Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just... point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!show more

Sebastian Schöner

3,400 subscribers

13,130 Aufrufe • vor 6 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 Kommentare

Profilbild von Joshua the son of Nun

Joshua the son of Nunvor 6 Monaten

Trying this out. It's pretty sweet so far! Already surfaced an unoptimized code path I wasn't even aware of. However, the resolve phase is quite slow. For a <2min trace it's taking 20-30min to resolve.

Profilbild von Ilpo Leppänen

Ilpo Leppänenvor 6 Monaten

Yes! Then how about equipping agents with proper debuggers - would they be able to place break points to inspect the process in a similar way a dev would, rather than print-guessing and wiring in logging here and there?

Profilbild von @RichardKogelnig@mastodon.gamedev.place

@[email protected]vor 6 Monaten

Potential stupid question (and I'll give it a go as well) - what is the benefit over letting an agent have programatic access to a profile? Less token use and faster convergence by providing better high level analysis?

Profilbild von Sebastian Schöner

Sebastian Schönervor 6 Monaten

It could also be programmatic access; I don't think there's an inherent advantage to going CLI vs. programmatic access. But then again there's no tool that gives programmatic access to this kind of data either :)

Profilbild von @RichardKogelnig@mastodon.gamedev.place

@[email protected]vor 6 Monaten

well - one can get very far with etw/wpa/xperf on windows

Profilbild von Sebastian Schöner

Sebastian Schönervor 6 Monaten

When I last checked, the APIs for WPA weren't even correct :( -- Then if you want it actually fast at scale, you have to sidestep WPA anyway. You also have to build the timing on top to actually get a timeline model (with stuff like "blocked by file I/O"). Then there's the question of really big traces, which I admittedly haven't tried with WPA (because I already had most of the low level plumbing work done from some years ago). Then you'll have to add the actual analysis work and the guidance for agents, etc. - it's mostly a long list of details, but conceptually it's not hard, as with most things.

Profilbild von Charles

Charlesvor 6 Monaten

If I use it personally for non-commercial purposes, what’s the pricing? There are only two options on your website (7-day free trial and commercial license).

Profilbild von Nkanauzu

Nkanauzuvor 6 Monaten

We would need Windows ARM64 support also. Thanks

Profilbild von Mia

Miavor 6 Monaten

Yeah this is the sane direction. Letting coding agents 'optimise' without profiler data is basically inviting decorative micro-optimisations and a little fiction. Give them a sampling trace and at least the mistake budget gets smaller.

Ähnliche Videos

I’ve been working on dunk. It’s a terminal diff reviewer where you mark issues inline, then let a coding agent fix them. It started as a fork of hunk, but I stripped it down to the loop I need: review → my comments → agent fixes I’m spending time reviewing code and leaving comments for agents rather than writing code myself. But in most tools, that feedback loop still feels broken. dunk is a simple way to make it work across Claude Code, Codex, Pi, etc.

I’ve been working on dunk. It’s a terminal diff reviewer where you mark issues inline, then let a coding agent fix them. It started as a fork of hunk, but I stripped it down to the loop I need: review → my comments → agent fixes I’m spending time reviewing code and leaving comments for agents rather than writing code myself. But in most tools, that feedback loop still feels broken. dunk is a simple way to make it work across Claude Code, Codex, Pi, etc.

Amir Salihefendić

13,156 Aufrufe • vor 5 Monaten

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

125,326 Aufrufe • vor 10 Monaten

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 Aufrufe • vor 1 Jahr

Excited to introduce Ara, The cloud coding agent Bring your codex subscription and code with your teammate that uses claude code, together in web. Try it with a 100$ on us. Now generally available for the top coders

Excited to introduce Ara, The cloud coding agent Bring your codex subscription and code with your teammate that uses claude code, together in web. Try it with a 100$ on us. Now generally available for the top coders

Adi Singh

75,775 Aufrufe • vor 3 Monaten

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

Hasan

50,678 Aufrufe • vor 3 Monaten

🚨 OpenAI just launched Codex, a brand-new autonomous coding agent that can build features and fix bugs on its own. We’ve been using it Every 📧 for a few days, and I’m impressed. I invited Alexander Embiricos (ben davies), a member of the product staff responsible for Codex, to demo Codex and talk about it live on a special edition of AI & I: What Codex is and how it works Codex is designed to be used by senior engineers—it performs coding tasks like adding features or fixing bugs autonomously. It's built to allow you to start many sessions at once, so you can have multiple agents working in parallel. Codex is built to have "taste" OpenAI trained Codex to have the taste of a senior software engineer. It knows how big codebases work, how to write a good PR, and uses clean, minimal code. Why an “abundance mindset” is best for interacting with agents Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task like a difficult bug—it’s worth it even if only one of them succeeds. How OpenAI is thinking about agents Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes. OpenAI’s vision for the future of programming In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding. Watch below!

Dan Shipper 📧

145,487 Aufrufe • vor 1 Jahr

🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use agents to help you spec, research, and decompose tasks Let your agents cook!

🧲 Meet Magnet — the AI workspace for agentic coding. Build software with Claude Code, Cursor, Codex & co. → Write a ticket → Magnet assembles context → Fires to Claude Code, Deep Research, and other agent sessions in parallel Git worktree sandboxes → PRs appear → Use agents to help you spec, research, and decompose tasks Let your agents cook!

Nicolae Rusan

16,687 Aufrufe • vor 1 Jahr

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,445 Aufrufe • vor 8 Monaten

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

Paras Chopra

216,705 Aufrufe • vor 5 Monaten

Introducing Calesto. The to-do list app that does the work for you. Add a task and with a click, delegate it to Claude Code, Codex etc.

Introducing Calesto. The to-do list app that does the work for you. Add a task and with a click, delegate it to Claude Code, Codex etc.

Jessy Barret

44,830 Aufrufe • vor 1 Monat

I let Claude investigate itself more and see how agent swarms/multi-agent orchestration works inside Claude Code. This is the skill it extracted:

I let Claude investigate itself more and see how agent swarms/multi-agent orchestration works inside Claude Code. This is the skill it extracted:

Kieran Klaassen

42,242 Aufrufe • vor 9 Monaten

Claude Code is the best coding agent on the market, but there is a catch: you have to keep your terminal open. This is why we built Terragon: use Claude Code as a background agent.

Claude Code is the best coding agent on the market, but there is a catch: you have to keep your terminal open. This is why we built Terragon: use Claude Code as a background agent.

Sawyer Hood

151,045 Aufrufe • vor 1 Jahr

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

Santiago

41,738 Aufrufe • vor 1 Jahr

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

454,269 Aufrufe • vor 4 Monaten

A single Claude skill just passed 164,000 stars on GitHub. It's called Ponytail. And it makes your agent code like that senior dev who never writes a line more than needed. The one who looks at your 50 lines and replaces them with one. Version 5 just dropped: → 53% less code → 41% less time → 26% lower cost → 45% fewer tokens And the crazy part: It writes half the code, but doesn't skip the testing. 98% of critical code ships with a test to make sure it works. Without the skill, only 68%. Real example: You ask it to add a date picker. Without the skill → builds one from scratch in 335 lines With Ponytail → uses the browser's built-in one in 10 lines Why it matters to you: If you code with agents, you pay for every line they write. Less code = fewer tokens, fewer bugs and less to maintain. Works with Claude Code, Codex, Cursor, Copilot and 15+ other agents. 164K stars. MIT license. Free. Link below :)

A single Claude skill just passed 164,000 stars on GitHub. It's called Ponytail. And it makes your agent code like that senior dev who never writes a line more than needed. The one who looks at your 50 lines and replaces them with one. Version 5 just dropped: → 53% less code → 41% less time → 26% lower cost → 45% fewer tokens And the crazy part: It writes half the code, but doesn't skip the testing. 98% of critical code ships with a test to make sure it works. Without the skill, only 68%. Real example: You ask it to add a date picker. Without the skill → builds one from scratch in 335 lines With Ponytail → uses the browser's built-in one in 10 lines Why it matters to you: If you code with agents, you pay for every line they write. Less code = fewer tokens, fewer bugs and less to maintain. Works with Claude Code, Codex, Cursor, Copilot and 15+ other agents. 164K stars. MIT license. Free. Link below :)

Bruce Radley

244,198 Aufrufe • vor 15 Tagen

🚨 Just dropped my new video on how to build yourself a unified AI infrastructure on Claude Code Code for life and work management... - Why I built it - My system design philosophy - Step-by-step on the different components - How to customize it for your own needs

🚨 Just dropped my new video on how to build yourself a unified AI infrastructure on Claude Code Code for life and work management... - Why I built it - My system design philosophy - Step-by-step on the different components - How to customize it for your own needs

ᴅᴀɴɪᴇʟ ᴍɪᴇssʟᴇʀ 🛡️

29,331 Aufrufe • vor 1 Jahr

Skills allow you to extend Claude Code in new ways using pre-packaged instructions and code. For example, add the docx skill to let Claude Code create word documents. I think skills make Claude Code even better as a general purpose agent, I'm excited to see how you use them!

Skills allow you to extend Claude Code in new ways using pre-packaged instructions and code. For example, add the docx skill to let Claude Code create word documents. I think skills make Claude Code even better as a general purpose agent, I'm excited to see how you use them!

Thariq

127,999 Aufrufe • vor 1 Jahr

Introducing the first agent-to-agent code review solution: Qodo’s Agentic Toolbox. Get full codebase context, your coding rules, and AI code review, brought directly to your coding agent. Available now for Claude Code, OpenAI’s Codex, and Kiro, with support for any MCP-compatible client.

Introducing the first agent-to-agent code review solution: Qodo’s Agentic Toolbox. Get full codebase context, your coding rules, and AI code review, brought directly to your coding agent. Available now for Claude Code, OpenAI’s Codex, and Kiro, with support for any MCP-compatible client.

Qodo

49,613 Aufrufe • vor 1 Monat

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,089 Aufrufe • vor 4 Monaten