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。

Excited to share our progress 🔥 Introducing Codegen: the IDE for Refactors. Codegen allows you to programmatically analyze and manipulate your codebase. ✅ Safely transform code at scale 🔍 Visualize complex code structures ⚡ Purpose-built for AI-assisted development 1/

Jay Hack

73,398 subscribers

69,989 次观看 • 1 年前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

11 条评论

Jay Hack 的头像

Jay Hack1 年前

In short: Codegen enables you to rapidly build and deploy safe codemods across massive codebases. Detailed technical overview and use cases below: 2/

Jay Hack 的头像

Jay Hack1 年前

Huge codebases have many valuable tasks where: 💡 The desired modifications are known (easy to verify) 👍 Changes can be made through static analysis 💥 They impact large portions of your codebase The hard part: getting your code into the right shape. 3/

Jay Hack 的头像

Jay Hack1 年前

Our insight is that static analysis is key 🔑. These tasks can often be done with deterministic programs operating on the codebase “graph.” With @codegen, we make these changes seamless and scalable. 4/

Jay Hack 的头像

Jay Hack1 年前

Codegen is built on a custom language server optimized for these tasks. We parse your codebase “graph” and wrap it in a python SDK. We pair it with an execution environment, integrated AI assistant, and seamless PR logistics, making large-scale changes safe and accessible. 5/

Jay Hack 的头像

Jay Hack1 年前

Today, we’ve merged hundreds of thousands of LOC at companies like @tryramp and others. Killer apps include: ⚡ Adding type coverage 🗑️ Removing feature flags 📚 Documentation generation 🔄 Eliminating circular imports 🔍 Identifying critical code paths ... and more. 6/

Jay Hack 的头像

Jay Hack1 年前

In the coming weeks, we will demonstrate our capabilities with demos and real customer use cases. Our intention is to show the world that “metaprogramming,” or getting programs to manipulate programs, is the future of building software. 7/

Jay Hack 的头像

Jay Hack1 年前

Today, we operate on multi-million line JS/TS and Python codebases. Kotlin/Java available Q4 ♨️. Interested in using Codegen on your enterprise codebase? Ping us for a live demo (on your codebase) at 8/

Jay Hack 的头像

Jay Hack1 年前

Lastly, we are assembling the most cracked team on the planet to build the future of programming. Are you exceptional at the following? 💻 Compilers and programming languages 🪩 Web app craftsmanship ⚙️ Systems engineering Drop us a line at [email protected]! 🚀

vikranth 的头像

vikranth1 年前

@codegen so bullish

Ramsey 的头像

Ramsey1 年前

@codegen That’s what I call an amazing demo

Jay Hack 的头像

Jay Hack1 年前

@codegen Thanks, Rancel 🙏 The in-depth (4 mins) video in the second tweet shows more on our approach.

相关视频

Vibe coding won't scale your team. Codegen 3 will. 🚀 Introducing Codegen 3.0: The Operating System for Code Agents Now with Claude Code integration, AI code review, agent analytics and more. Try your first runs free today.

Vibe coding won't scale your team. Codegen 3 will. 🚀 Introducing Codegen 3.0: The Operating System for Code Agents Now with Claude Code integration, AI code review, agent analytics and more. Try your first runs free today.

Codegen

1,168,797 次观看 • 10 个月前

Excited to share what I've been building 🚀 Introducing Codegen ⚡ Agent-driven software development for enterprise codebases ⚡ We've raised $16mm from Thrive Capital and others to bring this to the world - 👇 More below

Excited to share what I've been building 🚀 Introducing Codegen ⚡ Agent-driven software development for enterprise codebases ⚡ We've raised $16mm from Thrive Capital and others to bring this to the world - 👇 More below

Jay Hack

368,825 次观看 • 2 年前

AI coding tools are everywhere. Yet they all fall short when scaling to 100s of developers and complex codebases. We’re solving this problem Augment Code. Introducing Augment Code, the first developer AI purpose-built for teams.🧵

AI coding tools are everywhere. Yet they all fall short when scaling to 100s of developers and complex codebases. We’re solving this problem Augment Code. Introducing Augment Code, the first developer AI purpose-built for teams.🧵

Scott Dietzen

91,368 次观看 • 1 年前

Introducing Kombai, the first AI agent built for frontend development. Kombai vastly outperforms SOTA models + generic agents in real-world benchmarks. Watch it add a complex new feature to an OSS codebase with 500K+ lines of code. More use cases and links in comments

Introducing Kombai, the first AI agent built for frontend development. Kombai vastly outperforms SOTA models + generic agents in real-world benchmarks. Watch it add a complex new feature to an OSS codebase with 500K+ lines of code. More use cases and links in comments

Dipanjan Dey

2,074,645 次观看 • 11 个月前

Introducing CodeRabbit Plugin for Claude Code! The CodeRabbit plugin for Claude Code creates an autonomous AI development workflow, helping you write and fix code without manual intervention. Type /coderabbit:review (or just say “review my code”) to get AI-powered fixes directly in your dev flow! Try it today, it’s free!

Introducing CodeRabbit Plugin for Claude Code! The CodeRabbit plugin for Claude Code creates an autonomous AI development workflow, helping you write and fix code without manual intervention. Type /coderabbit:review (or just say “review my code”) to get AI-powered fixes directly in your dev flow! Try it today, it’s free!

CodeRabbit

27,190 次观看 • 5 个月前

🤖 Meet Agent Mode in JetBrains AI Assistant for VS Code! 🔗 Go beyond simple code completion and delegate complex coding tasks to our AI agent that can: ✨ Analyze your entire codebase ✨ Make multi-file edits simultaneously ✨ Handle intricate refactoring operations ✨ Solve complex programming challenges under your supervision Think of it as having an intelligent coding partner that understands your project context and can execute sophisticated tasks while you maintain full control.

🤖 Meet Agent Mode in JetBrains AI Assistant for VS Code! 🔗 Go beyond simple code completion and delegate complex coding tasks to our AI agent that can: ✨ Analyze your entire codebase ✨ Make multi-file edits simultaneously ✨ Handle intricate refactoring operations ✨ Solve complex programming challenges under your supervision Think of it as having an intelligent coding partner that understands your project context and can execute sophisticated tasks while you maintain full control.

JetBrains

15,129 次观看 • 1 年前

#ChatGPT for your codebase! 🤯 You now can upload your entire codebase/Git repos to #OpenChat & ask #GPT4 to implement anything! With the full context of your code, #OpenChat can answer your questions accurately and effortlessly! Powered by ! 🔥 Link to code ↓

#ChatGPT for your codebase! 🤯 You now can upload your entire codebase/Git repos to #OpenChat & ask #GPT4 to implement anything! With the full context of your code, #OpenChat can answer your questions accurately and effortlessly! Powered by ! 🔥 Link to code ↓

Charly Wargnier

175,644 次观看 • 3 年前

Introducing Asterisk MCP - An MCP server that fixes security vulnerabilities while you vibe code. Supports Cursor, Windsurf, Cline, Claude, and any IDE that supports the model context protocol. It can perform codebase-wide scans, analyze snippets in your conversation history, and verify changes/fixes for security issues. mcp dot asterisk dot so

Introducing Asterisk MCP - An MCP server that fixes security vulnerabilities while you vibe code. Supports Cursor, Windsurf, Cline, Claude, and any IDE that supports the model context protocol. It can perform codebase-wide scans, analyze snippets in your conversation history, and verify changes/fixes for security issues. mcp dot asterisk dot so

mufeed vh

14,312 次观看 • 1 年前

Hey Flutter folks! 👋🏼 I'm excited to share Vide — a Flutter AI-IDE I've been building. It uses your code and allows an AI to: - Runs and tests widgets it creates - Implement pixel-perfect widgets based on a single screenshot - Writes code exactly the way you want Vide hooks into Flutter, giving you a dev focused environment — deeply integrated with AI. More info & web demo soon! Join the waitlist below 👇🏼

Hey Flutter folks! 👋🏼 I'm excited to share Vide — a Flutter AI-IDE I've been building. It uses your code and allows an AI to: - Runs and tests widgets it creates - Implement pixel-perfect widgets based on a single screenshot - Writes code exactly the way you want Vide hooks into Flutter, giving you a dev focused environment — deeply integrated with AI. More info & web demo soon! Join the waitlist below 👇🏼

Norbert Kozsir

15,116 次观看 • 1 年前

🚀 Introducing Kineto! Our AI-powered platform lets you create web apps and websites without writing a single line of code. Perfect for small, single-purpose applications like plant trackers, fitness apps, blogs, planners, quiz apps... the list goes on! Built for creative minds who want to focus on ideas, not code. Join the waitlist:

🚀 Introducing Kineto! Our AI-powered platform lets you create web apps and websites without writing a single line of code. Perfect for small, single-purpose applications like plant trackers, fitness apps, blogs, planners, quiz apps... the list goes on! Built for creative minds who want to focus on ideas, not code. Join the waitlist:

JetBrains

83,189 次观看 • 11 个月前

Micro Agent now auto-generates unit tests for you! 🧪⚡ Say goodbye to manual test writing—our AI instantly creates Jest, Mocha, Pytest, and Rust test cases to boost your development speed. Code smarter, test faster.

Micro Agent now auto-generates unit tests for you! 🧪⚡ Say goodbye to manual test writing—our AI instantly creates Jest, Mocha, Pytest, and Rust test cases to boost your development speed. Code smarter, test faster.

MicroGPT

689,037 次观看 • 1 年前

Introducing Deep Graph Codebase to MCP with One Click... Now Available for Gemini CLI too! 🤩 Transform any public GitHub repository into an AI-ready Code Graph by simply changing the URL from to This instantly prepares the repository for seamless integration with AI assistants. It's that easy! You can now use repositories like ollama as a code graph within any project using Gemini CLI... just add the MCP Server JSON configuration to your .gemini/settings.json file

Introducing Deep Graph Codebase to MCP with One Click... Now Available for Gemini CLI too! 🤩 Transform any public GitHub repository into an AI-ready Code Graph by simply changing the URL from to This instantly prepares the repository for seamless integration with AI assistants. It's that easy! You can now use repositories like ollama as a code graph within any project using Gemini CLI... just add the MCP Server JSON configuration to your .gemini/settings.json file

Daniel San

53,516 次观看 • 1 年前

Codex now runs in your IDE Available for VS Code, Cursor, and other forks, the new extension makes it easy to share context—files, snippets, and diffs—so you can work faster with Codex. It’s been a top feature request, and we’re excited to hear what you think!

Codex now runs in your IDE Available for VS Code, Cursor, and other forks, the new extension makes it easy to share context—files, snippets, and diffs—so you can work faster with Codex. It’s been a top feature request, and we’re excited to hear what you think!

OpenAI Developers

182,463 次观看 • 10 个月前

curl This is our Meta-Prompt. It allows LLMs to understand our Reader, Embeddings, Reranker, and Classifier APIs for improved codegen. Using the meta-prompt is straightforward. Just copy the prompt into your preferred LLM interface like ChatGPT, Claude, or whatever works for you, add your instructions, and you're set. In this example, we copied the entire prompt into Anthropic Claude and asked it to grab every sentence from Hacker News front page and visualize them using UMAP with matplotlib. This task is nontrivial as it combines multiple APIs from our Search Foundation, like Reader and Embedding where Claude may not have knowledge of. So if you asked Claude directly, it probably wouldn't give an optimal answer. But with the meta-prompt, Claude now has good knowledge about our APIs and can generate much better code! We can copy paste the code directly to Google Colab and with minimum modification, the code just works!

curl This is our Meta-Prompt. It allows LLMs to understand our Reader, Embeddings, Reranker, and Classifier APIs for improved codegen. Using the meta-prompt is straightforward. Just copy the prompt into your preferred LLM interface like ChatGPT, Claude, or whatever works for you, add your instructions, and you're set. In this example, we copied the entire prompt into Anthropic Claude and asked it to grab every sentence from Hacker News front page and visualize them using UMAP with matplotlib. This task is nontrivial as it combines multiple APIs from our Search Foundation, like Reader and Embedding where Claude may not have knowledge of. So if you asked Claude directly, it probably wouldn't give an optimal answer. But with the meta-prompt, Claude now has good knowledge about our APIs and can generate much better code! We can copy paste the code directly to Google Colab and with minimum modification, the code just works!

Jina AI

209,078 次观看 • 1 年前

Dear Gnuses, We're excited to share a behind-the-code look at how AI processing functions in the ecosystem, and a first glimpse of the upcoming GNUS wallet, demonstrated by creator, Kenneth Hurley in our latest video! After rigorous unit testing and codebase audits by SolidProof and Shieldify, we're almost ready to transition from our robust testnet to a beta network. We're rapidly progressing to a smooth and secure rollout. Stay tuned for more exciting updates! 🔥🤝

Dear Gnuses, We're excited to share a behind-the-code look at how AI processing functions in the ecosystem, and a first glimpse of the upcoming GNUS wallet, demonstrated by creator, Kenneth Hurley in our latest video! After rigorous unit testing and codebase audits by SolidProof and Shieldify, we're almost ready to transition from our robust testnet to a beta network. We're rapidly progressing to a smooth and secure rollout. Stay tuned for more exciting updates! 🔥🤝

GNUS.ai

58,260 次观看 • 2 年前

Before software engineers even begin writing code, they have to set the stage of the entire development process. This process requires engineers to make complex tradeoffs between requirements, system design, and implementations details. Current IDEs that rely on AI features, like chat and inline coding, can help engineers get the job done quickly on small development tasks. Still, engineers spend much more time on larger projects—even after the initial code is generated—by conducting rigorous testing and creating documentation. This is where today’s AI IDEs can do more to accelerate the development lifecycle—and this is why we built Kiro. Kiro is an AI IDE that helps you go from prototype to production with spec-driven development and agent hooks. From simple to complex tasks, Kiro works alongside you to turn prompts into detailed specs, then into working code, docs, and test so what you build is exactly what you want and ready to share with your team. After a developer builds the code with Kiro, Kiro’s agent hooks help engineers solve challenging problems and automate tasks like generating documentation and unit tests. Kiro brings structure and mature engineering practices to AI coding, so you can go from concept to application while being in the driver’s seat every step of the way. Kiro is free during preview, and supports Mac, Windows, and Linux, and most popular programming languages. We're excited for you to try it out and let us know what you think ➡️

Before software engineers even begin writing code, they have to set the stage of the entire development process. This process requires engineers to make complex tradeoffs between requirements, system design, and implementations details. Current IDEs that rely on AI features, like chat and inline coding, can help engineers get the job done quickly on small development tasks. Still, engineers spend much more time on larger projects—even after the initial code is generated—by conducting rigorous testing and creating documentation. This is where today’s AI IDEs can do more to accelerate the development lifecycle—and this is why we built Kiro. Kiro is an AI IDE that helps you go from prototype to production with spec-driven development and agent hooks. From simple to complex tasks, Kiro works alongside you to turn prompts into detailed specs, then into working code, docs, and test so what you build is exactly what you want and ready to share with your team. After a developer builds the code with Kiro, Kiro’s agent hooks help engineers solve challenging problems and automate tasks like generating documentation and unit tests. Kiro brings structure and mature engineering practices to AI coding, so you can go from concept to application while being in the driver’s seat every step of the way. Kiro is free during preview, and supports Mac, Windows, and Linux, and most popular programming languages. We're excited for you to try it out and let us know what you think ➡️

Swami Sivasubramanian

154,343 次观看 • 1 年前

Claude Code now runs in GitLab CI/CD pipelines 🚀 Tag @ Claude in issues or merge requests to run automated coding tasks in secure containers, with all changes following your branch protection and review workflows. ✅ Available via the Anthropic API, Amazon Bedrock, and Google Vertex AI ✅ Customize Claude Code for your codebase by adding a file to your repository root ✅ Delegate code reviews, bug fixes, and implementation plans to complete routine tasks asynchronously Get started with Claude Code in GitLab:

Claude Code now runs in GitLab CI/CD pipelines 🚀 Tag @ Claude in issues or merge requests to run automated coding tasks in secure containers, with all changes following your branch protection and review workflows. ✅ Available via the Anthropic API, Amazon Bedrock, and Google Vertex AI ✅ Customize Claude Code for your codebase by adding a file to your repository root ✅ Delegate code reviews, bug fixes, and implementation plans to complete routine tasks asynchronously Get started with Claude Code in GitLab:

🦊 GitLab

33,641 次观看 • 11 个月前

AI coding agents aren't just about autocorrect, but how do you get the best coding experience with an AI-powered coding agent? In our new short course, Build Apps with Windsurf’s AI Coding Agents, you'll learn how to build, debug, and deploy applications with agentic AI-powered integrated development environment (IDE). AI coding agents, like Codeium's @windsurf, don’t just suggest code, they analyze your codebase, track changes, retrieve relevant information, and apply updates across multiple files. They can help debug, refactor, and even modernize legacy frameworks. But to use them effectively, you need the right approach. This new course shows you how to: 🛠️ Use AI agents to build and refine applications, like a Wikipedia analysis app. 🐞 Debug and refactor JavaScript with AI-assisted automation. 🔍 Understand how search and retrieval power AI coding agents. 🤖 Guide an AI agent effectively—prompting, iterating, and correcting when needed. Taught by Anshul Ramachandran (Anshul Ramachandran), this course gives you hands-on coding experience, insights into how these AI systems work under the hood, and best practices to improve your development workflow. 🔗 Enroll for free:

AI coding agents aren't just about autocorrect, but how do you get the best coding experience with an AI-powered coding agent? In our new short course, Build Apps with Windsurf’s AI Coding Agents, you'll learn how to build, debug, and deploy applications with agentic AI-powered integrated development environment (IDE). AI coding agents, like Codeium's @windsurf, don’t just suggest code, they analyze your codebase, track changes, retrieve relevant information, and apply updates across multiple files. They can help debug, refactor, and even modernize legacy frameworks. But to use them effectively, you need the right approach. This new course shows you how to: 🛠️ Use AI agents to build and refine applications, like a Wikipedia analysis app. 🐞 Debug and refactor JavaScript with AI-assisted automation. 🔍 Understand how search and retrieval power AI coding agents. 🤖 Guide an AI agent effectively—prompting, iterating, and correcting when needed. Taught by Anshul Ramachandran (Anshul Ramachandran), this course gives you hands-on coding experience, insights into how these AI systems work under the hood, and best practices to improve your development workflow. 🔗 Enroll for free:

DeepLearning.AI

23,255 次观看 • 1 年前

ANTHROPIC 🔥: Claude desktop app got a built-in web browser for Claude Code. This feature allows Claude to open and debug URLs directly inside the app. Browsers are now secondary, AI first 👀

ANTHROPIC 🔥: Claude desktop app got a built-in web browser for Claude Code. This feature allows Claude to open and debug URLs directly inside the app. Browsers are now secondary, AI first 👀

🚨 AI News | TestingCatalog

90,373 次观看 • 9 天前