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。

Asking two agents in different harnesses to debug your code (from andirockk on IG)

Justine Moore

201,472 subscribers

610,155 次观看 • 1 个月前 •via X (Twitter)

喜剧教育科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

You can now upload your code repository directly from your device into Gemini Advanced to streamline your workflows. Debug, refactor, rewrite, & optimize your code with the comprehensive context of your project in mind. 🧑‍💻 Try it out →

You can now upload your code repository directly from your device into Gemini Advanced to streamline your workflows. Debug, refactor, rewrite, & optimize your code with the comprehensive context of your project in mind. 🧑‍💻 Try it out →

Google Gemini

425,670 次观看 • 1 年前

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

124,382 次观看 • 1 年前

pov: your vibecoder friend trying to debug the app built using claude code

pov: your vibecoder friend trying to debug the app built using claude code

dev

358,584 次观看 • 4 个月前

It’s getting insanely easy to build complex multi-agent systems in n8n. You can now build supervisor agents that delegates tasks to specialized sub agents. Just add the sub agents via AI Agent Tool node. All in one place and a lot easier to debug! Zero code!

It’s getting insanely easy to build complex multi-agent systems in n8n. You can now build supervisor agents that delegates tasks to specialized sub agents. Just add the sub agents via AI Agent Tool node. All in one place and a lot easier to debug! Zero code!

elvis

45,690 次观看 • 11 个月前

we built PokeOS. Poke now - interacts with your iMessage proactively - fills forms/searches on your local browser - can write/debug code directly in your IDE

we built PokeOS. Poke now - interacts with your iMessage proactively - fills forms/searches on your local browser - can write/debug code directly in your IDE

rajan agarwal

80,263 次观看 • 9 个月前

Connect your agents directly to Chrome DevTools. 🛠️ The new Chrome DevTools MCP server allows agents to inspect the DOM and debug console errors in real-time using Gemini CLI or any compatible agent. Check out the documentation on GitHub →

Connect your agents directly to Chrome DevTools. 🛠️ The new Chrome DevTools MCP server allows agents to inspect the DOM and debug console errors in real-time using Gemini CLI or any compatible agent. Check out the documentation on GitHub →

Google for Developers

22,793 次观看 • 6 个月前

Ghostwriter Chat! Talk with AI to generate code, debug, follow up & iterate—right in your editor. Who wants early access?

Ghostwriter Chat! Talk with AI to generate code, debug, follow up & iterate—right in your editor. Who wants early access?

Amjad Masad

764,575 次观看 • 3 年前

Homeland Security agents showed up at two elementary schools in my district asking for 6 different students. They lied and said they had permission from guardians to see them. Thankfully, both principals denied them access. These actions are disgusting and shameful.

Homeland Security agents showed up at two elementary schools in my district asking for 6 different students. They lied and said they had permission from guardians to see them. Thankfully, both principals denied them access. These actions are disgusting and shameful.

Congressman Robert Garcia

599,291 次观看 • 1 年前

Comet Android can debug your code from your phone. Analyzed CI logs, Traced the failure, Figured out a fix, Committed the fix and opened a PR that’s ready to merge

Comet Android can debug your code from your phone. Analyzed CI logs, Traced the failure, Figured out a fix, Committed the fix and opened a PR that’s ready to merge

Aravind Srinivas

66,281 次观看 • 6 个月前

Introducing the Orca Mobile Emulator. AI agents can now use mobile apps inside Orca ADE. Each worktree gets its own emulator — so you and your agents can build, test, debug, and validate mobile flows right where the code lives. Works with Codex, Claude Code, OpenCode, or any agent.

Introducing the Orca Mobile Emulator. AI agents can now use mobile apps inside Orca ADE. Each worktree gets its own emulator — so you and your agents can build, test, debug, and validate mobile flows right where the code lives. Works with Codex, Claude Code, OpenCode, or any agent.

Orca ADE

31,191 次观看 • 21 天前

🧵 Making Proactive Agents with Code Generation Last week we shared about how you can use code generation to compose tools. But code generation can also give your agents new capabilities- like proactively acting on your behalf.

🧵 Making Proactive Agents with Code Generation Last week we shared about how you can use code generation to compose tools. But code generation can also give your agents new capabilities- like proactively acting on your behalf.

Thariq

35,608 次观看 • 7 个月前

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Agent apps don’t win on the model, they win on the harness. But creating that harness is painful. Terminal Use is hosting infrastructure for background agents built for iterating: fork filesystems and try multiple agents in parallel. The platform is CLI-first, which allows your coding agents like Claude Code & Codex to help you debug, hypothesize improvements, and analyze outputs. Congrats on the launch Vivek Raja, Stavros Filosidis, and Filip Balucha!

Y Combinator

61,500 次观看 • 4 个月前

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

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 次观看 • 1 年前

Introducing Oz: the platform to orchestrate agents in the cloud. Spin up hundreds of agents from your terminal, browser, the API, or your phone. Each agent gets a @docker environment to build, test, and write PRs. Come back from your lunch break to code that’s ready to merge.

Introducing Oz: the platform to orchestrate agents in the cloud. Spin up hundreds of agents from your terminal, browser, the API, or your phone. Each agent gets a @docker environment to build, test, and write PRs. Come back from your lunch break to code that’s ready to merge.

Warp

2,371,450 次观看 • 4 个月前

Your terminal, now with context-aware intelligence. Debug faster, run multi-step tasks, and stay in flow. Intelligent Terminal brings your favorite agents into the command line so you can debug, execute, and keep building without breaking focus.

Your terminal, now with context-aware intelligence. Debug faster, run multi-step tasks, and stay in flow. Intelligent Terminal brings your favorite agents into the command line so you can debug, execute, and keep building without breaking focus.

Microsoft Developer

13,802 次观看 • 17 天前

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Jason Zhou

11,981 次观看 • 8 个月前

we built the first sane way to debug your agent locally. you can see your traces. codex/claude code can too. this lets them write evals and test your agents automatically. best part: it's completely free and open source. install with 1 line. (github below)

we built the first sane way to debug your agent locally. you can see your traces. codex/claude code can too. this lets them write evals and test your agents automatically. best part: it's completely free and open source. install with 1 line. (github below)

ben hylak

193,223 次观看 • 1 个月前

"Declarative code compiles to imperative code that's hard to debug, I'm not sure we're in a better place now than we were with jQuery" ThePrimeagen

"Declarative code compiles to imperative code that's hard to debug, I'm not sure we're in a better place now than we were with jQuery" ThePrimeagen

Marc Grabanski

140,477 次观看 • 3 年前

Our society is too blind to see the writing on the wall. Two people from two different races get a different reception on the same matter in the same society.

Our society is too blind to see the writing on the wall. Two people from two different races get a different reception on the same matter in the same society.

Mzilikazi wa Afrika

112,935 次观看 • 2 年前