generative AI capabilities Archives

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.

AppWizard

June 3, 2025

Adobe Photoshop finally launches on Android

Adobe has launched its Photoshop app for Android devices, featuring desktop-level tools and generative AI capabilities. The app includes layering, masking, and the Spot Healing Brush, with a free version offering professional-grade tools. It integrates with Adobe Stock for access to curated assets and is compatible with other Adobe Creative Cloud applications. Notable features include Generative Fill and Generative Expand, powered by Adobe's Firefly AI. Advanced tools like Object Select and Content-Aware Fill are available through a premium subscription priced at .99 per month or .99 annually. The beta version is available for download on the Google Play Store.

Tech Optimizer

June 2, 2025

Streamline code conversion and testing from Microsoft SQL Server and Oracle to PostgreSQL with Amazon Bedrock

Organizations are transitioning from legacy database systems like Microsoft SQL Server and Oracle to open-source alternatives such as PostgreSQL to reduce costs and enhance scalability. This migration process involves several steps, including schema conversion, business logic transformation, data migration, application changes, and performance tuning. Amazon Bedrock aids this process by automating schema and code conversion, data transformation, identifying code compatibility issues, and generating test cases for validation. The migration challenges include adapting database objects to PostgreSQL's syntax, converting stored procedures and functions, executing ETL processes for data accuracy, modifying application code, and optimizing performance. Amazon Bedrock utilizes generative AI to simplify these tasks, significantly reducing manual effort and errors. An example of code conversion from Microsoft SQL Server to PostgreSQL is provided, illustrating how to convert a stored procedure into a PostgreSQL function while generating corresponding test cases. The process involves using the Amazon Bedrock chat interface to submit prompts for conversion and validation. To support the migration, table creation scripts for the Employees and SalaryUpdateLog tables are included, along with test data that covers various employee scenarios. This data allows for comprehensive testing of the converted function, ensuring it correctly applies salary updates based on specified criteria.

Winsage

May 24, 2025

Note, Paint and Snip With AI: Microsoft Adds New Features, but Not for Everyone

Notepad will soon include generative AI capabilities powered by Copilot, allowing users to assist in text creation by right-clicking and inputting instructions. This feature will be available only to Microsoft 365 or Copilot Pro subscribers. Paint will enable users to create custom stickers through prompts, but this feature will only be available on devices with Copilot Plus. The Snipping Tool will introduce a "perfect screenshot" capability accessible to all users, eliminating the need for manual cropping or resizing.

Tech Optimizer

May 24, 2025

Connect Amazon Bedrock Agents with Amazon Aurora PostgreSQL using Amazon RDS Data API

Generative AI applications are being integrated with relational databases, allowing organizations to utilize structured data for training AI models. This integration involves using the RDS Data API with Amazon Aurora PostgreSQL-Compatible Edition and Amazon Bedrock for AI model access and automation. The solution enables natural language queries to be converted into SQL statements, executed against the database, and returns results in a user-friendly format. The architecture includes several steps: invoking the Amazon Bedrock agent with natural language input, generating SQL queries using large language models (LLMs), executing those queries via the Data API, and returning formatted results. Security measures are in place to restrict operations to read-only, preventing modifications that could compromise data integrity. To implement this solution, prerequisites include deploying an Aurora PostgreSQL cluster using AWS CDK and setting up the necessary Lambda functions and IAM roles. The agent is designed to convert natural language prompts into SQL queries and execute them securely. Testing can be conducted through the Amazon Bedrock console or the InvokeAgent API, with options for tracing the agent's steps. Key considerations for this integration include limiting it to read-only workloads, implementing parameter validation to prevent SQL injection, and ensuring comprehensive logging and auditing. For multi-tenant applications, appropriate isolation controls should be established. To avoid future charges, all resources created through CDK should be deleted after use.

Winsage

May 23, 2025

Microsoft dumps AI into Notepad

Microsoft has updated Notepad to include the Copilot feature for text generation, requiring users to sign in with their Microsoft account to access the Write feature. Users can generate text by selecting the Write option from the Copilot menu, which can then be reviewed, saved, or refined. Microsoft has also introduced AI-driven features in Paint, including a sticker generator and a smart selection tool. These updates reflect Microsoft's efforts to innovate its built-in Windows applications, although some users question the necessity of AI in simpler tools like Notepad.

Winsage

May 20, 2025

Securing the Model Context Protocol: Building a safer agentic future on Windows

The Model Context Protocol (MCP) is a lightweight, open protocol functioning as JSON-RPC over HTTP, facilitating standardized discovery and invocation of tools. MCP defines three roles: MCP Hosts (applications accessing capabilities), MCP Clients (initiators of requests), and MCP Servers (services exposing functionalities). Windows 11 will incorporate MCP to enable developers to create intelligent applications leveraging generative AI. An early preview of MCP capabilities will be available for developer feedback. MCP introduces security risks, including cross-prompt injection, authentication gaps, credential leakage, tool poisoning, lack of containment, limited security review, registry risks, and command injection. To address these, Windows 11's MCP Security Architecture will establish security requirements for MCP servers, ensuring user safety and transparency, enforcing least privilege, and implementing security controls like proxy-mediated communication, tool-level authorization, a central server registry, and runtime isolation. MCP servers must comply with security requirements, including mandatory code signing, unchanged tool definitions at runtime, security testing, mandatory package identity, and declared privileges. An early private preview of MCP server capability will be offered to developers post-Microsoft Build for feedback, with a secure-by-default enforcement strategy planned for broader availability. Microsoft aims to enhance defenses continuously and collaborate with partners to bolster MCP's security framework.

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.

Winsage

May 14, 2025

Microsoft shares its process (and discarded ideas) for redone Windows 11 Start menu

Microsoft is testing a revamped Start menu for Windows 11, which retains familiar elements but offers reorganization and customization options. The redesign process included concepts that were ultimately discarded, such as a Windows XP-inspired sidebar, a full-screen Start experience from Windows 8, and various layouts emphasizing different functionalities. Ideas included an abundance of icons, thumbnail previews for recently opened files, a dedicated area for calendar reminders, and a "create" button suggesting generative AI capabilities. Microsoft engaged over 300 Windows 11 enthusiasts for feedback to inform the redesign, aiming to enhance user experience while maintaining familiarity.

Winsage

April 15, 2025

This Windows 10 bug looks serious – but apparently it’s lying

A new bug has emerged on Windows 10 machines following the KB5057589 update, which began rolling out on April 8 and focuses on enhancing the Windows Recovery Environment (WinRE). Users have reported encountering the 0x80070643 error during installation, indicating a potential failure of a crucial data protection tool. Microsoft advises users to remain calm, suggesting that the error message is largely inaccurate and often resolves after a reboot. While some issues related to the update have been fixed, Microsoft is actively working on further solutions. Windows Update may continue to display the update as failed, but this should clear after the next daily scan. Windows 10 will reach its end-of-support date on October 14, 2025, after which Microsoft will stop providing security patches and support unless users opt for the Extended Security Updates program. Meanwhile, Windows 11 is receiving regular updates and new features, including enhancements to the Start menu and the introduction of passwordless sign-in options.