Technology & AI

Google DeepMind's Genie 4 world model enters limited research preview

The AI builds interactive virtual worlds with sound and dialogue, and users steer them through plain-language instructions as they run.

By Standard Topic. AI-generated from the reporting listed under Coverage. Published . Updated .

This story is no longer being updated. It reflects reporting up to .

What happened

Google DeepMind's Genie 4 generates interactive simulated environments in real time, producing visuals, environmental sounds, music and dialogue. Users can change a running scene with natural-language prompts. Access is currently limited to trusted testers, while Google AI Ultra subscribers and early API partners are expected to get it later.

Why it matters

Users can alter scenes midway, such as changing the weather or adding a person, which expands how the tool can be used. DeepMind says the technology is still at an early research stage.

Timeline

  1. Oct 27, 10:50 PM ET: Google DeepMind announces Genie 4, an AI that generates virtual worlds in real time.
  2. Oct 28, 12:14 PM ET: Genie 4 rolls out to trusted testers, with Google AI Ultra and early API partners to follow.
  3. Oct 28, 12:59 PM ET: DeepMind says the technology is still in an early research stage despite impressive demonstrations.
  4. Oct 28, 5:18 PM ET: Google says SynthID will mark all Genie 4 output, while only trusted testers currently have access.

Coverage

More on this story

More from Technology & AI

All Technology & AI news · Technology & AI story archive