Google has open-sourced Jetpacker, a demo travel app built for Google I/O that showcases how to integrate generative AI features into Android apps using on-device and cloud models. The app uses Gemini…
A developer explains how to integrate custom quantized AI models into Android apps, covering linear quantization, per-channel vs. per-tensor scaling, and hardware acceleration via NPU, GPU, DSP, and G…
In a comparison of privacy features between Samsung Galaxy and Google Pixel phones, neither device emerges as a clear winner, according to an analysis by Android Authority. Samsung's Secure Folder off…
A developer building on Chrome's on-device Gemini Nano LLM found that on-device AI changes assumptions from cloud API development. They built a Chrome extension called Quill as a testbed, discovering …
A developer detailed how to build high-speed vision analyzers on Android by orchestrating data movement between the camera sensor, RAM, and hardware accelerators like NPUs, GPUs, and DSPs to minimize …
A developer built a 3-tier on-device AI concierge widget that runs entirely in the visitor's browser, using Google's Gemini Nano, a MiniLM embedding model, and keyword matching, achieving zero cost pe…
Arcrawls uses Gemini Nano and DistilBERT on-device to analyze page sentiment and generate daily browsing summaries without sending data to the cloud, according to a Hacker News post by user fujidevv.…
A developer's guide explains why edge AI benchmarking on Android requires measuring thermal throttling, memory pressure, and accuracy loss—not just execution time—and recommends using Kotlin 2.x with …
A developer demonstrated how to use the Antigravity CLI, an agentic AI assistant, to build an image analysis demo with Angular, Firebase Hybrid & On-device Inference Web SDK, and Gemini models. The de…
Google's AICore transforms AI models from app-bundled assets into system services on Android, enabling heterogeneous parallelism across NPU, GPU, and DSP. The approach addresses the memory wall via ze…
Theia, a new Chrome extension, fact-checks ChatGPT, Claude, and Gemini in real time, flagging hallucinations and sycophancy by scoring replies against primary sources and running an on-device sycophan…
A browser extension can now run a small language model locally, with no server or API key, using either Chrome's built-in Gemini Nano or a custom model via Transformers.js on WebGPU. The approach enab…
A developer explains that the primary bottleneck in edge AI inference on Android devices is the memory wall caused by excessive data copying, not the neural network itself. They advocate for zero-copy…
A developer built LaunchPad, a tool that drafts native posts for 42 launch channels from a single product brief, using on-device AI via Chrome's Gemini Nano or the user's own API keys. The project fac…
A developer explains how to overcome the 'Abstraction Tax' in Android Edge AI by using custom C++ operations via the NDK. The post details techniques like coarse-grained delegation and zero-copy data …
A developer used Antigravity CLI to build an image analysis demo with Angular, Firebase Hybrid & On-device Inference Web SDK, and Gemini models. The demo analyzes uploaded images to generate alternati…
Chrome's Built-In AI APIs enable applications to run AI workloads like language detection, translation, summarization, and writing assistance directly in the browser without deploying model infrastruc…
A developer explains how Knowledge Distillation (KD) enables high-performance AI on Android by transferring 'dark knowledge' from large Teacher models to compact Student models. The technique uses sof…
Google is rebranding its Pixel Magic Cue feature as Gemini 'Proactive Assistance,' according to code found in the Phone by Google app. The change aligns the feature under the Gemini brand, with refere…
A developer explains how Quantization-Aware Training (QAT) enables deploying deep learning models on Android without sacrificing accuracy, addressing the 'Quantization Cliff' problem of post-training …