正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

The first GPT-4V-powered frontend engineer agent. Just upload a picture of a design, and the agent autonomously codes it up, looks at a render for mistakes, improves the code accordingly, repeat. Utterly insane.

Matt Shumer

372,947 subscribers

1,370,425 次观看 • 2 年前 •via X (Twitter)

科学技术教育艺术

Anya Rossi• Live Now

Private livecam show

10 条评论

Matt Shumer 的头像

Matt Shumer2 年前

Built this after seeing the results of the text -> design agent I built yesterday. We’ll have a whole new frontend stack soon!

Robert Scoble 的头像

Robert Scoble2 年前

@artificialguybr This is so intriguing. So much is about to change. Thanks for showing it to us!

Matt Shumer 的头像

Matt Shumer2 年前

@artificialguybr Absolutely… insane times we’re living in.

Furkan Gözükara 的头像

Furkan Gözükara2 年前

Very primitive cherry pick demo

Matt Shumer 的头像

Matt Shumer2 年前

Yes :) In all seriousness, what I’ve found to hold true in AI is that once something is good enough to demo, with iteration and tweaking (and model progress) you can expect it to become something really amazing. This feels like something that will be huge in a year or two.

Kristoph 的头像

Kristoph2 年前

I love how chatGPT codes just like any other developer. It makes it looks sort of like the design but not exactly like the design 🤣

Matt Shumer 的头像

Matt Shumer2 年前

😂 this hits hard

Andrew Durot 的头像

Andrew Durot2 年前

Wait I'm confused? This is yours or a open source? How you access gpt4 image? Through a headless browser?

Matt Shumer 的头像

Matt Shumer2 年前

Just built it for fun! Not open source, sorry

Jason Staats⚡ 的头像

Jason Staats⚡2 年前

Can we call it Enhance

相关视频

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

kirill avery

16,454 次观看 • 3 个月前

This is just insane… My GPT-4 coding assistant can now: - build and design a frontend - create a backend with working db - correctly hook them up - upload code to GitHub - deploy it to Vercel I can now build *complete* apps with nothing more than my voice. The future is here!

This is just insane… My GPT-4 coding assistant can now: - build and design a frontend - create a backend with working db - correctly hook them up - upload code to GitHub - deploy it to Vercel I can now build complete apps with nothing more than my voice. The future is here!

Mckay Wrigley

5,715,787 次观看 • 3 年前

Every frontend developer just stopped opening DevTools. Your AI coding agent can now reverse-engineer the entire design system of any website directly from the terminal. Just type: /design And it instantly extracts: • Brand colors • Fonts & typography • Spacing system • Buttons & UI components • Layout patterns • Design tokens Then saves everything into a structured DESIGN.md file your AI agent can understand and reuse. Powered by Hyperbrowser + Claude Code MCP. The crazy part? You can now study, replicate, and rebuild world-class UI systems in minutes instead of wasting hours manually inspecting websites. This changes how vibe coding works forever. Repo👇

divyansh tiwari

78,201 次观看 • 2 个月前

GPT Engineer github: Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.

GPT Engineer github: Specify what you want it to build, the AI asks for clarification, and then builds it. GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.

AK

349,149 次观看 • 3 年前

I made two AI Agents play tic-tac-toe with each other while the third agent watched as a judge. Agent X powered by Gemini Flash 2.0 Agent O powered by DeepSeek v3 Judge Agent powered by GPT-4o 100% Opensource code with step-by-step tutorial.

I made two AI Agents play tic-tac-toe with each other while the third agent watched as a judge. Agent X powered by Gemini Flash 2.0 Agent O powered by DeepSeek v3 Judge Agent powered by GPT-4o 100% Opensource code with step-by-step tutorial.

Shubham Saboo

118,528 次观看 • 1 年前

Introducing Claude Engineer 2.0, with agents! 🚀 Biggest update yet with the addition of a code editor and code execution agents, and dynamic editing. When editing files (especially large ones), Engineer will direct a coding agent, and the agent will provide changes in batches. Batches are smartly selected based on file complexity. The code execution agent will run the code and check for issues. It can even start processes (like live servers) and end them. It's insanely powerful! 🔥

Introducing Claude Engineer 2.0, with agents! 🚀 Biggest update yet with the addition of a code editor and code execution agents, and dynamic editing. When editing files (especially large ones), Engineer will direct a coding agent, and the agent will provide changes in batches. Batches are smartly selected based on file complexity. The code execution agent will run the code and check for issues. It can even start processes (like live servers) and end them. It's insanely powerful! 🔥

Pietro Schirano

393,470 次观看 • 2 年前

One shot a general purpose agent iOS app with GPT 5.5… the general agent is powered by GLM 5.2 and it has fulll vibe coding capabilities. Pretty cool.

One shot a general purpose agent iOS app with GPT 5.5… the general agent is powered by GLM 5.2 and it has fulll vibe coding capabilities. Pretty cool.

Riley Brown

68,305 次观看 • 1 个月前

Excited to announce the newest Webflow app we've been building 🔥 Miyagi: An AI app for Webflow made up of 3 powerful agents: • Design Agent: Automate tasks in the Webflow Designer • Code Agent: Vibe code in Webflow • CMS Agent: Bulk edit and create content in the CMS Take a look at some more info & examples below 👇🧵

Excited to announce the newest Webflow app we've been building 🔥 Miyagi: An AI app for Webflow made up of 3 powerful agents: • Design Agent: Automate tasks in the Webflow Designer • Code Agent: Vibe code in Webflow • CMS Agent: Bulk edit and create content in the CMS Take a look at some more info & examples below 👇🧵

Bradford Huber

12,501 次观看 • 1 年前

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

James Rochabrun

61,199 次观看 • 1 个月前

Introducing: AI Researcher 🧪 A Gemini 3-powered multi-agent AI system that autonomously runs ML experiments Just give it a research question, and it will: - Design experiments - Spin up specialist agents with their own GPUs to run them - Write a paper And it's open-source!

Introducing: AI Researcher 🧪 A Gemini 3-powered multi-agent AI system that autonomously runs ML experiments Just give it a research question, and it will: - Design experiments - Spin up specialist agents with their own GPUs to run them - Write a paper And it's open-source!

Matt Shumer

198,461 次观看 • 8 个月前

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

118,124 次观看 • 1 个月前

says it documented the first AI agent buying compute with #Bitcoin. An OpenClaw🦞 agent reportedly spun up a server and purchased AI credits autonomously. Software paying for real services. PayPerQ Alby 🐝 Roland Graham breaks it down👇

says it documented the first AI agent buying compute with #Bitcoin. An OpenClaw🦞 agent reportedly spun up a server and purchased AI credits autonomously. Software paying for real services. PayPerQ Alby 🐝 Roland Graham breaks it down👇

Bitcoin.com News

10,336 次观看 • 5 个月前

GPT-Engineer is insane. Simply specify what you want to build with a prompt, and the AI agent builds the entire codebase. It's completely free and open-source, and it's already at nearly 17,000 stars on GitHub 🤯

GPT-Engineer is insane. Simply specify what you want to build with a prompt, and the AI agent builds the entire codebase. It's completely free and open-source, and it's already at nearly 17,000 stars on GitHub 🤯

Rowan Cheung

1,373,609 次观看 • 3 年前

INSANE: Grok 3 + Replit Agent is a Superpower!! Using the pair, I built an AI agent that reviews my Pull Requests Here's the flow: • Grok 3 generates PR-reviewing agent code using Composio + LlamaIndex • Replit Agent automatically crafts the front-end interface • Get a ready-to-run workflow where you paste the url to your PR, and the agent generates a code review instantly with suggestions. Built with Grok Replit ⠕ Agent Powered by LlamaIndex 🦙 Groq Inc repl link:

INSANE: Grok 3 + Replit Agent is a Superpower!! Using the pair, I built an AI agent that reviews my Pull Requests Here's the flow: • Grok 3 generates PR-reviewing agent code using Composio + LlamaIndex • Replit Agent automatically crafts the front-end interface • Get a ready-to-run workflow where you paste the url to your PR, and the agent generates a code review instantly with suggestions. Built with Grok Replit ⠕ Agent Powered by LlamaIndex 🦙 Groq Inc repl link:

Karan Vaidya

1,684,869 次观看 • 1 年前

Image upload is live in the Bubble AI Agent — hand it a design reference or a mockup and it builds out that interface in the editor. It's also gotten better at understanding your app, so expression generation and responses are more reliable across the board. A picture is now worth a thousand prompts. 😉

Image upload is live in the Bubble AI Agent — hand it a design reference or a mockup and it builds out that interface in the editor. It's also gotten better at understanding your app, so expression generation and responses are more reliable across the board. A picture is now worth a thousand prompts. 😉

Bubble

11,192,349 次观看 • 3 个月前

GPT-5.6-Sol one-shotted this voxel-based Manhattan. Just look at the precision... it's insane. It ran for almost a week, completely autonomously, to get the job done.

GPT-5.6-Sol one-shotted this voxel-based Manhattan. Just look at the precision... it's insane. It ran for almost a week, completely autonomously, to get the job done.

Matt Shumer

1,052,239 次观看 • 18 天前

Here is a demo of the most comprehensive research agent for your code docs, powered by Nozomio Labs. It turns your indexed repos and docs into a dynamic tree that the agent can access on the fly, using SOTA tools to reduce code hallucinations. Now using the latest Anthropic model, Claude Opus 4.5.

Here is a demo of the most comprehensive research agent for your code docs, powered by Nozomio Labs. It turns your indexed repos and docs into a dynamic tree that the agent can access on the fly, using SOTA tools to reduce code hallucinations. Now using the latest Anthropic model, Claude Opus 4.5.

Arlan

28,405 次观看 • 8 个月前

I built an AI startup insight tool Agent using Firecrawl FIRE-1 and GPT-4o. FIRE-1 AI Agent navigates websites, clicks buttons, and extracts company data autonomously without writing a single line of custom code. 100% Opensource Code with step-by-step tutorial.

I built an AI startup insight tool Agent using Firecrawl FIRE-1 and GPT-4o. FIRE-1 AI Agent navigates websites, clicks buttons, and extracts company data autonomously without writing a single line of custom code. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

23,184 次观看 • 1 年前

Today we're launching Latent-Y: the world's first autonomous agent for drug design, lab-validated end to end. Give it a research goal. Latent-Y reasons, designs, iterates, and delivers lab-ready antibodies, autonomously or collaboratively, with the biological reasoning of a PhD protein design expert. Technical report: Blog post: Apply for access:

Today we're launching Latent-Y: the world's first autonomous agent for drug design, lab-validated end to end. Give it a research goal. Latent-Y reasons, designs, iterates, and delivers lab-ready antibodies, autonomously or collaboratively, with the biological reasoning of a PhD protein design expert. Technical report: Blog post: Apply for access:

Simon Kohl

121,080 次观看 • 4 个月前