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.

My talk from the AI Engineer Code Summit is out! 🚨 "How Claude Code Works" and what we can learn about frontier agent architectures. Coding agents are suddenly really really good, and I'm trying to understand why. In short: better models, simple loop design, and bash tools

Jared Zoneraich

5,542 subscribers

13,936 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

124,713 views • 6 months ago

You know what's better than Claude Code? 4 Claude Code agents working together Here is my multi-agent setup (and how you can do the same)

You know what's better than Claude Code? 4 Claude Code agents working together Here is my multi-agent setup (and how you can do the same)

David Ondrej

37,181 views • 1 year ago

Tutorial: How to make a creative coding animation with Claude 2 and OpenProcessing Claude 2 is one of my favorite coding tools. Here's a demo how you can learn programming and write a simple animation with it in minutes. You can run the code at OpenProcessing. Links in comment

Tutorial: How to make a creative coding animation with Claude 2 and OpenProcessing Claude 2 is one of my favorite coding tools. Here's a demo how you can learn programming and write a simple animation with it in minutes. You can run the code at OpenProcessing. Links in comment

Kris Kashtanova

18,369 views • 2 years ago

Claude Code is now included in the Claude Pro plan which means Pro plan subscribers can use their rate limits for Claude apps and Claude Code! To celebrate, here's a conversation with Claude Code's founding engineer, Boris Cherny, on: - how we use Claude Code at Anthropic - underrated tips for using it effectively - the future of coding tools - and more!

Claude Code is now included in the Claude Pro plan which means Pro plan subscribers can use their rate limits for Claude apps and Claude Code! To celebrate, here's a conversation with Claude Code's founding engineer, Boris Cherny, on: - how we use Claude Code at Anthropic - underrated tips for using it effectively - the future of coding tools - and more!

Alex Albert

123,686 views • 1 year ago

We're launching Niteshift – the full-stack cloud for coding agents Verification is the new bottleneck. Software teams can now define their dev environment and verification tools once. Then run any frontier agent in the cloud: Claude Code, Codex, or OpenCode

We're launching Niteshift – the full-stack cloud for coding agents Verification is the new bottleneck. Software teams can now define their dev environment and verification tools once. Then run any frontier agent in the cloud: Claude Code, Codex, or OpenCode

Sajid Mehmood

87,407 views • 1 month ago

We’ve been building this in secret for a while. We love Claude Code, and we’ve reimplemented “Claude Code” in Genspark. Introducing Genspark AI Developer - “Claude Code” in the browser - “Claude Code” on mobile - Everyone can build, no coding experience required - Supports multiple frontier models: Claude Sonnet 4, Claude Opus 4.1, GPT‑5, Kimi + Groq 1/4

We’ve been building this in secret for a while. We love Claude Code, and we’ve reimplemented “Claude Code” in Genspark. Introducing Genspark AI Developer - “Claude Code” in the browser - “Claude Code” on mobile - Everyone can build, no coding experience required - Supports multiple frontier models: Claude Sonnet 4, Claude Opus 4.1, GPT‑5, Kimi + Groq 1/4

Eric Jing

23,245,863 views • 11 months ago

A masterclass from Jeremy Howard on why AI coding tools can be a trap -- and what 45 years of programming taught him that most vibe coders will never learn. - AI coding tools exploit gambling psychology - The difference between typing code and software engineering - Enterprise coding AND prompt-only vibe coding are "inhumane" i.e. disconnecting humans from understanding-building - AI tools remove the "desirable difficulty" you need to build deep mental models. Out on MLST now!

A masterclass from Jeremy Howard on why AI coding tools can be a trap -- and what 45 years of programming taught him that most vibe coders will never learn. - AI coding tools exploit gambling psychology - The difference between typing code and software engineering - Enterprise coding AND prompt-only vibe coding are "inhumane" i.e. disconnecting humans from understanding-building - AI tools remove the "desirable difficulty" you need to build deep mental models. Out on MLST now!

Machine Learning Street Talk

169,851 views • 4 months ago

Claude Tag is the next evolution of agents. It's a proactive, multiplayer agent with memory and identity, built on top of Claude Code. Learn more about how Claude Tag works and best practices for using it in this deep dive.

Claude Tag is the next evolution of agents. It's a proactive, multiplayer agent with memory and identity, built on top of Claude Code. Learn more about how Claude Tag works and best practices for using it in this deep dive.

ClaudeDevs

443,121 views • 14 days ago

Claude Code is a major (and accidental!) hit for Anthropic that surprised even its creator, Boris Cherny. Claude Code, an Agentic AI coding product that lives in the terminal. Most of the new code at Anthropic is created through it today. And in the last 5 months since it was launched publicly, Claude Code went from $0 to $400M in revenue run rate (as per The Information). 00:00 – Intro 01:15 – Did You Expect Claude Code’s Success? 04:22 – How Claude Code Works and Origins 08:05 – Command Line vs IDE: Why Start Claude Code in the Terminal? 11:31 – The Evolution of Programming: From Punch Cards to Agents 13:20 – Product Follows Model: Simple Interfaces and Fast Evolution 15:17 – Who Is Claude Code For? (Engineers, Designers, PMs & More) 17:46 – What Can Claude Code Actually Do? (Actions & Capabilities) 21:14 – Agentic Actions, Subagents, and Workflows 25:30 – Claude Code’s Awareness, Memory, and Knowledge Sharing 33:28 – Model Context Protocol (MCP) and Customization 35:30 – Safety, Human Oversight, and Enterprise Considerations 38:10 – UX/UI: Making Claude Code Useful and Enjoyable 40:44 – Pricing for Power Users and Subscription Models 43:36 – Real-World Use Cases: Debugging, Testing, and More 46:44 – How Does Claude Code Transform Onboarding? 49:36 – The Future of Coding: Agents, Teams, and Collaboration 54:11 – The AI Coding Wars: Competition & Ecosystem 57:27 – The Future of Coding as a Profession 58:41 – What’s Next for Claude Code

Claude Code is a major (and accidental!) hit for Anthropic that surprised even its creator, Boris Cherny. Claude Code, an Agentic AI coding product that lives in the terminal. Most of the new code at Anthropic is created through it today. And in the last 5 months since it was launched publicly, Claude Code went from $0 to $400M in revenue run rate (as per The Information). 00:00 – Intro 01:15 – Did You Expect Claude Code’s Success? 04:22 – How Claude Code Works and Origins 08:05 – Command Line vs IDE: Why Start Claude Code in the Terminal? 11:31 – The Evolution of Programming: From Punch Cards to Agents 13:20 – Product Follows Model: Simple Interfaces and Fast Evolution 15:17 – Who Is Claude Code For? (Engineers, Designers, PMs & More) 17:46 – What Can Claude Code Actually Do? (Actions & Capabilities) 21:14 – Agentic Actions, Subagents, and Workflows 25:30 – Claude Code’s Awareness, Memory, and Knowledge Sharing 33:28 – Model Context Protocol (MCP) and Customization 35:30 – Safety, Human Oversight, and Enterprise Considerations 38:10 – UX/UI: Making Claude Code Useful and Enjoyable 40:44 – Pricing for Power Users and Subscription Models 43:36 – Real-World Use Cases: Debugging, Testing, and More 46:44 – How Does Claude Code Transform Onboarding? 49:36 – The Future of Coding: Agents, Teams, and Collaboration 54:11 – The AI Coding Wars: Competition & Ecosystem 57:27 – The Future of Coding as a Profession 58:41 – What’s Next for Claude Code

Matt Turck

82,161 views • 11 months ago

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

393,366 views • 2 years ago

Frontier LLM models (especially Opus) are very good at finding vulnerabilities in codebases. With the right skills and a sub-agent architecture, they can outperform any traditional SAST tool. I collected the skills I use in this repository. Load them into any AI coding IDE such as Claude Code, Codex, Opencode etc. to find vulnerabilities in your code. You don’t need any third-party tools.

Frontier LLM models (especially Opus) are very good at finding vulnerabilities in codebases. With the right skills and a sub-agent architecture, they can outperform any traditional SAST tool. I collected the skills I use in this repository. Load them into any AI coding IDE such as Claude Code, Codex, Opencode etc. to find vulnerabilities in your code. You don’t need any third-party tools.

Utku Sen 🇬🇧

93,957 views • 3 months ago

Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From NVIDIA Berkeley AI Research CMU Robotics Institute Stanford AI Lab 🧵

Robotics: coding agents’ next frontier. So how good are they? We introduce CaP-X: an open-source framework and benchmark for coding agents, where they write code for robot perception and control, execute it on sim and real robots, observe the outcomes, and iteratively improve code reliability. From NVIDIA Berkeley AI Research CMU Robotics Institute Stanford AI Lab 🧵

Max Fu

173,471 views • 3 months ago

Anthropic is leading the Industry with models - like Sonnet and Opus - and developer tools - like Claude Code. Here are 5 tips to get more out of Claude Code!

Anthropic is leading the Industry with models - like Sonnet and Opus - and developer tools - like Claude Code. Here are 5 tips to get more out of Claude Code!

Jon Meyers

14,226 views • 9 months ago

🚀Introducing Code Arena: the next generation of live coding evals for frontier AI models. Built to test how models plan, scaffold, debug, and build real web apps step-by-step. Try Claude, GPT-5, GLM-4.6 and Gemini in Code Arena today!

🚀Introducing Code Arena: the next generation of live coding evals for frontier AI models. Built to test how models plan, scaffold, debug, and build real web apps step-by-step. Try Claude, GPT-5, GLM-4.6 and Gemini in Code Arena today!

Arena.ai

328,087 views • 8 months ago

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 views • 1 month ago

Make Claude Code 10x more powerful! Code Context is an MCP plugin that brings semantic code search to Claude Code, Gemini CLI, or any AI coding agent. Full codebase indexing means richer context and better code generation. 100% open-source.

Make Claude Code 10x more powerful! Code Context is an MCP plugin that brings semantic code search to Claude Code, Gemini CLI, or any AI coding agent. Full codebase indexing means richer context and better code generation. 100% open-source.

Akshay 🚀

136,975 views • 11 months ago

BREAKING: agents are taking over app dev Claude Code, OpenClaw, Codex, and Hermes can now design, build, and publish through the Anything CLI with no human in the loop

BREAKING: agents are taking over app dev Claude Code, OpenClaw, Codex, and Hermes can now design, build, and publish through the Anything CLI with no human in the loop

Anything

364,818 views • 29 days ago

Wondering why your maker-turned-manager suddenly seems distracted in meetings? Maybe they're addicted to coding agents! In this episode of Lightcone, Calvin French-Owen — a co-founder of Segment and former engineer on OpenAI's Codex team — joins us to talk about why coding agents suddenly feel so powerful, the differences between Codex, Claude Code, and Cursor, and what the future of work will look like. 0:00 Intro 1:15 Garry can’t stop using Claude Code! 4:00 Contrast with IDE’s, context-splitting 6:23 Distribution models, top down vs bottom up 9:11 Licensing and optimization 12:28 Tips on becoming a top 1% user of coding agents 17:36 When can the agents work 24-48 hour running jobs on their own? 21:34 Can the agent teach things like architecture? 26:27 Will the next generation have even better taste and multitasking ability? 29:58 Maker vs manager schedules 31:36 How would Calvin build Segment now? 35:52 The importance of testing 38:52 The Claude bots are talking (to each other!) 40:10 Examples of complex issues, how will the tools evolve 43:00 Outro

Wondering why your maker-turned-manager suddenly seems distracted in meetings? Maybe they're addicted to coding agents! In this episode of Lightcone, Calvin French-Owen — a co-founder of Segment and former engineer on OpenAI's Codex team — joins us to talk about why coding agents suddenly feel so powerful, the differences between Codex, Claude Code, and Cursor, and what the future of work will look like. 0:00 Intro 1:15 Garry can’t stop using Claude Code! 4:00 Contrast with IDE’s, context-splitting 6:23 Distribution models, top down vs bottom up 9:11 Licensing and optimization 12:28 Tips on becoming a top 1% user of coding agents 17:36 When can the agents work 24-48 hour running jobs on their own? 21:34 Can the agent teach things like architecture? 26:27 Will the next generation have even better taste and multitasking ability? 29:58 Maker vs manager schedules 31:36 How would Calvin build Segment now? 35:52 The importance of testing 38:52 The Claude bots are talking (to each other!) 40:10 Examples of complex issues, how will the tools evolve 43:00 Outro

Y Combinator

18,418 views • 5 months ago

Codex is having a moment....and feels a bit like Claude at the beginning of the year. Builders are noticing first, Wall St/consensus will take a bit to catch up Matan Grinberg from Factory says he switched from Claude Code to Codex ~2 months ago and that OpenAI’s coding models are “really really good right now”

Codex is having a moment....and feels a bit like Claude at the beginning of the year. Builders are noticing first, Wall St/consensus will take a bit to catch up Matan Grinberg from Factory says he switched from Claude Code to Codex ~2 months ago and that OpenAI’s coding models are “really really good right now”

Deirdre Bosa

21,927 views • 1 month ago

A conversation with Claude Code's creator Boris Cherny on the future of agentic coding, the evolution of coding models, and how he uses Claude Code to build Claude Code.

A conversation with Claude Code's creator Boris Cherny on the future of agentic coding, the evolution of coding models, and how he uses Claude Code to build Claude Code.

Alex Albert

81,455 views • 10 months ago