DeepMind releases Genie 4 world model, opening to testers first
The story so far
Google DeepMind released the world model Genie 4, currently available to trusted testers in research preview form, not yet for consumers and developers. DeepMind states that in the coming weeks, it will expand to Project Genie for Google AI Ultra subscribers, as well as early partners of the Gemini API and Google AI Studio. DeepMind claims Genie 4 can generate interactive simulated worlds with native audio in real-time, allowing users to change weather, camera angles, and scene elements with natural language prompts, with characters able to converse and respond to scene events. The longest coherent scenes are two minutes, twice as long as Genie 3. Gemini 3.8 Flash acts as a guiding agent in the loop, responsible for breaking down goals and validating frame by frame. Google states that all videos and audio generated by Genie 4 will be watermarked with SynthID. DeepMind claims this technology can be used to build training environments for robots or for rapid prototyping in creative fields.
AI-written from the reports · Updated 19 days ago
Developments
2 developments
- 31 Oct, 01:00 · 3 reportsGoogle's first data center satellite onlineThe Verge · AI:Google’s satellite AI server transmits its first response to Earth
- 28 Oct, 00:00 · 9 reportsGenie 4 ReleasedGoogle DeepMind:Genie 4: A new generation of world simulation
Coverage timeline
Follow the coverage to see every side of the story.
- The Verge · AIGoogle’s satellite AI server transmits its first response to Earth
Google's Project Suncatcher satellite successfully launched its on-board Tensor Processing Units (TPUs), enabling the on-board Gemma 4 model to create haikus about space based on prompts.
- TechCrunch · AIGoogle’s first data center satellite is online and writing poetry
Google Suncatcher satellite, carrying four Tensor Processing Units (TPUs), has been launched by SpaceX and is now operational, successfully sending prompts to Google DeepMind's Gemma 4 large language model to create poems.
- MarkTechPostFeaturedMeet Google DeepMind’s Genie 4: Real-Time World Model With Native Audio
Google DeepMind released the research preview version of Genie 4, which can generate explorable worlds from text and image prompts in real-time and natively generate environmental sounds, music, and character dialogues. The model introduces Gemini as a planner in the simulation loop, with Gemini 3.8 Flash disassembling goals, checking frames, and replanning, while Gemini Omni anchors the appearance and behavior of the world.
- ITHome · AIGoogle has launched its most powerful world model, Genie 4
Google DeepMind released the research preview version of the world model Genie 4, capable of generating highly realistic interactive virtual worlds, supporting real-time scene editing and synchronized audio generation, and plans to open it to AI Ultra subscribers.
- ITHome · AIFeaturedGoogle DeepMind releases Genie 4 world model, supporting real-time natural language rewriting and native audio
Google DeepMind released the Genie 4 world model on October 27, positioning it as a major research milestone. Users can change weather, camera angles, characters, and objects in real-time using natural language commands instead of regenerating a video.
- ITHome · AIFeaturedGoogle DeepMind launches the world model Genie 4, supporting synchronous generation and real-time editing of audio and video
Google DeepMind has launched the world model Genie 4, which is currently in the research preview phase. It can generate interactive virtual worlds and modify scenes by inputting prompts during runtime, as well as generate real-time audio synchronized with the visuals. Compared to the previous Genie 3, Genie 4 has improved visual realism and supports real-time adjustments of weather, camera angles, and adding or deleting characters and objects. It can maintain a continuous scene for up to two minutes, twice as long as the previous generation.
- The DecoderGoogle Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMs
DeepMind has released Genie 4, the company's first real-time voice-generating instant world model, where users can move scenes with the keyboard and guide events with text prompts. Genie 4 is built on the video model Gemini Omni and is planned and simulated in the background by the Gemini large model family, supporting background sound effects, character dialogues, and real-time interaction. It is currently only available to selected testers and will be opened to Google AI Ultra subscribers in the future, integrating SynthID watermarking to mark AI-generated content.
- TechCrunch · AIFeaturedGoogle’s Genie 4 world model adds audio, more realistic worlds, and real-time steering
Google DeepMind released the world model Genie 4 as a research preview, capable of generating photorealistic and interactive scenes, and supports entering prompts during simulation to change weather, camera angles, or add people and objects in real time.
- Google DeepMindFeaturedGenie 4: A new generation of world simulation
Google DeepMind releases world model Genie 4, which can generate interactive simulated worlds with native audio in real-time, and change weather, camera angles, and scene elements in real-time with text prompts. Genie 4 natively generates environmental sounds and voice conversations for the first time, with characters able to converse in real-time and respond to scene events; Gemini 3.8 Flash acts as a guiding intelligence in the loop, breaking down goals into steps and verifying frame by frame.
- Ars Technica · AIFeaturedDeepMind unveils Genie 4 world model promising more realistic physics and humans
Google DeepMind announced the Genie 4 world model, claiming it outperforms Genie 3 in almost every aspect, with more realistic physics simulations and character representations. Some improvements come from Google's updated Gemini model.
- The Verge · AIGoogle’s next Genie AI model generates more realistic experiences
Google releases Genie 4 world model, supporting more realistic interactive experiences. The model adopts the Gemini 3.8 Flash architecture, capable of updating experiences in real-time via natural language, generating audio, and supporting scenes up to two minutes long (an improvement over Genie 3's one minute).