Google✓

Today we're introducing Genie 4 — our newest interactive world model from @GoogleDeepMind 🌐

Today, Gemini 4 Argon is officially rolling out.

We asked Gemini 4 Argon to make a realistic 3D scene in pure Python with zero external libraries. It wrote 5,000+ lines of code and built its own 3D ray-tracing engine, custom video tool, and audio mixer to render and document this sunlit library from scratch — producing, narrating, and assembling this video with Gemini 3.8 TTS and music by Lyria 3.5.

RT @GoogleDeepMind: This is Genie 4, our most realistic and interactive world model yet. 🌐 Explore dynamic environments in real time to see how the scene responds, sounds, and how the people in it move, react, and speak.

View the source code →

Interactive world models like Genie 4 advance our ability to test simulated scenarios before bringing them into the physical world. We paired Genie 4 with Gemini 4 Argon in our @GoogleDeepMind robotics research — showing the possibilities of simulating a breadth of scenarios in imagined worlds 🤖

RT @patloeber: our team shipped a bunch of guides to help you build with Gemini 4 Argon: - Dev guide: - What's new + migration checklist: - Building 3D games: - Long decode guide (1M output):

We’ve started rolling out Genie 4 as a research preview to trusted testers. It’s coming soon to Google AI Ultra subscribers in Project Genie and early access partners in the Gemini API and @GoogleAIStudio. Learn more ↓

RT @NewsFromGoogle: Yesterday, we began rolling out Gemini 4 Argon — our newest frontier model that excels at complex, real-world tasks across coding, finance, legal, cybersecurity, and science — more widely. We gave early access to enterprise customers and startups, who have already seen strong wins with Argon. Here’s what those teams — including those at @Deloitte and @Box — and more had to say ↓

Genie 4 incorporates and builds on capabilities from the Gemini family: Gemini Omni anchors simulations in real-world appearance and behavior, while other Gemini models provide the reasoning to maintain coherence and continuity. Here's what's new: ✨ Live steering: Use text prompts to change or add things in the world 🔊 Native audio: Hear ambient soundscapes, music, and interactive dialogue 🌊 Unprecedented realism: Experience a leap in visual details, from realistic physics to natural human movement 🧠 Gemini reasoning: Interprets prompts, tracks world state to remember what just happened, and plans multi-step events so scenes stay more coherent

From optimizing codebases to creative writing, here's how @TulseeDoshi and other Google teams are using Gemini 4 Argon 👇

RT @NewsFromGoogle: Gemini 4 Argon is already helping researchers unlock new scientific breakthroughs across fusion, biology, and quantum computing: ⚛️ In nuclear fusion, Argon helped discover a broader class of counterexamples to Grad's conjecture — a nearly 60-year-old assumption in plasma physics — creating new benchmarks for stellarator 3D magnetic fields. 🧬 In biology, it designed five novel, lab-verified serine esterases in a matter of hours — enzyme engineering that would previously have taken months. This work demonstrates the potential for rapid acceleration in fields such as biomanufacturing, green chemistry, and drug development. 🩺 In rare disease research, scientists at @GamowLabs used Argon to analyze de-identified genomes from newborns with rare developmental lung disorders — pinpointing a chromosomal rearrangement that routine software missed for years, and explaining why it went undetected. 🧮 In quantum computing, Argon translated our AlphaQubit error-correction decoder into a single optimized hardware kernel — nearly doubling inference throughput — and cut spacetime costs for a key quantum subroutine by more than 100x.

Learn more ↓

Starting from a single Nano Banana image, Gemini 4 Argon created this finished 3D cathedral audio-reactive scene. Driving Blender MCP in an autonomous loop in @Antigravity to: 🏛️ Sculpt intricate Gothic architecture 🎥 Align complex camera grids 🔊 Stage dynamic, audio-reactive lighting

Today, at our Research@ event, we shared research breakthroughs that can help amplify human ingenuity. From agents that can help solve real-world problems, like public health threats and environmental crises like extreme flooding, to models that can aid advanced medical workflows and improve doctor-patient relations, our latest updates will help advance science and technology. Here are some recent highlights.

Learn more ↓

Learn more about all of our updates from Research@ ↓

Let your video create its own soundtrack 🎶 Using Canvas in @GeminiApp, Gemini 4 Argon created a tool that traces musical scale lines across live video — triggering notes whenever motion crosses the screen.

@_philschmid @antigravity @soumyadesign Make 3D musical instruments using Argon, WebMIDI, and Three.js. 🎹 by @alexanderchen

Learn more ↓

Gemini 4 Argon is here. To show you what it can do, here are 5 builds from our team 🧵 ↓

Step inside 1,000-year-old ruins: see how Gemini 4 Argon turns fragmented archaeological records into an explorable 3D digital heritage site. We dropped raw LiDAR scans and archives of Chaco Canyon into @Antigravity, using Argon and Blender MCP to build it in 3D 🏛️

Go from standard photos to digital oil paintings. This prompt in Argon generates a custom multi-pass canvas renderer in Python. 🌆 by @_philschmid

Argon turned that 3D data into an interactive webpage where you can click through individual rooms, read the historical context, and test a solar dial modeled after the site's ancient solstice and equinox alignments ☀️ Explore these ruins in @GoogleAIStudio:

@_philschmid Play an interactive WebGL Mahjong game built in @Antigravity featuring responsive, realistic spring physics and sound effects. Play it here → 🀄 by @soumyadesign

From drawing in webcam “fog" to playing HTML synths, the builds with Gemini 4 Argon are incredibly creative. Here’s what developers are spinning up 🧵↓

RT @GeminiApp: With Gemini 4 Argon, spend less time on repetitive admin and more time on your craft. Just connect your @GoogleWorkspace apps to turn scattered recipes, handwritten guest lists, and photos of seating charts into a polished proposal deck, email draft, and automated tracker.

🎹 Playable HTML Music @maxescu is generating fully playable synthesizers in a single HTML file. Test out the sound on his latest build at

We used Gemini 4 Argon in @GoogleAIStudio to build an interactive 3D island sandbox 🏝️ Every brush stroke simulates living terrain, sand, and water physics in real time using custom Three.js and GLSL shaders.

I can't believe this worked... Gemini 4 Argon made a Jupiter/Moog combo synth in under 30 minutes. It's all in a single HTML file, and you can play with it here:

🌴 Build your own island with the applet in @GoogleAIStudio ↓

🐝 SVG Bicycle Tower @HarshithLucky3 built a 12-layer SVG tower balanced on a pelican riding a bicycle — topped with a tiny bee chasing the cat to the top 🐝 🚲 What should get added to the stack next?

RT @OfficialLoganK: A conversation with Sergey Brin, @joshwoodward, @tulseedoshi, and @melvinjohnsonp about Gemini 4 Argon, how we got here, and the path ahead!

now i added bee 🐝 Gemini 4 Argon High > SVG of a 12 layer riding tower: a pelican on a bicycle, carrying a scooter, flamingo, tricycle, turtle, unicycle, crab, skateboard, and a tiny-limbed game controller - bee is chasing cat so cat starts climbing to top and then they became friends

Personal Intelligence is now rolling out for Gemini on Android Auto and in the coming months to cars with Google built-in, so you can get even better hands-free help on the road. With your permission, Personal Intelligence securely connects information from the Google apps you already use — like Gmail, Google Calendar, and Search — so you can make complex requests, get personalized recommendations, retrieve details from past conversations and more.

RT @googledevs: The community is putting Gemini 4 Argon to work 👏 See how they're experimenting with Argon across different projects 🧵

Gemini is now available in @GoogleMaps navigation on CarPlay. Find the best place to park, report a traffic incident, or change your route with just a quick conversation. Tap the Gemini icon in Google Maps CarPlay during your next drive to try it out 🚘

Start getting tailored assistance on your drive today ↓

We taught a robot to play cornhole using Gemini 4 Argon 🦾 Just by watching a video of humans playing, Argon mapped the physics, coded its own simulation to practice, and taught @Apptronik's Apollo humanoid to sink 7 shots in a row.

Researchers at @wiz_io put Gemini 4 Argon to the test against complex cyber threats. In real-world testing, it found more than two times more vulnerabilities than baseline models — catching a critical risk that previous frontier models missed. See how they did it ↓

RT @GoogleLabs: What would happen if Dreambeans ☁️ dreamt up ☁️ your morning ☀️? We brought together Google Labs’ very own Sahana R. (Product Manager), Brian R. (VP of Product), and his impossibly adorable floof Nala to dance with destiny in an exercise we’re calling “Dreambeans Roulette”! Here’s the rundown: 1️⃣ Open Dreambeans 2️⃣ Select a story 3️⃣ Go out and do it! Discover where Dreambeans takes us in “Dreambeans Roulette: Part 1” and follow along in this three-part series! Dreambeans is available in the US, for users 18+. More regions coming soon. Learn more at

Learn more about Gemini 4 Argon ↓

Learn more ↓

RT @GoogleDeepMind: Gemini 4 Argon built a 3D periodic table synced to Tom Lehrer’s song, “The Elements.” Created in @Antigravity, it animates orbiting electrons, atomic data, and light spectra.