← Все новости

Google I/O in 60 seconds

**Google** announced updates to the **Gemini model family**, including **Gemini 1.5 Pro** with **2 million token support**, and the new **Gemini Flash** model optimized for speed with **1 million token capacity**. The Gemini suite now includes **Ultra**, **Pro**, **Flash**, and **Nano** models, with **Gemini Nano** integrated into **Chrome 126**. Additional Gemini features include **Gemini Gems** (custom GPTs), **Gemini Live** for voice conversations, and **Project Astra**, a live video understanding assistant. The **Gemma model family** was updated with **Gemma 2** at **27B parameters**, offering near-**llama-3-70b** performance at half the size, plus **PaliGemma**, a vision-language open model inspired by **PaLI-3**. Other launches include **DeepMind's Veo**, **Imagen 3** for photorealistic image generation, and a **Music AI Sandbox** collaboration with YouTube. **SynthID watermarking** now extends to text, images, audio, and video. The **Trillium TPUv6** codename was revealed. Google also integrated AI across its product suite including Workspace, Email, Docs, Sheets, Photos, Search, and Lens. *"The world awaits Apple's answer."*
Читать оригинал на AINews / smol.ai →