Google DeepMind's Gemini 3.1 Flash-Lite generates websites in real time, 2.5x faster than predecessor

Google has launched three new Gemini-powered features for Google TV: visual responses that display live scores and tutorials, deep dives with narrated visual breakdowns on complex topics, and sports briefs offering narrated game overviews. The features are rolling out to U.S. and Canada users now, with expansion to Australia, New Zealand, and the UK planned for spring 2026.

OpenAI is releasing a set of open-source prompts developers can use to make their applications safer for teens. The policies, designed to work with OpenAI's gpt-oss-safeguard model, address graphic violence, sexual content, harmful body ideals, dangerous activities, and age-restricted goods.

Anthropic has released 'auto mode' for Claude Code, a permissions system that sits between conservative defaults and fully disabled safeguards. The feature uses a classifier to automatically approve safe actions like file writes and bash commands while blocking potentially destructive operations.

Amazon Web Services has integrated Claude's tool use (function calling) capability into Bedrock, enabling serverless document processing for custom entity recognition. The solution uses Claude 3.5 Sonnet to extract structured data like names, dates, and addresses from driver's licenses and other documents without traditional model training.

OpenAI is adding visual shopping capabilities to ChatGPT, allowing users to compare products with images, prices, and ratings directly in chat. The feature rolls out this week to all plans, including free tier, powered by OpenAI's Agentic Commerce Protocol (ACP). OpenAI is abandoning its own checkout system, instead positioning itself as a product discovery layer that sends users to retailer checkout pages.

OpenAI has launched ChatGPT Library, a dedicated online storage system that automatically saves all files you upload or generate within ChatGPT conversations. The feature is available exclusively to ChatGPT Plus, Pro, and Business subscribers on the web platform, with geographic restrictions excluding the European Economic Area, Switzerland, and the UK.

Stability AI released Stable Audio 2.5, positioned as the first audio generation model built specifically for enterprise sound production. The model introduces improvements in quality and control for creating dynamic compositions adaptable to custom brand needs.

Stability AI and NVIDIA have launched Stable Diffusion 3.5 NIM, a microservice designed to accelerate image generation performance and simplify enterprise deployment. The collaboration packages Stable Diffusion 3.5 as an NVIDIA NIM (NVIDIA Inference Microservice) for optimized inference.

Stability AI has released TensorRT-optimized versions of the Stable Diffusion 3.5 model family in collaboration with NVIDIA. The optimization uses FP8 quantization to achieve 2x faster generation speed and 40% lower VRAM requirements on supported RTX GPUs.

Stability AI has released Stable Video 4D 2.0 (SV4D 2.0), an upgraded version of its multi-view video diffusion model designed to generate 4D assets from single object-centric videos. The update claims to deliver higher-quality outputs on real-world video footage.

Stability AI has open-sourced Stable Audio Open Small in partnership with Arm, a smaller and faster variant of its text-to-audio model designed for on-device deployment. The model maintains output quality and prompt adherence while reducing computational requirements for real-world edge deployment on devices powered by Arm's technology, which runs on 99% of smartphones globally.

Stability AI has released ONNX-optimized versions of Stable Diffusion engineered to run faster and more efficiently on AMD Radeon GPUs and Ryzen AI APUs. The collaboration with AMD targets broader hardware compatibility for the image generation model.