a powerful new way for us to understand and protect the environment.Timecodes:00:00 Coming up 00:43 Introduction 03:35 AI for nature05:30 Mapping the biosphere 16:14 Deforestation drivers19:45 Species mapping26:50 Perch and acoustic ecology37:00 Animal communication38:55 The future of ecology with AI40:33 Hannah's thoughts___Further reading:Natural forests of the world: sciety.org/articles/activity/10.31223/x5zx6pgithub.com/google-deepmind/forest_typology Forest loss driversiopscience.iop.org/article/10.1088/1748-9326/add606wri.org/insights/forest-loss-drivers-data-trendsglobalforestwatch.org/blog/data-and-tools/new-drivers-data-forest-lossPerchgithub.com/google-research/perchnature.com/articles/s41598-023-49989-z.epdfhttps://blog.google/outreach-initiatives/arts-culture/a-new-ai-tool-to-help-monitor-coral-reef-health/Deep learning based remote sensing (open source)github.com/google-deepmind/jeogithub.com/google-deepmind/geeflowSpecies mapping paperarxiv.org/abs/2503.11900Google resourcesearthengine.google.comagri.withgoogle.comhttps://blog.google/outreach-initiatives/entrepreneurs/ai-nature-climate-accelerator-nonprofits-speciesnet/Agile modelingarxiv.org/abs/2505.03071github.com/google-research/perch-hopliteDolphinGemma https://blog.google/technology/ai/dolphingemma/___Thanks to everyone who made this possible, including but not limited to: Presenter: Professor Hannah FrySeries Producer: Dan HardoonEditor: Rami TzabarCommissioner & Producer: Emma YousifMusic composition: Eleni ShawAudio engineer: Richard CourticeProduction Manager: Dan LazardStudio Manager: Nicholas DukeVideo Director: Bernardo ResendeVideo Editor: Bilal Merhi Audio Engineer: Perry RogantinCamera and Lighting Operator: Robert MessereProduction Coordination: Zoey Roberts, Sarah Ellen Morton Visual Identity and Design: Rob Ashley Commissioned by Google DeepMind___Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on Linkedin linkedin.com/company/deepmind
A quest for a cure: AI drug design with Isomorphic Labs Google DeepMind 2025-06-05 | In this episode, host Hannah Fry is joined by Max Jaderberg and Rebecca Paul of Isomorphic Labs to explore the future of drug discovery in the age of AI. They discuss how new technology, particularly AlphaFold 3, is revolutionizing the field by predicting the structure of life’s molecules, paving the way for faster and more efficient drug discovery.They dig into the immense complexities of designing new drugs: How do you find the right molecular key for the right biological lock? How can AI help scientists understand disease better and overcome challenges like drug toxicity? And what about the diseases that are currently considered “undruggable”? Finally, they explore the ultimate impact of this technology, from the future of personalized medicine to the ambitious goal of being able to eventually design treatments for all diseases.Further reading:AlphaFold 3: nature.com/articles/s41586-024-07487-w AlphaFold Server: alphafoldserver.comIsomorphic Labs: isomorphiclabs.com AlphaFold 3 code and weights: github.com/google-deepmind/alphafold3 Timecodes:00:00 Intro02:11 AI & Disease05:30 AI in Biology06:51 Molecules and Proteins12:05 AlphaFold 314:40 Demo16:20 Human-AI collaboration24:30 Drug Design Challenges39:00 Beyond Animal Models44:35 AI Drug Future46:30 Outro___Thanks to everyone who made this possible, including but not limited to: Presenter: Professor Hannah FrySeries Producer: Dan HardoonEditor: Rami TzabarCommissioner & Producer: Emma YousifMusic composition: Eleni ShawAudio engineer: Richard CourticeProduction Manager: Dan LazardStudio Manager: Nicholas DukeVideo Director: Bernardo ResendeVideo Editor: Bilal Merhi Audio Engineer: Perry RogantinCamera and Lighting Operator: Robert MessereProduction Coordination: Zoey Roberts, Sarah Ellen Morton Visual Identity and Design: Rob Ashley Commissioned by Google DeepMind___Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on Linkedin linkedin.com/company/deepmind
Gemini 2.5 Pro Deep Think Demo | Competitive coding problem Google DeepMind 2025-05-22 | Watch as Tong He, a research scientist at Google DeepMind, introduces the new Gemini 2.5 Pro Deep Think, an enhanced reasoning mode that uses parallel thinking techniques.See how Deep Think uses its reasoning capabilities to tackle a challenging coding problem from the competitive coding platform ‘Codeforces’.Learn more at https://blog.google/technology/google-deepmind/google-gemini-updates-io-2025/---Subscribe to our channel / @googledeepmind Find us on X / googledeepmind Follow us on Instagram / googledeepmind Add us on Linkedin / deepmind
Redefining robotics with Carolina Parada Google DeepMind 2025-05-22 | On this episode, Hannah is joined by Carolina Parada, Senior Director and Head of Robotics at Google DeepMind. They explore the recent leap forward in robotic capabilities, highlighting advancements in multimodal understanding and embodied reasoning, which enable robots to interact with the physical world with unprecedented generality. They dig into the two-system approach - ‘slow and fast thinking‘ - that enables both complex reasoning and rapid, reactive movements. Using examples from robots learning dexterous tasks such as tying shoelaces to adapting to entirely new scenarios in real-time, Parada highlights how key breakthroughs in understanding, dexterity, and control are now coming together to rapidly advance robotics unlike ever before. Further reading/viewing: https://deepmind.google/models/gemini-robotics/https://deepmind.google/discover/blog/advances-in-robot-dexterity/youtube.com/playlist?list=PLqYmG7hTraZC4Mx6pEKr6FVJehafA7vWETimecodes:00:00 Introduction01:46 Carolina's background02:57 Current state of robotics05:20 Gemini robotics videos12:45 Conceptual understanding & multimodal capabilities 16:50 Embodied reasoning 21:00 Thinking fast and slow 27:44 Emerging properties 24:53 Looking back 34:28 Sim2real gap 37:00 Safety42:00 Work to be done 45:00 Hannah's thoughts___Thanks to everyone who made this possible, including but not limited to: Presenter: Professor Hannah FrySeries Producer: Dan HardoonEditor: Rami TzabarCommissioner & Producer: Emma YousifMusic composition: Eleni ShawAudio engineer: Richard CourticeProduction Manager: Dan LazardStudio Manager: Nicholas DukeVideo Director: Bernardo ResendeVideo Editor: Alex Baro Cayetano, Bilal Merhi Audio Engineer: Perry RogantinCamera and Lighting Operator: Robert MessereProduction Coordination: Zoey Roberts, Sarah Ellen Morton Visual Identity and Design: Rob Ashley Commissioned by Google DeepMind___Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on Linkedin linkedin.com/company/deepmind
Veo 3 demo | Sailor and the sea Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Prompt: A medium shot frames an old sailor, his knitted blue sailor hat casting a shadow over his eyes, a thick grey beard obscuring his chin. He holds his pipe in one hand, gesturing with it towards the churning, grey sea beyond the ship's railing. "This ocean, it's a force, a wild, untamed might. And she commands your awe, with every breaking light"Find out more: https://deepmind.google/models/veo/
Veo 3 demo | Owl and badger Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: A follow shot of a wise old owl high in the air, peeking through the clouds in a moonlit sky above a forest. The wise old owl carefully circles a clearing looking around to the forest floor. After a few moments, it dives down to a moonlit path and sits next to a badger. Audio: wings flapping, birdsong, loud and pleasant wind rustling and the sound of intermittent pleasant sounds buzzing, twigs snapping underfoot, croaking. A light orchestral score with woodwinds throughout with a cheerful, optimistic rhythm, full of innocent curiosity.A wise old owl and a nervous badger sit on a moonlit forest path. ""They left behind a...a 'ball' today. It bounced higher than I can jump.” the badger stammered, trying to comprehend it. “What manner of magic is that?"" the owl hooted thoughtfully. Audio: Owl hooting, badger's nervous chitters, rustling leaves, crickets.A wise old owl flies away out of the frame and a nervous young badger runs in a different direction out of the frame. In the background, you can see a squirrel hurrying past making noise of rustling dried autumn leaves as it goes. Audio: birdsong, loud and leaves rustling, and the sound of intermittent pleasant sounds buzzing, twigs snapping underfoot, and the sounds of squirrels scurrying through the dried autumn leaves. The sound of an owl hooting in the distance, badger's nervous chitters, rustling leaves, crickets, sounds that are full of innocent curiosity.
Veo 3 demo | Duck interrogation Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: A detective interrogates a nervous-looking rubber duck. "Where were you on the night of the bubble bath?!" he quacks. Audio: Detective's stern quack, nervous squeaks from rubber duck.
Veo 3 demo | Dialog Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/
Veo 3 demo | Off-road rally Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: The scene explodes with the raw, visceral, and unpredictable energy of a hardcore off-road rally, captured with a dynamic, almost found-footage or embedded sports documentary aesthetic. The camera is often shaky, seemingly mounted inside one of the vehicles or held by a daring spectator very close to the action, frequently splattered with mud or water, catching unintentional lens flares from the natural, often harsh, sunlight filtering through trees or reflecting off wet surfaces. We are immersed in a challenging, untamed natural environment – perhaps a dense, muddy forest trail, a treacherous rocky incline littered with loose scree, or a series_of shallow, fast-flowing river crossings. Several heavily modified, entirely unidentifiable, and unbranded off-road vehicles are engaged in a frenetic, no-holds-barred race. These are not showroom models; they are custom-built, rugged machines – open-wheeled buggies with exposed engines and prominent roll cages, heavily armored pickup trucks with oversized, knobby tires and snorkel exhausts, their original forms and manufacturers completely obscured by extreme modifications, layers of caked-on mud, and a general air of brutal functionality. The dominant sounds are the deafening, guttural roar of powerful, untamed engines, the whine of transmissions, the percussive impact of suspension bottoming out, and the constant spray of mud and water. Within an 8-second sequence, one of the lead vehicles, a low-slung, open-cockpit buggy so caked in thick, brown mud that its original color is a mystery, approaches a wide, shallow river crossing at incredible speed. Without the slightest hesitation, its unseen driver powers straight into the water. The impact sends an enormous, almost solid, opaque sheet of muddy water, mixed with stones and debris from the riverbed, spectacularly high into the air, completely engulfing the small buggy for a terrifying moment, obscuring it from view as if it has been swallowed by the river itself. Right on its tail, a pursuing, equally mud-encrusted, custom-built truck – a hulking, high-clearance beast with a heavily reinforced external roll cage and no discernible badging – arrives at the river crossing just as this massive wall of airborne water reaches its peak. Instead of slowing or attempting to find a clearer path, the truck's driver, with unwavering aggression, plunges directly into and through this opaque, turbulent curtain of muddy spray at full throttle. A split second later, the truck bursts out from the other side of the deluge, water cascading from its roof and chassis, its oversized windshield wipers struggling frantically to clear the torrent of muddy water obscuring the driver's vision. It lands heavily on the far bank, suspension groaning, but still in hot pursuit of the now-reappearing buggy. This thrilling, messy, and visually spectacular sequence of one vehicle creating a massive environmental obstacle and the next immediately conquering it through sheer force, forms the core, immersive, attention-grabbing event of the 8-second sequence. The race continues with undiminished ferocity, the natural terrain itself an active participant in the conflict.
Veo 3 demo | Magical origami Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: The scene opens with a top-down or wide-angle shot showcasing a vast, perfectly flat, neutral-colored surface – perhaps the polished concrete floor of an enormous, empty aircraft hangar, or a giant, minimalist tabletop stretching beyond the frame, under bright, even, shadowless studio lighting. This surface is meticulously covered with thousands upon thousands of small, identical, brightly colored paper squares, arranged in a simple, orderly grid. Each square is a single, vibrant, uncreased sheet – a sea of reds, blues, yellows, greens, oranges, creating a stunning, static mosaic of pure potential. The atmosphere is one of quiet anticipation, a sense of immense latent energy waiting to be unleashed. There is no visible mechanism, no hint of how these papers might be manipulated. Within an 8-second sequence, initiated by an unseen cue – perhaps a subtle, almost inaudible, low-frequency hum that ripples almost invisibly across the surface, or a sudden, soft flash of diffused light – all the thousands of paper squares simultaneously, and with breathtaking precision, leap a few inches into the air as if startled into life. Then, in a mesmerizing, perfectly synchronized, and incredibly high-speed aerial ballet, they begin to fold themselves in mid-air. With impossible, almost magical celerity and accuracy, unseen forces guide each individual square through a complex series of sharp creases, neat tucks, and intricate folds. The swarm of fluttering, self-constructing papers is a blur of color and motion, a chaotic yet utterly controlled explosion of activity. Within a mere five to six seconds, this frenetic process of airborne origami completes. Each of the thousands of squares has transformed into an identical, perfectly formed, complex origami figure – perhaps graceful cranes with outstretched wings, delicate multi-petaled lotus flowers, or miniature, intricately detailed dragons. In the final two to three seconds of the sequence, these newly formed origami figures, still hovering in mid-air, then smoothly and rapidly arrange themselves, like a flock of perfectly trained birds or a sophisticated, self-organizing swarm of nanobots, into a stunning, larger, three-dimensional collective pattern or a recognizable mosaic image – perhaps a giant, hovering sphere composed of countless tiny birds, or a complex, flowing wave of flowers, or even a pixel-perfect, three-dimensional representation of a face or symbol. This collective sculpture holds its form for a beat before the individual origami figures begin to gently, gracefully, and silently settle back down onto the surface, now arranged in their magnificent new configuration. This entire rapid, impossible, and beautiful transformation – from simple squares to a synchronized swarm of self-folding forms creating a complex collective artwork – is the core, eye-popping, and meticulously detailed VFX spectacle of the 8-second sequence. The visual is one of magical precision, emergent complexity, and the beauty of mass synchronized action.
Veo 3 demo | Irish coast Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: In rural Ireland, circa 1860s, two women, their long, modest dresses of homespun fabric whipping gently in the strong coastal wind, walk with determined strides across a windswept cliff top. The ground is carpeted with hardy wildflowers in muted hues. They move steadily towards the precipitous edge, where the vast, turbulent grey-green ocean roars and crashes against the sheer rock face far below, sending plumes of white spray into the air.
Veo 3 demo | Sweet typing Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: xxx
Veo 3 demo | Crystailine flowers bloom Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: A snow-covered plain of iridescent moon-dust under twilight skies. Thirty-foot crystalline flowers bloom, refracting light into slow-moving rainbows. A fur-cloaked figure walks between these colossal blossoms, leaving the only footprints in untouched dust.
Veo 3 demo | Forest spirit Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: A breathtaking, painterly 2D animated continuous visual narrative, rendered with the lush, vibrant, and slightly surreal, almost dreamlike, infused with the intricate, delicate detail of traditional Japanese woodblock prints (Ukiyo-e), follows a young, adventurous, and kind-hearted girl (perhaps with bright, curious eyes and wearing simple, practical, beautifully patterned traditional Japanese farm attire) as she befriends a colossal, gentle, ancient Forest Spirit. The Spirit is a magnificent, awe-inspiring creature, its form a harmonious blend of animal and plant – perhaps with moss-covered, antler-like branches, fur like shimmering leaves that change color with its mood, and eyes like deep, tranquil forest pools. They meet in a sun-dappled, sacred grove deep within an ancient, primeval forest, where impossibly tall, gnarled trees form a living cathedral and tiny, glowing, friendly forest sprites (Kodama-like) peek from behind mossy rocks and giant, fantastical mushrooms. The girl, initially awestruck, offers the massive Spirit a small, carefully cultivated offering – perhaps a perfectly ripe persimmon or a handful of wild berries – her gesture one of pure, innocent respect and affection. The Forest Spirit responds with a slow, gentle inclination of its massive head, its leafy fur rustling like a thousand whispers, and perhaps causes a shower of magical, luminous flower petals to drift down from the canopy, or a tiny, new sapling to sprout at the girl's feet. The animation captures the incredible, detailed textures of the forest, the Spirit's majestic yet gentle presence, and the profound, unspoken emotional connection forming between the child and this ancient guardian of nature. The color palette is a rich symphony of deep forest greens, earthy browns, vibrant floral hues, and the soft, magical glow of the sprites and the Spirit's own subtle luminescence. This continuous, sweeping visual journey is a celebration of the profound, often mystical, bond between humanity and nature, the innocence and courage of childhood, and the power of kindness and respect to bridge even the most fantastical of divides, an affectionate, visually intoxicating ode to ecological harmony and interspecies understanding. The only implied sounds are the gentle rustling of leaves, the distant calls of unseen forest birds, the girl's soft, respectful breathing, the Spirit's deep, resonant, almost inaudible hum, and a soaring, emotionally resonant, orchestral score.
Veo 3 demo | Classical violinist Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: A woman, classical violinist with intense focus plays a complex, rapid passage from a Vivaldi concerto in an ornate, sunlit baroque hall during a rehearsal. Their bow dances across the strings with virtuosic speed and precision. Audio: Bright, virtuosic violin playing, resonant acoustics of the hall, distant footsteps of crew, conductor's occasional soft count-in (muffled), rustling sheet music.
Veo 3 demo | Feathers journey Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: A delicate feather rests on a fence post. A gust of wind lifts it, sending it dancing over rooftops. It floats and spins, finally caught in a spiderweb on a high balcony.
Veo 3 demo | Sizzling onions Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: A close up in a smooth, slow pan focuses intently on diced onions hitting a scorching hot pan, instantly creating a dramatic sizzle. Audio: distinct sizzle.
Veo 3 demo | Chrome city Google DeepMind 2025-05-20 | Created with Veo 3 - our new state-of-the-art video generation model, designed to empower filmmakers and storytellers. Veo 3 lets you add sound effects, ambient noise, and even dialogue to your creations – generating all audio natively. It also delivers best in class quality, excelling in physics, realism and prompt adherence.Find out more: https://deepmind.google/models/veo/Prompt: A fast-tracking shot through a futuristic city with buildings made from reflective organic chrome. It is daytime, rainbows, and an alien planet fills the sky. Camera zooms into robotic bee working inside a reflective organic chrome
Gemini 2.5: Vibe coding nature to simulation Google DeepMind 2025-05-18 | See how our updated Gemini 2.5 Pro (I/O edition) transforms images of nature into code to represent unique patterns Try it for yourself in the Gemini App: gemini.google.comRead more about Gemini 2.5 on our blog: https://goo.gle/423mnK4 And our website: https://deepmind.google/technologies/...---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on Linkedin linkedin.com/company/deepmind
AI and the future of health with Joelle Barral Google DeepMind 2025-05-08 | In this episode, Professor Hannah Fry interviews Joelle Barral, Senior Director of Research at Google DeepMind, about AI in healthcare. They discuss existing AI applications including image analysis for diabetic retinopathy and the expansion of diagnostic tools as a result of multi-modal models. The conversation highlights AI's potential to improve healthcare delivery, personalize treatment, expand access worldwide, and ultimately, bring back the joy of practicing medicine.Further reading:MedGemini: https://research.google/blog/advancing-medical-ai-with-med-gemini/AMIE: https://research.google/blog/from-diagnosis-to-treatment-advancing-amie-for-longitudinal-disease-management/Timecodes00:00 Intro04:35 Diagnosis and medical imaging 08:00 New gold standard11:14 Multimodality and sound 15:15 Who makes the call?16:13 Holistic view 21:00 Data points25:28 Patient experience 27:45 AIME 29:41 Physician in your family 33:24 Future for medical professionals 40:11 Hannah's thoughts ___Thanks to everyone who made this possible, including but not limited to: Presenter: Professor Hannah FrySeries Producer: Dan HardoonEditor: Rami TzabarCommissioner & Producer: Emma YousifMusic composition: Eleni ShawAudio engineer: Richard CourticeProduction Manager: Dan LazardVideo Studio Production: Nicholas DukeVideo Director: Bernardo ResendeVideo Editor: Bilal MerhiAudio Engineer: Perry RogantinCamera and Lighting Operator: Robert MessereProduction Coordination: Zoey Roberts, Sarah Ellen Morton Visual Identity and Design: Rob Ashley Commissioned by Google DeepMind___Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on Linkedin linkedin.com/company/deepmind
Consciousness, reasoning and the philosophy of AI with Murray Shanahan Google DeepMind 2025-04-24 | In this episode, Hannah is once again joined by Murray Shanahan, Professor of Cognitive Robotics at Imperial College London and Principal Scientist at Google DeepMind, for a philosophical deep dive on AI. They explore everything from consciousness and metacognition in animals, to symbolic AI and neural networks. Murray also shares insights into his involvement with the film 'Ex Machina' and discusses the idea of reasoning, anthropomorphism, and the future of AI.Further reading / listening: Toward the future, S1 Ep 7: youtu.be/yf31XT1G1RQ?si=6mAEsQhKwKPWk9oH Papers by Murray: scholar.google.co.uk/citations?user=00bnGpAAAAAJ&hl=enTimecodes00:00 Introduction02:00 Ex Machina03:28 John McCarthy & Coining "AI"05:45 Symbolic AI09:43 AI Reasoning14:42 Turing Test18:10 Alternative Tests21:58 Anthropomorphism26:42 Embodied AI28:17 AI Consciousness34:00 Octopus Analogy37:48 Prompt Engineering39:40 Exotic Mind-Like Entities 40:44 Conclusion___Thanks to everyone who made this possible, including but not limited to: Presenter: Professor Hannah FrySeries Producer: Dan HardoonEditor: Rami TzabarCommissioner & Producer: Emma YousifMusic composition: Eleni ShawAudio engineer: Richard CourticeProduction Manager: Dan LazardVideo Studio Production: Nicholas DukeVideo Director: Bernardo ResendeVideo Editor: Alex Baro Cayetano, Bilal MerhiAudio Engineer: Perry RogantinCamera and Lighting Operator: Robert MessereProduction Coordination: Zoey Roberts, Sarah Ellen Morton Visual Identity and Design: Rob Ashley Commissioned by Google DeepMind___Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on Linkedin linkedin.com/company/deepmind
Is human data enough? With David Silver Google DeepMind 2025-04-10 | In this episode of Google DeepMind: The Podcast, VP of Reinforcement Learning, David Silver, describes his vision for the future of AI, exploring the concept of the "era of experience" versus the current "era of human data". Using AlphaGo and AlphaZero as examples, he highlights how these systems surpassed human capabilities by engaging in reinforcement learning without prior human knowledge. This approach contrasts with large language models, which depend on human data and feedback. Silver emphasizes the need to explore this path to drive AI progress and achieve artificial superintelligence. ___Additional resourcesThe Era of Experience Paper (position paper): https://goo.gle/3EiRKIHMeta-Gradient Reinforcement Learning (2018) arxiv.org/abs/1805.09801Go to Zero (S1, Google DeepMind Podcast) youtube.com/watch?v=OkAwsrHMTgMAlphaGo the documentary: youtu.be/WXuK6gekU1Y?si=NedlhUqbV8H-ZVDn___Timestamps00:00 Introduction01:50 Era of experience 03:45 AlphaZero 10:19 Move 3715:20 Reinforcement learning and human feedback24:30 AlphaProof 29:50 Math Olympiads 35:00 Experience based methods 42:56 Hannah's reflections44:00 Fan Hui joins___Thanks to everyone who made this possible, including but not limited to: Presenter: Professor Hannah FrySeries Producer: Dan HardoonSeries Editor: Rami TzabarCommissioner & Producer: Emma YousifMusic Composition: Eleni ShawAudio Engineer: Richard CourticeProduction Manager: Dan LazardVideo Studio Production: Nicholas DukeVideo Director and Editor: Bernardo ResendeVideo Editor: Bilal MerhiAudio Engineer: Perry RogantinCamera and Lighting Operator: Robert MessereProduction Coordination: Zoey Roberts, Sarah Ellen Morton Visual Identity and Design: Rob Ashley Commissioned by Google DeepMind___Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on Linkedin linkedin.com/company/deepmind
Thomas story Google DeepMind 2025-04-02 | When Googler Thomas Wagner’s son received a diagnosis of Alexander disease, a rare genetic disorder, he set out to learn everything he could. He used Gemini to summarize research in medical journals, making it easier for him to understand.He realized there might be similarities between Alexander disease, which had very little active research, and other diseases with much more funding and ongoing research. He began to reach out to those researchers, scientists and doctors, many of whom had never heard of Alexander disease before. Through these conversations, Thomas has helped jumpstart new research into potential treatments.___A special thanks to: Dr. Amy Waldman, Neurologist at Children’s Hospital of Philadelphia, Dr. Corina Amor, Ph.D., Assistant Professor at Cold Spring Harbor Laboratory and the Amor Lab team, Pranam Chatterjee, Ph.D., Assistant Professor of Biomedical Engineering at Duke University, Albee Messing, V.M.D., Ph.D., Professor Emeritus of Neuropathology in the Department of Comparative Biosciences and all the doctors, scientists and researchers working tirelessly to find a cure for Alexander disease.A huge thank you to the Wagner and Holzhuber family, volunteers and friends of Team Max, the Googlers who have supported this journey, Max's doctors, nurses and therapists and every scientist who has ever responded to an email.___Find out more about Thomas' story on our blog: https://g.co/thomasTo support breakthrough research on treatments of Alexander Disease: https://EndAxD.orgTo find out more about Leukodystrophies: https://ULF.orgTo find out more about the science of Alexander Disease: https://alexander-disease.waisman.wisc.eduTo join Team Max and support Thomas and family directly: jointeammax.orgLearn more about Gemini 2.0 at https://deepmind.google/technologies/gemini___Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind___Gemini results are informational only and not a diagnosis. Consult your medical authority for advice.Google One AI Premium Plan subscription and browser for set up required. Gemini Advanced is available for ages 18+. Availability may vary by device, country, and language. Results for illustrative purposes and may vary. Check responses for accuracy.Features may differ depending on subscription and results may vary. Some extensions require setup. Country availability may vary. Check responses for accuracy.
Creating with Veo 2 Google DeepMind 2025-03-26 | See how creators are using Veo 2, our state-of-the-art video generation model, to bring their wildest ideas to life. Veo 2 delivers 4K outputs, expansive styles, and more detail than ever. With enhanced realism, advanced motion capabilities, and unparalleled camera control, it produces videos with exceptional detail and fidelity. Learn more about Veo 2: https://deepmind.google/technologies/veo/veo-2/
Gemini 2.5: Make your own interactive demo Google DeepMind 2025-03-25 | See how Gemini 2.5 Pro Experimental uses its reasoning capabilities to create an interactive p5js demo of cosmic fish with a simple prompt. What will Gemini create if you change ‘fish’ and ‘nebulae’ to something else? Prompt: Create a beautiful, interactive p5js demo (no HTML). I like fish and nebulae. Show me what the fish are thinking.Try it for yourself in AI studio: http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-pro-exp-03-25 Or if you're a Gemini Advanced user, you can select it in the model dropdown on desktop and mobile: gemini.google.comRead more about Gemini 2.5 on our blog: https://goo.gle/423mnK4 And our website: https://deepmind.google/technologies/gemini---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini 2.5: Create your own dinosaur game from a single line prompt Google DeepMind 2025-03-25 | See how Gemini 2.5 Pro Experimental uses its reasoning capabilities to create a game, using executable code from a single line prompt. What will Gemini create if you change 'dinosaur' to something else? Prompt: Make me a captivating endless runner game. Key instructions on the screen. p5js scene, no HTML. I like pixelated dinosaurs and interesting backgrounds.Try it for yourself in AI studio: http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-pro-exp-03-25 Or if you're a Gemini Advanced user, you can select it in the model dropdown on desktop and mobile: gemini.google.comRead more about Gemini 2.5 on our blog: https://goo.gle/423mnK4 And our website: https://deepmind.google/technologies/gemini---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini 2.5: Create a JavaScript animation of complex flocking behavior Google DeepMind 2025-03-25 | Gemini 2.5 Pro Experimental is also our most advanced coding model yet. See it in action as it creates an interactive p5js demo of colorful boids inside a spinning hexagon. Prompt: p5js (no HTML) swarm of 30 colorful boids swimming inside a rotating hexagon. I like supernova nebulae.Try it for yourself in AI studio: http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-pro-exp-03-25 Or if you're a Gemini Advanced user, you can select it in the model dropdown on desktop and mobile: gemini.google.comRead more about Gemini 2.5 on our blog: https://goo.gle/423mnK4 And our website: https://deepmind.google/technologies/gemini---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini 2.5: Create an interactive plot of economic data Google DeepMind 2025-03-25 | Gemini 2.5 Pro unlocks state-of-the-art performance in coding, math and science. See how it uses its reasoning capabilities to create an interactive bubble chart to visualize economic and health indicators over time. What else can you create? Prompt: Create an animated bubble chart using Plotly Express of how economic and health indicators have evolved over the years for each continent.Try it for yourself in AI studio: http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-pro-exp-03-25 Or if you're a Gemini Advanced user, you can select it in the model dropdown on desktop and mobile: gemini.google.comRead more about Gemini 2.5 on our blog: https://goo.gle/423mnK4 And our website: https://deepmind.google/technologies/gemini---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini 2.5: Code a visualization of a Mandelbrot set Google DeepMind 2025-03-25 | Gemini 2.5 Pro Experimental unlocks state-of-the-art performance in coding, math and science, and multimodal reasoning. See how it creates a p5js simulation of intricate fractal patterns to explore a Mandelbrot set.Prompt: p5js to explore a Mandelbrot set.Try it for yourself in AI studio: http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-pro-exp-03-25 Or if you're a Gemini Advanced user, you can select it in the model dropdown on desktop and mobile: gemini.google.comRead more about Gemini 2.5 on our blog: https://goo.gle/423mnK4 And our website: https://deepmind.google/technologies/gemini---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini 2.5: Code particle simulations with dynamic motion Google DeepMind 2025-03-25 | See how Gemini 2.5 Pro Experimental uses its reasoning capabilities to create an interactive simulation of a reflection nebula. Prompt: Please give me an HTML file with a colorful particle simulation of a reflection nebula.Try it for yourself in AI studio: http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-pro-exp-03-25 Or if you're a Gemini Advanced user, you can select it in the model dropdown on desktop and mobile: gemini.google.comRead more about Gemini 2.5 on our blog: https://goo.gle/423mnK4 And our website: https://deepmind.google/technologies/gemini---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Lunch Packing with ALOHA 2 Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. ALOHA 2 packs a lunch, using its dexterous capabilities to unzip a lunch box. ---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Workshop Organization Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. A Bi-Arm Franka organizes a workshop setup.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Salad Making Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. With Gemini Robotics, robots like the ALOHA 2 are able to reason and complete multi-step takss. Here, an ALOHA 2 manipulates a set of tongs to pick up specific items from a group in order to make a salad.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Desk Organization Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. ALOHA 2 organizes a desk according to the user's instructions.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Fruit Bowl Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. ALOHA 2 responds to live instructions and changing environments in order to complete its task of delivering fruit to different bowls.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Stacking Dice Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. ALOHA 2 manipulates two dice in order to make them match each other.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Electrical Socket Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. A Bi-Arm Franka plugs in a light to an electrical socket.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Whiteboard Erasing Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. ALOHA 2 reacts to human interactions to erase a whiteboard.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Slam Dunk Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. ALOHA 2 reasons through instructions from the user to "slam dunk" a basketball, an action it was not trained to do.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Matching Reasoning Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. Robots such as ALOHA 2 can reason with objects, using multiple perspectives to make small adjustments where necessary in order to achieve the desired result.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Folding an Origami Fox Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. ALOHA 2 demonstrates its capabilities by folding an origami fox. ---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Timing Belt Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. See how Gemini Robotics can apply to industrial use cases by seating a belt using a bi-arm Franka.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics Demo: Playing Cards Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. Watch ALOHA 2 demonstrate its reasoning and dexterity capabilities by interacting with a deck of cards.---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
Gemini Robotics: Developing the next generation of humanoid robots with Apptronik Google DeepMind 2025-03-12 | Our new Gemini Robotics model brings Gemini 2.0 to the physical world. We're partnering with Apptronik to develop the next generation of humanoid robots with Gemini 2.0. Learn more at deepmind.google/robotics---Subscribe to our channel youtube.com/@googledeepmindFind us on X twitter.com/GoogleDeepMindFollow us on Instagram instagram.com/googledeepmindAdd us on LinkedIn linkedin.com/company/deepmind
