The paper in your inbox every morning
Straight from the source · The whole story, in order

The Tech Gazette

Ongoing Story
Vol. I No. 54 Saturday, November 14, 2026 Closing 8:46 AM UTC · next edition 10:00 AM UTC
ClosedOngoing story

Genie 4

Since Tuesday, October 27 · updated 12 days ago · 4 pieces from 4 sources, in the order they came out.

2 news · 1 announcement · 1 analysis

RSS

Its model sheet: who made it, where it runs, what it replaces →

Latest

  1. Jack Clark (Import AI)Monday, November 2Import AI 479: Spacewar; low-latency tasks versus LLMs; Genie 4
  2. Google for Developers · YouTubeTuesday, October 27Introducing Genie 4

From the start

    Tuesday, October 27

  1. NewsGoogle DeepMind · YouTube4:00 PM UTCWatch
    Genie 4: A new generation of world simulation

    Meet Genie 4, Google DeepMind’s most realistic and interactive world model yet. Built on our Gemini models, Genie 4 lets you step inside dynamic worlds in real time, steer scenes on the fly with natural language, and wat…

  2. AnnouncementGoogle DeepMind4:01 PM UTCNews
    Genie 4: A new generation of world simulation

    Genie 4: our new world model unlocking unprecedented realism in real-time simulation.

  3. NewsGoogle for Developers · YouTube4:18 PM UTCWatch
    Introducing Genie 4

    Raia Hadsell, Diego Rivas, and Hang Qi from Google DeepMind join host Logan Kilpatrick to introduce Genie 4, the latest world model from Google DeepMind. Their conversation covers: *What world models are *The arc from Ge…

  4. Monday, November 2

  5. AnalysisJack Clark (Import AI)2:30 PM UTCColumns
    Import AI 479: Spacewar; low-latency tasks versus LLMs; Genie 4

    Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe. Subscribe now LLMs are very bad at low-latency tasks…

The story so far.