WITH THIS APP TAKE A SCREEN RECORDING AND TURN IT INTO A FULL PRODUCT DEMO VIDEO IN 20 MINUTES 3D ANIMATIONS, AI VOICEOVER, MUSIC, AND CALLOUTS. ONE APP.
LOOM VIDEOS ARE COOKED.
Imagine your AI doing design research before generating UI. Studying real screens and user flows instead of guessing
That’s Refero MCP https://t.co/uuZ6XLwIXa
𝗪𝗵𝗮𝘁 𝘄𝗲 𝘂𝘀𝗲𝗱 𝘁𝗼 𝗽𝗮𝘆 𝗮 𝗪𝗲𝗯𝗚𝗟 𝗱𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿 𝗳𝗼𝗿, 𝗜 𝗽𝘂𝘁 𝘁𝗼𝗴𝗲𝘁𝗵𝗲𝗿 𝗺𝘆𝘀𝗲𝗹𝗳 𝗶𝗻 𝟮 𝗱𝗮𝘆𝘀. 𝗦𝘁𝗿𝗲𝘀𝘀-𝘁𝗲𝘀𝘁𝗶𝗻𝗴 𝗚𝗲𝗺𝗶𝗻𝗶 𝟯.𝟭 𝗣𝗿𝗼 𝘁𝗼 𝘁𝗵𝗲 𝗺𝗮𝘅 🤯
The previous post, where I recreated the first part of our Three.js animation from https://t.co/86N8LPQCy7 with the help of a neural network, got a lot of reactions. So I decided to go further and take the experiment all the way to the end.
𝗚𝗼𝗮𝗹: build the FULL site animation using prompts only. Without a single line of code written by hand. So you understand the scale — back in the day, a live developer used to make a similar animation for us for a whole month, and it was accompanied by constant nerve-wracking and edits.
𝗡𝗼𝘄 𝘁𝗵𝗲 𝗿𝗲𝘀𝘂𝗹𝘁 𝘄𝗮𝘀 𝗿𝗲𝗮𝗱𝘆 𝗶𝗻 𝟮 𝗱𝗮𝘆𝘀. 𝗔𝗻𝗱 𝗶𝘁 𝗴𝗲𝗻𝘂𝗶𝗻𝗲𝗹𝘆 𝗶𝗺𝗽𝗿𝗲𝘀𝘀𝗲𝗱 𝗺𝗲.
Gemini 3.1 Pro produced a fully working project: a wave of thousands of particles collapses into a 3D sphere on scroll, then smoothly breaks apart into three separate spheres (like in the original) and merges back. All of this is driven by GLSL shader math and tied to scroll via GSAP.
𝗪𝗵𝗮𝘁 𝗜 𝗵𝗮𝗱 𝘁𝗼 𝘁𝗶𝗻𝗸𝗲𝗿 𝘄𝗶𝘁𝗵:
⚡ Morphing logic. Splitting one form into three with particle flow is complex geometry. The neural net wrote the shaders for a smooth split and reverse merge by itself.
⚡ Synchronization with GSAP. Camera movement, scaling, and the split triggers are perfectly fitted to the page scroll.
After that, all that was left was to bring everything to the final look and polish the animation so that it feels as smooth live as in the original.
What used to require a month of work from a dedicated specialist and a solid budget is now solved over a weekend. You just need to act as the art director and steer the model’s logic correctly. Neural nets really are changing the rules.
𝗥𝗮𝘁𝗲 𝘁𝗵𝗲 𝗳𝗶𝗻𝗮𝗹 𝗿𝗲𝘀𝘂𝗹𝘁 𝗳𝗿𝗼𝗺 𝟭 𝘁𝗼 𝟭𝟬 🔥
And the main question: what do you think — is it already time for WebGL developers to start quietly updating their resumes, or can the leather bags still sleep peacefully for now? Write in the comments 👇
We just open-sourced Paperclip: the orchestration layer for zero-human companies
It's everything you need to run an autonomous business: org charts, goal alignment, task ownership, budgets, agent templates
Just run `npx paperclipai onboard`
https://t.co/wuDdEmrSMx
More 👇
🚨 Someone just solved the biggest bottleneck in AI agents. And it's a 12MB binary.
It's called Pinchtab. It gives any AI agent full browser control through a plain HTTP API.
Not locked to a framework. Not tied to an SDK. Any agent, any language, even curl.
No config. No setup. No dependencies. Just a single Go binary.
Here's why every existing solution is broken:
→ OpenClaw's browser? Only works inside OpenClaw
→ Playwright MCP? Framework-locked
→ Browser Use? Coupled to its own stack
Pinchtab is a standalone HTTP server. Your agent sends HTTP requests. That's it.
Here's what this thing does:
→ Launches and manages its own Chrome instances
→ Exposes an accessibility-first DOM tree with stable element refs
→ Click, type, scroll, navigate. All via simple HTTP calls
→ Built-in stealth mode that bypasses bot detection on major sites
→ Persistent sessions. Log in once, stays logged in across restarts
→ Multi-instance orchestration with a real-time dashboard
→ Works headless or headed (human does 2FA, agent takes over)
Here's the wildest part:
A full page snapshot costs ~800 tokens with Pinchtab's /text endpoint.
The same page via screenshots? ~10,000 tokens.
That's 13x cheaper. On a 50-page monitoring task, you're paying $0.01 instead of $0.30.
It even has smart diff mode. Only returns what changed since the last snapshot. Your agent stops re-reading the entire page every single call.
1.6K GitHub stars. 478 commits. 15 releases. Actively maintained.
100% Open Source. MIT License.
Parcontre les gars 1er degrés c’est pas drôle y’a ma petite sœur et tout nos petits reufs qui joue à ce jeu comment on fait pour voir qu’elle joue pas à ce genre de jeu bizarre s’il vous plait
C'est normal que YGG ce soit fait piraté aussi facilement
Toute la dernière réeecriture du site était full IA
Quand on vous dit que l'IA doit resté un outil et ne doit pas remplacé le dev, on ce moque pas de vous
l'IA peu faire des choses fonctionnels mais 0 sécurité derrière
Les méthodes les plus simples pour faire fortune :
– Vendre le désir aux hommes
– Vendre la beauté aux femmes
– Vendre la tranquillité aux parents
– Vendre des rêves aux enfants
– Vendre la sécurité aux riches
– Vendre l'espoir aux fauchés
Même jeu. Emballage différent.
Anthropic is NERVOUS because
they know what’s coming:
- opensource AI will win
- AGI will run local, not on their servers
calling it now
> be early
> Buy a GPU
> get ur hands dirty
> learn how it works
> you’ll thank yourself later
bookmark this for later, it’s gonna be great
Introducing HeroUI Studio
a node-based tool that turns any SVG into animated SVGs using Gemini 3.1 Pro it preserves the original aesthetics
25 early access spots → https://t.co/D0Vsiflpic
Maple is now live https://t.co/ULVVknxXsT!
For years now I have been searching for the observability platform that fits my needs, most of the them lack in features I want, others are too simple and the rest either lack tooling to integrate with AI or are just plainly too expensive.
I wanted to change that so I build Maple,
build on the things I have seen work building at scale over the last 4 years.
Build on top of OTEL and @tinybird clickhouse it's both realtime and super fast.
It includes
- Trace view with advanced filters with autocomplete
- Logs
- Metrics
- Live Service Architecture Overview
and a MCP to make debugging so much easier
Maple is also open source https://t.co/OYHtgOZqUh and self-hostable with a one click deployment coming soon.
It is also available as a hosted version by me today with a free trial so you can give it a try.
Maple has already made my life debugging issues so much easier hope it will for you guys as well.
This is just the start with a lot more things coming soon