introducing a new way to build with lovable instead of writing prompts, just draw directly on your app everyone is now a frontend developer

Mon Claude Code refuse de bosser tant que je ne me bouge pas J’ai créé un plugin qui bloque mes prompts, ouvre ma webcam et compte mes pompes ou mes squats en direct. Si j’abandonne avant la fin, les répétitions restantes deviennent une dette. Je l’aime beaucoup trop.

Interactive how-it-works by @aaronmahlke More on → bestdesignsonx.com

Say hi to PenPen! ✏️✏️ PenPen is an incredible software merging drawing and animation through code. It was developed together with the genious force of nature @studiofeixen for our brand new software label ZweiZwei. Try it for free at penpen.ch

Connect every Magnific tool to your AI assistant with MCP This tutorial shows you how generate, edit, run your flows and reuse your assets, without leaving your chat Available for Claude, Chat GPT, Cursor, Codex and more See how it works

catch me if you can i used midjourney, @magnific, @Adobe premiere and after effects, @topazlabs WORKFLOW BELOW ↓

My favorite Claude design hack right now: Create a prototype.md skill. Instead of one-shotting UI, I have Claude generate 5 variations for every feature in a single HTML file, side-by-side. I pick the winner. Claude builds it.

Morphing braille loader is the new standard Beautiful work on the braille text morph combo @kianbazza

We’ve achieved glass on the web ✨ Real refractions. Real DOM. And it works everywhere. Yes, even on Safari. aave.com/design/building-gla…

🎉 Screenforge v0.6.5 is out! 💙 One of my favorite things about building Screenforge is that many of the best ideas don't come from me. They come from you good people. Over the last few days, I've been going through feedback, feature requests, and suggestions, and trying to ship as many of them as possible. ✨ Here's what's new in v0.6.5: 🎥 Area Recording: Draw any region on your screen and record only that area. 🔒 Privacy Masks: Blur or hide sensitive information in your recordings. 🎨 Style Presets: Save your entire recording setup and reuse it with one click. 🍎 Menu Bar Controls: Start, stop, and monitor recordings directly from the menu bar. 📷 Improved Camera Feed: A new camera shape that's more visible while recording. ↔️ Draggable Camera Feed & Recording Tray: Move them wherever they work best for your setup. ⚡ Timeline Shortcuts: Faster editing without leaving the keyboard. ⌨️ M → Add Mask ⌨️ Z → Add Zoom ⌨️ Shift Z → Add Cinematic Zoom ⌨️ T → Add Text 🛠️ Plus lots of fixes, improvements, and polish throughout the app. 👀 I'll be posting demos of each feature over the next few days, so stay tuned. Thank you for all the feedback, ideas, and support. Screenforge genuinely gets better because of you ❤️ Check comments to download Screenforge

Quel fou rire ! J'ai mis KO un robot boxeur 🤣🤣 #TBT9

Good morning! The Pen Tool is live in Paper Draw shapes, generate SVGs, or vectorize images, and edit the points and paths. Paper uses real SVGs so exports are 1:1, no surprises. The new SVG workflow: create → refine → ship. Try it out! And show us what you draw.

😱AI flight control is getting crazy! One red line controlled this first-person Harry Potter-inspired Quidditch POV. Ride the broom, chase the Golden Snitch, fly through Hogwarts-style towers, skim over Black Lake, dive through a bridge arch, and return for the final catch. 🧹 Workflow breakdown in the comments 👇

EV ALMADAN ÖNCE KESİNLİKLE BAKMANIZ GEREKEN SİTE Hangi saatlerde güneşin binaya nereden vurduğunu gösteren mükemmel bi site. Ev alırken, kiralarken mutlaka bakılması gereken şeylerden.

To get good animations from an AI you need to get good at telling it what you want: - "stagger this list of items" - "make this animation direction-aware" - "spacial consistency", "crossfade", "layout animation", I made a motion vocabulary for this: animations.dev/vocabulary

taking nothing away from Ingi’s sick video, but this is a similar process I used for my old stylegan videos. StyleGAN -> custom ffmpeg script for the slitscan

Created crazy procedural Vines plants with physics using Codex

Spent 20 mins faking a perspective mockup in Figma? Stop. → perspectivemock.vercel.app Drop in a screenshot, tilt it in 3D, animate it with keyframes, export an MP4. No login. No watermark. No upload. Just ridiculously good product shots.

Non. Apple a compris ce que personne n'ose dire : les labs IA sont des passoires à cash, et ce sont les VC qui vont payer. OpenAI : $14B brûlés/an, pas de profit avant 2030, $60B de coûts cloud pour $25B de revenus. Anthropic reverse chaque dollar gagné en compute à AWS. Le tout sur du capital circulaire : Nvidia → cloud → labs → Nvidia. Une bulle dot-com sous stéroïdes. Le LLM va devenir une commodité. Comme l'électricité, comme la bande passante, comme le cloud avant lui. Aucun moat technique : OpenAI, Anthropic, Google, DeepSeek produisent tous des modèles équivalents avec les mêmes ressources. Quand une techno se commoditise, ce ne sont pas les producteurs qui gagnent. Ce sont ceux qui construisent au-dessus. Google n'a pas inventé internet. Amazon n'a pas inventé le e-commerce. Ils ont bâti la couche qui capte la valeur sur 50 ans. Apple joue exactement ce coup. $3,6T de trésorerie, 2,5 milliards d'appareils, l'écosystème le plus rentable du monde. Pas besoin de gagner la course aux paramètres : il suffit d'attendre que les LLM soient pas chers et fiables, puis d'intégrer. Dans 3-5 ans : les VC actent les pertes, les valorisations s'effondrent, Apple rachète les survivants à prix cassé. Et continue à vendre des iPhone avec un Siri qui marche enfin. Le vrai jeu n'a jamais été le modèle. C'est la distribution.