NewApp Digest
search bot

Coding

AI-powered app maker Wabi pivots to a messaging experience
AppWizard
September 29, 2026

AI-powered app maker Wabi pivots to a messaging experience

Wabi, an AI startup, has launched Wabi 2.0, a platform that serves as a sophisticated AI messenger while maintaining app-building capabilities. The founder, Eugenia Kuyda, describes Wabi 2.0 as a "personal agent" that enhances user experience by integrating conversation and task management. The platform distinguishes itself by targeting AI agents with conversational and productivity features, rather than competing with traditional coding tools. Users can request tasks that the agent fulfills by generating a tailored user interface for specific needs, such as health tracking or family management. Access to Wabi 2.0 is currently limited to invite codes distributed via X.
Google Play Store looks like it's working on a special home for your vibe-coded apps
AppWizard
September 22, 2026

Google Play Store looks like it’s working on a special home for your vibe-coded apps

Google is developing AI Studio, which allows users to create applications using vibe coding, making app development more accessible to novice developers. The company is integrating this with its Gemini platform to simplify the coding process for Android users. A new section in the Play Store, tentatively called “Your creations,” is being explored for AI Studio creations, likely located within the “Manage apps & device” screen. Currently, publishing apps from AI Studio requires formal registration and testing. The “Your creations” interface may provide a way to manage personal projects while balancing ease of sideloading. Although there are hints of a connection between AI Studio and the Play Store, details about registration and testing processes remain unclear. The language suggests that applications could be shared with a broader audience, differing from traditional publication methods. An APK teardown indicates potential future features, but not all may be released publicly.
Google’s Android Bench 2.0 tests AI agents on week-long app builds
AppWizard
September 19, 2026

Google’s Android Bench 2.0 tests AI agents on week-long app builds

Google has launched Android Bench 2.0, an upgraded benchmark for evaluating AI coding agents, which now includes 30 long-horizon tasks that can take human engineers days or weeks to complete. The best pass rate for these tasks is around 28%, down from approximately 91% in the previous version. The benchmark measures both pass rates and completion rates, acknowledging partial progress rather than just failures. It assesses various challenges, including app creation and feature integration, using a comprehensive scoring methodology that evaluates functionality, regression checks, and visual fidelity. AI models perform better with new code than with modifications to existing systems, facing challenges in runtime validation and cross-platform conversions. The current leaderboard shows OpenAI’s GPT-6 Astra leading with a 28% pass rate, while Gemini 3.8 Flash has an 8% pass rate. Developers using AI agents should be aware that while AI can generate significant portions of applications, further refinements will require human input. The benchmark is available on Google’s Android Bench leaderboard.
Google just put the latest AI models through a brutal coding test
AppWizard
September 18, 2026

Google just put the latest AI models through a brutal coding test

Google has launched Android Bench 2.0, a benchmark for evaluating large language models (LLMs) and AI agents on complex Android development tasks. This version focuses on long-horizon tasks (LHTs) that are more intricate than those assessed by the original benchmark. Key tasks include upgrading dependencies, adding major new features, and building Android apps from scratch. The new grading system uses continuous scoring instead of a binary pass-or-fail method, providing a more detailed performance evaluation. Currently, GPT-6 Astra leads the leaderboard with a 28% pass rate, followed by Gemini 3.8 Flash at 8%. Other evaluated models include Claude Fable 5.1, GPT-5.6 Sol, and Claude Opus 5. Google plans to expand the leaderboard with more models and results.
Microsoft explained why Windows 11 dropped these Windows 10 features
Winsage
September 17, 2026

Microsoft explained why Windows 11 dropped these Windows 10 features

Windows 11 was released in 2021 and received mixed reactions, with users noting the removal of several familiar features from Windows 10. The taskbar was locked in place, preventing repositioning, and the ability to drag files onto taskbar applications was initially absent but restored within a year. The Start menu lost flexible resizing options, and Microsoft faced challenges in transferring established features due to the new framework. By 2026, Microsoft announced changes allowing users to relocate the taskbar, responding to user demand. The Start menu remained less flexible than its predecessor, leading to user frustration. Microsoft acknowledged the need for a movable taskbar, which was implemented in a preview by May 2026, coinciding with the September 2026 Patch Tuesday update. The integration of AI into development processes has accelerated feature implementation, but also introduced new stability issues.
AI vibe coding is so fast that Microsoft had to change how it reviews Edge extensions
Winsage
September 9, 2026

AI vibe coding is so fast that Microsoft had to change how it reviews Edge extensions

Users of Windows and Windows Phone previously faced an app gap, but the rise of artificial intelligence has led to increased development activity, creating challenges for Microsoft regarding the Edge browser. The ad blocker uBlock Origin has stopped functioning on Edge, similar to its status on Chrome. Microsoft revamped the Edge Add-ons site last year to improve user experience with a more intuitive interface and better categorization. This update allows users to find and install extensions more easily, and the Edge team is focused on maintaining quality amidst the growing number of extension submissions.
Microsoft engineer says "typing code is absolutely over," and Windows 11 is already being built that way
Winsage
September 5, 2026

Microsoft engineer says “typing code is absolutely over,” and Windows 11 is already being built that way

David Fowler, an engineer with 18 years at Microsoft, claims that traditional software development methods are becoming obsolete, stating, “Typing code is absolutely over.” He has co-created technologies like SignalR and NuGet and currently leads Aspire, a toolchain for building distributed applications that emphasizes AI-driven development. CEO Satya Nadella noted that AI contributes to 20-30% of the code produced at Microsoft. While developers will still interact with code, manual typing is becoming less central, with a shift towards strategic software engineering tasks. Microsoft Research found that AI-generated suggestions in Visual Studio IntelliCode are often overlooked by developers. GitHub Copilot has evolved to autonomously perform tasks, including building Windows development environments as of February 2026. Linus Torvalds supports AI in Linux development, viewing it as a useful tool. A report from Veracode indicated that about 44% of AI-generated code contains known vulnerabilities, highlighting the need for oversight. Microsoft’s MDASH system uses AI for enhanced vulnerability assessments. Microsoft emphasizes native Windows development through the open-source WinUI 3 framework and provides resources for beginners using Copilot. Project Zenith aims to optimize Windows 11 for developers, supporting local AI-powered development. Fowler's statement signifies a transformation in developers' roles, focusing on strategic aspects rather than typing code, while the need for skilled software engineers remains essential.
Search