Artificial Intelligence · Models & labs · 4 outlets (L 0 · C 0 · R 0 · 4 not rated)
Google DeepMind announces Genie 4 world model with audio
Google DeepMind announced Genie 4, an AI world model for generating interactive experiences.[1, 2, 3 +1] The Verge reported the model allows more realistic worlds, real-time updates via natural language prompt, audio generation, and uses Gemini 3.8 Flash under the hood.[4] TechCrunch described it as a research preview for trusted testers with real-time audio and mid-simulation text prompts.[2]
Ars Technica reported Genie 4 will roll out to developers and Google AI Ultra subscribers soon.[1] The Decoder reported Gemini models help plan in the background to keep the simulation consistent, but longer sessions lead to visual inconsistencies in the early research model.[3]
Covered by Ars Technica, TechCrunch, The Decoder and 1 more
Read first DeepMind's Genie 4 world model adds audio and more realistic people to simulations
How balanced is this coverage?
None of the 4 outlets that covered it has a lean score, so none can be placed left to right.
Too few left- or right-leaning outlets to compare: 0 of 42 left-leaning, 0 of 33 center and 0 of 38 right-leaning outlets covered it.
No rated outlet covered it, so there is nothing to place on the axis.
Not rated Ars Technica, The Decoder, TechCrunch, The Verge. Not placed: they have no lean score.