rewriting Archives

AppWizard

June 12, 2025

I tried Google’s secret, open source, offline AI app to see if it’s better than Gemini

Google has introduced the AI Edge Gallery, an application that allows users to download and run large language models (LLMs) directly on their Android devices for offline processing. The app features four distinct LLMs categorized into three functions: Ask Image, Prompt Lab, and AI Chat. Users can engage in image analysis, chat interactions, and prompt-based tasks. The installation process is cumbersome, requiring users to download the app from GitHub and create a Hugging Face account. Once operational, the app has a sleek interface and smooth functionality. It can provide travel planning advice, explain complex theories, generate recipes, rewrite text, summarize content, and recognize images, although it struggles with less common subjects like landmarks. AI Edge Gallery does not have the same level of control over devices as Google's Gemini and cannot execute commands like turning on the flashlight.

AppWizard

June 4, 2025

Google Unveils Gemini Nano for On-Device AI in Android Apps

Google has updated the Gemini Nano APIs through the ML Kit, introducing new GenAI APIs that allow developers to perform on-device inference for generative AI capabilities in Android applications. These APIs enhance user privacy by executing all operations locally, eliminating cloud processing costs. Features include summarization of articles up to 3,000 words, proofreading for grammatical accuracy, rewriting text in various tones, and generating image descriptions. The GenAI APIs are optimized for Android devices using MediaTek Dimensity, Qualcomm Snapdragon, and Google Tensor platforms, including the Pixel 9 series and Samsung Galaxy S25. They operate without internet connectivity, ensuring rapid response times and improved performance for tasks like summarization and proofreading. The local processing also enhances privacy and security, protecting sensitive user information with safety protocols.

Winsage

May 30, 2025

Windows 11 Version 24H2 Gets a Featured-Packed Optional Update

Microsoft has released the May optional update for Windows 11 version 24H2, introducing features such as the Win + C keyboard shortcut for quick access to Copilot, a drag tray feature, and cross-device resume notifications for OneDrive files. The Copilot+ feature is now available in the European Economic Area (EEA) and supports intelligent text actions in Spanish and French. Users can utilize the 'Ask Copilot' option to highlight text or images and open Copilot with the selected content. New text actions for summarizing, creating bulleted lists, or rewriting highlighted text are available for AMD and Intel-powered Copilot+ PCs. Pen users can configure a shortcut button for Click to Do, and Windows Search improvements allow direct typing of settings. The Narrator feature provides detailed descriptions of images for blind and low-vision users. Energy saver controls for IT admins have been introduced, along with HDR and Dolby Vision controls. A new FAQs section in Settings assists users with common inquiries, and mouse settings have been simplified. Users can now edit images shared through the Windows Share window, and a new drag tray area appears when dragging local files. Taskbar policies have been improved to allow unpinning specific apps. The features will roll out with the upcoming Patch Tuesday update, alongside the optional KB5058481 update for Windows 10, which reinstates the clock view displaying seconds on the calendar flyout.

Winsage

May 23, 2025

Windows 11 Notepad gets AI-powered text writing capabilities

Microsoft is piloting an AI-driven text generation feature called "Write" in Notepad for Windows Insiders using version 11.2504.46.0. The feature allows users to create content from prompts, either starting from scratch or enhancing existing text. Users can access it by right-clicking, selecting "Write" from the Copilot menu, or using the Ctrl + Q shortcut. After entering instructions, AI-generated text can be incorporated into documents or discarded. A Microsoft personal account is required to use the feature, which utilizes AI credits from Microsoft 365 subscriptions. Microsoft has also introduced other AI features in Notepad, including a text rewriting tool named "Rewrite," a character counter, spell-check, and autocorrect. Additionally, new AI capabilities have been rolled out for Paint and Snipping Tool users in the Windows Insider program, including a sticker generator and enhanced screenshot tools.

AppWizard

May 17, 2025

Google’s ML Kit GenAI APIs with Gemini Nano: On-Device AI for Privacy-Preserving Android Apps

Google announced on May 14, 2025, the expansion of its ML Kit offerings with new GenAI APIs powered by the Gemini Nano model, aimed at providing Android developers with access to advanced AI features while ensuring user privacy through on-device processing. The ML Kit GenAI APIs include four key capabilities: summarization, proofreading, rewriting, and image description. These APIs process data locally, keeping user data on the device, ensuring consistent functionality without internet connectivity, and avoiding recurring server costs. This development enhances the accessibility of sophisticated AI capabilities for Android developers and aligns with consumer privacy concerns. The architecture allows for future expansion of capabilities as Gemini models evolve.

AppWizard

May 16, 2025

Google to give app devs access to Gemini Nano for on-device AI

Google is preparing to unveil new mobile AI tools at the upcoming I/O event, including a suite of APIs that will enable developers to use Gemini Nano for on-device AI applications. The ML Kit SDK will be updated to support on-device generative AI functionalities through Gemini Nano, which integrates with existing models and offers predefined features for ease of implementation. The ML Kit’s GenAI APIs will allow applications to perform tasks such as summarization, proofreading, rewriting, and image description without cloud data transmission. However, Gemini Nano's capabilities are limited compared to cloud-based options, with summaries restricted to three bullet points and image descriptions available only in English. The standard version, Gemini Nano XS, requires about 100MB of storage, while the smaller Gemini Nano XXS is text-only and occupies a quarter of that size. ML Kit is compatible with devices beyond Google's Pixel lineup, including the OnePlus 13, Samsung Galaxy S25, and Xiaomi 15, providing developers opportunities to enhance applications with generative AI features.

AppWizard

May 16, 2025

Google is about to unleash Gemini Nano’s power for third-party Android apps

Google is expanding its Gemini Nano AI model by introducing new ML Kit GenAI APIs, expected to be unveiled at the I/O 2025 event. These APIs will allow developers to integrate features such as text summarization, proofreading, rewriting, and image description generation into their applications. Gemini Nano operates on devices, enhancing privacy by processing data locally. The ML Kit GenAI APIs will support various languages and functionalities, including generating concise summaries, correcting grammar, transforming chat messages, and providing image descriptions. Unlike the experimental AI Edge SDK, the GenAI APIs will be in beta, allowing for broader device compatibility beyond the Pixel 9 series, including other Android devices. Public documentation for the ML Kit GenAI APIs is now available for developers.

Winsage

May 13, 2025

Announcing Windows 11 Insider Preview Build 26120.3964 (Beta Channel)

Windows 11 Insider Preview Build 26120.3964 (KB5058496) has been released for the Beta Channel, specifically for Windows 11, version 24H2. Users on version 23H2 can choose to upgrade to version 24H2 with this build. The update introduces a new AI-powered agent in Settings for easier navigation and task automation, currently available for Snapdragon-powered Copilot+ PCs, with support for AMD and Intel PCs coming soon. Enhanced intelligent text actions have been added to Click to Do for AMD and Intel-powered Copilot+ PCs, allowing users to summarize, create bulleted lists, or rewrite text. A dedicated FAQs section has been added to the Settings > System > About page. Several fixes have been implemented, including improvements to the Start menu, File Explorer, and voice access. Known issues include problems with PC reset display and Xbox Controller connectivity. Entra ID support for AI features in Paint and Notepad has been rolled out for IT-managed PCs.

Winsage

May 13, 2025

Announcing Windows 11 Insider Preview Build 26200.5600 (Dev Channel)

Windows 11 Insider Preview Build 26200.5581 (KB5058493) has been released to the Dev Channel. New features include enhanced intelligent text actions in Click to Do for AMD and Intel™-powered Copilot+ PCs, allowing users to Summarize, Create a bulleted list, or Rewrite text. These features are available when the default language is English and at least 10 words are selected. For users with French or Spanish as their primary language, only Summarize, Create a bulleted list, and Refine options are temporarily available. Improvements include the ability to safely remove devices compatible with Dynamic Lighting and the introduction of a FAQs section in Settings to help users find information about their PC. Fixes have been made to the Start menu, File Explorer, Voice Access, Taskbar, Windows Spotlight, and Live captions. Known issues include problems with the PC reset option and Xbox Controller connectivity. Entra ID support for AI features in Paint and Notepad has been rolled out for IT-managed PCs, allowing access to tools like Cocreator and Generative Fill in Paint, and summarization or rewriting in Notepad. Windows Insiders in the Dev Channel receive updates based on Windows 11, version 24H2, and features may evolve or be removed based on feedback.

Winsage

May 7, 2025

Microsoft unveils new AI agents that can modify Windows settings

Microsoft has introduced a suite of Windows experiences for Copilot+ PCs, featuring AI agents that help users adjust settings on their computers by interpreting user intent and automating tasks with consent. Users can communicate in natural language to receive guidance or have changes executed directly. This feature will initially be available to English-speaking Windows Insiders on Snapdragon-powered devices, with plans for broader support. Additionally, Microsoft is enhancing Windows search capabilities and expanding Click to Do actions, allowing users to schedule meetings, send messages, consult M365 Copilot, convert data in Excel, and draft documents in Word. Creative tools like Photos, Paint, and the Snipping Tool are receiving updates, including dynamic lighting controls in Photos, a sticker generator in Paint, and new capture capabilities in the Snipping Tool. Upcoming features for Windows 11 Insiders include a phone companion for the Start menu, AI-driven actions in File Explorer, and a new writing function in Notepad for generating text from prompts. Microsoft is also testing a "Draw & Hold" feature in the Snipping Tool and has introduced a text rewriting tool called "Rewrite."