• Menu
  • Skip to right header navigation
  • Skip to main content
  • Skip to primary sidebar

DigiBanker

Bringing you cutting-edge new technologies and disruptive financial innovations.

  • Home
  • Pricing
  • Features
    • Overview Of Features
    • Search
    • Favorites
  • Share!
  • Log In
  • Home
  • Pricing
  • Features
    • Overview Of Features
    • Search
    • Favorites
  • Share!
  • Log In

Google DeepMind’s foundation world model can simulate real world scenarios by remembering what it has generated and reasoning over long time horizons and can be used to train general-purpose AI agents essential to reaching “artificial general intelligence”

August 7, 2025 //  by Finnovate

Google DeepMind has revealed Genie 3, its latest foundation world model that can be used to train general-purpose AI agents, a capability that the AI lab says makes for a crucial stepping stone on the path to “artificial general intelligence,” or human-like intelligence. Still in research preview and not publicly available, Genie 3 builds on both its predecessor Genie 2 and DeepMind’s latest video generation model Veo 3. Perhaps most importantly, Genie 3’s simulations stay physically consistent over time because the model can remember what it previously generated — a capability that DeepMind says its researchers didn’t explicitly program into the model. While Genie 3 has implications for educational experiences, gaming or prototyping creative concepts, its real unlock will manifest in training agents for general-purpose tasks, which he said is essential to reaching AGI.  “We think world models are key on the path to AGI, specifically for embodied agents, where simulating real world scenarios is particularly challenging,” Jack Parker-Holder, a research scientist on DeepMind’s open-endedness team, said. Genie 3 is supposedly designed to solve that bottleneck. Like Veo, it doesn’t rely on a hard-coded physics engine; instead, DeepMind says, the model teaches itself how the world works by remembering what it has generated and reasoning over long time horizons.  That memory, the company says, lends to consistency in Genie 3’s simulated worlds, which in turn allows it to develop a grasp of physics, similar to how humans understand that a glass teetering on the edge of a table is about to fall, or that they should duck to avoid a falling object. Notably, DeepMind says the model also has the potential to push AI agents to their limits — forcing them to learn from their own experience, similar to how humans learn in the real world.

Read Article

Category: Additional Reading

Previous Post: « Microsoft’s paper discusses closed-domain hallucination detection method, designed to provide traceability for processes with any number of generative steps, through an evidence trail that identifies error stage and verifies each claim separately
Next Post: US-based crypto and fintech companies are expanding their platforms to build ‘super apps’ to offer a broad range of services that include tokenized RWAs, stocks, derivatives, ETF tokens and prediction markets, indicating unification of crypto UX »

Copyright © 2025 Finnovate Research · All Rights Reserved · Privacy Policy
Finnovate Research · Knyvett House · Watermans Business Park · The Causeway Staines · TW18 3BA · United Kingdom · About · Contact Us · Tel: +44-20-3070-0188

We use cookies to provide the best website experience for you. If you continue to use this site we will assume that you are happy with it.