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。

Mount Archil's elastic POSIX file system in your E2B sandbox for high-performance, shared access to S3, R2, and GCS. One use case is spinning up large fleets of parallel agents on large datasets without bottlenecks. See how to get started below.

Vasek Mlejnsky

8,582 subscribers

10,572 次观看 • 1 个月前 •via X (Twitter)

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

Here is how to set up a team of AI agents to work on your project without disrupting anything. This is the top 1 upgrade you can do to your development environment: Start using dev containers to isolate agents and run them in parallel in their own cloud containers. Let me show you:

Here is how to set up a team of AI agents to work on your project without disrupting anything. This is the top 1 upgrade you can do to your development environment: Start using dev containers to isolate agents and run them in parallel in their own cloud containers. Let me show you:

Santiago

22,742 次观看 • 11 个月前

Here is how to implement low rep and high sets for tonnage with a large group Screenshots of traditional and high tonnage example in thread but they are the SAME Don’t use unless appropriate for your athletes Please ask questions happy to answer Dylan Surface

Here is how to implement low rep and high sets for tonnage with a large group Screenshots of traditional and high tonnage example in thread but they are the SAME Don’t use unless appropriate for your athletes Please ask questions happy to answer Dylan Surface

Official Strength Debates

56,469 次观看 • 3 年前

I’m running to clean up Columbia because our government is too large and continues growing at the expense of your freedoms. Our taxes are too high, our roads and bridges are dilapidated, our judicial system is unjust and unfair, and our education system is failing our kids. I’m ready to use my business background and conservative backbone to clean up Columbia for you!

I’m running to clean up Columbia because our government is too large and continues growing at the expense of your freedoms. Our taxes are too high, our roads and bridges are dilapidated, our judicial system is unjust and unfair, and our education system is failing our kids. I’m ready to use my business background and conservative backbone to clean up Columbia for you!

Ralph Norman for Governor

101,425 次观看 • 9 个月前

🔬 Training Transformers to solve 95% failure rate of Cancer Trials the AI for Science pod is back with Ron Alfa, CEO of NOETIK, and Daniel Bear, VP Research at Noetik, explaining exactly how their team of top AI x Bio researchers and engineers (shoutout owl) will use AI to cure cancer, by focusing on key bottlenecks like patient selection, and training large cancer foundation models like TARIO-2, an autoregressive transformer trained on one of the largest sets of tumor spatial transcriptomics datasets in the world... which first required years of blind faith in collecting good data to even get going:

🔬 Training Transformers to solve 95% failure rate of Cancer Trials the AI for Science pod is back with Ron Alfa, CEO of NOETIK, and Daniel Bear, VP Research at Noetik, explaining exactly how their team of top AI x Bio researchers and engineers (shoutout owl) will use AI to cure cancer, by focusing on key bottlenecks like patient selection, and training large cancer foundation models like TARIO-2, an autoregressive transformer trained on one of the largest sets of tumor spatial transcriptomics datasets in the world... which first required years of blind faith in collecting good data to even get going:

Latent.Space

18,310 次观看 • 3 个月前

This is the most insane application of MCP I've used. Context is king! Your coding agents thrive on high-quality context. Qodo Aware is a production-ready deep research agent that solves this. This is huge! Watch how I use it in Codex to retrieve context from large codebases.

This is the most insane application of MCP I've used. Context is king! Your coding agents thrive on high-quality context. Qodo Aware is a production-ready deep research agent that solves this. This is huge! Watch how I use it in Codex to retrieve context from large codebases.

elvis

80,225 次观看 • 11 个月前

File systems are quickly becoming a core abstraction for AI agents for knowledge work. By having access to a file system, agents can effectively manage context, process any amount of information, and create new files and data. The challenge is that local file systems are inherently limited in size, lack governance capabilities, and are inherently personal -not collaborative- in nature. Now, with the Box API and LangChain's deepagent SDK, you can bring the full power of a secure, collaborative cloud file system to your AI agents. Repo ↓

File systems are quickly becoming a core abstraction for AI agents for knowledge work. By having access to a file system, agents can effectively manage context, process any amount of information, and create new files and data. The challenge is that local file systems are inherently limited in size, lack governance capabilities, and are inherently personal -not collaborative- in nature. Now, with the Box API and LangChain's deepagent SDK, you can bring the full power of a secure, collaborative cloud file system to your AI agents. Repo ↓

Box

227,348 次观看 • 6 个月前

When we ask an agent to "fix this bug," we're approving hundreds of actions we'll never see. These agents have our production credentials; and increasingly, they run in the background while we work on something else. Engineers are spinning up multiple Claude Code sessions in parallel, and ClawdBot hit >100k GitHub stars in weeks by letting agents handle email, workflows, even car purchases. The shift to agents without constant supervision is here. Today we're launching MintMCP : governance for AI agents.

When we ask an agent to "fix this bug," we're approving hundreds of actions we'll never see. These agents have our production credentials; and increasingly, they run in the background while we work on something else. Engineers are spinning up multiple Claude Code sessions in parallel, and ClawdBot hit >100k GitHub stars in weeks by letting agents handle email, workflows, even car purchases. The shift to agents without constant supervision is here. Today we're launching MintMCP : governance for AI agents.

Jiquan Ngiam

470,221 次观看 • 6 个月前

[1/16] The real world is large, and we want our AI models to operate on the scale of reality. Over the past two years, my colleagues and I have developed fVDB, a deep learning framework for large-scale, high performance spatial intelligence. We finally announced this work at SIGGRAPH and have released the framework in early access. Here’s a small tour of what fVDB is, and what we’ve used it to do.

[1/16] The real world is large, and we want our AI models to operate on the scale of reality. Over the past two years, my colleagues and I have developed fVDB, a deep learning framework for large-scale, high performance spatial intelligence. We finally announced this work at SIGGRAPH and have released the framework in early access. Here’s a small tour of what fVDB is, and what we’ve used it to do.

Francis Williams

34,026 次观看 • 2 年前

No one wants their phone to get stolen but in the worst case, OPay has a USSD Code to secure your funds - Night Guard to protect your funds at night and now LARGE TRANSACTION SHIELD which allows you to set any limit of your choice to block large amounts from leaving your account. OPay will require a facial verification for a transaction that exceds the limit you have set. Would you be trying this? Let me know in the comments below 👇🏾

No one wants their phone to get stolen but in the worst case, OPay has a USSD Code to secure your funds - Night Guard to protect your funds at night and now LARGE TRANSACTION SHIELD which allows you to set any limit of your choice to block large amounts from leaving your account. OPay will require a facial verification for a transaction that exceds the limit you have set. Would you be trying this? Let me know in the comments below 👇🏾

Uncle Chu

34,299 次观看 • 1 年前

It's time! ⚡️ Today we're unveiling Autohive 🐝 - a modern platform to find, create and use AI agents to help automate the toil in your organization. We see a future where team members are delegating to teams of agents to achieve significantly more, and bring more fun to work for everyone. Link to sign up to join the early access list below 👇

It's time! ⚡️ Today we're unveiling Autohive 🐝 - a modern platform to find, create and use AI agents to help automate the toil in your organization. We see a future where team members are delegating to teams of agents to achieve significantly more, and bring more fun to work for everyone. Link to sign up to join the early access list below 👇

John-Daniel Trask

30,536 次观看 • 1 年前

See your data on Google Earth's real-world canvas. You can now import large-scale KML and GeoJSON datasets—up to billions of features—directly into Google Earth. Don’t just view your data; validate it against reality. Customize styling, create custom data layers, and uncover new insights to create visualizations that drive decisions. Take advantage of increased storage and file size quotas in our professional plans to securely overlay your proprietary intelligence atop our trusted imagery and data layers to create a single source of truth.

See your data on Google Earth's real-world canvas. You can now import large-scale KML and GeoJSON datasets—up to billions of features—directly into Google Earth. Don’t just view your data; validate it against reality. Customize styling, create custom data layers, and uncover new insights to create visualizations that drive decisions. Take advantage of increased storage and file size quotas in our professional plans to securely overlay your proprietary intelligence atop our trusted imagery and data layers to create a single source of truth.

Google Earth

25,901 次观看 • 6 个月前

AI agents are only as powerful as the content they can access. Anthropic announced Dispatch in Claude Cowork — assign tasks from your phone, let Claude navigate your computer, get complex work done autonomously. But without a file system built for AI, even the most capable agent is working blind. Connect Claude Cowork to Box and your files become the foundation it reasons from. Is your content infrastructure ready for AI agents?

AI agents are only as powerful as the content they can access. Anthropic announced Dispatch in Claude Cowork — assign tasks from your phone, let Claude navigate your computer, get complex work done autonomously. But without a file system built for AI, even the most capable agent is working blind. Connect Claude Cowork to Box and your files become the foundation it reasons from. Is your content infrastructure ready for AI agents?

Box

432,932 次观看 • 4 个月前

Making a video is easy, making it engaging is hard so we turned the patterns pros use into HyperFrames skills for agents now your agent can add the graphics and captions where they belong, based on your message adjustable to your brand and repeatable get started below ↓

HeyGen

943,565 次观看 • 1 个月前

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

127,724 次观看 • 1 年前

Here is a KEY experiment, which may determine whether we truly understand the physics of "UFO levitation"? In movie 1, we can see that lowering a spinning wheel will make a large base-wheel turn anti-clockwise. Or if we raise the same spinning wheel, that will make a large base-wheel turn clockwise. Now let's turn the experiment around! Instead of lowering or raising an upper spinning wheel, we can apply an external force, that makes the large base-wheel turn anti-clockwise, or else clockwise. What happens then to the upper spinning wheel? Will it still go up or down as before? 🥳🛸 In slide 2, we can see one of many examples drawn in crops (by friendly aliens), to suggest that "spinning one wheel" (say a large base-wheel) will cause another spinning wheel (say a small upper wheel) to "lift up". Such a novel "lifting motion" will not cause any downward Newtonian action-reaction, because all of the force is applied as a horizontal spin-torque to the large base-wheel. It seems like "magic", but that may be how Nature works! I will do this critical experiment in a few weeks, once some needed parts arrive. Meanwhile if other inventors would like to have a go, please feel free, and communicate your new results here. 🛸

Here is a KEY experiment, which may determine whether we truly understand the physics of "UFO levitation"? In movie 1, we can see that lowering a spinning wheel will make a large base-wheel turn anti-clockwise. Or if we raise the same spinning wheel, that will make a large base-wheel turn clockwise. Now let's turn the experiment around! Instead of lowering or raising an upper spinning wheel, we can apply an external force, that makes the large base-wheel turn anti-clockwise, or else clockwise. What happens then to the upper spinning wheel? Will it still go up or down as before? 🥳🛸 In slide 2, we can see one of many examples drawn in crops (by friendly aliens), to suggest that "spinning one wheel" (say a large base-wheel) will cause another spinning wheel (say a small upper wheel) to "lift up". Such a novel "lifting motion" will not cause any downward Newtonian action-reaction, because all of the force is applied as a horizontal spin-torque to the large base-wheel. It seems like "magic", but that may be how Nature works! I will do this critical experiment in a few weeks, once some needed parts arrive. Meanwhile if other inventors would like to have a go, please feel free, and communicate your new results here. 🛸

Red Collie (Dr. Horace Drew) scientist/inventor

13,847 次观看 • 5 个月前

Dennon Lewis 🏃‍♂️💨 To produce high volumes of sprinting you have to train for it; you cannot hope to turn up on a Saturday and just repeatedly output sprint after sprint without conditioning yourself for it. Dennon records the highest sprint for a large percentage of Dorking’s game, this is down to his position and style of play but as mentioned above, his training has to replicate that. If you’d like to find out more about how your training should be tailored to complement your game, reach out and let’s get a plan in place 💪

Dennon Lewis 🏃‍♂️💨 To produce high volumes of sprinting you have to train for it; you cannot hope to turn up on a Saturday and just repeatedly output sprint after sprint without conditioning yourself for it. Dennon records the highest sprint for a large percentage of Dorking’s game, this is down to his position and style of play but as mentioned above, his training has to replicate that. If you’d like to find out more about how your training should be tailored to complement your game, reach out and let’s get a plan in place 💪

Ben Bacon - Your Peak Performance

18,381 次观看 • 8 个月前

How do you deploy AI agents for financial institutions without compromising on security, isolation, or scale? Rogo powers complex research, analysis, and deal workflows for leading financial firms, supporting complex tasks across tens of thousands of concurrent users. To meet the diverse needs of financial teams, Rogo relies on both specialist and general-purpose agents that can adapt to a wide range of workflows. With Claude Managed Agents and self-hosted sandboxes, Rogo gets the orchestration and post-training capabilities needed to design these agent systems, while E2B provides the execution layer underneath. Every piece of code generated by an agent runs inside its own E2B sandbox with full auditability and traceability. Each sandbox is powered by an isolated microVM, providing the kernel-level isolation critical for Rogo's customers. The result is a seamless agent experience backed by the security, reliability, and compliance requirements that financial institutions demand.

How do you deploy AI agents for financial institutions without compromising on security, isolation, or scale? Rogo powers complex research, analysis, and deal workflows for leading financial firms, supporting complex tasks across tens of thousands of concurrent users. To meet the diverse needs of financial teams, Rogo relies on both specialist and general-purpose agents that can adapt to a wide range of workflows. With Claude Managed Agents and self-hosted sandboxes, Rogo gets the orchestration and post-training capabilities needed to design these agent systems, while E2B provides the execution layer underneath. Every piece of code generated by an agent runs inside its own E2B sandbox with full auditability and traceability. Each sandbox is powered by an isolated microVM, providing the kernel-level isolation critical for Rogo's customers. The result is a seamless agent experience backed by the security, reliability, and compliance requirements that financial institutions demand.

Vasek Mlejnsky

16,630 次观看 • 2 个月前