Understand this story
On October 27, 2026, Google DeepMind released the world model Genie 4, focused on real-time interactive simulation and introducing native audio to the series for the first time. According to the official introduction, the model is built on capabilities from the Gemini family: Gemini Omni is responsible for making the simulation match the appearance and behavior of the real world, while other Gemini models provide the complex reasoning needed to maintain the simulation's coherence; users can control scenes in real time using natural language, and each world also instantly generates ambient sound, music, and interactive dialogue. The next day, Google DeepMind further explained that Gemini 3.8 Flash breaks down goals in a loop and checks frames to maintain causal coherence across multi-step events, and that Gemini 4 Argon has also been used to jointly simulate tasks with Gemini Robotics; the company said it remains an early experimental model, that object permanence and complex physical interactions still drift during long runs, that all generated content carries a SynthID watermark, and that it is currently being previewed to trusted testers first. On October 28, Ethan Mollick posted that Genie 4 can run DOOM, and tested it generating a game-like environment as it goes, saying the experience is not perfect. On October 29, Peter Yang used Genie 4 to build 5 worlds in real time, arguing that world models are the next big direction for AI after LLMs.
AI-generated from public reports
Latest development · Report
Google Admits AI Mode Drags Down Search Revenue, Market Cap Falls 15% in a Single Day, Erasing $500 BillionDevelopments
4 confirmed developments
Peter Yang proposes that world models are the next big direction after LLMs
Source:Peter Yang- Source:Ethan Mollick
Ethan Mollick says Genie 4's real-time generation of gamified environments is an amazing experience
Source:Ethan Mollick- Source:Google Blog
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 31
Latent Space
Google Admits AI Mode Drags Down Search Revenue, Market Cap Falls 15% in a Single Day, Erasing $500 Billion
Google Chief Business Officer Philipp Schindler said in the earnings report that AI Mode queries are growing strongly, but AI Mode's monetization capability is lower, which has affected revenue. Combined with other poor earnings data, tech stocks fell sharply, and Google's market cap dropped 15%, about $500 billion, its worst performance since its 2004 IPO. The article also mentions that OpenAI is raising funds at a $1.25 trillion valuation rather than $1.4 trillion, and the backdrop of cooling public-market sentiment toward AI.
Oct 30
TMTPost · AGI
ByteDance World Model Exposed: Zhang Yiming's Strategy and Its Divergence from Google Genie 4's Approach
A TMTPost article states that ByteDance has listed world models as one of its four major AI priorities for 2026, with the goal of releasing at least one version by the end of the year, benchmarked against Google Genie 3, and that users can enter cloud-generated worlds via Pico headsets using voice and motion. The article also reviews Google Genie 4, released on October 28, which supports real-time changes to weather, camera movement, and the introduction of characters using natural language, and adds sound for the first time. The article also mentions that ByteDance's internal evaluations show its world model's overall performance is about 10% behind the then-current global SOTA, with generation metrics at about 20fps.
TMTPost · AGIRelated discussion
TMTPost · AGI joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Latent Space
Elorian Releases DecoyCount Benchmark: Frontier Models All Score Below 50% on Visual Counting Accuracy
Elorian and Mercor jointly released the DecoyCount benchmark, which tests whether models truly count objects or rely on visual shortcuts. Frontier models all scored below 50% accuracy, with the highest being GPT-6 Astra at 43.17%. Elorian says its visual reasoning model Glimpse scored 50.48% in a single run on 1,660 questions, making it the only model to exceed 50%, but this result comes from internal testing and did not use an agent or tool framework, whereas the six models in the paper each took the average of three runs. Elorian CEO Andrew Dai said the benchmark examines both vision and reasoning, and can distinguish whether a model failed to see the objects or miscounted them.
Oct 29
Leiphone.com
Leiphone.com's In-Depth Breakdown of Google DeepMind's World Model Genie 4
Google DeepMind has released Genie 4, a new-generation world model that can generate interactive environments in real time and collaborates with Gemini 3.8 Flash through a division of labor: the latter observes the visuals, decomposes tasks, and adjusts plans. Leiphone.com analyzes its technical challenges from three aspects—dynamic language condition injection, Agent causal hallucination, and dual-model asynchronous collaboration—and notes that DeepMind has not yet disclosed the network architecture or scheduling implementation of Genie 4.
CNET
Google Releases Two New Models: Gemini 4 Carbon and Genie 4
Google has released the large language model Gemini 4 Carbon and the world model Genie 4; the former surpasses its own Gemini 4 Argon and OpenAI's GPT-6 Astra on comprehensive capability benchmarks. Gemini 4 Carbon focuses on vulnerability detection and patching and is currently available only to select cybersecurity experts; Genie 4 adds audio capabilities, allowing developers to add background sound and dialogue to AI worlds, and a waitlist is now open.
Peter Yang
Peter Yang uses Genie 4 to build 5 worlds in real time
Peter Yang believes that world models are the next big direction for AI after LLMs. In a new video, he demonstrates how to use Google Genie 4 + Gemini to build 5 worlds in real time, including a monster attacking San Francisco, eating ramen at a street stall in Tokyo, and riding a dragon to attack a castle; he says the visuals are excellent, but what impressed him more was the real-time audio and interactivity, and he shares his views on the impact on film and games.
Oct 28
The Rundown AI
Google DeepMind releases the Genie 4 world model, which can generate sound effects and converse with characters in the scene
Google DeepMind has released Genie 4, a new-generation world model that can turn prompts into explorable, realistic scenes in real time, and for the first time the Genie model itself generates background sounds and music, while characters in the scene can also hold real-time conversations. Users move via the keyboard and use text prompts to modify content in the scene instantly, with the scene remaining coherent across multiple inputs. In the demo, a simulated Apptronik Apollo robot plays checkers, with each move planned by Gemini 4 Argon, pointing to Genie's future use in robot training.
Testing Catalog
October 28 AI Daily Brief: Genie 4 and MAI-Image-2.7 Released
Google DeepMind released the interactive world model Genie 4, which supports natural language control and native audio. It is first being opened to Trusted Testers, with later integration into Google AI Ultra and the Gemini API. Microsoft AI launched the image editing model MAI-Image-2.7-Preview, ranking 3rd on Arena Edit and 2nd on AA-Image-Editing. Liquid AI open-sourced the LFM3 series of six 2B-class text, vision, audio, and omni-modal models, using a triple-hybrid architecture.
Latent Space
Anthropic Abolishes Coding Interviews: Felix Reiseberg Says "Hunger beats tenure"
Anthropic hiring manager Felix Reiseberg announced that the company will no longer use traditional coding interviews to evaluate candidates, citing the fact that Claude is already stronger than humans at both React challenges and assembly problems, and that truly impactful builders do not win through such tests. He advises junior engineers to pick an idea that can drive business impact, build a working prototype over the weekend, focus on just one good idea, and leverage their fresh perspective on users. On the same day, Google DeepMind released the Genie 4 world model, and Claude Opus 5.5 (58 points) topped the Artificial Analysis Intelligence Index v5.
ScienceNet
Google DeepMind Releases Research Preview of World Model Genie 4
On October 27, Google DeepMind released a research preview of its new-generation world model Genie 4, extending the simulation duration for scene consistency to about two minutes—twice that of its predecessor Genie 3—and improving visual realism, physics simulation, and the naturalness of character movements. The model supports real-time changes to weather, viewpoint adjustments, or adding characters and objects via natural language instructions, and features native audio generation capabilities. Google also demonstrated an experiment in which Genie 4, in collaboration with Gemini 4 Argon, simulated Apptronik's Apollo humanoid robot playing checkers, and plans to open it to Google AI Ultra subscribers through Project Genie in the coming weeks.
MarkTechPost
Google DeepMind Releases Genie 4 Real-Time World Model with Native Audio Generation
Google DeepMind has released the Genie 4 world model as a research preview to trusted testers; it can generate explorable worlds in real time from text and image prompts, and natively generate ambient sound, music, and character dialogue. The model introduces Gemini 3.8 Flash as a planner within the simulation loop, responsible for breaking down goals, inspecting frames, and replanning, which DeepMind calls an early step toward hybrid world models. Genie 4 is hosted only on Google's platform and will later be opened to AI Ultra users and Gemini API partners; all video and audio carry SynthID watermarks.
36Kr · AISelected
Google DeepMind releases the world model Genie 4, supporting real-time interaction and native audio
On October 27, Google DeepMind launched its next-generation world model Genie 4, calling it the most realistic and interactive world model to date, with a single generated interactive experience lasting up to 2 minutes, compared with 1 minute for the previous generation, Genie 3. The new model introduces native audio generation, real-time control via natural language, and simulation of complex physics and character behavior, while the Gemini series of models handles instruction translation, event planning, and progress tracking. Genie 4 is currently available as a research preview to a small number of trusted testers, and will later be provided to Google AI Ultra subscribers and early partners of the Gemini API and Google AI Studio.
Analytics India Magazine
Google DeepMind Releases Genie 4 Real-Time World Model
Google DeepMind has released Genie 4, which can generate interactive 3D environments with realistic visuals, sound, and dialogue in real time; it is currently available as a research preview to trusted testers in the creative, news, education, gaming, and engineering fields. The model combines capabilities from the Gemini series, supports modifying scenes, weather, camera angles, and characters via natural language prompts, and natively generates ambient sound and interactive dialogue. Gemini 3.8 Flash acts as a guiding agent in complex simulations, handling task decomposition and progress checks, and all generated content carries a SynthID watermark.
English text is being prepared.
Google DeepMind Releases World Model Genie 4, Supporting Native Audio Generation
Google DeepMind has officially released its new-generation world model Genie 4. Compared with Genie 3, it improves visual realism, physical simulation, and real-time interaction capabilities, and for the first time supports native audio generation, capable of synchronously generating ambient sound effects, music, and character dialogue. Users can control the camera or character movement with the keyboard, and can also use natural language instructions to adjust weather, switch viewpoints, and add characters or objects in real time, without needing to regenerate the entire scene. Genie 4 integrates capabilities from the Gemini series: Gemini Omni provides real-world visual and behavioral knowledge, while Gemini 3.8 Flash handles task planning and scene guidance. It is currently available as a research preview to some invited testers, with plans to later open it through Project Genie to Google AI Ultra subscribers and some developers.
The PaperSelected
Google DeepMind Releases Research Preview of World Model Genie 4
Google's DeepMind has released a research preview of its new-generation world model Genie 4, extending the simulation duration for scene consistency to about two minutes—twice that of the previous generation Genie 3—while improving visual realism, physics simulation, and the naturalness of character movements. Users can use natural language instructions to change the weather in real time, adjust the viewing angle, or add characters and objects within the simulation, and the model also features native audio generation capabilities. Google also demonstrated an experiment in which Genie 4 collaborates with the large model Gemini 4 Argon to simulate Apptronik's Apollo humanoid robot playing checkers, and plans to make it available to Google AI Ultra subscribers through Project Genie in the coming weeks.
Ethan Mollick
Ethan Mollick tests Genie 4 generating a Victorian afternoon tea scene in real time
Ethan Mollick used Genie 4 to generate a Victorian afternoon tea scene in real time, entering commands such as "a mouse in formal attire," "a porcupine walks by," "the mouse grows wings," and "the mouse flies toward the teacup," and said he could walk freely around the scene. He stated that the visuals still have flaws, but that the progress compared with two years ago is enormous.
indigo
Google Genie 4 launches, built on Gemini Omni
Google Genie 4 launches, built on Gemini Omni, and can present realistic details in spaces and specific themes. This version features advanced physics effects, fully real-time control, support for ambient sound effects, music, background noise, and interactive dialogue, and uses Gemini reasoning to plan multi-step events to maintain coherence as scenes evolve.
36Kr · AISelected
Google DeepMind releases the world model Genie 4, natively generating sound and dialogue for the first time
Google DeepMind has released Genie 4, a new-generation general-purpose world model. For the first time in the Genie series, it natively generates ambient sound and improvised character dialogue, doubles the duration of a single coherent world to about 2 minutes, and renders real-machine footage at about 24 frames per second. The model uses Gemini 3.8 Flash to perform multi-step reasoning and control in the background and Gemini 4 Argon to break down action instructions, forming a hybrid world model architecture. It has opened beta applications to Google AI Ultra users and is also available in the Gemini API and Google AI Studio.
English text is being prepared.
Google DeepMind launches world model Genie 4, achieving synchronized audio-video generation for the first time
Google DeepMind launched the world model Genie 4 on Tuesday. Currently in research preview, it can generate interactive virtual worlds and modify scenes by entering prompts during simulation runs. The model can generate real-time audio synchronized with the virtual world, covering music, ambient sound, and interactive dialogue, and scenes can remain coherent for up to two minutes—twice as long as the previous generation, Genie 3. Genie 4 will be gradually opened to Google AI Ultra subscribers, the Genie program, and early partners of the Gemini API and Google AI Studio. The team also acknowledges that the longer the simulation runs, the more easily details drift, and that audio accuracy and on-screen text clarity remain unresolved.
IT Home · Artificial Intelligence
Google DeepMind releases the Genie 4 world model, supporting real-time natural language modification
Google DeepMind has released the Genie 4 world model, positioned as a major research milestone, allowing users to use natural language instructions to change weather, camera, and characters in real time. It is DeepMind's first model to natively generate audio within real-time world simulation, with audio and visuals produced synchronously, and it shows stronger performance in physical scenarios such as aerodynamics and collisions as well as in character movements. Genie 4 is currently available only as a research preview to trusted testers, and in the coming weeks will expand to Project Genie for Google AI Ultra subscribers as well as early partners of the Gemini API and Google AI Studio; engineer Diego Rivas acknowledged that long-duration simulations may show detail drift, and that audio accuracy and the readability of in-frame text have not yet been fully resolved.
SiliconANGLE
Google previews Genie 4 world model, which can generate 3D environments with audio
Google previews the Genie 4 world model, which can generate realistic three-dimensional environments based on natural language descriptions and supports editing operations such as changing the weather and adding objects with follow-up prompts. Compared with the previous generation, Genie 4 is better at rendering complex details such as fluid motion, can also generate accompanying audio such as crashing waves, and makes virtual characters move naturally and be controllable through real-time interaction. Internally, the model calls Gemini Omni to ensure visual realism and Gemini 3.8 Flash to maintain inter-frame consistency. It is currently being tested with a small number of early users and will later be offered through the Google AI Ultra subscription, the Gemini API, and Google AI Studio.
AYi AI Notes
Google DeepMind releases the world model Genie 4, supporting real-time text-based scene changes and native ambient sound
Google DeepMind has officially released the world model Genie 4, which supports real-time text-based scene changes, comes with native ambient sound and interactive dialogue, and has Gemini 3.8 Flash serving as the behind-the-scenes director. Unlike pre-rendered video models, Genie 4 simulates physical collisions in real time as the player acts within the scene, and a single simulation can remain continuously stable for about two minutes. The author believes its real purpose is to provide a low-cost physical training ground for embodied agents, but it is currently still a research preview available to only a few testers, and details drift over time.
sspai
Morning Brief: Apple releases M6 iMac and MacBook Pro, Google DeepMind releases…
On October 27, Apple released a 24-inch iMac and a 14-inch MacBook Pro equipped with the M6 chip. The iMac starts at 12,499 yuan in China, and the MacBook Pro starts at 15,999 yuan; both go on sale officially on November 6. Google DeepMind released the world model Genie 4 the same day, integrating the capabilities of the Gemini series of models, supporting real-time scene adjustment via natural language and generating native audio, and has rolled it out to a small number of trusted testers. Ant Group released the AI assistant Lingguang 2.0, adding cross-session memory, long-horizon task scheduling and tool connectivity, with its positioning shifting from task executor to affairs manager.
Google BlogFirst-partySelected
Alphabet Q3 2026 Earnings: Revenue Up 25% Year-over-Year, Gemini App Reaches 1 Billion Users
Alphabet's Q3 2026 revenue grew 25% year-over-year, with annualized revenue reaching $500 billion, and Google Cloud revenue up 103%. CEO Sundar Pichai said first-party model APIs process nearly 32 billion tokens per minute, 40% more than last quarter; the Gemini app has reached 1 billion users, making it the fastest-growing product in Google's history. A new model in the Gemini 4 series, Carbon, was also released that day; it ranks first on the Artificial Analysis Intelligence Index with a score of 59, will first be made available to select trusted cybersecurity defenders, and is being tested by the U.S. government.
Demis Hassabis
DeepMind Releases Interactive World Model Genie 4
Demis Hassabis shared Google DeepMind's interactive world model Genie 4, saying it integrates real-time physics, reasoning, and audio capabilities. The official Google DeepMind account called it its most realistic and interactive world model to date, allowing real-time exploration of dynamic environments and observation of how scenes respond, produce sound, and how the people within them move, react, and speak. Hassabis also mentioned simulations nested within simulations.
The New Stack
Google DeepMind releases the Genie 4 world model, providing AI agents with an interactive testing environment
Google DeepMind has released the Genie 4 world model, which can render interactive environments in real time with simulated physics, human motion, and native audio, with Gemini Omni shaping the scenes and Gemini 3.8 Flash planning the next steps. Genie 4 lets developers generate testing environments on demand, for scenarios such as the Apptronik Apollo humanoid robot playing checkers, but Google acknowledges that its physics is not always accurate, and objects may shift or behave abnormally during long runs. Google has not yet published benchmark data for Genie 4 in repeated agent testing, including whether the same prompt can produce consistent results.
Ayi AI Notes
Google DeepMind Releases World Model Genie 4
Google DeepMind has released the world model Genie 4, which supports real-time text-based scene modification, native ambient sound, and interactive dialogue, with Gemini 3.8 Flash serving as the real-time director in the background. The author says it no longer pre-renders video, but instead simulates physical collisions in real time and dynamically loads scenes as the player acts. Currently, the limit for a single simulation is about two minutes; over time, details will drift, and it is only a research preview available to a small number of testers.
The Decoder
Google DeepMind releases Genie 4 world model, capable of generating interactive scenes with sound in real time
Google DeepMind launches Genie 4, the successor to Genie 3. It is its first real-time world model capable of directly generating sound, computing scenes frame by frame and responding to users' keyboard operations and text prompts. Gemini models handle planning in the background; for example, Gemini 3.8 Flash continuously observes the screen, breaks goals into steps, and checks the result of each step. DeepMind is also testing the use of Gemini 4 Argon to combine Genie with its robotics research Gemini Robotics; in a demo, it simulated the Apptronik humanoid robot Apollo playing chess. DeepMind says the model is still an early experimental version: visual details drift over long simulations, objects do not necessarily persist, and it is currently limited to select testers. All videos and audio tracks will carry a SynthID watermark.
WallstreetcnSelected
Google Launches World Model Genie 4, Doubling Simulation Duration to 2 Minutes and Achieving Synchronized Audio-Video Generation for the First Time
Google has released its new-generation world model Genie 4, which extends the maximum simulation duration to about 2 minutes, twice that of Genie 3, and for the first time achieves synchronized audio-video generation. Users can use natural language to change the environment, control the camera, and add characters in real time. The model is currently available as a research preview to a small number of screened testers, will be opened to Google AI Ultra subscribers in the coming weeks, and will gradually provide early access to some developers via the Gemini API and Google AI Studio. Google says Gemini is responsible for providing reasoning and planning for the simulated world, while the actual real-time interactive operation runs on the lighter Gemini 3.8 Flash, and all generated audio and video are embedded with SynthID watermarks.
Philipp SchmidSelected
Google Releases Genie 4, a Real-Time Multimodal World Model
Google has released Genie 4, adding native audio, movable and talking characters, more refined physics, and real-time prompt editing. Genie is a real-time multimodal world model that can render playable environments frame by frame based on keyboard operations and text prompts. A waitlist is currently open, with priority for Google AI Ultra users.
Logan Kilpatrick
Google Teases Genie 4 World Model Coming to API
Logan Kilpatrick posted an early preview of Genie 4, calling it Google's new frontier world model, which will be available via API for the first time.
Ethan Mollick
Ethan Mollick: Genie 4 can run DOOM
Ethan Mollick posted that Genie 4 can run DOOM, and quoted an absurd description: walking through an ordinary office, every computer and every wall is running DOOM, everything is DOOM; then his colleagues turn into demons, wield chain guns, and even give him a bonus.
Ethan Mollick
Ethan Mollick tests Genie 4 generating game scenes in real time
Ethan Mollick tested Genie 4 and said it can generate game-like environments while generating, and that entering "Neogothic brutalist city inhabited by robots and horses" produces a scene in about one minute. He then asked for a dragon and a friendly otter NPC to be added, and these changes were all made in real time. He said the experience is not perfect.
TechCrunch AI
Google DeepMind releases a research preview of the world model Genie 4, adding real-time audio and real-time control
Google DeepMind has released a research preview of its world model Genie 4, which can generate more realistic interactive worlds, support real-time scene changes via prompts entered during simulation, and generate music, ambient sound, and interactive dialogue that match the scene. Genie 4 can modify weather, camera angles, or add characters and objects in real time, and maintains scene consistency for up to two minutes—twice that of its predecessor Genie 3—with improvements in physics and character anthropomorphism as well. Gemini handles the planning steps and frame checking, and the team says Genie 4 still has issues such as detail drift, audio accuracy, and the readability of in-scene text.
Testing Catalog
Google Releases World Model Genie 4, Supporting Dynamic World Modification and Native Audio
Google has officially released the world model Genie 4, which it calls its most realistic and interactive world model to date. Users can dynamically change the world with prompts and generate scenes with native audio. The model will first be opened to Trusted Testers as a research preview, and will subsequently be made available via the Gemini API and AI Studio to Google AI Ultra subscribers and early access partners.
Sundar Pichai
Google Releases Genie 4 World Model, Supporting Real-Time Control and Native Audio
Google releases the Genie 4 world model, calling it its most realistic and interactive world model to date. The model can control events, camera angles, and actions in dynamic environments in real time, generate native audio that matches the world, and use Gemini's reasoning capabilities to generate more coherent multi-step events. It is currently available as a research preview to trusted testers, and will later be offered to Google AI Ultra subscribers through Project Genie, and to early partners through the Gemini API and AI Studio.
Google AI
Google DeepMind Releases Genie 4 World Model
Google DeepMind has released the Genie 4 world model, which the company calls its most realistic and interactive world model to date. Users can control scenes and soundscapes in real time using natural language, for example by changing the weather, moving the camera, or adding new elements; Gemini acts as the simulation's "brain" behind the scenes, responsible for turning requests into actions, planning complex events, and tracking changes in the scene. Genie 4 also adds ambient sound effects and interactive voice dialogue that can be adjusted in real time.
Google DeepMindFirst-partySelected
Google DeepMind releases world model Genie 4, supporting native audio and real-time interaction
Google DeepMind has released the world model Genie 4, which can generate interactive worlds in real time and, for the first time, natively generate ambient sound and character dialogue. The model builds on capabilities from the Gemini series; Gemini 3.8 Flash breaks down goals in a loop and checks frames to maintain causal coherence across multi-step events, and Gemini 4 Argon has also been used for joint simulation tasks with Gemini Robotics. The company says it remains an early experimental model: over long runs, object permanence and complex physical interactions still drift, all generated content carries a SynthID watermark, and it is currently available in preview to trusted testers first.
Oct 27
Google BlogFirst-partySelected
Google DeepMind releases world model Genie 4, supporting real-time interactive simulation and native audio
Google DeepMind releases the world model Genie 4, focused on real-time interactive simulation and introducing native audio for the first time in the series. The model is built on capabilities from the Gemini family: Gemini Omni is responsible for making simulations match the appearance and behavior of the real world, while other Gemini models provide the complex reasoning needed to maintain simulation coherence. Users can control scenes in real time using natural language, such as moving the camera, changing the weather, or introducing new characters, and each world also generates ambient sound, music, and interactive dialogue on the fly.
Heat trend for this story
- Current
- 6
- Period peak
- 256 Oct 28 13:00
- 24-hour change
- -71%
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.