Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

You probably heard that I don't like Javascript. So I vibe-coded a Curve Finance UI in Python running in your browser, and reinvented how routing can be done. Swaps are calculated as electric circuits using laws of Physics + EVM running in the browser. Unprofitable to sandwich

newmichwill's profile picture

Michael Egorov

43,121 subscribers

52,973 görüntüleme • 17 gün önce •via X (Twitter)

Bilim & TeknolojiEğitim
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

I vibe coded Steam, but for the browser. Imagine the retro and indie titles you love, running in WebAssembly and WebGPU at near-native performance. With full controller support! Drop a comment/like below if you dig it. Actively looking for feedback
1:19

I vibe coded Steam, but for the browser. Imagine the retro and indie titles you love, running in WebAssembly and WebGPU at near-native performance. With full controller support! Drop a comment/like below if you dig it. Actively looking for feedback

Alex St. Louis

25,174 görüntüleme • 3 ay önce

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source
0:59

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Sumanth

62,485 görüntüleme • 1 yıl önce

Can GPT-4 code an entire game for you? Yes, yes it can. Here's how I recreated a Snake game that runs in your browser using Chat GPT-4 and Replit ⠕, with ZERO knowledge of Javascript all in less than 20 mins 🧵
0:29

Can GPT-4 code an entire game for you? Yes, yes it can. Here's how I recreated a Snake game that runs in your browser using Chat GPT-4 and Replit ⠕, with ZERO knowledge of Javascript all in less than 20 mins 🧵

Ammaar Reshi

3,930,195 görüntüleme • 3 yıl önce

Autopilot for your browser is here. You type the task. Composite does the rest. Imagine this: - You describe a browser task - Composite clicks, types, navigates, and finishes it like magic - Works on any website. In any browser. No migration needed. It’s not just AI. It’s your operations team, copilot, and Jarvis all inside your current browser. Composite uses your browser just like you would, but faster, smarter, and endlessly patient. How I use it: As a content creator, I auto-sync my content calendar across Notion, Trello, and Slack, while I’m busy writing the next viral post. No new browser. No learning curve. No vendor lock-in. Just pure agentic power in your browser. Put your browser on steroids. Get hours of work done in minutes here:
0:55

Autopilot for your browser is here. You type the task. Composite does the rest. Imagine this: - You describe a browser task - Composite clicks, types, navigates, and finishes it like magic - Works on any website. In any browser. No migration needed. It’s not just AI. It’s your operations team, copilot, and Jarvis all inside your current browser. Composite uses your browser just like you would, but faster, smarter, and endlessly patient. How I use it: As a content creator, I auto-sync my content calendar across Notion, Trello, and Slack, while I’m busy writing the next viral post. No new browser. No learning curve. No vendor lock-in. Just pure agentic power in your browser. Put your browser on steroids. Get hours of work done in minutes here:

Shushant Lakhyani

29,302 görüntüleme • 1 yıl önce

I built /schedule, but with access to your authenticated accounts in a secure browser. Using the Browserbase /cookie-sync skill, I saved my local browser cookies, and injected them into the remote browser in our schedulable Functions. The opportunities are endless, build Crons with CC to do ANYTHING a human can.
0:21

I built /schedule, but with access to your authenticated accounts in a secure browser. Using the Browserbase /cookie-sync skill, I saved my local browser cookies, and injected them into the remote browser in our schedulable Functions. The opportunities are endless, build Crons with CC to do ANYTHING a human can.

Kyle Jeong

49,399 görüntüleme • 5 ay önce

Can't believe in less than 24 hours I created my own game with Claude and Three.js. Running in a browser at 120 FPS. All I had to do was give Claude the repo for Threejs and describe an MMO-like game for it to build from scratch. All the assets and mechanics you see are all from a prompt. As you can see, it is far from done but the progress is insane. Everyone should be using Three.js now without a doubt!
0:59

Can't believe in less than 24 hours I created my own game with Claude and Three.js. Running in a browser at 120 FPS. All I had to do was give Claude the repo for Threejs and describe an MMO-like game for it to build from scratch. All the assets and mechanics you see are all from a prompt. As you can see, it is far from done but the progress is insane. Everyone should be using Three.js now without a doubt!

NeilXbt

23,504 görüntüleme • 25 gün önce

To me, microduck looks like a droid. So I made it sound like one Microduck is open source and hackable. That means you can program it to do whatever you want! I trained a 1.3m parameter LLM to output droid like responses. It is running in the browser The model has learned to respond with an emotion, alongside English like Happy, Excited, Sad Then the emotion is fed into a Rust based synthesizer to generate R2D2 like sounds that are aligned with the emotion --- completely procedurally, no wav files, no copyright violation You can chat with it. You can also customize it, give it a name and set your own colors! All set in a spaceship hangar backdrop with other friendly ducks---simulated with realistic physics and microduck's actual walking and skating policies! All in the browser, with WASM!!! I can put literally the SAME code in the browser, and then compile it into an ARM binary and put it in the actual robot in real life 🤯 If you like this and want to see more of it, please like and share so that my boss puts me in the priority list for the first microduck batch 😎 All open source of course! Microquack! 🦆 Hugging Face Space:
0:58

To me, microduck looks like a droid. So I made it sound like one Microduck is open source and hackable. That means you can program it to do whatever you want! I trained a 1.3m parameter LLM to output droid like responses. It is running in the browser The model has learned to respond with an emotion, alongside English like Happy, Excited, Sad Then the emotion is fed into a Rust based synthesizer to generate R2D2 like sounds that are aligned with the emotion --- completely procedurally, no wav files, no copyright violation You can chat with it. You can also customize it, give it a name and set your own colors! All set in a spaceship hangar backdrop with other friendly ducks---simulated with realistic physics and microduck's actual walking and skating policies! All in the browser, with WASM!!! I can put literally the SAME code in the browser, and then compile it into an ARM binary and put it in the actual robot in real life 🤯 If you like this and want to see more of it, please like and share so that my boss puts me in the priority list for the first microduck batch 😎 All open source of course! Microquack! 🦆 Hugging Face Space:

Onur Solmaz

33,500 görüntüleme • 10 gün önce

I have things running in the browser with threeJS that proprietary game engines wont build for another 3 years. If you are a particularly prideful and talented engineer who doesn't like begging for work you can just self fund a billion dollar startup now.
1:22

I have things running in the browser with threeJS that proprietary game engines wont build for another 3 years. If you are a particularly prideful and talented engineer who doesn't like begging for work you can just self fund a billion dollar startup now.

scaredofboobs🪲

24,372 görüntüleme • 6 ay önce

I went camping with my son on the weekend and all he could talk about was roasting "the perfect marshmallow". So I vibe coded him a marshmallow roasting simulator in a couple of hours. I provided the models and a lookdev render from Blender, Claude did the rest. Try it in your browser:
0:40

I went camping with my son on the weekend and all he could talk about was roasting "the perfect marshmallow". So I vibe coded him a marshmallow roasting simulator in a couple of hours. I provided the models and a lookdev render from Blender, Claude did the rest. Try it in your browser:

Andrew Price

20,949 görüntüleme • 4 ay önce

I guess I rebuilt the world as voxels now. Started with terrain and water systems, then added buildings, bridges, and roads. Search any location and watch it reconstruct as millions of voxels in real time. Running in the browser with WebGPU. Made with Omma AI, using Three.js.
0:39

I guess I rebuilt the world as voxels now. Started with terrain and water systems, then added buildings, bridges, and roads. Search any location and watch it reconstruct as millions of voxels in real time. Running in the browser with WebGPU. Made with Omma AI, using Three.js.

Gábor Pribék

62,529 görüntüleme • 1 ay önce

This is how I’m currently running my startup with Devin + OpenClaw🦞 The browser testing in Devin is mind-blowing. I was trying to duct tape and jerry-rig all this stuff together with Playwright + uploading videos to PRs and all sorts of stuff and Devin just does it all e2e. Wild. I didn't show how I'm using Linear, which I am using for issue tracking. I have a "land" skill that I tell Devin to use whenever all the browser testing is done and all the CI goes green and it just merges the PR
3:50

This is how I’m currently running my startup with Devin + OpenClaw🦞 The browser testing in Devin is mind-blowing. I was trying to duct tape and jerry-rig all this stuff together with Playwright + uploading videos to PRs and all sorts of stuff and Devin just does it all e2e. Wild. I didn't show how I'm using Linear, which I am using for issue tracking. I have a "land" skill that I tell Devin to use whenever all the browser testing is done and all the CI goes green and it just merges the PR

Ryan Carson

28,248 görüntüleme • 5 ay önce

takes vibe-coding a step further. Parallel AI teams, running directly in your browser. You can watch multiple agents think, build, and compete in real time, then pick the best result. Built by the MetaGPT and OpenManus teams. 3 wild use cases 🧵↓
0:21

takes vibe-coding a step further. Parallel AI teams, running directly in your browser. You can watch multiple agents think, build, and compete in real time, then pick the best result. Built by the MetaGPT and OpenManus teams. 3 wild use cases 🧵↓

Charly Wargnier

63,774 görüntüleme • 7 ay önce

Introducing 🌸 Kanna – a web ui for Claude Code + Codex running right in your browser (and my first open source project!) It's sort of like if Claude Code & Codex had a baby with a much better ui/ux 💅 Here's what makes Kanna special: 🔀 One-click switch between Claude Code / Codex 🌐 Runs in your browser on localhost - no app switching 🧩 Embedded split terminals, persisted between chats with a beautiful horizontal scrolling UX 📁 Full project file browser built in, embedded editor coming soon too. Coming soon: 🔒 End-to-end encryption + remote access via reverse proxy 🌿 Git integration, diffs, PRs 🧱 Plugins I wanted to replace switching between cursor, the github app, browser & (most recently) the codex app. The browser is hardest to recreate yet also the most flexible so it makes sense to build in the browser itself. Install in 5 seconds: bun install -g kanna-code then just type: kanna Kanna is purely a ui/ux layer. It uses your existing CLIs, is 100% compliant & no data ever leaves your machine. If running claude or codex in your terminal works, kanna works too. Kanna natively supports every tool call, model, reasoning effort, fast mode, plan mode, compaction, user questions, web searching, skills, agents, mcps, everything. There are a few libraries that do this but none that I found as comprehensive. All feedback welcome!
1:38

Introducing 🌸 Kanna – a web ui for Claude Code + Codex running right in your browser (and my first open source project!) It's sort of like if Claude Code & Codex had a baby with a much better ui/ux 💅 Here's what makes Kanna special: 🔀 One-click switch between Claude Code / Codex 🌐 Runs in your browser on localhost - no app switching 🧩 Embedded split terminals, persisted between chats with a beautiful horizontal scrolling UX 📁 Full project file browser built in, embedded editor coming soon too. Coming soon: 🔒 End-to-end encryption + remote access via reverse proxy 🌿 Git integration, diffs, PRs 🧱 Plugins I wanted to replace switching between cursor, the github app, browser & (most recently) the codex app. The browser is hardest to recreate yet also the most flexible so it makes sense to build in the browser itself. Install in 5 seconds: bun install -g kanna-code then just type: kanna Kanna is purely a ui/ux layer. It uses your existing CLIs, is 100% compliant & no data ever leaves your machine. If running claude or codex in your terminal works, kanna works too. Kanna natively supports every tool call, model, reasoning effort, fast mode, plan mode, compaction, user questions, web searching, skills, agents, mcps, everything. There are a few libraries that do this but none that I found as comprehensive. All feedback welcome!

Jake Mor

43,379 görüntüleme • 5 ay önce

This is another demo showing how Blender's geometry nodes can be used to calculate electric fields in 3D space! These are two spheres with surface charges, watch how the electric field lines change as I move them around and adjust their electric charges! releasing soon! #b3d #geometrynodes #PortfolioDay #electric #Engineering #Science #Physics #electronics #circuits #kicad #artist
0:36

This is another demo showing how Blender's geometry nodes can be used to calculate electric fields in 3D space! These are two spheres with surface charges, watch how the electric field lines change as I move them around and adjust their electric charges! releasing soon! #b3d #geometrynodes #PortfolioDay #electric #Engineering #Science #Physics #electronics #circuits #kicad #artist

Sam M

154,623 görüntüleme • 3 yıl önce

i gave a voice to my jarvis system everything running in real-time using open source models - roboflow RF-DETR for object detection - gemma 4 for scene summarization - kokoro text-to-speech - live in the browser using transformers js prompt: "you are a dystopian science fiction narrator in a cyberpunk world. describe the scene in one sentence"
0:24

i gave a voice to my jarvis system everything running in real-time using open source models - roboflow RF-DETR for object detection - gemma 4 for scene summarization - kokoro text-to-speech - live in the browser using transformers js prompt: "you are a dystopian science fiction narrator in a cyberpunk world. describe the scene in one sentence"

AA

28,753 görüntüleme • 5 ay önce

You don't need a PC to run Conso prompts to earn. You can do it directly from your phone. It may not be as fast as using a PC, and it can lag sometimes, but it works perfectly. Here is how: Step 1: Download the Misis browser. Click the link, download the extension, insert your invitation code, and sign in using your email. Step 2: Open another tab in the same Misis browser and sign in to ChatGPT. Open another tab for Gemini and do the same for your remaining AIs. That’s it. You’re ready to run your prompts to earn on CONSO from your phone.
3:16

You don't need a PC to run Conso prompts to earn. You can do it directly from your phone. It may not be as fast as using a PC, and it can lag sometimes, but it works perfectly. Here is how: Step 1: Download the Misis browser. Click the link, download the extension, insert your invitation code, and sign in using your email. Step 2: Open another tab in the same Misis browser and sign in to ChatGPT. Open another tab for Gemini and do the same for your remaining AIs. That’s it. You’re ready to run your prompts to earn on CONSO from your phone.

SCALE.

50,014 görüntüleme • 7 gün önce

We added a device tool bar to the Codex in-app browser, so it's easier to build and test responsive apps! Now, you can have Codex test your app in different dimensions, so it can fix bugs & improve UI for every device. Just click the 3 dots on the right of the URL bar to use it! As part of this change, we also: - improved the speed of browser use (~30% in my vibe testing) - tightened the animation of the cursor - added a way to hide the composer in full screen mode - fixed a few bugs for browser use in Windows Oliver Tepman and John Nastos cooked on this one! Try it out and let us know what you think!
0:25

We added a device tool bar to the Codex in-app browser, so it's easier to build and test responsive apps! Now, you can have Codex test your app in different dimensions, so it can fix bugs & improve UI for every device. Just click the 3 dots on the right of the URL bar to use it! As part of this change, we also: - improved the speed of browser use (~30% in my vibe testing) - tightened the animation of the cursor - added a way to hide the composer in full screen mode - fixed a few bugs for browser use in Windows Oliver Tepman and John Nastos cooked on this one! Try it out and let us know what you think!

James Sun

148,458 görüntüleme • 4 ay önce

i vibe coded a full trading card game in 7 days that absolutely vibemoggs modern magic: the gathering 537 unique cards and abilities build your own decks play in the browser for free to be an in-game tcg in my main game Final Abyss made with spawn try it out on their site - i’d love to know what you think!
4:22

i vibe coded a full trading card game in 7 days that absolutely vibemoggs modern magic: the gathering 537 unique cards and abilities build your own decks play in the browser for free to be an in-game tcg in my main game Final Abyss made with spawn try it out on their site - i’d love to know what you think!

Cal

34,074 görüntüleme • 5 ay önce

This is a very nice description of the problem. I think the first part of the solution is to not give into the hyper productivity hype: running a gazillion things in parallel. There's likely only a handful of humans that have the mental make-up to survive the permanent context switches. You can train your brain to become better at it, but there's a limit to that, and I found that it will lead to much worse outcomes in terms of output quality of both you and your clanker. I'm no neuroscientist, but I would assume there's a hard limit on how many things your brain can juggle at a time, probably made worse by the complexity that is code. I generally don't do more than 2-3 things in parallel. I use virtual desktops as "bundle of things that belong to a task", so terminals + editor + browser. Works fine, doesn't need any special OS support, expose on the virtual desktop let's me quickly switch to the task specific app I need. I also have a little pi extension that shows me what GH issue/PR the clanker session is about, with a link I can click to open the issue/PR in the browser. Plus 1 virtual desktop for entertainment, so the brain can get some rest. (better alternative: get up and walk a bit every 45 minutes) Video: - First desktop: pi session for a PR, extension shows me what PR I work on, can click to open in browser, aux terminal for random BS, editor, browser. Yes, I could split instead of having two terminal windows. I'm old. - Second desktop: clawdbot pi session, aux terminal for testing, editor, browser - Third desktop: entertainment booth
0:23

This is a very nice description of the problem. I think the first part of the solution is to not give into the hyper productivity hype: running a gazillion things in parallel. There's likely only a handful of humans that have the mental make-up to survive the permanent context switches. You can train your brain to become better at it, but there's a limit to that, and I found that it will lead to much worse outcomes in terms of output quality of both you and your clanker. I'm no neuroscientist, but I would assume there's a hard limit on how many things your brain can juggle at a time, probably made worse by the complexity that is code. I generally don't do more than 2-3 things in parallel. I use virtual desktops as "bundle of things that belong to a task", so terminals + editor + browser. Works fine, doesn't need any special OS support, expose on the virtual desktop let's me quickly switch to the task specific app I need. I also have a little pi extension that shows me what GH issue/PR the clanker session is about, with a link I can click to open the issue/PR in the browser. Plus 1 virtual desktop for entertainment, so the brain can get some rest. (better alternative: get up and walk a bit every 45 minutes) Video: - First desktop: pi session for a PR, extension shows me what PR I work on, can click to open in browser, aux terminal for random BS, editor, browser. Yes, I could split instead of having two terminal windows. I'm old. - Second desktop: clawdbot pi session, aux terminal for testing, editor, browser - Third desktop: entertainment booth

Mario Zechner

40,284 görüntüleme • 7 ay önce

Is this the future of AI browser agents? 👀 WebGPU-accelerated reasoning LLMs are now supported in Transformers.js! 🤯 Here's MiniThinky-v2 (1B) running 100% locally in the browser at ~60 tps (no API calls)! I can't wait to see what you build with it! Demo + source code in 🧵👇
0:22

Is this the future of AI browser agents? 👀 WebGPU-accelerated reasoning LLMs are now supported in Transformers.js! 🤯 Here's MiniThinky-v2 (1B) running 100% locally in the browser at ~60 tps (no API calls)! I can't wait to see what you build with it! Demo + source code in 🧵👇

Xenova

81,477 görüntüleme • 1 yıl önce