Discover 92 articles on AI in mobile performance
Showing 20 of 92 articles (Page 4 of 5)
Jakub Mroz from Software Mansion just shipped a fully local RAG pipeline in React Native. No cloud APIs, no data leaks, just on-device AI that actually works.
Abdallah W Shaban from Google's Flutter team just dropped GenUI SDK—a way to let AI generate entire interactive UIs on the fly, not just text responses. Think magazine-style layouts that adapt to each user, bui...
Trendyol scaled from 4,869 to 10,400 UI tests in under a year — while keeping execution under one hour. Here's how AI became their test generation engine.
Jakub Mroz from Software Mansion just built a note-taking app that understands what you mean, not just what you type. No cloud APIs, no recurring costs, and it works completely offline.
Real-time audio in React Native isn't just about playing files anymore. Callstack's engineering team reveals why buffer-based pipelines are becoming essential for voice AI, live streaming, and audio processing ...
Google just dropped an experimental Flutter extension that turns Gemini CLI into an AI coding assistant that can build production-ready apps from scratch. This isn't just autocomplete: it's an agent that plans,...
Caren Chang, Joanna Huang, and Chengji Yan from Google reveal how they're making Gemini Nano v3 940 tokens/second fast while keeping quality consistent across devices. The secret? LoRA adapters and rigorous eva...
Meta just shared how they moved billions of daily users to their new on-device ML framework. The performance gains are substantial.
Ander Dobo and Kenzie Davisson from Google's Flutter team just dropped a game-changer: an AI assistant that can actually fix your runtime errors, search pub.dev, and hot reload your app—all through natural lang...
Amanda Fitch from Flutter reveals Firebase Studio's new AI capabilities that can autonomously generate entire Flutter apps—complete with authentication, state management, and Firebase integration—without manual...
Software Mansion just dropped React Native RAG, bringing full Retrieval-Augmented Generation to mobile devices. No cloud required, no API costs, and your user data never leaves the phone.
Sandhya Mohan and Jose Alcérreca from Google just dropped Agent Mode for Gemini in Android Studio. This isn't another code completion tool—it's an AI that creates execution plans, makes multi-file changes, and ...
Caren Chang, Chengji Yan, and Taj Darra from Google just made on-device AI dramatically easier for Android developers. Four new ML Kit APIs let you integrate Gemini Nano without any prompt engineering or fine-t...
Ander Dobo and Sandhya Mohan from Google just dropped a game-changer for Flutter devs: Gemini AI now speaks Dart natively in Android Studio. No more wrestling with generic AI that doesn't understand your widget...
Kelvin Boateng from Google's Flutter team announces a new learning series that teaches developers to build apps that don't just respond—they proactively assist and automate. Ready to move beyond traditional UIs...
Duolingo's QA team cut manual regression testing by 70% using AI. Here's how they made it work at scale.
Norbert Klockiewicz from Software Mansion just dropped a library that lets you run LLaMA 3.2 models directly on mobile devices. No API calls, no backend costs, no data leaving the device.
Sandhya Mohan from Google just dropped the biggest Gemini in Android Studio update since launch. If you're still manually writing commit messages and test scenarios, this changes everything.
What if you could ditch Xcode's sluggish editor and use VSCode/Cursor for iOS development? Turns out, you can build a surprisingly functional setup.
DoorDash handles 2 billion orders annually, and every ETA prediction matters. Their old tree-based models couldn't keep up with the complexity.