The creator of Flowbite built a Chrome extension that helps you extract styles from any website and generate DESIGN(.)md or SKILL(.)md files

Agentic technology — AI that can make decisions, carry out complex tasks and work autonomously — is sparking a familiar debate that’s rekindled each time we meet a transformative technology. From the printing press and the camera to the personal computer and digital imaging software, the questions are different but the controversy is always the same: will new technology serve people or replace them? Artists always answer these questions by…

If you’re like me you gotta be curious… what’s it like designing at OpenAI?

This article explores my learning process in scaffolding an agentic design system IDE workspace using AI skills, MCPs and Figma. With Google’s Antigravity I did setup a mix of workflows in order to generate code from design as well as design from code.

OpenAI has been all over the news recently, whether that news is about acquisitions, competition with Anthropic, or bigger debates about AI’s impact on society.

Today, we’re launching Claude Design, a new Anthropic Labs product that lets you collaborate with Claude to create polished visual work like designs, prototypes, slides, one-pagers, and more.

After Anthropic released Claude Code’s 2.1.88 update, users quickly discovered that it contained a package with a source map file containing its TypeScript codebase, with one person on X calling attention to the leak and posting a file containing the code. The leaked data reportedly contains more than 512,000 lines of code and provides a look into the inner workings of the AI-powered coding tool, as reported earlier by Ars Technica and VentureBeat.

Website development is shifting from traditional engineering-heavy workflows to a new model where non-technical users can build full applications using AI-driven tools and simple command-based inputs. This approach is often referred to as vibe coding — focusing on intent and outcome rather than syntax and implementation.

Claude Sonnet 4.6 is our most capable Sonnet model yet. It’s a full upgrade of the model’s skills across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. Sonnet 4.6 also features a 1M token context window in beta.

Build a smooth horizontal parallax gallery in DOM/CSS/JS, then upgrade it to GPU-powered WebGL (Three.js) with shaders.