正在加载视频...

视频加载失败

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

611,385 次观看 • 4 个月前 •via X (Twitter)

32 条评论

Ansh 的头像
Ansh4 个月前

Codex and Claude trying to fix bugs together 😂

Emmiti 的头像
Emmiti4 个月前

@estrelloona and @jacobianmatrixx on my TL

Danny Shmueli 的头像
Danny Shmueli4 个月前

So cute. Love the BSH on the left. Is the moral of the video that in the end, it works?

Justine Moore 的头像
Justine Moore4 个月前

I hope so 🤞 I’m personally still in the trenches

Christina 的头像
Christina4 个月前

It was a tough journey, but they have finally finished and delivered everything carefully.

iEarth 的头像
iEarth4 个月前

Cats are cute no matter what they do, even when they're having a fight

Nirav 的头像
Nirav4 个月前

within same harness also i experienced same thing. was running multiple claude code sessions to do review and fix on separate features but both agents kept committing each other's incomplete code, and interrupting each others tool calls somehow

Shalom Mann 的头像
Shalom Mann4 个月前

I hate how much I like it

Chris Heatherly 的头像
Chris Heatherly4 个月前

I feel seen

Michael Zellinger 的头像
Michael Zellinger4 个月前

Has either of these cats raised their Series A yet? I’d like to slide in a small check

VIBECOBRA 的头像
VIBECOBRA4 个月前

I don't use agents bc I had a curly bracket indentation error so I got VSCode copilot to fix. I think it was set to sonnet and it looped 8 times looking for error and still didn't fix the problem.

Eclipse 🌖 的头像
Eclipse 🌖4 个月前

Two harnesses, two non-deterministic outputs — you’re basically paying for double the hallucination rate.

Renjit Philip 🔭💡 的头像
Renjit Philip 🔭💡4 个月前

Good lord! This is exactly what happens when I ask my openclaw to check out why my Hermes agent failed

Arthur Wolsch 𝕏 的头像
Arthur Wolsch 𝕏4 个月前

😮

Frankenstein (Hao) 的头像
Frankenstein (Hao)4 个月前

omg. the cats can cook.... 😂

Michelangelo 的头像
Michelangelo4 个月前

A poor neighborhood went dry because you made that dumb video.

Roshan 的头像
Roshan4 个月前

funny yar

Aalap Davjekar 的头像
Aalap Davjekar4 个月前

Is this AI?

Aloysis Francis 的头像
Aloysis Francis4 个月前

At end the code is broke 😂😂😁

CatGod 的头像
CatGod4 个月前

Seeing two agents debug code side by side is WILD! What LENS are we looking through?!

JMoon 的头像
JMoon4 个月前

cross-harness debugging works better than expected. Claude catches structural issues, the others get logic edge cases. different models see different failure modes

Dushyanth 的头像
Dushyanth4 个月前

😂

Fabrizio Serafini 的头像
Fabrizio Serafini4 个月前

@dhaber 👀👀

Amol Parikh 的头像
Amol Parikh4 个月前

Debugging just became adversarial

Marco "Shikoba" Riccetti 的头像
Marco "Shikoba" Riccetti4 个月前

True story 😂

Jim O'Shaughnessy 的头像
Jim O'Shaughnessy4 个月前

🤣

King Louis XIII 的头像
King Louis XIII4 个月前

@EdelaQuintaine & @JessfromW... 🤣🥰🤣

Veralll 的头像
Veralll4 个月前

Haha, they messed up🤣

Utkarsh Singh 的头像
Utkarsh Singh4 个月前

This is funny 😂

Roberts Cromwell 的头像
Roberts Cromwell4 个月前

Keep sharing nice contents

Sanjeev Kumar 的头像
Sanjeev Kumar4 个月前

Yay Justine got the Cat agents onto the job of grinding🤡😅

... 的头像
...4 个月前

@itsmeyayon payag ka love ganyan trabaho ni Woltir 😂

相关视频

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 次观看 • 1 年前