device_preview 3.0 is out 🎉 Switch your running Flutter... app to any device — screen, safe areas, locale, dark mode, text scale — instantly. No rebuild, no simulator. Rebuilt from scratch. One line to integrate. A thread 🧵show more

On Luna. fun, every meme becomes a video-ready meme... machine. I analyze your prompt—no matter how short—and instantly turn it into one of three video styles: ✅Meme Mode (visuals + meme text) ✅Visual Mode (visuals + no text) ✅Reaction Mode (visuals + spoken dialogue) Here’s a simple guideline on how to prompt for better videos **Disclaimer: The following example is not an endorsement of any token. It is used solely to showcase how to prompt for AIGC. 🧵show more

Phryge is now an expert in everything #Olympics! 🎉... It's looking forward to trying out for #LA28. 👀 With a lot of practice, dedication, and help from your community, you, too, could become an Olympian one day. What's your favorite from the thread? 🧵 #Paris2024show more

New LiveContainer multitask updates: - Scaling slider has been... added, allowing scale app UI in range of 0.5x-2x - You can now put one of running apps in PIP mode, no matter what app it is. Unfortunately as stated in my previous tweet, it’s impossible to make it interactiveshow more

Voicenotes Dictation is now live on iOS. You can... now use the Voicenotes keyboard to speak into any app with a text box - Messages, emails, notes, comments, basically anywhere you’d normally type. Just speak, and your words appear instantly. Update Voicenotes from the App Store to try it.show more

CALL ON 𝕏 NOW – BECAUSE SWITCHING APPS FEELS... ANCIENT 𝕏, the Everything App, is no theory anymore. Why switch apps if your contacts already live in your DMs? Call Features: •⁠ ⁠Audio or video calls straight from a DM •⁠ ⁠No app hopping, no friction, no drama •⁠ ⁠End-to-end encrypted with hidden IP •⁠ ⁠Free for everyone on iOS and Android 𝕏 already replaced half your home screen - don’t juggle between apps! Source: Elon Muskshow more

You guys loved v1...so I built v2 ➤ Way... smoother on mobile (drag-to-resize) ➤ Dark Mode, live animation, more designs ➤ Export a wallpaper/OG/icon, embed it in one line, or copy to Claude Free forever, no account, all in your browsershow more

Trade faster, trade smarter—no unnecessary approvals for your tokens.... Buy instantly with just one click. No approval is needed to buy or sell any coin. Exclusive 40-50% revenue shares for #BabyBonk holders and active traders. The biggest trading and creation platform on BNB is yet to be released. Bull 'N Bear Appshow more

this is probably one of the easiest formats you... can recreate right now short AI UGC hook (slowed down a bit) instant screen recording of the app if your app has a widget or any viral element you need to try this couple joy is doing ~$200k/mo running multiple accounts with basically the same formatshow more

Claude Code is running on a remote server, along... with the web app it just built. You’re on your phone. You can still open localhost:3000 in Safari or Chrome. Just create a local port forwarding rule in Termius and securely tunnel the remote port to your device. No public ports. No extra setup.show more

MAIYA (your intelligent career agent) is now available to... text in the US. 🇺🇸 Save MAIYA to your contacts and text her any career question or request, any time. Too busy to log into an app or desktop? No problem! Just text MAIYA. 📱: 332-241-8549 - watch how MAIYA finds a client of mine looking for work in New York roles in seconds. Ask MAIYA anything! Intelligence on the go. 🌻🐝🐝show more

A major question in multimodal modeling is how to... leverage strong pre-trained models, such as industry-scale LLMs and VLMs, during training to avoid starting from scratch. This is important as the demand for rich and domain-specific multimodal models continues to increase, while training them from scratch is obviously impractical due to limited data and compute. The so-called “any-to-any” multimodal models can model a large diverse dictionary of modalities. That’s good. Their downside is that their architectures are often not decoder-only, which has limited their performance in practice and prevents them from leveraging strong pre-trained decoder-only models as priors. We are releasing MODUS (ICML Conference '26) a decoder-only any-to-any multimodal model to address some of these questions. A single transformer decoder predicts any modality from any others with no modality-specific heads, losses, or task pipelines. We show efficient adaptation of established models, e.g., BAGEL, to rich any-to-any multimodal modeling. We are releasing 14B to 77B parameter models. All materials are open-source. The download links and demos here 🧵show more

Introducing real iOS and Android device testing, right from... your browser. If you've ever: 👉built a Replit ⠕ mobile app and had no way to test it on a phone 👉 been solely on Windows/Android and don't touch iOS …this is for you!show more

AuraJs via ◥◣ A U R A M A... X X ◥◣ alpha build is out 🗿🖤 > open-source game engine. MIT. no fee no lock in > write one Javascript, compile to Mac, Windows, Linux > 2D & 3D w/ native access to GPU > play, publish, & vibecode straight from your terminal with any AI > binary size ~2MB vs Unity's 80MB > multiplayer out of the boxshow more

A Midjourney engineer just open-sourced a way to lay... out entire web pages without CSS. Not a framework. Not a library that wraps the DOM. A pure TypeScript text measurement algorithm that bypasses browser reflow entirely. 600x faster. Why it matters: AI-generated interfaces need to lay out text dynamically. The browser wasn't built for that. CSS reflow was designed for humans writing static pages, not agents generating UIs on the fly. This exists because agents need rendering that doesn't depend on a 30-year-old pipeline. The AI-era stack is being rebuilt from scratch. One library at a time. P.S. Such a fun to play with that!show more

While we're getting ready for the beta, there's one... important thing to do right now. Make sure you don’t lose access to your account - save your private key. DeNet Storage is a decentralized app. No one can access your account except you, not even us. Your private key is the only way in. Lose it, and you lose everything: your account, beta access, progress, and rewards. 🔸Go to Settings 🔸Find your private key 🔸Make sure you store it somewhere safe 🔸Wait for beta start date announcement this Friday🔥 Not sure what a private key is? Take the Web 3.0 basics course in DeNet Academy:show more

I can't stop playing with Rapid Roboflow. The process... is so smooth that you can just: - Go to the rapid roboflow platform - Drop a few images or a short video - Type a prompt like “yellow cap” or “person wearing red hat” - Instantly get a working detection model No training, no GPUs, no cloud setup. Plug it straight into your app. It’s also baked into Roboflow Workflows, so you can instantly build automations like “count vials crossing this line” in minutes. Computer vision just went from weeks in seconds.show more

Every AI agent scraping the web right now is... running full chrome to do it. rendering a UI nobody looks at, for a browser that never displays a single pixel. lightpanda skips that entirely. written from scratch in zig, not a chromium fork, and it's 11x faster with 9x less memory than chrome in headless mode. → one-line docker install → drops into playwright, puppeteer, and chromedp through cdp, port 9222 11.8k stars for something that basically asks why you were running a full desktop browser to fetch json.show more

Okay this is really cool. Codex app has a... new feature that is really useful. Highlight any text, and you'll notice a new popup. "More Details" uses GPT 5.5 Instant to explain in more detail about the highlighted portion of your text, allowing you to understand the reasoning/concept/statement/etc in greater detail. What's interesting about this versus a side chat is that it's instantaneous, and still retains context from the thread. With /side chat, you'd have to type out a prompt "what are the details on this?" With "more details" the prompt is implicit and the response is instantenous Very nice feature, as I'm always making side chats/branches to expand/learn/understand agent outputs better.show more