Загрузка видео...

Не удалось загрузить видео

На главную

🖇🧑‍💻 𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗖𝗹𝗶𝗽𝗽𝘆 The AI programmer based on a team of autonomous agents ▸ ▸ Can plan the project, implement, run, debug, test (in the browser) ▸ A new programming workflow: it runs by itself, you give feedback to steer it 🧵👇

levchizhov's profile picture

Lev Chizhov

3,507 subscribers

86,922 просмотров • 3 лет назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

OpenAI Agents SDK + MCP = Vibe Coding Agents I now have a CRACKED workflow to develop agents, Cursor can not only write the code but look at the logs at LangWatch, so it can debug the interaction between agents and write the fix itself
2:49

OpenAI Agents SDK + MCP = Vibe Coding Agents I now have a CRACKED workflow to develop agents, Cursor can not only write the code but look at the logs at LangWatch, so it can debug the interaction between agents and write the fix itself

Rogerio Chaves

51,352 просмотров • 1 год назад

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.
0:37

Today, we launched browser use inside Codex to further close the build & verify loop for local development! Now, you can ask Codex to build your front end, and test it like a user would by clicking through the app. Codex sees everything a user sees through vision & checks the network/console logs to help debug & fix any issues that it finds. This change brings us closer to fully autonomous coding agents that delivers high quality and tested changes. Watch Codex test my app in the browser, catch & fix a real bug, and doing that loop again with a brand new feature.

James Sun

226,529 просмотров • 3 месяцев назад

🥳 A new way to tackle terminal errors! 🤖 With a team of AI Agents to search, test, plan, and fix, achieving up to a 34% resolved rate on SWE-bench. 🙌We're excited to introduce this beta feature, which we're continuously optimizing and refining — give it a try and share your feedback with us! #AI #Coding #MarsCode
0:51

🥳 A new way to tackle terminal errors! 🤖 With a team of AI Agents to search, test, plan, and fix, achieving up to a 34% resolved rate on SWE-bench. 🙌We're excited to introduce this beta feature, which we're continuously optimizing and refining — give it a try and share your feedback with us! #AI #Coding #MarsCode

Trae Plugin

461,056 просмотров • 2 лет назад

Robotics needs data. OVER delivers it. Robots aren’t just machines anymore, they’re becoming autonomous agents. The secret? A new generation of Physical AI Models. And the fuel? A global dataset built for scale. Let’s dive in 👇🧵
0:31

Robotics needs data. OVER delivers it. Robots aren’t just machines anymore, they’re becoming autonomous agents. The secret? A new generation of Physical AI Models. And the fuel? A global dataset built for scale. Let’s dive in 👇🧵

Over the Reality 🌐

24,934 просмотров • 10 месяцев назад

Give your AI agents a place to work. "The Delegation" is a 3D workspace where AI agents don't just chat, they collaborate in a living office. You can play with different teams: a Creative Agency, a Music Studio, or a Game Dev Team. 🧵Link to Demo & Code in the thread below👇
0:44

Give your AI agents a place to work. "The Delegation" is a 3D workspace where AI agents don't just chat, they collaborate in a living office. You can play with different teams: a Creative Agency, a Music Studio, or a Game Dev Team. 🧵Link to Demo & Code in the thread below👇

Arturo Paracuellos

21,792 просмотров • 4 месяцев назад

Today we are taking Vy to another dimension 🚀 and we can’t be more excited! You can now run multiple agents in parallel, all on your own device 🧠💻 That means: • You can kickoff a bunch of tasks in parallel • Vy will run them in the background • You can keep using your computer like nothing’s happening — no weird cloud browser, no giving your authentication to a third party, no purchasing a new license, nothing blocking your access or your IP Think of it like a team of AI coworkers 🧑‍💻 You give them jobs, they get to work, and come back when they’re done. You can check in any time, and they’ll update you when they finish. It’s smooth. It’s fast. It feels natural.
0:40

Today we are taking Vy to another dimension 🚀 and we can’t be more excited! You can now run multiple agents in parallel, all on your own device 🧠💻 That means: • You can kickoff a bunch of tasks in parallel • Vy will run them in the background • You can keep using your computer like nothing’s happening — no weird cloud browser, no giving your authentication to a third party, no purchasing a new license, nothing blocking your access or your IP Think of it like a team of AI coworkers 🧑‍💻 You give them jobs, they get to work, and come back when they’re done. You can check in any time, and they’ll update you when they finish. It’s smooth. It’s fast. It feels natural.

Vercept

10,668 просмотров • 11 месяцев назад

AI agents have a memory problem. You create the perfect workflow, debugging process, or project setup... A few days later, you're teaching the same lessons all over again. Most AI workflows disappear the moment the chat ends. That's why EvoMap caught my attention. Instead of letting successful AI workflows vanish, it turns them into reusable assets that agents can learn from again and again. Check it out: 🧵
1:05

AI agents have a memory problem. You create the perfect workflow, debugging process, or project setup... A few days later, you're teaching the same lessons all over again. Most AI workflows disappear the moment the chat ends. That's why EvoMap caught my attention. Instead of letting successful AI workflows vanish, it turns them into reusable assets that agents can learn from again and again. Check it out: 🧵

Shruti Codes

34,376 просмотров • 1 месяц назад

We built Claude Code into a browser & whiteboard! It's called Decode Decode It’s the fastest & best way to give UX feedback to Claude Code while coding locally & enables it to review & test changes itself See thread👇to learn how whiteboards makes it an even better browser
0:25

We built Claude Code into a browser & whiteboard! It's called Decode Decode It’s the fastest & best way to give UX feedback to Claude Code while coding locally & enables it to review & test changes itself See thread👇to learn how whiteboards makes it an even better browser

Francois Laberge

162,509 просмотров • 9 месяцев назад

Most AI tools give you more workers. Only one gives you a manager. is the Messenger for AI Agents — and it changes how solopreneurs, creators, and small teams run their entire workflow in one chat.
1:21

Most AI tools give you more workers. Only one gives you a manager. is the Messenger for AI Agents — and it changes how solopreneurs, creators, and small teams run their entire workflow in one chat.

Parul Gautam

67,269 просмотров • 7 месяцев назад

A browser that thinks for itself. I tried out the new Genspark AI Browser—and it changes the way you browse the web. In this example, I'll show you how you can display news directly as an AI podcast with a single click, summarize websites, and much more!
0:53

A browser that thinks for itself. I tried out the new Genspark AI Browser—and it changes the way you browse the web. In this example, I'll show you how you can display news directly as an AI podcast with a single click, summarize websites, and much more!

Chubby♨️

177,768 просмотров • 10 месяцев назад

Since the editor itself is a unit, you can plug it to a graph to debug inside and outside at the same time.
0:24

Since the editor itself is a unit, you can plug it to a graph to debug inside and outside at the same time.

Samuel Timbó

114,563 просмотров • 1 год назад

Your AI agents can now learn entire skill trees from the web. Meet the new HyperSkill Give it a topic. It reads the docs and builds a skill tree your agent can navigate.Browse the graph. Download. Drop into your project. Open source. Powered by Hyperbrowser.
0:24

Your AI agents can now learn entire skill trees from the web. Meet the new HyperSkill Give it a topic. It reads the docs and builds a skill tree your agent can navigate.Browse the graph. Download. Drop into your project. Open source. Powered by Hyperbrowser.

Hyperbrowser

95,806 просмотров • 4 месяцев назад

Cursor now has a built-in web browser. You can say "start my app" and it will run the dev server in a terminal and then navigate the browser to localhost:3000. It can take screenshots of the page for iterating on design, and you can send DOM elements to the agent with prompts!
0:24

Cursor now has a built-in web browser. You can say "start my app" and it will run the dev server in a terminal and then navigate the browser to localhost:3000. It can take screenshots of the page for iterating on design, and you can send DOM elements to the agent with prompts!

Lee Robinson

216,167 просмотров • 8 месяцев назад

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵
1:45

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵

Anicet

35,735 просмотров • 7 месяцев назад

AI agents are a real paradigm shift You can literally make your computer work for you to do any task. All I've used is: - Replit to get it running - Browser Use (free & open source) - Google AI Studio for the API - DeepSeek R1 to implement it (I'm not paying $200 for ChatGPT sorry) Here the AI agent fetches information on its own and reuses it to write new content. But you can use it for literally any industry. Run it once or schedule it at regular intervals... you're in total control And it's nothing like automating on Make or Zapier: AI agents adapt to every situation and can handle far more complex scenarios.
1:02

AI agents are a real paradigm shift You can literally make your computer work for you to do any task. All I've used is: - Replit to get it running - Browser Use (free & open source) - Google AI Studio for the API - DeepSeek R1 to implement it (I'm not paying $200 for ChatGPT sorry) Here the AI agent fetches information on its own and reuses it to write new content. But you can use it for literally any industry. Run it once or schedule it at regular intervals... you're in total control And it's nothing like automating on Make or Zapier: AI agents adapt to every situation and can handle far more complex scenarios.

Paul Couvert

76,636 просмотров • 1 год назад

is now the AI builder for everyone. The new v0 uses agentic AI to plan, research, build, and debug. It works in context, across multiple steps, and adapts as you go. If you have an idea, v0 can build it.
1:00

is now the AI builder for everyone. The new v0 uses agentic AI to plan, research, build, and debug. It works in context, across multiple steps, and adapts as you go. If you have an idea, v0 can build it.

v0

450,987 просмотров • 11 месяцев назад

I built a browser entirely powered by Nano Banana 🍌 It generates each website based only on the URL. You can even navigate to other links. A truly new kind of internet, generated on the fly, and it's super fun.
1:04

I built a browser entirely powered by Nano Banana 🍌 It generates each website based only on the URL. You can even navigate to other links. A truly new kind of internet, generated on the fly, and it's super fun.

Pietro Schirano

309,366 просмотров • 10 месяцев назад

ȘARPELE - A hybrid AI short film based on the novel by Mircea Eliade. It is a work meant to test the potential of AI elements in independent filmmaking, within the context of purposeful, grounded shots. I hope you enjoy the experiment!
2:08

ȘARPELE - A hybrid AI short film based on the novel by Mircea Eliade. It is a work meant to test the potential of AI elements in independent filmmaking, within the context of purposeful, grounded shots. I hope you enjoy the experiment!

Dacist Rapian

36,828 просмотров • 6 месяцев назад

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at
0:35

you don’t need a robot to see physical ai in action, you just need a browser. this week I finally tried something I've wanted to do for a while: design an SO-101 scene in three.js, connect it to a real leader arm, collect teleoperation data, train an ACT model, then port it to run in the browser. the result is the first ever demo of ACT that runs locally on the web. try it yourself now at

Binh Pham

120,373 просмотров • 29 дней назад