Google DeepMind Releases Genie 4 Preview With Audio, Longer Simulations and Planned API Access

1. 22:22
   雷锋网

   Genie 4 Explained: Technical Challenges in Moving From Video Generation to World Control

   Leiphone analyzes three challenges in Google DeepMind’s Genie 4 world model: incorporating changing language instructions, verifying causal outcomes, and coordinating asynchronous models. It examines how visually coherent simulations could create self-confirming success judgments and discusses independent checks, instruction timing, and layered memory as possible approaches. The article distinguishes these proposals from implementation details DeepMind has not disclosed.

2. 13:55
   Latent Space

   Gemini 4 Carbon tops leaderboards, launches for cyber defenders

   Google DeepMind announced Gemini 4 Carbon, initially available to trusted cyber defenders through the Fairwind Program, with wider developer access promised as soon as possible. Latent Space reports that Carbon leads Artificial Analysis Intelligence Index v5 with a score of 59 and ranks #1 in Text Arena, while trailing some rivals on coding benchmarks. The model supports a 1M-token context window, accepts text, image, video and speech inputs, and produces text output.

3. 00:59
   The DecoderPicks

   Google opens Android development to third-party AI agents and unveils new Gemini APIs

   Google introduced Android Studio Rabbit 2 with support for more than 40 coding agents through the open Agent Client Protocol, including Claude, Codex, and Google Antigravity. Android CLI updates add Compose previews and memory leak analysis for agents. Google also announced an alpha Agentic API powered by Gemini Nano 4, a beta AppFunctions API for shared tool calling, and a Connected Apps Platform preview linking apps to Google Search and Gemini.

1. 14:03
   雷锋网

   Huawei Wireless Unveils Innovations for Next-Generation Networks

   At Huawei’s Decoding China 2026 event, company vice president Fang Xiang announced a portfolio of innovations for next-generation communications networks. Huawei introduced VitaAAU, which it describes as the world’s first commercial U6GHz device, alongside its GigaGreen Plus and UBBPi series. VitaAAU has begun commercial deployment in markets including the UAE, while Huawei says its RANSpirit system is deployed across more than 25 large-scale networks worldwide.

2. 07:59
   Demis Hassabis · X

   Demis Hassabis introduces Genie 4 with real-time physics, reasoning, and audio

   Demis Hassabis shares Genie 4, describing it as an interactive world model bringing together real-time physics, reasoning, and audio, with simulations within simulations. In the quoted announcement, Google DeepMind describes exploring dynamic environments in real time, including how scenes respond and sound and how people move, react, and speak. https://twitter.com/GoogleDeepMind/status/2115114028338962672

3. 01:25
   The Decoder

   Google DeepMind introduces Genie 4 with real-time sound and Gemini-guided world simulation

   Google DeepMind introduced Genie 4, an experimental world model that generates interactive scenes frame by frame, including sound and character dialogue, with Gemini models planning events to maintain coherence. Users navigate with a keyboard and steer events through text prompts, but longer sessions can lose visual consistency and object persistence. Access is currently limited to select testers, with Google AI Ultra availability in the Project Genie web app planned soon.

4. 01:11
   Logan Kilpatrick · X

   Google Teases Genie 4, a Frontier World Model Coming Soon to the API

   An early look at Genie 4, our new frontier world model, coming soon to the API for the first time : ) https://t.co/Q6v1qgg0W1

5. 00:30
   TechCrunch · AIPicks

   Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering

   Google DeepMind released Genie 4 in research preview on Tuesday, adding synchronized real-time audio, more photorealistic worlds, and scene changes through prompts during simulations. It maintains consistent scenes for up to two minutes, double Genie 3’s limit, though objects can drift and audio accuracy and text legibility remain challenges. Trusted testers have access now, with rollout to Google AI Ultra subscribers in Project Genie and early access partners of the Gemini API and Google AI Studio planned in the coming weeks.

6. 00:15
   Sundar Pichai · XPicks

   Google introduces Genie 4 world model with real-time interaction and native audio

   Sundar Pichai introduced Genie 4 as Google's most realistic and interactive world model, with real-time control over environments, native audio including conversational characters, photorealistic scenes, and real-world physics simulation. It uses Gemini reasoning for more coherent multi-step events. A research preview has begun rolling out to trusted testers, with access coming soon to Google AI Ultra subscribers in Project Genie and early access partners through the Gemini API and AI Studio.

7. 00:13
   Google AI · XPicks

   Google DeepMind introduces Genie 4 with real-time world and soundscape control

   Introducing Genie 4 from @GoogleDeepMind, which Google AI describes as its most realistic and interactive world model yet 🌍 Users can use natural language to dynamically steer the world and its soundscape in real time, including changing the weather, moving the camera, or introducing new elements. https://t.co/ZfZGi9Chsx

8. 00:10
   Google DeepMind · XPicks

   Google DeepMind introduces Genie 4, its most realistic and interactive world model yet

   Google DeepMind introduces Genie 4 as its 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. https://t.co/6mmSUm9BBO

9. 00:01
   Google DeepMindPicks

   Google DeepMind announces Genie 4 for real-time world simulation with native audio

   Google DeepMind has released Genie 4 as a research preview for trusted testers, adding native audio, interactive dialogue, and real-time natural-language steering to world simulation. Gemini 3.8 Flash guides multi-step events by observing scenes, planning actions, and checking progress. Access is coming soon to Google AI Ultra subscribers in Project Genie and early access partners in the Gemini API and Google AI Studio; object permanence, physical interactions, and long-term consistency remain research challenges.

10. 00:00
    Ars Technica · AI

    Google DeepMind Unveils Genie 4, a World Model With More Realistic Physics and Humans

    Google DeepMind has unveiled Genie 4, an updated world model that improves on Genie 3 in almost every way, including more realistic physics and humans. The model generates virtual worlds frame by frame in real time as users explore them, and DeepMind says the technology could provide training environments for physical robots or support rapid prototyping in creative fields.

11. 00:00
    The Verge · AI

    Google announces Genie 4 with more realistic interactive worlds and audio generation

    Google announced Genie 4, a world model that it says generates more realistic interactive experiences, supports real-time natural language updates, generates audio, and uses Gemini 3.8 Flash for simulations. Experiences can last about two minutes, up from one minute with Genie 3, though details and object permanence can shift over time. It launches as a research preview for trusted testers, with Google AI Ultra access coming soon and a waitlist for Project Genie.

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.