Models & Labs
Google DeepMind Launches Agentic Video Understanding
Google DeepMindhigh confidence
Why it matters
- →Agentic video understanding significantly reduces token usage and costs for video analysis.
- →It enhances accuracy and efficiency, especially for long-form video content.
- →The technology positions Gemini models at the forefront of video analysis capabilities.
Google DeepMind has launched agentic video understanding across its Gemini models, including 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite. This new capability enhances video analysis by allowing models to dynamically interact with video content, improving accuracy and reducing costs. The feature is available through the Gemini API and is particularly beneficial for analyzing long-form videos. It enables precise tasks such as sub-second moment retrieval and anomaly detection, positioning Gemini 3.7 Flash as a leader in cost-efficient video analysis.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
