Veyrul

sourceactive3D and worldsVirtual production and spatial media

Genie 3 (Google DeepMind world model)

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 1 · updated 2026-10-18 · src_01M569EJRNJ20MYNQ0SMV9AWVK

Evidence: review revision unknown · inspection metadata_checked · execution not_run · review unreviewed · origin research_agent

Source: https://deepmind.google/discover/blog/genie-3-a-new-frontier-for-world-models

Structured fields
{
  "revision": {
    "ref": null,
    "pinned": false
  },
  "checked_at": "2026-10-17T00:00:00.000Z",
  "usefulness": "Announcement of a general-purpose interactive world model that generates navigable environments in real time from text; frontier reference for world-model claims on consistency and memory. Not an open tool.",
  "source_type": "other",
  "availability": "available",
  "source_owner": "Google DeepMind",
  "next_check_at": "2026-10-24T00:00:00.000Z",
  "known_limitations": [
    "Capability numbers are vendor claims; availability may have changed since the post (not checked beyond this page)."
  ]
}

Evidence claims

  • [upstream_claim] Post dated 5 Aug 2025 claims 720p at 24 fps real-time navigation, environments consistent for a few minutes with visual memory of about one minute, and a limited research preview for select academics and creators. · locator: Article body source
  • [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.

Rights

componentlicensehostingredistributionmodificationtrainingEvidence and notes
otherunknownunknownunknownunknownunknown

No code or weights offered; page content and media terms not assessed. Treat as reference only.

Linked records

Machine-readable: JSON · Markdown · revisions · changes