Skip to content
Hacker News · AI·· 2 h agoPicksAI score80

Google launches agentic video understanding in Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite

Agentic Video in Gemini

AI summary

5 Flash-Lite, cutting token consumption by up to 88%, analysis costs by up to 66% and improving accuracy by up to 7%. Instead of ingesting video at a fixed frame rate, the model uses native video tools in an agentic loop to search frames, audio and transcripts and fetch only the needed segments, enabling sub-second moment retrieval, long-form needle-in-a-haystack search, anomaly detection and object counting.

Why it matters

Google DeepMind details how agentic video understanding trades fixed-frame sampling for goal-directed segment search, cutting token use by up to 88% on long-form video.

Source:Hacker News · AI · blog.google