NVIDIA just dropped PersonaPlex-7B 🤯 A full-duplex voice model that listens and talks at the same time. No pauses. No turn-taking. Real conversation. 100% open source. Free. Voice AI just leveled up. huggingface.co/nvidia/persona…

看我找到了什么 一款专为 Visual Studio Code 设计的深色主题，灵感源于 JetBrains 的 Islands Dark 主题。 悬浮面板、语法高亮、深邃底色、玻璃边框、流畅动画、24px 大圆角美学，连滚动条都是药丸形。 github.com/bwya77/vscode-…

Important instruction for AI Coding agents writing tests: "Don't write tests for what the type system already guarantees." Helps hint against an entire class of shit tests.

Learn how to add memory to your agents.

New AI SDK recipe: add a custom memory tool to your agents!

Introducing React Doctor Scan your React codebase for anti-patterns: - Unnecessary useEffects - Fix accessibility issues - Prop drilling instead of context / composition Run as a CLI or agent skill. Repeat until passing. Fully open source

We integrated distributed security audits into our skills.sh manager. Principles: - Skills.sh is only a discovery service. It doesn't host the skills (this is different from npm) - The security model is that of the web: You need to decide whether you

This Skills .md file is really good.

detail.design is the kind of resource I wish existed 10 years ago. A curated collection of tiny UI details — physics-based modal dismissals, blur tricks for optical alignment, shaking disabled buttons — the stuff that separates good interfaces from ones that feel

I have been at 100% AI-contributed code for a few months now. Here are 9 ways it's changed my brain: 1. WAY more time thinking about integration testing 2. Friction via pre-commit hooks/CI/strong types is now super desirable 3. AI has no taste for UI, prototype extremely

Tailwind CSS 4.2.0 includes a big performance improvement. Measured a 3.8x speed improvement for recompiling (any edit) on our largest application Applies to Next.js, Vite, Webpack, and PostCSS integrations. Kudos Robin Malfait, great work!

AI at its best. We Ralph Wiggum'd a better WebStream implementation optimized for server-side Node.js environments. Up to 14.6x performance improvement, with 1100/1116 WPT tests passing. Autonomously. We're working to upstream this work to Node.js for the benefit of all.

I put a /do-work skill in each of my repos, and I love it. It's dead simple, just encodes how I build features/fix bugs: 1. Plan 2. Explore 3. Build 4. Run Tests/Types 5. Commit Having it in a skill lets me hang more complexity on each stage as needed. 1a. If designing a new

We're open sourcing dmux. Our internal tool for running Codex and Claude Code swarms. - tmux + worktrees + claude/codex/opencode - hooks for worktree automation - a/b claude vs codex - manage worktrees - multi-project per session ...more. ➡️ dmux.ai

Today, we’re introducing Pomelli’s latest feature update, ‘Photoshoot’ With Photoshoot, you can start from a single image of your product and easily create high quality, customized product shots to elevate your marketing. Available free of charge in the US, Canada, Australia

Creating a new Next.js application will soon automatically include the best agent setup for working with Next.js

I finally switched to Ghostty with 1 to 3 Claude Code agents running in worktrees across two different tabs. After months of learning how to manage everything properly. Read the full article if you want to get started 👇

Claude Code (or Opus 4.6) feels like it asks you far fewer questions during plan mode Try: "Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions

▲ + 📽️ ▪️Video is now supported on Vercel AI Gateway ▪️Grok Imagine Video & Image are 🆓 thru Feb 25 ▪️New 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘 AI SDK API Incredible apps and agents are waiting to be shipped!