
Featured
Google’s new anything-to-anything AI model is wild
Google’s new Gemini Omni video model can edit and generate strikingly realistic clips, but the results are still glitchy and expensive.
- Google’s Omni Flash can generate and edit video from prompts and uploaded clips.
- The Verge found it more capable than older Veo tests, but still glitchy.
- The model produced convincing deepfake-style clips of the writer herself.
theverge.com
Read storyLatest
Updated as new stories ingest
More stories on the way.
New intelligence is processed every two hours.
The Brief
One email a day. Only what matters.
Editorially curated. No noise. Unsubscribe in one click.