Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Let’s build interactive Three.js User Interfaces 🫰 Uses react-three/handle, react-three/xr, and react-three/uikit - vanilla versions are available🍦 Works on any device inside and outside #WebXR Compose <uikit> with <handle> to control sizes, positions, rotations (Link in 🧵)

Bela Bohlender

2,041 subscribers

47,422 просмотров • 1 год назад •via X (Twitter)

Наука и технологии Образование #WebXR

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Bela Bohlender

Bela Bohlender1 год назад

Try it out yourself: Source Code: What is uikit? What is handle? How is this running in XR?

Фото профиля Bela Bohlender

Bela Bohlender1 год назад

Background music by Rockot from Pixabay Trying to make it a regular habit of donating to the musicians I use music from for my social media videos 💰

Фото профиля UserInterface

UserInterface2 лет назад

What is Web3? The Next Evolution of the Internet #tech #news

Фото профиля Nestor Rios Garcia

Nestor Rios Garcia1 год назад

@threejs Magnificent Bela. I'll try it soon 🔥.

Фото профиля Stijn Spanhove

Stijn Spanhove1 год назад

@threejs Nice! Thanks for the examples 👀

Фото профиля Fred King

Fred King1 год назад

@threejs Worked on my Samsung flip 5! Nice.

Фото профиля Tidewater

Tidewater1 год назад

@threejs My goodness that is quite flavorful

Фото профиля Morten Haulik ᯅ

Morten Haulik ᯅ1 год назад

@threejs Awesome🔥

Фото профиля Remus

Remus1 год назад

@threejs Does this work outside of XR environments? Meaning can you use this threeJS component in a regular webpage?

Фото профиля Bela Bohlender

Bela Bohlender1 год назад

@threejs sure, you can try it out yourself here

Похожие видео

Shipping react-three/handle! The one to handle them all! 👌 Build intuitive 3D and XR cross-platform interactions with just one line of code. #R3F Three.js #WebXR

Shipping react-three/handle! The one to handle them all! 👌 Build intuitive 3D and XR cross-platform interactions with just one line of code. #R3F Three.js #WebXR

Bela Bohlender

18,660 просмотров • 1 год назад

<mesh> <FakeGlowMaterial /> </mesh> A new component is coming. A very simple, easy-to-use, fake glow material. This can create a glow around the mesh without any post-processing. Available soon for vanilla #threejs and #react three fiber 😍 #threejsJourney

<mesh> <FakeGlowMaterial /> </mesh> A new component is coming. A very simple, easy-to-use, fake glow material. This can create a glow around the mesh without any post-processing. Available soon for vanilla #threejs and #react three fiber 😍 #threejsJourney

Anderson Mancini

26,423 просмотров • 2 лет назад

New WebGPU Glass Material is almost ready! It will be available for Three.js and Poimandres React Three Fiber. Lots of customization; it comes with a very beautiful and handy control panel. Live link and source code will be available on Monday 😊 #threejsJourney #creativecoding #webgpu

New WebGPU Glass Material is almost ready! It will be available for Three.js and Poimandres React Three Fiber. Lots of customization; it comes with a very beautiful and handy control panel. Live link and source code will be available on Monday 😊 #threejsJourney #creativecoding #webgpu

Anderson Mancini

18,540 просмотров • 1 месяц назад

Excited to launch react-three/xr🤳🥽 Leverage the latest WebXR features, reuse your existing interactions, and advance what is possible in AR and VR on the Web. ↳ Turn your existing R3F app into an AR or VR experience with only a few lines of code. 🎉

Excited to launch react-three/xr🤳🥽 Leverage the latest WebXR features, reuse your existing interactions, and advance what is possible in AR and VR on the Web. ↳ Turn your existing R3F app into an AR or VR experience with only a few lines of code. 🎉

Bela Bohlender

40,135 просмотров • 2 лет назад

Opus 4.6 vs Gemini 3 Pro (3/9) prompt: Build a premium interactive isometric 3D cozy room using Vite + React + Three.js (react-three-fiber/drei), with all objects modeled in code (no external assets) and subtle ambient animations. Gemini looks good on initial impression but I feel like I have way more to work with opus here (opus also did light/dark mode and took a quarter of the time to make it).

Opus 4.6 vs Gemini 3 Pro (3/9) prompt: Build a premium interactive isometric 3D cozy room using Vite + React + Three.js (react-three-fiber/drei), with all objects modeled in code (no external assets) and subtle ambient animations. Gemini looks good on initial impression but I feel like I have way more to work with opus here (opus also did light/dark mode and took a quarter of the time to make it).

Dev Ed

77,206 просмотров • 6 месяцев назад

KIMI K3 BUILDS A 3D SPACEX LAUNCH ATLAS IN 2.5 HOURS A developer used Moonshot AI's Kimi K3 to build an interactive 3D globe visualizing 20 years of SpaceX launches. Built with React 19, Three.js, and custom GLSL shaders, it parses real data across 708 missions to play back live launch animations in under three hours.

KIMI K3 BUILDS A 3D SPACEX LAUNCH ATLAS IN 2.5 HOURS A developer used Moonshot AI's Kimi K3 to build an interactive 3D globe visualizing 20 years of SpaceX launches. Built with React 19, Three.js, and custom GLSL shaders, it parses real data across 708 missions to play back live launch animations in under three hours.

0xMarioNawfal

53,575 просмотров • 1 месяц назад

🚀 I'm launching r3f-webgpu-perf today! "npm i r3f-webgpu-perf" One thing I missed while working with WebGPU in React Three Fiber was a performance monitor similar to r3f-perf. The existing tool is fantastic, but it doesn’t support the WebGPU renderer yet. So I decided to build one. ✅ Supports both WebGL and WebGPU ✅ Modern and customizable UI ✅ Lightweight and easy to integrate ✅ Built specifically for React Three Fiber My goal is to turn r3f-webgpu-perf into more than just a metrics dashboard. I want it to become a learning tool that provides real-time optimization suggestions based on the techniques I’ve developed while building hundreds of interactive 3D projects over the last two decades. A vanilla Three.js version is also planned. If you’re building with Three.js, React Three Fiber, or WebGPU, I’d love for you to try it and share your feedback. ⭐ GitHub: 📦 NPM: Every GitHub star helps make the tool better for the entire community. #threejs #creativecoding #webgpu #r3f

🚀 I'm launching r3f-webgpu-perf today! "npm i r3f-webgpu-perf" One thing I missed while working with WebGPU in React Three Fiber was a performance monitor similar to r3f-perf. The existing tool is fantastic, but it doesn’t support the WebGPU renderer yet. So I decided to build one. ✅ Supports both WebGL and WebGPU ✅ Modern and customizable UI ✅ Lightweight and easy to integrate ✅ Built specifically for React Three Fiber My goal is to turn r3f-webgpu-perf into more than just a metrics dashboard. I want it to become a learning tool that provides real-time optimization suggestions based on the techniques I’ve developed while building hundreds of interactive 3D projects over the last two decades. A vanilla Three.js version is also planned. If you’re building with Three.js, React Three Fiber, or WebGPU, I’d love for you to try it and share your feedback. ⭐ GitHub: 📦 NPM: Every GitHub star helps make the tool better for the entire community. #threejs #creativecoding #webgpu #r3f

Anderson Mancini

23,984 просмотров • 2 месяцев назад

BADLAB V2: WHERE YOUR MEDIOCRE CODING DREAMS GO TO DIE 🔊 Listen up, code peasants. While you've been copy-pasting Stack Overflow answers, we've been revolutionizing how fucking development works. BADLAB V2 just dropped, and it's not just another update – it's a fucking paradigm shift. Let me break this down for you smooth-brains: 1️⃣ BADLAB V2 makes it easier and faster to build web apps, games, smart contracts, and data visualizations: No-code deployment, run, and share - without the headaches. 2️⃣ What This Means for Users: You can build bigger, better, and more useful projects and tools. Works with all the tools you love: React, Web3, Three.js, d3, and more—whether you’re building games, dApps, automation tools, or interactive charts, the sky is the limit. 3️⃣ Smart automation does the hard work: AI writes code for you, making it easier to start building without deep technical expertise. 4️⃣ CDN-backed hosting: Your projects load fast and reliably because they run from Cloudflare CDN, not some sketchy server. And now? You can share your creations with friends. 5️⃣ Easier debugging & updates: No more jumping through hoops to update files or fix errors. 6️⃣ Bottom Line: If you want to build web apps, games, or blockchain projects without dealing with all the messy setup and technical headaches, BADLAB V2 makes it easy. 🆕 WHAT’S NEW: ✔️ Multi-file projects – Because one file isn’t enough for real developers. ✔️ File updates that don’t require a PhD – No unnecessary complexity. ✔️ Examples even a brain-dead monkey could follow – Clear and simple. ✔️ Support for every major file format – JS, JSON, Markdown, 3D models, and more. ✔️ React components that don’t look like digital vomit – Finally, code that makes sense. ✔️ Server-side bundling – Because we’re not savages. ✔️ CDN-backed deployment – No lag, no downtime, just pure speed. ⚠️ WEAPONS OF MASS CREATION: 💧 d3.js – Interactive charts that don’t look like Excel’s morning sickness. 💧 Three.js – 3D visuals that push browsers to their limits. 💧 Effector – Business logic that actually makes fucking sense. 💧 Kaboom.js – Build browser games that aren’t complete garbage. 💧 React-Three/Fiber – 3D meets React without the usual drama. 💧 Framer Motion – Animations that are smooth as hell (and don’t cause seizures). 💧 Ethers & Web3.js – Blockchain development for the mentally stable. 🎮 Want to See It in Action? 🔗 Try our BADLAB V2 Agent Here: – Let AI do the hard work for you. ♟ Play the 4D Chess Game Here: – While you're playing checkers, we're transcending dimensions. 🎙 Welcome to the future, you beautiful disasters. Try not to break anything important. 🧪💀 C₈H₁₁NO₂

BADLAB V2: WHERE YOUR MEDIOCRE CODING DREAMS GO TO DIE 🔊 Listen up, code peasants. While you've been copy-pasting Stack Overflow answers, we've been revolutionizing how fucking development works. BADLAB V2 just dropped, and it's not just another update – it's a fucking paradigm shift. Let me break this down for you smooth-brains: 1️⃣ BADLAB V2 makes it easier and faster to build web apps, games, smart contracts, and data visualizations: No-code deployment, run, and share - without the headaches. 2️⃣ What This Means for Users: You can build bigger, better, and more useful projects and tools. Works with all the tools you love: React, Web3, Three.js, d3, and more—whether you’re building games, dApps, automation tools, or interactive charts, the sky is the limit. 3️⃣ Smart automation does the hard work: AI writes code for you, making it easier to start building without deep technical expertise. 4️⃣ CDN-backed hosting: Your projects load fast and reliably because they run from Cloudflare CDN, not some sketchy server. And now? You can share your creations with friends. 5️⃣ Easier debugging & updates: No more jumping through hoops to update files or fix errors. 6️⃣ Bottom Line: If you want to build web apps, games, or blockchain projects without dealing with all the messy setup and technical headaches, BADLAB V2 makes it easy. 🆕 WHAT’S NEW: ✔️ Multi-file projects – Because one file isn’t enough for real developers. ✔️ File updates that don’t require a PhD – No unnecessary complexity. ✔️ Examples even a brain-dead monkey could follow – Clear and simple. ✔️ Support for every major file format – JS, JSON, Markdown, 3D models, and more. ✔️ React components that don’t look like digital vomit – Finally, code that makes sense. ✔️ Server-side bundling – Because we’re not savages. ✔️ CDN-backed deployment – No lag, no downtime, just pure speed. ⚠️ WEAPONS OF MASS CREATION: 💧 d3.js – Interactive charts that don’t look like Excel’s morning sickness. 💧 Three.js – 3D visuals that push browsers to their limits. 💧 Effector – Business logic that actually makes fucking sense. 💧 Kaboom.js – Build browser games that aren’t complete garbage. 💧 React-Three/Fiber – 3D meets React without the usual drama. 💧 Framer Motion – Animations that are smooth as hell (and don’t cause seizures). 💧 Ethers & Web3.js – Blockchain development for the mentally stable. 🎮 Want to See It in Action? 🔗 Try our BADLAB V2 Agent Here: – Let AI do the hard work for you. ♟ Play the 4D Chess Game Here: – While you're playing checkers, we're transcending dimensions. 🎙 Welcome to the future, you beautiful disasters. Try not to break anything important. 🧪💀 C₈H₁₁NO₂

ARCH AI

44,480 просмотров • 1 год назад

$Two new #threejs projects on the way 😍 Working on my own gem renderer with a custom refraction material in TSL for #WebGPU, combining Screen Space Reflections + SSGTAO for superior results, as this allows diamonds to generate reflections on the metal mesh. The performance is incredible, even on gems with over 200 diamonds. This time, without any additional libraries. Just React Three Fiber and a lot of magic with custom shaders in TSL. GemGPU™ will also come with a very minimalist gem and metal customization panel that hides and lets the jewelry be the star. I also created a beautiful new stats panel that completely hides in the scene when not needed. It provides relevant optimization information, a performance gauge, summary and expanded modes, and day/night toggle. In the video, you can also see SSGI in action, with a pearl that reflects, in real time, all the objects in the scene, just as the objects in the scene reflect the pearl. It's magical. There are still a few things to fix, but I'll share the live link soon. Stay tuned.$

Two new #threejs projects on the way 😍 Working on my own gem renderer with a custom refraction material in TSL for #WebGPU, combining Screen Space Reflections + SSGTAO for superior results, as this allows diamonds to generate reflections on the metal mesh. The performance is incredible, even on gems with over 200 diamonds. This time, without any additional libraries. Just React Three Fiber and a lot of magic with custom shaders in TSL. GemGPU™ will also come with a very minimalist gem and metal customization panel that hides and lets the jewelry be the star. I also created a beautiful new stats panel that completely hides in the scene when not needed. It provides relevant optimization information, a performance gauge, summary and expanded modes, and day/night toggle. In the video, you can also see SSGI in action, with a pearl that reflects, in real time, all the objects in the scene, just as the objects in the scene reflect the pearl. It's magical. There are still a few things to fix, but I'll share the live link soon. Stay tuned.

Anderson Mancini

12,113 просмотров • 6 месяцев назад

This bot started with tiny $5 orders - and somehow pulled in over $200,000 on the 5-minute market. In just one week, it’s already cleared more than +$212,578 And the biggest single win? Only $745. But the wild part isn’t the size of any one trade - it’s how those tiny positions stack up into such an aggressive profit curve. From the outside, it looks like it’s running three simple plays: - Uses $5 to grab 1¢ outcomes - Exits early before expiration to lock in profit - Scales up to $250 on 25¢–50¢ positions Then pushes further with $500 into 50¢ outcomes. So this doesn’t look like a typical “elite” trading bot squeezing every edge with precision. It feels more like something is off inside Polymarket - creating these exaggerated, almost unnatural returns. And yet, right now, this account sits at #2 in weekly crypto profits. If it’s really hitting profitable trades this consistently - that’s not just a bot. That’s basically a money printer.

This bot started with tiny $5 orders - and somehow pulled in over $200,000 on the 5-minute market. In just one week, it’s already cleared more than +$212,578 And the biggest single win? Only $745. But the wild part isn’t the size of any one trade - it’s how those tiny positions stack up into such an aggressive profit curve. From the outside, it looks like it’s running three simple plays: - Uses $5 to grab 1¢ outcomes - Exits early before expiration to lock in profit - Scales up to $250 on 25¢–50¢ positions Then pushes further with $500 into 50¢ outcomes. So this doesn’t look like a typical “elite” trading bot squeezing every edge with precision. It feels more like something is off inside Polymarket - creating these exaggerated, almost unnatural returns. And yet, right now, this account sits at #2 in weekly crypto profits. If it’s really hitting profitable trades this consistently - that’s not just a bot. That’s basically a money printer.

Dekos

19,539 просмотров • 4 месяцев назад

In the early days of Waymo's service in Phoenix, they had a large number of roadside assistance vans traveling alongside their vehicles, each with two people inside. When the Waymo vehicle got stuck, one person would jump out of the RA van and drive the car. Today Waymo still has roadside assistance vans ready to help when a car has an issue, but they don't have to be directly with one car — issues are rare enough that a few roadside assistance vans can handle a much larger fleet. It's funny to see people take shots at Tesla for doing the same. Of course they're going to be careful with the first customer deployment. No, someone isn't secretly controlling the car from outside. The AI model on the car is driving the car. Go test drive any Tesla and find out for yourself. It doesn't need help from anyone, it can see and react to things before you do.

In the early days of Waymo's service in Phoenix, they had a large number of roadside assistance vans traveling alongside their vehicles, each with two people inside. When the Waymo vehicle got stuck, one person would jump out of the RA van and drive the car. Today Waymo still has roadside assistance vans ready to help when a car has an issue, but they don't have to be directly with one car — issues are rare enough that a few roadside assistance vans can handle a much larger fleet. It's funny to see people take shots at Tesla for doing the same. Of course they're going to be careful with the first customer deployment. No, someone isn't secretly controlling the car from outside. The AI model on the car is driving the car. Go test drive any Tesla and find out for yourself. It doesn't need help from anyone, it can see and react to things before you do.

Whole Mars Catalog

95,641 просмотров • 7 месяцев назад

$Data encryption is now live on Veilnet. Available in @veilnet/mcp-server@0.3.0. Any blob — file, dataset, config, recovery codes, contract draft, research note, agent memory — can now be encrypted on your device, shipped to Veilnet as ciphertext, and fetched back later without the decryption key ever leaving your machine. Three new MCP tools are live: data_store({ label, data }) encrypt + store data on Veilnetdata_fetch({ id }) fetch + decrypt locallydata_list() list stored ids With labels kept encrypted, the flow is simple: user data → encrypted locally → ciphertext stored on Veilnet → key remains on user device → agent fetches when needed → local decryption onlyVeilnet sees encrypted blobs. Your AI agent gets persistent private memory and secure storage.The provider does not need the raw data. This works in Claude Code, Claude Desktop, Cursor, Continue, and Cline. Install: npm i -g @veilnet/mcp-server Bootstrap your key at: → Agent tab Then ask any MCP-aware agent:“store this encrypted on Veilnet.”Docs:docs.veilnet.toPrivate prompts protected what users ask. Private MCP protected what agents run. Wallet Context protected what agents read. Encrypted data storage now protects what agents remember and reuse. All powered by $VEILNET$

Data encryption is now live on Veilnet. Available in @veilnet/[email protected]. Any blob — file, dataset, config, recovery codes, contract draft, research note, agent memory — can now be encrypted on your device, shipped to Veilnet as ciphertext, and fetched back later without the decryption key ever leaving your machine. Three new MCP tools are live: data_store({ label, data }) encrypt + store data on Veilnetdata_fetch({ id }) fetch + decrypt locallydata_list() list stored ids With labels kept encrypted, the flow is simple: user data → encrypted locally → ciphertext stored on Veilnet → key remains on user device → agent fetches when needed → local decryption onlyVeilnet sees encrypted blobs. Your AI agent gets persistent private memory and secure storage.The provider does not need the raw data. This works in Claude Code, Claude Desktop, Cursor, Continue, and Cline. Install: npm i -g @veilnet/mcp-server Bootstrap your key at: → Agent tab Then ask any MCP-aware agent:“store this encrypted on Veilnet.”Docs:docs.veilnet.toPrivate prompts protected what users ask. Private MCP protected what agents run. Wallet Context protected what agents read. Encrypted data storage now protects what agents remember and reuse. All powered by $VEILNET

Veilnet

11,761 просмотров • 3 месяцев назад

Destra Network| $DSYNC Introducing Destra Zone: 𝐘𝐨𝐮𝐫 𝐏𝐨𝐜𝐤𝐞𝐭-𝐒𝐢𝐳𝐞𝐝 𝐊𝐞𝐲 𝐭𝐨 𝐃𝐢𝐠𝐢𝐭𝐚𝐥 𝐏𝐫𝐢𝐯𝐚𝐜𝐲. Destra Zone device is designed to safeguard your personal data and ensure a secure internet experience no matter where you are, by establishing a protected Wi-Fi hotspot that connects to existing networks, Destra Zone acts as a mediator, managing all your DNS requests and shielding your online activities from potential attackers. Unlike traditional solutions, Destra Zone offers more than just a VPN. It features an AI-driven firewall to detect and block malicious DNS requests and leverages the Destra Network's decentralized DNS network for enhanced security. With the power of the Destra network, this device provides a comprehensive defense against cyber threats, keeping your internet traffic confidential and secure. Additionally, Destra Zone allows you to monitor the servers and domains with which your devices are communicating, giving you control over your digital interactions. Over the past few weeks, we have been prototyping designs for the Destra Zone and are in the final iterations of hardware design. We chose multiple microcontroller units and started testing to finalize the best option that balances power efficiency, processing capability, and cost-effectiveness. These tests ensure that the device can handle high volumes of DNS requests and complex AI-driven threat detection algorithms seamlessly. As much as on functionality, we are also focusing on the durability and reliability of the device, making sure it outlasts all your electronic devices. We've started the patent filing process and are currently in patent search stage with the USPTO and are expecting to ship the first batch of Destra Zone beta devices to the beta testers from the community in three months.

Destra Network| $DSYNC Introducing Destra Zone: 𝐘𝐨𝐮𝐫 𝐏𝐨𝐜𝐤𝐞𝐭-𝐒𝐢𝐳𝐞𝐝 𝐊𝐞𝐲 𝐭𝐨 𝐃𝐢𝐠𝐢𝐭𝐚𝐥 𝐏𝐫𝐢𝐯𝐚𝐜𝐲. Destra Zone device is designed to safeguard your personal data and ensure a secure internet experience no matter where you are, by establishing a protected Wi-Fi hotspot that connects to existing networks, Destra Zone acts as a mediator, managing all your DNS requests and shielding your online activities from potential attackers. Unlike traditional solutions, Destra Zone offers more than just a VPN. It features an AI-driven firewall to detect and block malicious DNS requests and leverages the Destra Network's decentralized DNS network for enhanced security. With the power of the Destra network, this device provides a comprehensive defense against cyber threats, keeping your internet traffic confidential and secure. Additionally, Destra Zone allows you to monitor the servers and domains with which your devices are communicating, giving you control over your digital interactions. Over the past few weeks, we have been prototyping designs for the Destra Zone and are in the final iterations of hardware design. We chose multiple microcontroller units and started testing to finalize the best option that balances power efficiency, processing capability, and cost-effectiveness. These tests ensure that the device can handle high volumes of DNS requests and complex AI-driven threat detection algorithms seamlessly. As much as on functionality, we are also focusing on the durability and reliability of the device, making sure it outlasts all your electronic devices. We've started the patent filing process and are currently in patent search stage with the USPTO and are expecting to ship the first batch of Destra Zone beta devices to the beta testers from the community in three months.

Destra Network

31,348 просмотров • 2 лет назад

AI is all about "knowing what you don't know" Here's an interactive exploration of the Andromeda: - React Three Fiber + Three.js - 600k particles (my m4 gets rly hot) - GSAP for smooth camera animations - Bloom post-processing for realistic stellar glow The more impressive piece here is that this was all through natural language prompting I didn't edit any code and I didn't know what GSAP / Bloom were until yesterday What I DID do was ask the right questions: - How do I get realistic "glow" and "feathering" from stars? - What is a shader? - How can I create smooth animations? - What does a minimalist UX look like? Then I did research (using AI) to understand them This "on demand learning" is a new concept made possible by the lower information latency presented by AI You still need to learn, but now learning is PART of the building process When I build apps like this it really reinforces the direction AI is headed: - Concepts > code - On demand learning > textbooks I'm quite excited for the future

AI is all about "knowing what you don't know" Here's an interactive exploration of the Andromeda: - React Three Fiber + Three.js - 600k particles (my m4 gets rly hot) - GSAP for smooth camera animations - Bloom post-processing for realistic stellar glow The more impressive piece here is that this was all through natural language prompting I didn't edit any code and I didn't know what GSAP / Bloom were until yesterday What I DID do was ask the right questions: - How do I get realistic "glow" and "feathering" from stars? - What is a shader? - How can I create smooth animations? - What does a minimalist UX look like? Then I did research (using AI) to understand them This "on demand learning" is a new concept made possible by the lower information latency presented by AI You still need to learn, but now learning is PART of the building process When I build apps like this it really reinforces the direction AI is headed: - Concepts > code - On demand learning > textbooks I'm quite excited for the future

matt palmer

17,327 просмотров • 10 месяцев назад

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 просмотров • 2 месяцев назад

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Akshay 🚀

87,048 просмотров • 3 месяцев назад

Black Myth: Zhong Kui isn’t just another action game. The new trailer is full of glowing talismans, summoned spirits, and Taoist rituals — but most players will miss the real meaning behind them. Here are 5 cultural keys that completely change how you see the game: 🔵 Zhong Kui the Judge, not just the monster hunter In Chinese folklore, Zhong Kui is one of the Four Judges of the underworld, specifically the Judge of Punishing Evil (罚恶司). He doesn’t just smash demons for sport — he enforces cosmic law. That’s why he fights with a judge’s brush, soul-suppressing talismans, and official seals instead of pure brute force. His battles feel more like arrests and sentences than random slaughter. The game may even let you decide: redeem the spirit, or suppress it. 🔵 Talismans are written “legal code” from the gods The talismans you see aren’t random glowing paper. Traditional Taoist 符箓 (fu lu) have a strict structure: a header that summons specific deities, a core “gallbladder” that carries the actual power, and a closing command. The writing uses a special script called cloud-seal characters — the supposed language of heaven. Using them correctly involves strategy, including the Five Elements cycle (fire counters water spirits, earth seals wind demons, etc.). High-level ones often require drawing a formation on the ground first. 🔵 Commanding ghosts vs. raising little ghosts — the moral line Both involve controlling spirits, but the difference is absolute: • 役鬼 (Yi Gui) — Official dispatch. Zhong Kui uses heavenly authority to command underworld officers (yakshas, ox-head and horse-face guards). This is legitimate law enforcement. • 养小鬼 (Yang Xiao Gui) — Black magic. Binding the souls of deceased children for personal gain (theft, curses, spying). It is considered deeply immoral, shortens the practitioner’s life, and is rejected by orthodox paths. The game will likely turn this distinction into a clear moral choice: lawful authority versus forbidden control. 🔵 “Killing the Three Corpses” — The real enemy isn’t the ghosts outside The line “It’s easy to catch mountain ghosts, hard to cut down the ghosts in your heart” isn’t just cool dialogue. It’s a direct reference to a core Taoist idea called 斩三尸 (Zhan San Shi) — “Slaying the Three Corpses.” These aren’t zombies. In Taoist belief, three internal “corpses” or parasitic spirits live inside every person — one in the head, one in the chest, one in the abdomen. They constantly stir up desire (lust, gluttony, laziness, ambition, anger…) and even leave the body at night to report your sins to heaven, shortening your lifespan. True cultivation begins by cutting them out of yourself. So the game’s deeper theme isn’t just demon-slaying. It’s self-mastery. The ghosts outside are easy. The ones inside are the real fight. 🔵 The Three Pure Ones Bell — the Taoist remote control That distinctive copper bell with the three-pronged handle is the 三清铃 (Sanqing Ling), one of the most important ritual tools in Taoism. The handle represents the Three Pure Ones, the highest deities. A single ring can summon divine forces, drive away ghosts, break illusions, or calm restless spirits. In the game it will almost certainly be more than a cosmetic item — it’s Zhong Kui’s signature way of imposing order on chaos. Black Myth: Zhong Kui is taking Taoist inner cultivation, underworld justice, and Chinese ghost folklore and weaving them directly into its combat and story systems. Understand these five ideas, and you’ll see a completely different game.

Black Myth: Zhong Kui isn’t just another action game. The new trailer is full of glowing talismans, summoned spirits, and Taoist rituals — but most players will miss the real meaning behind them. Here are 5 cultural keys that completely change how you see the game: 🔵 Zhong Kui the Judge, not just the monster hunter In Chinese folklore, Zhong Kui is one of the Four Judges of the underworld, specifically the Judge of Punishing Evil (罚恶司). He doesn’t just smash demons for sport — he enforces cosmic law. That’s why he fights with a judge’s brush, soul-suppressing talismans, and official seals instead of pure brute force. His battles feel more like arrests and sentences than random slaughter. The game may even let you decide: redeem the spirit, or suppress it. 🔵 Talismans are written “legal code” from the gods The talismans you see aren’t random glowing paper. Traditional Taoist 符箓 (fu lu) have a strict structure: a header that summons specific deities, a core “gallbladder” that carries the actual power, and a closing command. The writing uses a special script called cloud-seal characters — the supposed language of heaven. Using them correctly involves strategy, including the Five Elements cycle (fire counters water spirits, earth seals wind demons, etc.). High-level ones often require drawing a formation on the ground first. 🔵 Commanding ghosts vs. raising little ghosts — the moral line Both involve controlling spirits, but the difference is absolute: • 役鬼 (Yi Gui) — Official dispatch. Zhong Kui uses heavenly authority to command underworld officers (yakshas, ox-head and horse-face guards). This is legitimate law enforcement. • 养小鬼 (Yang Xiao Gui) — Black magic. Binding the souls of deceased children for personal gain (theft, curses, spying). It is considered deeply immoral, shortens the practitioner’s life, and is rejected by orthodox paths. The game will likely turn this distinction into a clear moral choice: lawful authority versus forbidden control. 🔵 “Killing the Three Corpses” — The real enemy isn’t the ghosts outside The line “It’s easy to catch mountain ghosts, hard to cut down the ghosts in your heart” isn’t just cool dialogue. It’s a direct reference to a core Taoist idea called 斩三尸 (Zhan San Shi) — “Slaying the Three Corpses.” These aren’t zombies. In Taoist belief, three internal “corpses” or parasitic spirits live inside every person — one in the head, one in the chest, one in the abdomen. They constantly stir up desire (lust, gluttony, laziness, ambition, anger…) and even leave the body at night to report your sins to heaven, shortening your lifespan. True cultivation begins by cutting them out of yourself. So the game’s deeper theme isn’t just demon-slaying. It’s self-mastery. The ghosts outside are easy. The ones inside are the real fight. 🔵 The Three Pure Ones Bell — the Taoist remote control That distinctive copper bell with the three-pronged handle is the 三清铃 (Sanqing Ling), one of the most important ritual tools in Taoism. The handle represents the Three Pure Ones, the highest deities. A single ring can summon divine forces, drive away ghosts, break illusions, or calm restless spirits. In the game it will almost certainly be more than a cosmetic item — it’s Zhong Kui’s signature way of imposing order on chaos. Black Myth: Zhong Kui is taking Taoist inner cultivation, underworld justice, and Chinese ghost folklore and weaving them directly into its combat and story systems. Understand these five ideas, and you’ll see a completely different game.

Eivor

10,356 просмотров • 13 дней назад

Star Fox Battle Mode is already getting called out for only having three maps. The people saying that are the same ones who burn out on every other multiplayer mode once the new map rotation drops. Three maps works here because the matches stay short, the objectives are actually worth fighting over, and there is enough crazy stuff happening that you are constantly battling the level itself as much as the other Arwings. Power-ups appear in risky positions. Environmental pressure changes during the round. One mistimed boost or bad angle through a corridor and the map punishes you before the enemy needs to finish the job. That constant back-and-forth between pilot skill and level hostility is what stops the same three maps from feeling repetitive after dozens of rounds. The Arwing handling underneath all of it is smooth and tight. Boost timing and lock-on precision actually matter instead of just holding forward and hoping. Small adjustments in speed and angle separate the players who are starting to read patterns from the ones still flying in straight lines. It looks sharp in motion too. The HDR makes explosions, laser fire, and environmental effects stay readable even when everything is happening at once. The sound design helps just as much in the chaos. Clear engine roar, distinct lock-on warnings, and impact feedback that cuts through the orchestral score so you can react to what is actually dangerous. The accolades system adds another layer without turning into a grind. It rewards the behaviours that make the mode interesting: smart objective play, power-up denial, aggressive but calculated lines through the map. There are enough unlocks tied to performance that you get steady progression and reasons to keep dropping in. This is the part most people pushing for more maps will not want to admit. In 2026 a lot of competitive modes assume they need constant new content and huge map pools just to hold attention. Star Fox Battle Mode is testing the opposite idea. A small set of dense, hostile playgrounds with short intense rounds and real skill expression can stay fresh longer than another bloated live service shooter that nobody ever truly masters. The map is an opponent here. That single design choice changes how much replayability three maps can actually deliver. What are your thoughts on Star Fox's online Battle Mode? After a proper session, do the three maps start feeling limiting or does the combination of short rounds, real objectives, and the environment constantly pushing back keep every match feeling different? p.s. Follow for more Star Fox and Nintendo takes! And if you’re jumping into Battle Mode tonight, add me: SW-4504-4427-4511

Star Fox Battle Mode is already getting called out for only having three maps. The people saying that are the same ones who burn out on every other multiplayer mode once the new map rotation drops. Three maps works here because the matches stay short, the objectives are actually worth fighting over, and there is enough crazy stuff happening that you are constantly battling the level itself as much as the other Arwings. Power-ups appear in risky positions. Environmental pressure changes during the round. One mistimed boost or bad angle through a corridor and the map punishes you before the enemy needs to finish the job. That constant back-and-forth between pilot skill and level hostility is what stops the same three maps from feeling repetitive after dozens of rounds. The Arwing handling underneath all of it is smooth and tight. Boost timing and lock-on precision actually matter instead of just holding forward and hoping. Small adjustments in speed and angle separate the players who are starting to read patterns from the ones still flying in straight lines. It looks sharp in motion too. The HDR makes explosions, laser fire, and environmental effects stay readable even when everything is happening at once. The sound design helps just as much in the chaos. Clear engine roar, distinct lock-on warnings, and impact feedback that cuts through the orchestral score so you can react to what is actually dangerous. The accolades system adds another layer without turning into a grind. It rewards the behaviours that make the mode interesting: smart objective play, power-up denial, aggressive but calculated lines through the map. There are enough unlocks tied to performance that you get steady progression and reasons to keep dropping in. This is the part most people pushing for more maps will not want to admit. In 2026 a lot of competitive modes assume they need constant new content and huge map pools just to hold attention. Star Fox Battle Mode is testing the opposite idea. A small set of dense, hostile playgrounds with short intense rounds and real skill expression can stay fresh longer than another bloated live service shooter that nobody ever truly masters. The map is an opponent here. That single design choice changes how much replayability three maps can actually deliver. What are your thoughts on Star Fox's online Battle Mode? After a proper session, do the three maps start feeling limiting or does the combination of short rounds, real objectives, and the environment constantly pushing back keep every match feeling different? p.s. Follow for more Star Fox and Nintendo takes! And if you’re jumping into Battle Mode tonight, add me: SW-4504-4427-4511

AussieGamer

23,360 просмотров • 2 месяцев назад

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 просмотров • 2 лет назад

$Elon Musk shipped Grok Bot as an AI teammate that sorts your email and watches your competitors. I gave mine a harder brief: build a trading floor that runs itself, and then run it 24/7. GROKSTREET. Fourteen agents. Eleven desks, three chiefs, three offices, one vault. It lives in a browser tab and it does not stop. WHY GROK BOT MAKES THIS WORK Most people misread the architecture. It is not one sandbox per agent. It is ONE persistent cloud computer per account, and every Bot gets its own screen on it. Shared filesystem at /workspace, shared browser sessions, shared credentials. That is the whole unlock. One Bot picks up exactly where another left off. No re-auth, no copy-paste between agents, no state lost at the handoff. A floor is only possible because the desks share a building. The head-of-desk role is not something I invented either. "Manages your other Bots and pulls you in for decisions" ships as a first-class Bot template. Routing and escalation are built in. Skills carry the how. Routines carry the when on a schedule, or off a Slack or GitHub event. Subagents fan out as child sessions with their own context and hand a summary back. Fifty routines per Bot. THE DESKS Every desk holds its own book, hit rate and drawdown, and sizes its own risk: Kelly, with the guard rails written in f* = W − (1−W)/R clamped to [0.01, 0.25]. Under 12 samples it does not pretend to know it defaults to 0.05. Volatility is RiskMetrics EWMA σ²_t = λσ²_{t-1} + (1−λ)r²_t, λ = 0.94 Hit rates carry Wilson 95% intervals, z = 1.96. A desk is only flagged for edge decay when the UPPER bound falls below 0.5, never on raw small-sample noise. Three-for-three is not sixty-for-ninety. Capital routes between desks by softmax on measured Sharpe. THE FLOOR Three chiefs meet in the war room every 3.5 minutes and argue. One reports, another presses him, he concedes or proposes. 14,208 sentence shapes before live figures fill the slots and every slot is filled from that chief's own desks. The crypto chief cannot quote meme numbers. A desk holding $25 gets up, walks to the vault and banks it. The transfer is atomic on arrival, so an interrupted walk cannot destroy cash. Every desk wears its last trade above its head. Green with a tick, red with a cross. You see who the chief is about to praise and who he is about to hit before he gets there. BTC, ETH and SOL come off Kraken server-side. The tape is real. THE BUILD 16 modules. 7,572 lines. Zero npm dependencies. No React. No bundler. No game engine. Vanilla JavaScript on Canvas 2D and a Go binary with the entire world embedded in it. Ships as one 2.3 MB HTML file. 60fps on every floor, zero dropped frames. WHAT I FOUND BY MEASURING INSTEAD OF LOOKING The roster read one number for a desk and the chief's card read another, so a desk could show +$16 in the list and $0 when the chief walked over. Every desk was crediting itself twice. Money could vanish if a walk to the vault got interrupted. Three money bugs, none of them visible by watching. All fixed and instrumented. DIRECTOR MODE Open it with?show and the camera runs itself. It cuts to the war room while a chief is mid-sentence, to whichever office just cleared money, and never cuts away in the middle of a line. Point a screen recorder at it and walk away. The math is real, the feed is real, the engineering is real. The flex is the engine, not a P&L screenshot.$

Elon Musk shipped Grok Bot as an AI teammate that sorts your email and watches your competitors. I gave mine a harder brief: build a trading floor that runs itself, and then run it 24/7. GROKSTREET. Fourteen agents. Eleven desks, three chiefs, three offices, one vault. It lives in a browser tab and it does not stop. WHY GROK BOT MAKES THIS WORK Most people misread the architecture. It is not one sandbox per agent. It is ONE persistent cloud computer per account, and every Bot gets its own screen on it. Shared filesystem at /workspace, shared browser sessions, shared credentials. That is the whole unlock. One Bot picks up exactly where another left off. No re-auth, no copy-paste between agents, no state lost at the handoff. A floor is only possible because the desks share a building. The head-of-desk role is not something I invented either. "Manages your other Bots and pulls you in for decisions" ships as a first-class Bot template. Routing and escalation are built in. Skills carry the how. Routines carry the when on a schedule, or off a Slack or GitHub event. Subagents fan out as child sessions with their own context and hand a summary back. Fifty routines per Bot. THE DESKS Every desk holds its own book, hit rate and drawdown, and sizes its own risk: Kelly, with the guard rails written in f* = W − (1−W)/R clamped to [0.01, 0.25]. Under 12 samples it does not pretend to know it defaults to 0.05. Volatility is RiskMetrics EWMA σ²_t = λσ²_{t-1} + (1−λ)r²_t, λ = 0.94 Hit rates carry Wilson 95% intervals, z = 1.96. A desk is only flagged for edge decay when the UPPER bound falls below 0.5, never on raw small-sample noise. Three-for-three is not sixty-for-ninety. Capital routes between desks by softmax on measured Sharpe. THE FLOOR Three chiefs meet in the war room every 3.5 minutes and argue. One reports, another presses him, he concedes or proposes. 14,208 sentence shapes before live figures fill the slots and every slot is filled from that chief's own desks. The crypto chief cannot quote meme numbers. A desk holding $25 gets up, walks to the vault and banks it. The transfer is atomic on arrival, so an interrupted walk cannot destroy cash. Every desk wears its last trade above its head. Green with a tick, red with a cross. You see who the chief is about to praise and who he is about to hit before he gets there. BTC, ETH and SOL come off Kraken server-side. The tape is real. THE BUILD 16 modules. 7,572 lines. Zero npm dependencies. No React. No bundler. No game engine. Vanilla JavaScript on Canvas 2D and a Go binary with the entire world embedded in it. Ships as one 2.3 MB HTML file. 60fps on every floor, zero dropped frames. WHAT I FOUND BY MEASURING INSTEAD OF LOOKING The roster read one number for a desk and the chief's card read another, so a desk could show +$16 in the list and $0 when the chief walked over. Every desk was crediting itself twice. Money could vanish if a walk to the vault got interrupted. Three money bugs, none of them visible by watching. All fixed and instrumented. DIRECTOR MODE Open it with?show and the camera runs itself. It cuts to the war room while a chief is mid-sentence, to whichever office just cleared money, and never cuts away in the middle of a line. Point a screen recorder at it and walk away. The math is real, the feed is real, the engineering is real. The flex is the engine, not a P&L screenshot.

AdiiX

51,085 просмотров • 3 дней назад