Google DeepMind @GoogleDeepMind · 01 Sep 2026
We’re bringing agentic video understanding to our latest Gemini models. They can now analyze videos with better accuracy while using up to 88% fewer tokens. 🧵 https://t.co/ZTjlaLk7tX
136 059Views
1 347Likes
135Reposts
96Replies
56Quotes
266Bookmarks
Is that a lot?
1.96×vs this author's median69 443 views is typical
57Percentile for this authorof 7 recent posts
2.04×vs 1M–10M median66 615 views is typical
8.98%Reachviews ÷ followers
1.20%Engagement rateof viewers reacted