Google has released Genie 4, a new world model within its Project Genie experience, to eligible Google AI Ultra subscribers. The update also includes upgrades to Genie 3, a Project Genie agent to help users build worlds, and a community gallery for discovering and remixing creations. Genie 4 allows users to edit generated environments mid-session with new prompts and adds real-time native audio that adapts to the scene.
blog.google
· 2026-11-18
Databricks released an updated version of its Genie AI agent that can complete extended, multi-step tasks without supervision, using an ontology built from customer data stored on the Databricks platform. CEO Ali Ghodsi demonstrated the tool by showing chats where Genie analyzed employee survey weaknesses, summarized a failed sales pitch, and prepared him for a podcast interview.
techcrunch.com
· 2026-11-11
Google announced Gemini 4 Carbon, a new large language model aimed at cybersecurity professionals for detecting and patching software vulnerabilities, which it says outperforms its own Gemini 4 Argon and OpenAI's GPT-6 Astra on benchmarks. The company also released Genie 4, a world model that simulates physical environments and now supports audio like background noise and dialogue. Both models remain restricted: Gemini 4 Carbon is limited to select cybersecurity experts while Genie 4 has a waitlist, with no public release date confirmed.
cnet.com
· 2026-10-28
Google announced Genie 4, a real-time world model that builds on Gemini Omni and can maintain a consistent simulated environment for up to two minutes, double its Genie 3 predecessor. Users can alter scenes in real time with natural language prompts, including weather, camera movement, and new objects or characters, while the model generates ambient sound and adaptive human dialogue. Genie 4 works alongside Gemini 3.8 Flash, which breaks down prompts into steps, and is currently limited to select trusted testers in a research preview.
androidauthority.com
· 2026-10-28
Google introduced a new AI world model capable of simulating environments by generating not only video but also accompanying human voices. The company described the system as part of its broader effort toward understanding and simulating the world, which it frames as a key step toward artificial general intelligence.
gizmodo.com
· 2026-10-27
Google DeepMind released Genie 4 in research preview, a world model that generates photorealistic, interactive environments with real-time audio including music, ambient sound, and dialogue. The new model allows mid-simulation prompt edits like changing weather or camera angle, maintains consistent scenes for up to two minutes, and offers improved physics and more lifelike characters compared to last year's Genie 3. It's currently available to select testers, with broader access planned for Google AI Ultra subscribers.
tech.slashdot.org
· 2026-10-27
Google DeepMind released Genie 4 in research preview, a world model that generates photorealistic, interactive simulated environments with synchronized audio including music, ambient sound, and dialogue. Users can edit scenes mid-simulation, such as changing weather or camera angles, and the model can maintain a consistent scene for up to two minutes, twice as long as its predecessor Genie 3. Gemini now acts as a planning layer that directs Genie 4's visual generation, including an experiment where it broke down robotics tasks for real-time simulation.
techcrunch.com
· 2026-10-27
Google DeepMind is running trusted-tester programs for Genie 4, an experimental AI world model that generates photorealistic, interactive simulations with native audio and real-time steering. Testers from film, journalism, education, gaming and engineering are trying it for tasks like pre-visualizing film scenes, turning archival photos into explorable environments, and rapidly prototyping game concepts.
deepmind.google
· 2026-10-27
Google DeepMind has released Genie 4, an upgraded world model that generates interactive virtual environments frame by frame from text prompts, now with audio support and more realistic human characters. The new version uses Gemini 3.8 Flash as a guiding agent to track goals and keep simulations consistent, though DeepMind says scenes still only hold together for a few minutes before losing context. Genie 4 also retains the ability to alter weather, add elements, or move the camera mid-simulation, as in Genie 3.
arstechnica.com
· 2026-10-27
Google announced Genie 4, a new AI world model that generates interactive experiences lasting up to two minutes, doubling the length possible with its predecessor Genie 3. The update adds real-time editing via natural language prompts, audio generation, and runs on Gemini 3.8 Flash, though Google warns object permanence can degrade over longer simulations.
theverge.com
· 2026-10-27
A developer built WorldTUI, a 360-million-parameter model based on Qwen2.5-Coder-0.5B, fine-tuned on recorded terminal sessions from real programs run in Docker. The model has no actual shell or filesystem behind it; it predicts screen changes in response to each keypress, and can simulate file creation, vim, tmux, and even the game snake. A browser demo lets users test it, including typing a misspelled command to reveal it's not a genuine shell.
simedw.com
· 2026-10-22
Databricks has acquired Row Zero, an early-stage startup whose cloud spreadsheet tool scales beyond 1 million live rows. Databricks plans to combine Row Zero with its Genie AI agent so users can query and manipulate secured data using familiar spreadsheet formulas rather than exporting it elsewhere. Terms were not disclosed; Row Zero had raised $10 million in May 2025 at a $40 million valuation, per PitchBook.
techcrunch.com
· 2026-09-24