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 …
Chrome is shipping built-in AI APIs that run Google's Gemini Nano language model inside the browser, enabling web developers to perform tasks like summarization, translation, and structured data gener…
Google's AICore enables on-device LLMs like Gemini Nano by leveraging weight pruning and sparsity to reduce model size and power consumption. The Lottery Ticket Hypothesis guides pruning to identify c…
Google Chrome has been silently downloading a 4GB AI model, Gemini Nano, to eligible desktop machines without user consent, sparking privacy concerns. The deployment, discovered by researcher Alexande…
Google's MediaPipe Tasks and AICore are revolutionizing on-device machine learning for Android developers by abstracting low-level tensor manipulation into declarative pipeline orchestration. MediaPip…
Google has been silently downloading its 4GB Gemini Nano AI model onto Chrome users' devices without consent since at least April, while a malicious Chrome extension disguised as Perplexity AI logged …
Google has been secretly downloading its Gemini Nano AI model to eligible Chrome browsers since April 2026 without user consent, raising privacy concerns. The 4GB model powers on-device AI features an…
Sudipta Das, a Google Summer of Code 2026 contributor at the Internet Archive, built a client-side AI extension for the Wayback Machine. The Chrome extension uses Gemini Nano to summarize archived pag…
Google announced a method to retrofit Multi-Token Prediction onto frozen Gemini Nano v3 models, accelerating on-device inference for Pixel 9 and 10 series devices. The approach appends a lightweight T…
Chrome now ships Gemini Nano, a language model accessible via the Prompt API, enabling on-device AI without API keys or inference costs. A developer integrated it into a free Mermaid diagram editor, u…
Google is downloading its 4GB Gemini Nano AI model onto users' computers via Chrome without clear notification. The lightweight model powers on-device features like scam detection but consumes signifi…