Skip to main content
See every side of every news story
Published loading...Updated

Why World Models Like Google’s Project Genie Work

Project Genie uses AI models to create short, explorable 3D worlds from text or images with 60-second sessions, initially for U.S. AI Ultra subscribers.

  • Google DeepMind rolled out Project Genie through Google Labs, now available to US AI Ultra subscribers paying $250 and 18 or older.
  • Google DeepMind said it released Project Genie to gather user feedback and train agents toward automated general intelligence by engaging external testers and users.
  • Users create worlds by prompting and Nano Banana Pro sketches a preview, while Genie 3 autoregressively generates pixel-consistent frames at 24 frames per second in 720p with minute-scale session consistency.
  • The rollout has already drawn attention from the video gaming industry as Project Genie raises concern among developers amid layoffs and negativity, while prototype guardrails and short session limits restrict early access.
  • DeepMind says the team plans enhancements and eventual scaling to persistent worlds, acknowledging glitches like lagging controls and characters walking through walls, while other labs like Runway are entering world-model development.
Insights by Ground AI
Podcasts & Opinions

20 Articles

Think freely.Subscribe and get full access to Ground NewsSubscriptions start at $9.99/yearSubscribe

Bias Distribution

  • 50% of the sources are Center
50% Center

Factuality Info Icon

To view factuality data please Upgrade to Premium

Ownership

Info Icon

To view ownership data please Upgrade to Vantage

Forbes broke the news in United States on Thursday, January 29, 2026.
Too Big Arrow Icon
Sources are mostly out of (0)

Similar News Topics

News
Feed Dots Icon
For You
Search Icon
Search
Blindspot LogoBlindspotLocal