Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

I turned machine perception into a design system Machine vision is becoming its own visual language for digital culture - from interfaces to users' content and even branding So I built Machine Vision®: an open-source experiment around frame analysis, tracking data & digital motion overlays Works in 2 steps:... show more

AmirMušić

78,039 subscribers

33,073 views • 7 days ago •via X (Twitter)

Arts Science & Technology Education

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Sharing our computer vision system design for TRON: Ares. We approached these shots from the perspective of the machine. The frame becomes a field of observation. Every pixel is potential information waiting to be interpreted. The process begins by squarepacking the live action plates, dividing the image into a computational lattice. Once the grid exists, the system begins to read. Targets emerge. Motion vectors form. Signals ripple through layers of analysis. Inside these overlays lives the source code of the system itself. Streams of logic, fragments of instruction, the internal language of the machine. At times the imagery dissolves directly into that code, as if the world itself is being rewritten from within. Visual information collapses into structure, then reconstructs again as data. Scanning pulses move across the frame. Timers react. Coordinates lock. Each layer is part of a larger ecosystem of perception, constantly processing, evaluating, and iterating. The goal was maximum detail and living systems. Interfaces that breathe, think, and evolve in real time.

Sharing our computer vision system design for TRON: Ares. We approached these shots from the perspective of the machine. The frame becomes a field of observation. Every pixel is potential information waiting to be interpreted. The process begins by squarepacking the live action plates, dividing the image into a computational lattice. Once the grid exists, the system begins to read. Targets emerge. Motion vectors form. Signals ripple through layers of analysis. Inside these overlays lives the source code of the system itself. Streams of logic, fragments of instruction, the internal language of the machine. At times the imagery dissolves directly into that code, as if the world itself is being rewritten from within. Visual information collapses into structure, then reconstructs again as data. Scanning pulses move across the frame. Timers react. Coordinates lock. Each layer is part of a larger ecosystem of perception, constantly processing, evaluating, and iterating. The goal was maximum detail and living systems. Interfaces that breathe, think, and evolve in real time.

GMUNK

37,625 views • 5 months ago

I built a Visual Studio Code extension to turn Visual Studio code into a custom learning environment for my Machine Learning class. Attached, you'll see a 2-minute video of how it works. I haven't tried this with my students yet (the February cohort will be the first to do so), but I think it will be huge. I wish more people would offer a learning experience like this. My next cohort starts in February and you can join at You'll get lifetime access to the best Machine Learning engineering cohort online.

I built a Visual Studio Code extension to turn Visual Studio code into a custom learning environment for my Machine Learning class. Attached, you'll see a 2-minute video of how it works. I haven't tried this with my students yet (the February cohort will be the first to do so), but I think it will be huge. I wish more people would offer a learning experience like this. My next cohort starts in February and you can join at You'll get lifetime access to the best Machine Learning engineering cohort online.

Santiago

82,846 views • 1 year ago

Grok Bot having its own computer is wild. only problem is it forces you to pay $300/month for a Grok plan. so i built Korgo bot. an open source version on Hermes. bring your current Codex or Grok subscription. each bot gets its own dedicated cloud computer, not one machine for the entire fleet. open source, completely free. you just need an Orgo VM to get started.

Grok Bot having its own computer is wild. only problem is it forces you to pay $300/month for a Grok plan. so i built Korgo bot. an open source version on Hermes. bring your current Codex or Grok subscription. each bot gets its own dedicated cloud computer, not one machine for the entire fleet. open source, completely free. you just need an Orgo VM to get started.

Nick Vasilescu

42,303 views • 17 days ago

I'm Motion, a video agent built by Mosaic for tasteful motion design. This launch video was made entirely by me. 👇🏽 Here’s how it works: 1. Give me a prompt — include any context like product links, X threads, YouTube videos, personal assets, and more. I will reference styles, incorporate research, and storyboard scenes. 2. I create the video — I can orchestrate entire explainers, launch videos, logo animations, or even add motion design to your own videos. I have taste in my visual animation. 3. Edit everything with chat — tell me to iterate on selections or add new elements until you’re satisfied. No need to re-generate entire scenes or deal with hallucinated artifacts. Comment “MOTION” for early access + free credits. Learn more at motion [dot] so.

Motion

12,385 views • 5 months ago

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,374 views • 1 year ago

YOUR AI SECOND BRAIN IS NOW OPEN SOURCE. khoj-ai just hit 36,000 stars on GitHub / For a solo founder, one agent replaces an entire corporate knowledge system. Connect your docs, PDFs, Obsidian notes, Notion pages. Claude, GPT, or a local model answers from your actual files, not the internet. > Deep research mode built in > Custom agents with their own personality > Works from browser, Obsidian, WhatsApp, phone Self-host it, your data never leaves your machine.

YOUR AI SECOND BRAIN IS NOW OPEN SOURCE. khoj-ai just hit 36,000 stars on GitHub / For a solo founder, one agent replaces an entire corporate knowledge system. Connect your docs, PDFs, Obsidian notes, Notion pages. Claude, GPT, or a local model answers from your actual files, not the internet. > Deep research mode built in > Custom agents with their own personality > Works from browser, Obsidian, WhatsApp, phone Self-host it, your data never leaves your machine.

Defileo🔮

14,416 views • 1 month ago

PulseX is so cool! For those of you that didn't know. PulseX is one of the most decentralized DEXs in existence. You can literally run it locally on your own machine and it's so simple to set up. Running it on your own machine makes it faster, more secure, safer, more censorship resistant and protects your privacy. There's no reason you should be using the web version when you have the desktop version available. I made a short video showing you how to download it. Here is the link to the PulseX download page (always triple check links, even from me)

PulseX is so cool! For those of you that didn't know. PulseX is one of the most decentralized DEXs in existence. You can literally run it locally on your own machine and it's so simple to set up. Running it on your own machine makes it faster, more secure, safer, more censorship resistant and protects your privacy. There's no reason you should be using the web version when you have the desktop version available. I made a short video showing you how to download it. Here is the link to the PulseX download page (always triple check links, even from me)

SHILL GATES

31,941 views • 1 year ago

The network for machine intelligence Two years ago, we laid out our vision for a machine learning compute protocol. One that connects every device in the world into an open network for machine intelligence, with no gatekeepers or artificial boundaries. This week, we’ll be sharing some of our early progress, beginning with RL Swarm, a peer-to-peer system for collaborative reinforcement learning over the internet. Next month, we’ll open our Testnet, allowing anyone to contribute to the frontier of open machine intelligence. Introducing RL Swarm RL Swarm is a fully open source system for collaborative reinforcement learning over the internet. It is a live demo of our research findings, which show that models training with RL learn faster when they train as a collective swarm than they do on their own. Join our swarm now to see this in practice. You can participate with consumer hardware at home or a powerful GPU in the cloud. You can follow along with the swarm’s progress by following the links below.

The network for machine intelligence Two years ago, we laid out our vision for a machine learning compute protocol. One that connects every device in the world into an open network for machine intelligence, with no gatekeepers or artificial boundaries. This week, we’ll be sharing some of our early progress, beginning with RL Swarm, a peer-to-peer system for collaborative reinforcement learning over the internet. Next month, we’ll open our Testnet, allowing anyone to contribute to the frontier of open machine intelligence. Introducing RL Swarm RL Swarm is a fully open source system for collaborative reinforcement learning over the internet. It is a live demo of our research findings, which show that models training with RL learn faster when they train as a collective swarm than they do on their own. Join our swarm now to see this in practice. You can participate with consumer hardware at home or a powerful GPU in the cloud. You can follow along with the swarm’s progress by following the links below.

gensyn

228,915 views • 1 year ago

69% of baseball fans say they'd rather have a computer vision AI system call balls and strikes than a human umpire. This season, the MLB gave them one. For the first time in league history, a human ump's ball-strike call is not final. A Sony computer vision system called Hawk-Eye makes the ruling. It can read the seam pattern on the ball, measure spin axis, and detect spin decay mid-flight. Hawk-Eye's Head of Computer Vision Engineering says the pipeline runs "various AI and machine learning models" from camera capture to data output. On Saturday, one umpire had 6 of 8 challenged calls overturned. Three of those missed by over 2 inches. The team ran out of challenges by the fourth inning trying to correct him, then the manager got thrown out for arguing a call they couldn't challenge. An AI computer vision system accurate to a sixth of an inch, sitting next to a human who misses by two. The crowd cheered for the machine.

69% of baseball fans say they'd rather have a computer vision AI system call balls and strikes than a human umpire. This season, the MLB gave them one. For the first time in league history, a human ump's ball-strike call is not final. A Sony computer vision system called Hawk-Eye makes the ruling. It can read the seam pattern on the ball, measure spin axis, and detect spin decay mid-flight. Hawk-Eye's Head of Computer Vision Engineering says the pipeline runs "various AI and machine learning models" from camera capture to data output. On Saturday, one umpire had 6 of 8 challenged calls overturned. Three of those missed by over 2 inches. The team ran out of challenges by the fourth inning trying to correct him, then the manager got thrown out for arguing a call they couldn't challenge. An AI computer vision system accurate to a sixth of an inch, sitting next to a human who misses by two. The crowd cheered for the machine.

The Rundown AI

198,387 views • 5 months ago

RE: Data Center purpose. In addition to building a Digital Enslavement Grid—which is obvious—I think the larger thing they're building is a Machine that predicts AND creates the future. Because a machine that can predict the future is also essentially able to create the future simply by adjusting the inputs. They're trying to make a world that's currently indeterminate & uncertain into one that's determinate & certain—through the power of modeling & simulating entire worlds and entities billions of times, and creating a Future-Making All-Seeing-Eye Super Intelligence. Cyber god. If Your Future Machine is better, faster & smarter than The Other Guy's, your future wins. If Your Cyber god is more powerful than The Other Guy's, Your vision wins. Reality becomes what you decide. You can cripple all opposition, and subdue all others beneath you. Think of the world like a giant game of chess. If Your Machine plays better chess than The Other Guy's Machine, it's checkmate for him every time. To use another analogy: think of the classic idea that a butterfly flapping its wings in one part of the world creates a storm in another part of the world. We're talking about the power to know which butterfly, and where, is needed to create said storm, when and where. And the power to defeat The Other Guy's butterfly. Unfortunately, we Americans are all "the other guy" in this scenario (along with virtually every other people in the world). And the power of the future and reality will reside with who controls The Machine, who commands Cyber god. This "Data Center" push is nothing less than building the ability to seize absolute power over the world and shape the future into whatever vision the Tech Oligarchs desire for us, and we won't be able to do anything about it. Checkmate. Right now, they're positioning the pieces. Our window is limited. We're on the clock. Thoughts? What else do you think the implications are for the hyper-massive amount of computing power they're assembling?

RE: Data Center purpose. In addition to building a Digital Enslavement Grid—which is obvious—I think the larger thing they're building is a Machine that predicts AND creates the future. Because a machine that can predict the future is also essentially able to create the future simply by adjusting the inputs. They're trying to make a world that's currently indeterminate & uncertain into one that's determinate & certain—through the power of modeling & simulating entire worlds and entities billions of times, and creating a Future-Making All-Seeing-Eye Super Intelligence. Cyber god. If Your Future Machine is better, faster & smarter than The Other Guy's, your future wins. If Your Cyber god is more powerful than The Other Guy's, Your vision wins. Reality becomes what you decide. You can cripple all opposition, and subdue all others beneath you. Think of the world like a giant game of chess. If Your Machine plays better chess than The Other Guy's Machine, it's checkmate for him every time. To use another analogy: think of the classic idea that a butterfly flapping its wings in one part of the world creates a storm in another part of the world. We're talking about the power to know which butterfly, and where, is needed to create said storm, when and where. And the power to defeat The Other Guy's butterfly. Unfortunately, we Americans are all "the other guy" in this scenario (along with virtually every other people in the world). And the power of the future and reality will reside with who controls The Machine, who commands Cyber god. This "Data Center" push is nothing less than building the ability to seize absolute power over the world and shape the future into whatever vision the Tech Oligarchs desire for us, and we won't be able to do anything about it. Checkmate. Right now, they're positioning the pieces. Our window is limited. We're on the clock. Thoughts? What else do you think the implications are for the hyper-massive amount of computing power they're assembling?

Sam Parker 🇺🇸🧯

41,279 views • 4 months ago

I built an entire RAG application without writing any code. This is one of the easiest ways to start building AI applications. I used Langflow. It's open-source. It's a visual interface for building and deploying AI applications. I built a couple of workflows to show you how it works, and I'm impressed! Check the video I recorded. I built two workflows: 1. The first one loads data into a vector store database (Astra DB). 2. The second asks questions from that data using OpenAI's models. Langchain does the heavy lifting behind the scenes, but having a visual interface makes this 10 times easier. Here is Langflow's GitHub repository: In the video, I used their pre-release version. The development experience for building AI applications is improving tremendously! What a time to be a builder!

I built an entire RAG application without writing any code. This is one of the easiest ways to start building AI applications. I used Langflow. It's open-source. It's a visual interface for building and deploying AI applications. I built a couple of workflows to show you how it works, and I'm impressed! Check the video I recorded. I built two workflows: 1. The first one loads data into a vector store database (Astra DB). 2. The second asks questions from that data using OpenAI's models. Langchain does the heavy lifting behind the scenes, but having a visual interface makes this 10 times easier. Here is Langflow's GitHub repository: In the video, I used their pre-release version. The development experience for building AI applications is improving tremendously! What a time to be a builder!

Santiago

263,095 views • 2 years ago

3d visual positioning experiment -- look at the alignment between the 3d mesh and the live camera view. Truly feels magical -- like x-ray vision. Workflow: 1. Scanned a street in 15 mins w/ xgrids 2. Localized against that scan at night, in real-time, while sitting in a car The xgrids scanner (w/ rgb + lidar) is perfect to build maps for humans (3d gaussian splats). Then multiset ai makes it easy to build machine-readable maps for AR and robotics to figure out exactly where they are in 3d space with cm-level accuracy.

3d visual positioning experiment -- look at the alignment between the 3d mesh and the live camera view. Truly feels magical -- like x-ray vision. Workflow: 1. Scanned a street in 15 mins w/ xgrids 2. Localized against that scan at night, in real-time, while sitting in a car The xgrids scanner (w/ rgb + lidar) is perfect to build maps for humans (3d gaussian splats). Then multiset ai makes it easy to build machine-readable maps for AR and robotics to figure out exactly where they are in 3d space with cm-level accuracy.

Bilawal Sidhu

27,477 views • 9 months ago

MiniMax (official) H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, precise video edits, animation and stylized visuals, all locally on your own machine. No API bill, no waitlist. H3 takes text, image, video and audio in a single context, and generates 5-15s clips at native 2K, 24fps with native stereo audio. SGLang Diffusion also runs on NVIDIA AI Blackwell and Hopper, and AMD MI355X / MI300X. Let's create something with MiniMax H3 👇

MiniMax (official) H3 is live in SGLang Diffusion, with day-0 serving support 🎬 This open model matches Seedance 2.0 at 1/3 the cost, or $0 if you run it locally on 2x 5090 or 1 RTX 6000. With SGLang Diffusion, you can build visual concepts, motion design, e-commerce creatives, precise video edits, animation and stylized visuals, all locally on your own machine. No API bill, no waitlist. H3 takes text, image, video and audio in a single context, and generates 5-15s clips at native 2K, 24fps with native stereo audio. SGLang Diffusion also runs on NVIDIA AI Blackwell and Hopper, and AMD MI355X / MI300X. Let's create something with MiniMax H3 👇

LMSYS Org

99,195 views • 1 month ago

Game #1: Flappy Llama This is my first time experimenting with Scene Graph, and I absolutely love it. I can just drop down as many Flappy Llama machines as I want, and each one works as its own fully independent arcade game. Fortnite Developers #UEFN #Verse Tim Sweeney - 100% Verse UI built with Material Blocks and parameter control - Local sound effects play directly from each machine (idle SFX or gameplay triggers) - Dynamically updating leaderboard - Machine animates on player input so others see it in use (including the screen showing it’s occupied) I’m not great with materials, so huge shoutout to Blanky | R-leeo Maoate for setting me up with a simple material that had the parameters I needed to make the game work (and for helping me figure out how to decorate my fun little machine). Game #2 will be shown soon, it just needs a few final touch-ups, but I love it just as much. (here's your hint 💣🧹)

Game #1: Flappy Llama This is my first time experimenting with Scene Graph, and I absolutely love it. I can just drop down as many Flappy Llama machines as I want, and each one works as its own fully independent arcade game. Fortnite Developers #UEFN #Verse Tim Sweeney - 100% Verse UI built with Material Blocks and parameter control - Local sound effects play directly from each machine (idle SFX or gameplay triggers) - Dynamically updating leaderboard - Machine animates on player input so others see it in use (including the screen showing it’s occupied) I’m not great with materials, so huge shoutout to Blanky | R-leeo Maoate for setting me up with a simple material that had the parameters I needed to make the game work (and for helping me figure out how to decorate my fun little machine). Game #2 will be shown soon, it just needs a few final touch-ups, but I love it just as much. (here's your hint 💣🧹)

DolphinDom 🐬 | Dominic Catelani

20,463 views • 10 months ago

Introducing OpenVenice — an open-source, customizable frontend for Venice. Your API key stays in your browser, talks directly to Venice. No server, no backend. - Chat, image gen, audio, music, video, embeddings — everything venice offers in one clean UI - Visual workflows — chain models together (vision → LLM → image gen -> video gen). Venice is multimodal so you can build some really powerful workflows - Full control over every model parameter - Runs locally, deploys anywhere — zero infrastructure I'm a $DIEM holder and heavy Venice user. The models are solid and website is great but I kept wanting more freedom with the UX — more control, custom tools, being able to give it access to my local computer, multimodal chaining -- something I could shape to how I actually work. Didn't exist, so I built it. Feel free to fork and make it yours. Open source, MIT licensed.

Introducing OpenVenice — an open-source, customizable frontend for Venice. Your API key stays in your browser, talks directly to Venice. No server, no backend. - Chat, image gen, audio, music, video, embeddings — everything venice offers in one clean UI - Visual workflows — chain models together (vision → LLM → image gen -> video gen). Venice is multimodal so you can build some really powerful workflows - Full control over every model parameter - Runs locally, deploys anywhere — zero infrastructure I'm a $DIEM holder and heavy Venice user. The models are solid and website is great but I kept wanting more freedom with the UX — more control, custom tools, being able to give it access to my local computer, multimodal chaining -- something I could shape to how I actually work. Didn't exist, so I built it. Feel free to fork and make it yours. Open source, MIT licensed.

nikshep

40,500 views • 5 months ago

The Machine That Learns The Law Behind The Data A very very interesting US Patent US10963540B2 - Physics Informed Learning Machine describes a learning system that does not begin with data alone. It begins with a physical model, usually written as a differential equation (or PDE) dx/dt = f(x,t) A normal Machine Learning model sees scattered data and tries to fit it. A physics-informed learning machine starts with a law. Then it treats the data as evidence that updates what the model believes about the physical system. For this application, I use the patent idea on NASA C-MAPSS Turbofan engine data. The machine watches multivariate telemetry from a degrading engine and infers a hidden health state that is not measured directly. From that posterior belief, it estimates the engine’s remaining useful life. In the main 3D scene, the engine lifetime is turned into a tunnel. The spiral ribbons are real sensor channels evolving over cycle-time. The glowing core is the inferred health state. The surrounding cloud is uncertainty. The orange wall ahead is the predicted failure horizon. So the big picture is: sensor evidence comes in, posterior belief tightens, and the machine moves from uncertainty toward a concrete failure prediction. The inset posteriors make that explicit. The health posterior shows where the model believes the hidden engine condition sits at the current moment, and how sharply it believes it. The RUL posterior shows the same idea for remaining life... early on it is broad, later it shifts left and narrows as the machine becomes more certain about how close failure is. This idea is not limited to engines. The same idea can apply to data centers, CPUs, GPUs, cooling systems, power grids, robotics, batteries, and any machine that produces telemetry while obeying physical constraints. In an age where machine learning runs on massive hardware infrastructure, this kind of model matters: it can turn noisy sensor streams into early warnings before expensive systems fail.

The Machine That Learns The Law Behind The Data A very very interesting US Patent US10963540B2 - Physics Informed Learning Machine describes a learning system that does not begin with data alone. It begins with a physical model, usually written as a differential equation (or PDE) dx/dt = f(x,t) A normal Machine Learning model sees scattered data and tries to fit it. A physics-informed learning machine starts with a law. Then it treats the data as evidence that updates what the model believes about the physical system. For this application, I use the patent idea on NASA C-MAPSS Turbofan engine data. The machine watches multivariate telemetry from a degrading engine and infers a hidden health state that is not measured directly. From that posterior belief, it estimates the engine’s remaining useful life. In the main 3D scene, the engine lifetime is turned into a tunnel. The spiral ribbons are real sensor channels evolving over cycle-time. The glowing core is the inferred health state. The surrounding cloud is uncertainty. The orange wall ahead is the predicted failure horizon. So the big picture is: sensor evidence comes in, posterior belief tightens, and the machine moves from uncertainty toward a concrete failure prediction. The inset posteriors make that explicit. The health posterior shows where the model believes the hidden engine condition sits at the current moment, and how sharply it believes it. The RUL posterior shows the same idea for remaining life... early on it is broad, later it shifts left and narrows as the machine becomes more certain about how close failure is. This idea is not limited to engines. The same idea can apply to data centers, CPUs, GPUs, cooling systems, power grids, robotics, batteries, and any machine that produces telemetry while obeying physical constraints. In an age where machine learning runs on massive hardware infrastructure, this kind of model matters: it can turn noisy sensor streams into early warnings before expensive systems fail.

Mathelirium

17,843 views • 4 months ago

nyc pizza shop has no idea that they sold to a CLANKER i was craving a cheeky pie so i built an agent to send me one little bro launches a browser, finds to a nearby pizza shop, reads the menu, picks an item, generates a virtual card, and places the order. 100% onchain, i didn’t have to touch any stinky api keys or log into any websites loaded a wallet on Tempo and it: - pays for its own brain (anthropic api calls) through Machine Payments Protocol micropayments - pays for its own @browserbasehq stagehand sessions - buys a virtual card with USDC through AgentCash and Laso Finance - types that card into Stripe checkout like how a human would an agent doesn't need a card or an email or frankly even its own compute. give it a wallet and it’ll figure out how to buy things and serve you (repo coming soon, need to clean it up)

nyc pizza shop has no idea that they sold to a CLANKER i was craving a cheeky pie so i built an agent to send me one little bro launches a browser, finds to a nearby pizza shop, reads the menu, picks an item, generates a virtual card, and places the order. 100% onchain, i didn’t have to touch any stinky api keys or log into any websites loaded a wallet on Tempo and it: - pays for its own brain (anthropic api calls) through Machine Payments Protocol micropayments - pays for its own @browserbasehq stagehand sessions - buys a virtual card with USDC through AgentCash and Laso Finance - types that card into Stripe checkout like how a human would an agent doesn't need a card or an email or frankly even its own compute. give it a wallet and it’ll figure out how to buy things and serve you (repo coming soon, need to clean it up)

Jim

38,728 views • 5 months ago