css
30 articles about css in AI news
CLAUDE.md for Mobile: How One File Fixes Claude Code's CSS Blindspot
A specialized CLAUDE.md file fixes Claude Code's generic CSS by injecting mobile-specific rules, preventing iOS zoom, untappable buttons, and dark mode failures before shipping.
Google DeepMind Unveils Gemini-Powered Browser That Generates Websites in Real-Time
Google DeepMind has demonstrated a browser prototype powered by Gemini 3.1 Flash-Lite that generates complete HTML/CSS websites dynamically based on user prompts and navigation context, shifting from static page retrieval to on-demand interface generation.
Claude Code's Built-In Preview MCP: Instant Frontend Previews Without Configuration
Claude Code Desktop now includes a built-in MCP server for instant HTML/CSS/JS previews—no installation or configuration needed.
Nokia Deploys Agentic AI Agents Across Fixed Network Platforms
Nokia launched agentic AI agents across its fixed network platforms to automate troubleshooting and accelerate fiber deployment by 25%.
GPT-5.5 Demo Shows AI Generating Functional Excel-Like Spreadsheet
A user demonstrated GPT-5.5 creating a web-based spreadsheet with formatting and grid behavior. This showcases incremental progress in AI's ability to generate complex, interactive frontend code from natural language.
Claude Design's /artboard Command: A New Tool for UI-First Development
Claude Code users can now use the new /artboard command to generate UI mockups and component specs directly within their workflow, streamlining front-end development.
Stop Thinking 'Progressive Disclosure' for Claude Skills — Think
A mental model shift from 'progressive disclosure' to 'progressive discovery' makes building Claude Skills more intuitive by clarifying Claude's active role in finding what it needs.
Claude Code's Playwright MCP Server: Generate Web Tests from Natural Language
Claude Code now integrates with Playwright via MCP, letting you generate complete test automation from simple prompts without leaving your terminal.
Onlook: Open-Source AI Tool Edits React Code Visually, Hits 23.9K GitHub Stars
Onlook, an open-source desktop app, enables visual editing of live React and Next.js applications, with AI generating and writing code changes directly to the codebase. It has gained 23.9K GitHub stars, positioning itself as a free alternative to paid design tools like Figma.
From Vibe Code to Viable Product: The 6 Claude Code Prompts You're Missing
A developer's year-long journey reveals the critical prompts for edge cases, error states, and integrations that turn a 48-hour Claude Code MVP into a shippable product.
How to Force Claude Code to Ship 100-Performance Code with Google Lighthouse
A complete performance guardrail system that makes Claude Code validate every change against Lighthouse (100 score required) and optionally Google Analytics/Search Console before shipping.
Google DeepMind: Web Environment, Not Model Weights, Is Key AI Agent Attack Surface
Google DeepMind researchers present a systematic framework showing that the web environment itself—not just the model—is a primary attack surface for AI agents. In benchmarks, hidden prompt injections hijacked agents in up to 86% of scenarios, with memory poisoning attacks exceeding 80% success.
Developer Icons: Open-Source, Typed React Library for Tech Logos
Developer Icons, a new open-source library, offers fully-typed React components for tech logos with consistent design and optimization, eliminating the common hassle of mismatched SVG assets.
How to Fix Claude Code's Remote Control Issues and Get Visual Feedback
Practical solutions for Claude Code's remote control instability and lack of visual feedback when building UI components.
Claude Code Hooks: How to Auto-Format, Lint, and Test on Every Save
Configure hooks in .claude/settings.json to run prettier, eslint, and tests automatically, ensuring clean code without manual intervention.
Google DeepMind Maps Six 'AI Agent Traps' That Can Hijack Autonomous Systems in the Wild
Google DeepMind has published a framework identifying six categories of 'traps'—from hidden web instructions to poisoned memory—that can exploit autonomous AI agents. This research provides the first systematic taxonomy for a growing attack surface as agents gain web access and tool-use capabilities.
Claude Code 2.5: New CLI, Dashboard, and Best Practices for Web Devs
Anthropic's latest Claude Code update adds a CLI, usage dashboard, and web-focused best practices. Here's how to use them.
Safari MCP Cuts Browser Automation CPU Usage by 95% for Mac Developers
Replace your Chromium-based MCP browser tool with Safari MCP to eliminate Chrome's resource drain while keeping your existing logged-in sessions.
ExSpec: Run Gherkin Tests in Real Browsers with Claude Code—No Step Definitions Required
ExSpec lets you write plain-text Gherkin specs and have Claude Code execute them in a real browser, eliminating brittle step definitions and glue code.
CC-Lens: The Open-Source Dashboard That Shows You Exactly How You Use Claude Code
Run `npx cc-lens` to get a real-time, local analytics dashboard for your Claude Code usage, revealing token costs, project activity, and tool efficiency.
Add Vector Memory to Claude Code: The claude-memory-mcp Server Solves CLAUDE.md's 200-Line Limit
Install this open-source MCP server to give Claude Code persistent, searchable memory across projects. It surfaces only relevant context, solving CLAUDE.md's scaling problems.
AI2's MolmoWeb: Open 8B-Parameter Web Agent Navigates Using Screenshots, Challenges Proprietary Systems
The Allen Institute for AI released MolmoWeb, a fully open web agent that operates websites using only screenshots. The 8B-parameter model outperforms other open models and approaches proprietary performance, with all training data and weights publicly released.
Master CLAUDE.md & /init: The 2-Minute Setup That Cuts Claude Code Prompting by 80%
Stop repeating project context. Use CLAUDE.md files and the /init command to give Claude Code persistent memory about your codebase, tech stack, and coding style.
Anthropic Deploys Multi-Agent Harness to Scale Claude's Frontend Design & Autonomous Software Engineering
Anthropic engineers detail a multi-agent system that orchestrates multiple Claude instances to tackle complex, long-running software tasks like frontend design. The approach aims to overcome single-model context and reasoning limits.
Claude Code's New Read Cache Blocks 8% of Token Waste Automatically
The claude-context-optimizer plugin v3.1 now actively blocks Claude from re-reading unchanged files, saving an average 8% of tokens per session.
How to Build a Real Project on Claude Code's Free Plan (Without the Pain)
A non-technical user's struggle reveals the exact workflow and prompts to make Claude Code's free tier work for serious development.
Build a 4-File, 4-Command System for Seamless Claude Code Sessions
Replace manual prompts with a structured file system and custom slash commands for continuous, context-aware development sessions.
How to Use Claude Code for a Complete Website Redesign in Two Waves
A developer used Claude Code to overhaul his personal site in two strategic waves: first fixing infrastructure, then redesigning content and layout.
How to Use Claude Code's Subagent Feature for Isolated Task Execution
Claude Code's new subagent feature lets you run isolated tasks in separate interpreter sessions, preventing context pollution and improving reliability.
Claude Code + Stitch: A New AI-Powered Design-to-Code Workflow Emerges, Challenging Figma's Dominance
A new workflow combining Anthropic's Claude Code with the Stitch design system is being hailed as a superior AI-native alternative to traditional tools like Figma. It enables rapid, high-fidelity conversion of design concepts into production-ready code.