Brooo... This AI skill got me hooked FR 😂❤️
Now you can add those cursor-following mascot characters to your website that look around, react when you click them, and add a whole new layer of personality to your UI.
There are 52 premade characters, or you can ask your AI agent to draw a completely custom one, even one that looks like you.
And I forgot to show you how it reacts to a click event... you gotta check this out :)
Shout-out to @nilbuild for cooking this 🔥
Follow me for more amazing AI, Coding & Web Dev insights 💎
Brooooooooooooo WTF... this browser DevTools feature is mind-blowing. 🤯
Visit any website, open DevTools, click on the 3 dots menu... choose "More tools"... then "CSS Overview", and click "Capture overview".
It generates a detailed breakdown of the page's colors, fonts, media queries, unused declarations, and more.
Such a simple way to analyze any website's design system instantly.
We aren't using browsers to their full potential, there's so much more to discover, ngl :)
Watch the video for a quick demo 🎥
Follow me for more amazing AI, Coding & Web Dev insights 💎
NEED FOR SPEED PERO POR EL MUNDO REAL
Se llama https://t.co/eA7tBvigNX y funciona en el navegador, sin instalar nada.
El mundo se genera en tiempo real delante de ti con datos de OpenStreetMap y elevación por satélite mientras conduces.
Y puedes montar carreras multijugador.
Esto ya empieza a parecerse al Need for Speed + Google Maps que prometían.
Un jugador:
→ busca una ubicación
→ clica donde quieras en el mapa y dale a
“Hop Here”
→ cuando caigas en paracaídas mantén X para llamar al coche a la carretera
Multijugador:
→ dale a “Create race” y elige salida y meta
→ se traza la ruta sola
→ “Share Race” para sacar el enlace y a correr
Gemini Spark is coming to the @GeminiApp for macOS.
Plus, we’re rolling out more updates to your 24/7 personal AI agent in the Gemini app:
🔌 Support for custom Model Context Protocol (MCP) to build a more tailored assistant
📎 Integrations with @Canva, @Dropbox, @Instacart, @OpenTable and @ZillowRentals
✅ Connections with Google Tasks and Google Keep to turn brain-dumps into action items
🗞️ Track real-time topics and events like sports, stocks and news so you don't have to hit refresh
OpenAI vydal 6 pluginov pre Codex, každý pre inú pracovnú rolu 🔥
Jedno kliknutie a Codex sa stane špecialistom na tvoje odvetvie s predpripravenými nástrojmi a kontextom, bez akéhokoľvek nastavovania.
Viac info vo vlákne ↓
👀 Anthropic quietly released an official plugin that scans your project and auto-sets up hooks, skills, MCP servers, subagents, and automations. Most people are only using Claude Code at 20% of its potential.
This is amazing. Do this:
1. Set model to Opus 4.8
2. Reasoning effort to /ultracode
Enables Claude Code's new Dynamic Workflows.
Claude will autonomously detect complex tasks, write an orchestration script, and spawn an agent swarm.
It’s Codex Thursday, and yes, we have updates for you.
First up: Appshots, a new way to bring the context of what you’re working on into Codex.
On your Mac, press Command-Command to attach your app window to a Codex thread. Codex gets both a screenshot and text from the window, including content beyond what’s visible onscreen.
Appshots are available across plans on Mac, with enterprise access coming soon.
🚨 JUST IN - Google published a long piece about "Optimizing your website for generative AI features on Google Search" 👀
A lot in it https://t.co/22t75EtwUH
🧵