News

@sitepointdotcom
sitepoint.com > chrome-window-ai-prompt-api-tutorial

Getting Started with Chrome's window.ai Prompt API

3+ hour, 6+ min ago  (448+ words) 7 Day Free Trial. Cancel Anytime. This tutorial walks through everything needed to go from enabling the flags to building a working summarization tool. Because inference happens on-device, there is no network round-trip for generation. Local development needs no API key....

@sitepointdotcom
sitepoint.com > local-first-ai-webgpu-chrome-guide

The Complete Guide to Local-First AI: WebGPU, Wasm, and Chrome's Built-in Model

3+ hour, 9+ min ago  (737+ words) 7 Day Free Trial. Cancel Anytime. Local-first AI in the browser has crossed the threshold from experimental curiosity to production-viable technology. This guide is a deep technical walkthrough for experienced JavaScript and web developers who want to understand the architecture beneath…...

@sitepointdotcom
sitepoint.com > webgpu-vs-webgl-inference-benchmarks

WebGPU vs. WebGL: Performance Benchmarks for Client-Side Inference

3+ hour, 9+ min ago  (506+ words) 7 Day Free Trial. Cancel Anytime. Running LLMs and vision models directly in the browser has shifted from novelty to genuine engineering goal. When comparing WebGPU vs. WebGL for client-side inference, the question reduces to how efficiently each API can execute…...

@sitepointdotcom
sitepoint.com > browser-based-rag-private-docs

Building a Privacy-Preserving RAG System in the Browser

3+ hour, 9+ min ago  (1002+ words) 7 Day Free Trial. Cancel Anytime. The complete working demo and source code will be published at the project repository upon article publication. The pipeline follows the same logical stages as any server-side RAG system: ingestion, chunking, embedding, vector storage, query…...

@sitepointdotcom
sitepoint.com > deepseek-r1-open-source-reasoning

DeepSeek-R1: The Open-Source Reasoning Model

3+ hour, 32+ min ago  (1102+ words) 7 Day Free Trial. Cancel Anytime. For the past two years, frontier reasoning capabilities in large language models have been locked behind closed-source walls. DeepSeek-R1 upends that dynamic'this article covers the architecture, benchmarks against GPT-4o and Claude 3.5 Sonnet, three concrete paths…...

@sitepointdotcom
sitepoint.com > definitive-guide-local-first-ai-2026

The Definitive Guide to Local-First AI

3+ hour, 32+ min ago  (942+ words) 7 Day Free Trial. Cancel Anytime. Local-first AI means running inference directly on the client device, inside the browser, with no data ever leaving the user's machine. This guide covers the full local-first AI stack, from raw WebGPU compute shaders through…...

@sitepointdotcom
sitepoint.com > case-study-cloud-to-local-ai-pwa

Case Study: Cloud to Local-First AI Migration

3+ hour, 37+ min ago  (712+ words) 7 Day Free Trial. Cancel Anytime. The app in question was a document summarization and Q&A tool. At roughly 50,000 monthly active users, OpenAI API costs had climbed to $2,400 per month, and enterprise prospects kept walking away the moment they learned…...

@sitepointdotcom
sitepoint.com > profiling-webgpu-memory-local-ai

Debuggability in Local AI: Profiling WebGPU Memory Usage

8+ hour, 9+ min ago  (474+ words) 7 Day Free Trial. Cancel Anytime. Running large language models directly in the browser through WebGPU has moved from experimental novelty to practical reality. But there is a quiet problem lurking in single-page applications that load and unload these models: GPU…...

@sitepointdotcom
sitepoint.com > react-20-suspense-ssr-updates

React 20 Conf Recap: Suspense Updates and SSR

8+ hour, 9+ min ago  (764+ words) 7 Day Free Trial. Cancel Anytime. Since React 18 introduced renderToPipeableStream and selective hydration, the SSR story has improved with each major release. This article is for experienced React developers already shipping streaming SSR applications who want to understand what future improvements…...

@sitepointdotcom
sitepoint.com > ollama-javascript-developers

Ollama for JavaScript Developers

8+ hour, 29+ min ago  (1155+ words) 7 Day Free Trial. Cancel Anytime. Ollama for JavaScript developers changes the equation entirely. It provides one-command local model hosting with a REST API that any HTTP client can talk to, and that includes the native fetch already shipping in modern…...