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.

Introducing vmux - incredibly fast, stateful cloud sandboxes for coding agents for the first time you get persistent GPU/CPU sandboxes via Modal/CF backed by Durable Objects to stream logs live, native preview URLs, and attach a real shell spin up a notebook or train nanogpt via codex - with... show more

Surya

15,890 subscribers

75,417 views • 5 months ago •via X (Twitter)

Education News & Politics Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We're thrilled to share Modal Notebooks: a new, powerful cloud-hosted GPU notebook. It has modern real-time collaborative editing and is backed by our AI infrastructure — swap GPUs in seconds. Modal Notebooks are generally available, and you can start using them now. 🧵

We're thrilled to share Modal Notebooks: a new, powerful cloud-hosted GPU notebook. It has modern real-time collaborative editing and is backed by our AI infrastructure — swap GPUs in seconds. Modal Notebooks are generally available, and you can start using them now. 🧵

Eric Zhang

262,014 views • 10 months ago

Modal's Agent-Native Cloud: DX→AX, sandboxes, elastic inference, and 100,000 rollouts Modal CTO Akshat Bubna explains why developer experience is becoming agent experience, why agents need infra they can operate instead of YAML they have to reason through, how sandboxes turn the agent loop into something real, why elastic inference and GPU snapshotting matter for production AI, how RL rollouts can require 100,000 sandboxes, and why Modal’s $355M Series C marks a new phase for AI-native cloud infrastructure.

Modal's Agent-Native Cloud: DX→AX, sandboxes, elastic inference, and 100,000 rollouts Modal CTO Akshat Bubna explains why developer experience is becoming agent experience, why agents need infra they can operate instead of YAML they have to reason through, how sandboxes turn the agent loop into something real, why elastic inference and GPU snapshotting matter for production AI, how RL rollouts can require 100,000 sandboxes, and why Modal’s $355M Series C marks a new phase for AI-native cloud infrastructure.

Latent.Space

15,359 views • 11 days ago

Docker is excited to partner with E2B, a platform for running AI-generated code in secure cloud sandboxes. Docker + E2B now gives AI agents access to real tools (GitHub, Perplexity, Browserbase) in secure sandboxes via the MCP Catalog.

Docker is excited to partner with E2B, a platform for running AI-generated code in secure cloud sandboxes. Docker + E2B now gives AI agents access to real tools (GitHub, Perplexity, Browserbase) in secure sandboxes via the MCP Catalog.

Docker

45,595 views • 8 months ago

deploy to preview in under 3 seconds cold with vmux! i told a friend i didnt have any modal credits left on saturday, by monday night i rolled my own cpu modal - seems prevalent if llms can code you should give them easy access(besides ssh) to provision, run code, and deploy containers fast

deploy to preview in under 3 seconds cold with vmux! i told a friend i didnt have any modal credits left on saturday, by monday night i rolled my own cpu modal - seems prevalent if llms can code you should give them easy access(besides ssh) to provision, run code, and deploy containers fast

Surya Dantuluri

12,275 views • 6 months ago

You can now spin up a persistent cloud development environment in one prompt with the @DigitalOcean plugin for Codex. It runs in your DigitalOcean account and keeps working when you step away.

You can now spin up a persistent cloud development environment in one prompt with the @DigitalOcean plugin for Codex. It runs in your DigitalOcean account and keeps working when you step away.

OpenAI Developers

293,997 views • 24 days ago

Every agent needs its own computer: my conversation with Ivan Burazin, CEO of Daytona, about sandboxes and the emerging agent stack. 00:00 Intro 02:13 What is an AI agent sandbox? 03:17 Security risks of running agents locally 05:17 Stateful vs. stateless hyperscalers 07:04 The history of cloud IDEs and the end of localhost 09:45 Do all AI agents need a sandbox? 12:26 Sandbox use cases: RL evals & background agents 14:10 Unpacking the emerging AI Agent Stack 16:20 The unsolved problem of agent memory and learning 19:37 Where sandboxes fit in the agent harness 21:35 OpenAI, Anthropic, and agent SDKs 23:06 Ivan's founder journey: From CodeAnywhere to Daytona 26:59 GTM strategies and building developer communities 33:48 Why customer support is your best GTM strategy 35:34 Leveraging Twitter during the AI super cycle 40:50 The technical anatomy of a sandbox 41:53 Why fast spin-up speeds maximize GPU efficiency 46:09 Firecracker, QEMU, and isolation primitives 49:58 Why sandbox snapshots and state forking matter 51:40 Why Daytona built a custom scheduler from scratch 55:24 The challenge of long-running stateful sandboxes 58:10 The build your own sandbox trap 1:01:03 Why AI agents might trigger a global CPU shortage 1:02:46 The future of the AI Agent Stack

Every agent needs its own computer: my conversation with Ivan Burazin, CEO of Daytona, about sandboxes and the emerging agent stack. 00:00 Intro 02:13 What is an AI agent sandbox? 03:17 Security risks of running agents locally 05:17 Stateful vs. stateless hyperscalers 07:04 The history of cloud IDEs and the end of localhost 09:45 Do all AI agents need a sandbox? 12:26 Sandbox use cases: RL evals & background agents 14:10 Unpacking the emerging AI Agent Stack 16:20 The unsolved problem of agent memory and learning 19:37 Where sandboxes fit in the agent harness 21:35 OpenAI, Anthropic, and agent SDKs 23:06 Ivan's founder journey: From CodeAnywhere to Daytona 26:59 GTM strategies and building developer communities 33:48 Why customer support is your best GTM strategy 35:34 Leveraging Twitter during the AI super cycle 40:50 The technical anatomy of a sandbox 41:53 Why fast spin-up speeds maximize GPU efficiency 46:09 Firecracker, QEMU, and isolation primitives 49:58 Why sandbox snapshots and state forking matter 51:40 Why Daytona built a custom scheduler from scratch 55:24 The challenge of long-running stateful sandboxes 58:10 The build your own sandbox trap 1:01:03 Why AI agents might trigger a global CPU shortage 1:02:46 The future of the AI Agent Stack

Matt Turck

11,908 views • 2 months ago

🧲 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

16,608 views • 1 year ago

Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and provisioning sandboxes from scratch, there's now a faster path. Managed Agents in the Gemini API are officially live. Get maximum agentic power with zero infrastructure overhead. One simple API call delivers a managed, remote sandbox for your agent so you can focus entirely on behavior. 📁 Fully customizable with your instructions, tools, and data via and 🌐 Test, iterate, and scale long-horizon tasks natively in the cloud. The hardest part of building agents is now the part you don't have to build. 👇 Get started now:

Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and provisioning sandboxes from scratch, there's now a faster path. Managed Agents in the Gemini API are officially live. Get maximum agentic power with zero infrastructure overhead. One simple API call delivers a managed, remote sandbox for your agent so you can focus entirely on behavior. 📁 Fully customizable with your instructions, tools, and data via and 🌐 Test, iterate, and scale long-horizon tasks natively in the cloud. The hardest part of building agents is now the part you don't have to build. 👇 Get started now:

Google for Developers

39,196 views • 1 month ago

Coding agents shouldn't run on a laptop. That's why I've been building Cave. It's a self-hosted platform for running OpenCode agents in isolated sandboxes on your own server. You give it a GitHub repo, it creates an isolated sandbox, clones the code, sets everything up, and gives you a coding agent. Check in from your phone, run multiple agents side by side. It's not open source yet (it will be), but I'm opening a private beta so you can install it on your own server already. I've been dogfooding it since day one. If you're running a software factory: multiple agents working in parallel across repos, Cave gives you one place to monitor and manage all of it. Now, I'm looking for people who want to give it a spin. DM me, happy to set you up 😊 🚀

Coding agents shouldn't run on a laptop. That's why I've been building Cave. It's a self-hosted platform for running OpenCode agents in isolated sandboxes on your own server. You give it a GitHub repo, it creates an isolated sandbox, clones the code, sets everything up, and gives you a coding agent. Check in from your phone, run multiple agents side by side. It's not open source yet (it will be), but I'm opening a private beta so you can install it on your own server already. I've been dogfooding it since day one. If you're running a software factory: multiple agents working in parallel across repos, Cave gives you one place to monitor and manage all of it. Now, I'm looking for people who want to give it a spin. DM me, happy to set you up 😊 🚀

André König

36,095 views • 3 months ago

We’re introducing Canvas and welcoming Audio Overview to the Google Gemini today. Turn docs, slides + Deep Research reports into podcasts with Audio Overview. Or create a doc or coding project with Canvas – it spins up prototypes super fast and you can edit with Gemini in real-time.

We’re introducing Canvas and welcoming Audio Overview to the Google Gemini today. Turn docs, slides + Deep Research reports into podcasts with Audio Overview. Or create a doc or coding project with Canvas – it spins up prototypes super fast and you can edit with Gemini in real-time.

Sundar Pichai

384,050 views • 1 year ago

Introducing MagicPath 2.0. MagicPath is now a multiplayer canvas for humans and agents like Codex or Claude Code to design and build with AI. Use your codebase, grab data from anywhere, and see the agents work in real time as a team while building fully functional prototypes.

Introducing MagicPath 2.0. MagicPath is now a multiplayer canvas for humans and agents like Codex or Claude Code to design and build with AI. Use your codebase, grab data from anywhere, and see the agents work in real time as a team while building fully functional prototypes.

Pietro Schirano

324,078 views • 2 months ago

Hermes Agent is now in the Cloud! Setup couldn't be simpler: pick a model and a server size. Two clicks and 60 seconds later, your agent is live. Running a team? Spin up agents for everyone at your org with granular access controls and unified billing, all from Nous Portal.

Hermes Agent is now in the Cloud! Setup couldn't be simpler: pick a model and a server size. Two clicks and 60 seconds later, your agent is live. Running a team? Spin up agents for everyone at your org with granular access controls and unified billing, all from Nous Portal.

Nous Research

1,516,106 views • 11 days ago

multi-chat and web search are live in build mode the coding agent can now pull real-time info from the web to ground your session in the latest documentation and with multi-chat you can spin up a fresh conversation to explore a new feature or idea, and jump back to previous sessions whenever you need

multi-chat and web search are live in build mode the coding agent can now pull real-time info from the web to ground your session in the latest documentation and with multi-chat you can spin up a fresh conversation to explore a new feature or idea, and jump back to previous sessions whenever you need

Google AI Studio

44,266 views • 2 months ago

AI coding agents are great at building frontends, but they usually fail the moment you ask for a database or auth. You end up with a "cool demo" that doesn't actually work. I just tried InsForge 2.0, and it’s the first time I've seen an AI agent ship a fullstack app in seconds. Here is why it’s a game-changer:

AI coding agents are great at building frontends, but they usually fail the moment you ask for a database or auth. You end up with a "cool demo" that doesn't actually work. I just tried InsForge 2.0, and it’s the first time I've seen an AI agent ship a fullstack app in seconds. Here is why it’s a game-changer:

Chidanand Tripathi

82,745 views • 4 months ago

We are super excited to make Restate Cloud publicly available today. Durable Execution, observability, and production-grade availability for workflows or AI agents. This release makes very smooth to work with serverless compute platforms like Cloudflare, Vercel, or Deno. And of course, your own infra on AWS, GCP, or Kubernetes. Signup is free and a few clicks with your GitHub account. A new built-in tutorial let's you run a first durable agent running in seconds. 👇

We are super excited to make Restate Cloud publicly available today. Durable Execution, observability, and production-grade availability for workflows or AI agents. This release makes very smooth to work with serverless compute platforms like Cloudflare, Vercel, or Deno. And of course, your own infra on AWS, GCP, or Kubernetes. Signup is free and a few clicks with your GitHub account. A new built-in tutorial let's you run a first durable agent running in seconds. 👇

Stephan Ewen

30,681 views • 9 months ago

Microsoft sold every spare CPU it had to Anthropic and OpenAI. Amazon tripled its CPU buys year over year and still can't keep up. Two of AWS's biggest customers asked Andy Jassy if they could buy the entire 2026 production run of Graviton chips. He said no. The ratio inside an AI datacenter used to be 100 megawatts of GPUs to 1 megawatt of CPUs. CPUs handled storage, checkpointing, pre-processing. Light work. GPUs did the actual training and inference. Then OpenAI shipped o1-preview in September 2024. RL post-training went from "check the model output with a regex" to "run classifiers" to "compile the code and run the unit tests" to "spin up a sandbox, call three databases, run a physics simulation, verify the answer." Every rollout now needs a CPU-backed environment to verify against. Codex 5.4 runs agentically for 6-7 hours at a time. Each database call, each cron job, each scraped URL is CPU work. Coding agent revenue went from a couple billion to north of $10B in six months. That compute is sitting on CPUs. The CPU to GPU ratio is now approaching 1:1. The entire global cloud was built for 1:8. That's why GitHub has been unstable for weeks. Nvidia and Arm both announced they're entering the server CPU market in March. TSMC will only meet 80% of server CPU wafer demand this year. High-end server CPU prices are already up 50%. When the GPU king and the IP licensor both pivot to CPUs in the same month, the boring chip isn't boring anymore.

Microsoft sold every spare CPU it had to Anthropic and OpenAI. Amazon tripled its CPU buys year over year and still can't keep up. Two of AWS's biggest customers asked Andy Jassy if they could buy the entire 2026 production run of Graviton chips. He said no. The ratio inside an AI datacenter used to be 100 megawatts of GPUs to 1 megawatt of CPUs. CPUs handled storage, checkpointing, pre-processing. Light work. GPUs did the actual training and inference. Then OpenAI shipped o1-preview in September 2024. RL post-training went from "check the model output with a regex" to "run classifiers" to "compile the code and run the unit tests" to "spin up a sandbox, call three databases, run a physics simulation, verify the answer." Every rollout now needs a CPU-backed environment to verify against. Codex 5.4 runs agentically for 6-7 hours at a time. Each database call, each cron job, each scraped URL is CPU work. Coding agent revenue went from a couple billion to north of $10B in six months. That compute is sitting on CPUs. The CPU to GPU ratio is now approaching 1:1. The entire global cloud was built for 1:8. That's why GitHub has been unstable for weeks. Nvidia and Arm both announced they're entering the server CPU market in March. TSMC will only meet 80% of server CPU wafer demand this year. High-end server CPU prices are already up 50%. When the GPU king and the IP licensor both pivot to CPUs in the same month, the boring chip isn't boring anymore.

Aakash Gupta

290,767 views • 3 months ago

Today I built this voice agent while on a call with it Introducing /this-needs-a-call - it's a slash command to start a phone call - grill or be grilled by the voice agent in realtime - your coding agent listens in on the call via MCP and works while you talk for hours

Today I built this voice agent while on a call with it Introducing /this-needs-a-call - it's a slash command to start a phone call - grill or be grilled by the voice agent in realtime - your coding agent listens in on the call via MCP and works while you talk for hours

jacob paris ▲

32,463 views • 19 days ago

Evernote Search just got a serious glow-up ✨ We made several visible improvements to the search modal, including: 👉 A centered search modal with scrollable suggestions 👉 Higher priority for results with title matches 👉 A new default section view for recent notes, grouped by when they were last updated We also made some behind-the-scenes performance boosts to speed up loading time and give you smarter, faster suggestions while typing. All these changes add up to a faster, smarter, more seamless search experience. Available in v10.143 and up on Desktop and Web. Happy searching! 💚

Evernote Search just got a serious glow-up ✨ We made several visible improvements to the search modal, including: 👉 A centered search modal with scrollable suggestions 👉 Higher priority for results with title matches 👉 A new default section view for recent notes, grouped by when they were last updated We also made some behind-the-scenes performance boosts to speed up loading time and give you smarter, faster suggestions while typing. All these changes add up to a faster, smarter, more seamless search experience. Available in v10.143 and up on Desktop and Web. Happy searching! 💚

Evernote

16,707 views • 1 year ago

We built a real-time multiplayer game generated entirely by a neural network—and now you can actually play it. In collaboration with Modal, we just launched the live demo for MultiGen, our diffusion-based multiplayer game engine. Grab some friends and try it here 👇

We built a real-time multiplayer game generated entirely by a neural network—and now you can actually play it. In collaboration with Modal, we just launched the live demo for MultiGen, our diffusion-based multiplayer game engine. Grab some friends and try it here 👇

Gordon Wetzstein

26,537 views • 3 months ago

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

New open source project: Easel, a macOS workspace for AI-assisted product design and frontend iteration powered by the Codex SDK. Think of it as "Claude Design for Codex." It brings together a local project library, design-system setup, Codex chat, and a live web preview with a point-and-click inspector. Set up your design system however you like. Import one from Figma , bring your own, or have the agent generate it as a design.md. Then use it to build prototypes and slide decks. Codex-first, with Claude and other AI providers and local models planned for future releases. OpenAI Developers

James Rochabrun

61,199 views • 1 month ago