New top AI video models, Google dominates, top 3D model generator, Grok 4.1, GPT-Codex-Max: AI NEWS
This week saw significant advancements in AI with new open-source video generators, Google's Gemini 3, Nano Banana Pro, XAI's Grock 4.1, OpenAI's coding model, and Depth Anything 3, which excels in 3D mapping from minimal input.
MAIN POINTS FROM TRANSCRIPT
- Two new state-of-the-art open-source video generators were released.
- Google's Gemini 3 and Nano Banana Pro set new standards in AI models and image editing.
- Depth Anything 3 creates accurate 3D maps from limited images or chaotic videos.
- Meta's Segment Anything Model 3 excels in object detection, segmentation, and tracking.
TAKEAWAYS
- Depth Anything 3 outperforms other models in camera pose and reconstruction accuracy.
- The GitHub repository for Depth Anything 3 offers various model versions for local use.
- Google's new AI models include an advanced weather forecasting system.
- Meta's SAM 3 enhances image and video object tracking capabilities.