# Sandbox Published articles for Sandbox. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## How sandbox boundaries affect AI coding agent evaluations DevFeed: [How sandbox boundaries affect AI coding agent evaluations]() Original publisher: [Read original article]() Author: Waldek Mastykarz Published: 2026-09-16T09:09:51Z Content type: opinion Language: en Sources: [Developer Blogs]() Topics: [AI-assisted coding](), [Testing](), [Artificial Intelligence](), [coding]() Tags: [agent-experience](), [ai](), [ai-coding](), [ax](), [coding](), [developers](), [eval](), [evaluation](), [measurement](), [sandbox]() ### AI overview The article explains that an AI coding agent evaluation can produce misleading scores when the agent retrieves answers from its prompt, environment, or other accessible resources. It argues that evaluators should define the capability being tested and set information boundaries accordingly, including restricting access to evidence when measuring internal model knowledge. ### Source excerpt Your AI coding agent passed the eval. But did the model know the answer, or did it find it somewhere on your machine? A correct answer can still invalidate your measurement. The post Your AI coding agent evaluation is only as good as its sandbox appeared first on Microsoft for Developers. ## How to Run Codex in an Ubuntu Virtual Machine on Proxmox DevFeed: [How to Run Codex in an Ubuntu Virtual Machine on Proxmox]() Original publisher: [Read original article]() Author: Travis Henderson Published: 2026-09-15T12:00:11Z Content type: tutorial Language: en Sources: [Atomic Object]() Topics: [AI-assisted coding](), [codex](), [Linux](), [Ubuntu](), [Proxmox](), [OpenSSH](), [Authorization]() Tags: [ai-agent](), [ai-for-developers](), [codex](), [coding-agents](), [development](), [linux](), [openssh](), [permissions](), [proxmox](), [sandbox](), [ubuntu]() ### AI overview This guide explains how to isolate Codex in a headless Ubuntu virtual machine running on Proxmox, using a separate Linux account and OpenSSH. The setup limits the files, dependencies, and network access available to the agent while keeping administrator tasks separate, but it does not eliminate risks from credentials, network access, or mistakes pushed to GitHub. ### Source excerpt The more useful coding agents become, the more access they tend to need. Installing dependencies, running commands, changing files, and generally more autonomy are part of the appeal. They're also the point where I start thinking about what else the coding agent can reach, especially while these tools are changing so quickly. My answer is [...] The post Your Coding Agent Should be in Jail. Here's Why and How. appeared first on Atomic Spin. ## Introducing Encore x E2B DevFeed: [Introducing Encore x E2B]() Original publisher: [Read original article]() Author: Ivan Cernja Published: 2026-09-15T00:00:00Z Content type: release Language: en Sources: [Encore Updates]() Topics: [AI-assisted coding](), [Cloud](), [backends](), [SDKs](), [Databases](), [Deployment](), [API](), [Code]() Tags: [agents](), [api](), [backend](), [cloud](), [code](), [coding](), [coding-agents](), [database](), [deployment](), [pull-request](), [sandbox](), [sdk]() ### AI overview Encore and E2B can provide coding agents with isolated sandboxes containing complete local backends. The integration lets agents build and verify end-to-end changes against infrastructure such as databases, queues, and APIs, while supporting deployment in the user's AWS or GCP account. ### Source excerpt Give coding agents an isolated sandbox with a complete backend inside it -- and keep both in your own cloud. ## Claude Managed Agents: How They Work and Where They Fit DevFeed: [Claude Managed Agents: How They Work and Where They Fit]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-09-14T11:29:41Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agent Harness](), [Claude](), [Artificial Intelligence](), [sdlc](), [context window](), [Network](), [Processes]() Tags: [agent](), [agents](), [ai](), [claude](), [context-window](), [infrastructure](), [network](), [platform](), [sandbox](), [sdlc](), [software](), [tools]() ### AI overview This article explains Claude Managed Agents, a hosted runtime and managed agent harness operated by Anthropic. It describes how the harness coordinates tools and execution, the sandbox provides isolated command and file access, and the session preserves durable task history outside the model's context window. It also discusses the additional platform layer needed to connect multiple agents across a business process and the SDLC. ### Source excerpt What Claude Managed Agents are, how the runtime works, and how platform teams connect several agents across the SDLC. ## Visual Studio Code 1.138 (Insiders) DevFeed: [Visual Studio Code 1.138 (Insiders)]() Original publisher: [Read original article]() Author: Visual Studio Code Team Published: 2026-09-12T11:03:34.159469Z Content type: release Language: en Sources: [Visual Studio Code - Code Editing. Redefined.]() Topics: [Visual Studio Code](), [releases](), [SDKs]() Tags: [agents](), [codex](), [release](), [release-notes](), [sandbox](), [vs-code]() ### AI overview Visual Studio Code 1.138 Insiders adds improvements to Agent Host sessions, including shareable links, adjacent sessions, repository context, voice awareness, SDK setup recovery, sandbox-policy consistency, and session cleanup controls. ### Source excerpt Learn what's new in Visual Studio Code 1.138 (Insiders) Read the full article ## How to Sandbox a Linux Process with Landlock, No Root Required DevFeed: [How to Sandbox a Linux Process with Landlock, No Root Required]() Original publisher: [Read original article]() Author: Chris Roy Published: 2026-09-11T21:42:27Z Content type: tutorial Language: en Sources: [freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More]() Topics: [Processes]() Tags: [c](), [gcc](), [how-to](), [kernel](), [linux](), [process](), [sandbox](), [security](), [selinux](), [ubuntu]() ### AI overview A hands-on guide to sandboxing a Linux process with Landlock without root privileges. It explains the kernel feature, prerequisites, its self-restriction model, and the system calls used to define and apply filesystem-access rules. ### Source excerpt Here's a program restricting itself, then trying to read two files: without landlock: read /etc/hostname ok read /tmp/secret.txt ok with landlock, /etc allowed: read ## OpenAI's researchers burned $7,000 a day on AI agents -- now it's opening the floodgates DevFeed: [OpenAI's researchers burned $7,000 a day on AI agents -- now it's opening the floodgates]() Original publisher: [Read original article]() Author: Amanda Caswell Published: 2026-09-11T21:27:42Z Content type: news Language: en Sources: [The New Stack]() Topics: [Inference](), [long-context]() Tags: [agents](), [ai](), [ai-agents](), [ai-infrastructure](), [api](), [cloud-services](), [codex](), [compute](), [developers](), [inference](), [openai](), [research](), [sandbox](), [tools]() ### AI overview OpenAI's public-beta Agents API lets developers run long-lived agents with managed job state, context compression, optional tools, parallel subagents, and execution in OpenAI's sandbox or developer-controlled infrastructure. The article highlights the resulting inference and compute costs, citing internal research-agent usage figures. ### Source excerpt OpenAI rolled out its Agents API in public beta Thursday, opening the backend behind Codex to developers looking to run The post OpenAI's researchers burned $7,000 a day on AI agents -- now it's opening the floodgates appeared first on The New Stack. ## What Is an Agent Harness? The Architecture Behind Claude Code, DeepSeek Harness, and Hermes Agent DevFeed: [What Is an Agent Harness? The Architecture Behind Claude Code, DeepSeek Harness, and Hermes Agent]() Original publisher: [Read original article]() Author: Rudrendu Paul Published: 2026-09-11T15:07:18Z Content type: tutorial Language: en Sources: [freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More]() Topics: [AI Bots](), [AI-assisted coding]() Tags: [agent](), [ai-agents](), [architecture](), [artificial-intelligence](), [claude-code](), [deepseek](), [developer-tools](), [llm](), [machine-learning](), [mcp](), [memory](), [python](), [sandbox](), [software-engineering](), [tools]() ### AI overview An explainer and hands-on guide to agent harnesses: the runtime infrastructure around an LLM that manages model calls, tool execution, memory, and filesystem sandboxing. It compares popular harnesses and introduces a small Python implementation. ### Source excerpt On August 13, 2026, DeepSeek published a GitHub repository called deepseek-harness. Within two days, it had passed 95,386 stars and 8,826 forks (a vanity metric on its own, but a spike this fast signa ## Vercel Sandbox now provides 64 GB of storage DevFeed: [Vercel Sandbox now provides 64 GB of storage]() Original publisher: [Read original article]() Author: Luke Phillips-Sheard Published: 2026-09-11T06:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [Vercel]() Tags: [agent](), [dependencies](), [documentation](), [sandbox](), [sandboxes](), [storage](), [vercel]() ### AI overview Vercel Sandbox storage has increased from 32 GB to 64 GB for all sandboxes, including those created from managed or custom images and those using the deprecated runtime property. ### Source excerpt Every Vercel Sandbox now includes 64 GB of storage, up from 32 GB. This includes sandboxes created from a Vercel Managed Image or custom image, as well as those configured with the deprecated runtime property. The additional space provides more room for large repositories, dependencies, build artifacts, data workloads that spill to disk, and storage-intensive agent tasks. Learn more about Sandbox images in the documentation. Read more ## How Tailscale built a customer-facing model router on AI Gateway DevFeed: [How Tailscale built a customer-facing model router on AI Gateway]() Original publisher: [Read original article]() Author: Susan Aziz Published: 2026-09-11T04:00:00Z Content type: article Language: en Sources: [Vercel News]() Topics: [AI Platform](), [networking](), [API keys]() Tags: [ai-gateway](), [ai-models](), [api](), [model-routing](), [sandbox](), [security](), [vercel]() ### AI overview Tailscale describes using Vercel AI Gateway and Sandbox to deliver customer-facing access to hundreds of AI models through tailnet identity. The article explains that provider integration and secure agent execution were complex enough that Tailscale chose managed routing and sandboxing instead of building those layers in-house. ### Source excerpt Tailscale on Vercel Hundreds of AI models shipped to customers in-product Model access granted and revoked by tailnet network identity Went from model routing prototype to paying customers in months Tailscale connects a company's laptops, servers, cloud instances, and personal devices into one private network called a tailnet. Remy Guercio, who leads product for Aperture by Tailscale, describes it simply: "It's basically like a VPC that can span any cloud, on-prem, your house, and your phone." Aperture takes that same idea and applies it to AI. Instead of giving every employee, agent, or tool a separate provider API key, Aperture lets companies control model access through the tailnet itself. Add someone to the network, and they can immediately use approved models. Remove them, and access disappears. Under the hood, Aperture is built on Vercel AI Gateway and Vercel Sandbox. AI Gateway gives Tailscale one API for hundreds of models. Sandbox gives agents a safe place to run. Together, they let Tailscale offer model access and agent execution inside a customer's private network, without their team building every piece of AI infrastructure from scratch. Model routing is harder than it looks Tailscale is an infrastructure company, so building the routing and execution layers in-house was the obvious first option. But once they took a deeper look into the engineering effort required, they chose not to. The provider layer looked deceptively simple from the outside. "You would think all of the endpoints are the same," Remy says. "They are not." David Carney, Co-founder and Chief Strategy Officer, has the receipts, because Tailscale still maintains that plumbing for a few customers who haven't migrated to Aperture yet. "There are a lot of things the big providers don't do that blow my mind that the gateway does, like simply putting the cost in the response," he says. "We initially built those systems for customers ourselves, and the complexity is insane." Agents raised the s ## Update Chrome now to protect against an actively exploited vulnerability DevFeed: [Update Chrome now to protect against an actively exploited vulnerability]() Original publisher: [Read original article]() Author: Pieter Arntz Published: 2026-09-10T10:52:08Z Content type: news Language: en Sources: [Malwarebytes]() Topics: [Vulnerabilities](), [bug]() Tags: [browser](), [bugs](), [chrome](), [javascript](), [memory](), [news](), [sandbox](), [security](), [stable-channel](), [update](), [vulnerability](), [webgl]() ### AI overview Chrome's desktop update fixes 230 security issues, including CVE-2026-87491, an actively exploited V8 out-of-bounds write flaw. The article explains how to update Chrome and describes the vulnerability's potential impact within the browser sandbox. ### Source excerpt Chrome issues another monster update, fixing an actively exploited V8 vulnerability and 229 other flaws. ## Introducing the Agents API DevFeed: [Introducing the Agents API]() Original publisher: [Read original article]() Published: 2026-09-10T00:00:00Z Content type: release Language: en Sources: [OpenAI News]() Topics: [AI Bots]() Tags: [agents](), [api](), [cloud](), [codex](), [developers](), [infrastructure](), [launch](), [orchestration](), [product](), [sandbox](), [tool]() ### AI overview OpenAI introduces the Agents API in public beta, providing a managed harness and infrastructure for building production-ready, long-running agents with tools and configurable compute environments. ### Source excerpt Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use. ## Build with OpenAI Agents API on Vercel DevFeed: [Build with OpenAI Agents API on Vercel]() Original publisher: [Read original article]() Author: Allen Zhou Published: 2026-09-10T00:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [AI Bots]() Tags: [agent](), [agents](), [api](), [architecture](), [code](), [guide](), [integration](), [openai](), [sandbox](), [scale](), [tool](), [vercel]() ### AI overview Vercel now supports building and deploying long-running, tool-using agents with the OpenAI Agents API. OpenAI manages agent loops and session state, while Vercel provides hosted applications, Sandbox execution, persistent workspaces, webhook and queue integration, and scale-to-zero operation. ### Source excerpt You can now build and deploy long-running, tool-using agents with the OpenAI Agents API on Vercel. OpenAI manages the agent loop and session state, while Vercel hosts the application and connects each session to Vercel Sandbox for code execution and file access. With this integration, you get: An OpenAI-managed agent loop and session state Reliable Sandbox creation and reconnection through signed OpenAI webhooks and Vercel Queues An isolated execution environment for every agent session A persistent workspace that retains files across follow-up instructions A scale-to-zero architecture without an always-on worker Follow the step-by-step guide to build and deploy an agent, or explore the sample application. Read more ## How Heurist Finance built an AI-native investment workbench on Amazon Bedrock AgentCore DevFeed: [How Heurist Finance built an AI-native investment workbench on Amazon Bedrock AgentCore]() Original publisher: [Read original article]() Author: JW Wang Published: 2026-09-09T18:11:12Z Content type: article Language: en Sources: [Artificial Intelligence]() Topics: [Amazon Bedrock](), [Claude](), [Orchestration](), [tracing]() Tags: [advanced-300](), [agent](), [ai](), [amazon-bedrock-agentcore](), [anthropic-claude](), [customer-solutions](), [identity](), [memory](), [observability](), [sandbox](), [tracing]() ### AI overview Heurist Finance uses Amazon Bedrock AgentCore to run a conversational investment workbench that accesses premium data per query and produces auditable, personalized research responses. ### Source excerpt Learn how Heurist built Heurist Finance, a conversational AI investment workbench, on Amazon Bedrock AgentCore. This customer story shows how AgentCore payments, Identity, Memory, Code Interpreter, and Observability let a small team buy premium market data per query, isolate analysis in a sandbox, and keep every action auditable. ## 6 Benefits of Sandbox Environments (and How Docker Sandboxes Delivers Them) DevFeed: [6 Benefits of Sandbox Environments (and How Docker Sandboxes Delivers Them)]() Original publisher: [Read original article]() Author: Kevin Wittek Published: 2026-09-08T23:05:55Z Content type: article Language: en Sources: [Docker]() Topics: [Docker](), [Authorization]() Tags: [agentic-ai](), [ai-agents](), [ai-ml](), [autonomous](), [concepts](), [docker-ai-governance](), [docker-sandboxes](), [linux](), [policy](), [products](), [sandbox](), [secrets]() ### AI overview The article explains how Docker Sandboxes isolate untrusted code and autonomous AI agents from host machines and external systems. It highlights runtime policy controls, credential handling, disposability, and microVM-based isolation. ### Source excerpt Learn about the key benefits of sandbox environments with Docker including isolation, definable controls, secrets credential handling, and more. ## Vercel Sandbox routing is now 18x faster globally DevFeed: [Vercel Sandbox routing is now 18x faster globally]() Original publisher: [Read original article]() Author: Andy Waller Published: 2026-09-08T20:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [networking](), [SDKs]() Tags: [latency](), [routing](), [sandbox](), [vercel]() ### AI overview Vercel Sandbox public-domain routing now resolves domains from the nearest regional replica, reducing median lookup latency from 62 ms to 3.4 ms. The change applies automatically and has no pricing changes. ### Source excerpt Requests to Vercel Sandbox public domains are now routed 18x faster. Domains created with the sandbox.domain() SDK call are now resolved from the nearest regional replica, instead of a single centralized store. Incoming requests reach the process running in the sandbox with less latency. Median domain lookup latency dropped from 62ms to 3.4ms (18x faster). The improvement is largest in regions farthest from the previous store: lookups are now up to 112x faster in Sydney (syd1) and up to 146x faster in Cape Town (cpt1), at p99. This applies automatically to every request to a sandbox domain. There are no pricing changes. Learn more about Vercel Sandbox in our documentation. Read more ## Introducing Encore x Daytona DevFeed: [Introducing Encore x Daytona]() Original publisher: [Read original article]() Author: Ivan Cernja Published: 2026-09-08T00:00:00Z Content type: release Language: en Sources: [Encore Updates]() Topics: [AI-assisted coding](), [coding](), [Cloud]() Tags: [agents](), [coding-agents](), [infrastructure](), [sandbox](), [tests](), [tools]() ### AI overview Encore and Daytona provide coding agents with isolated, persistent sandboxes for building and verifying complete backends against local infrastructure that mirrors production declarations. ### Source excerpt Let your coding agents build and verify against real infrastructure, inside a sandbox. ## How we closed 1,500 GitHub issues in one month DevFeed: [How we closed 1,500 GitHub issues in one month]() Original publisher: [Read original article]() Author: Marcos Hernanz Published: 2026-09-04T04:00:00Z Content type: article Language: en Sources: [Next.js Blog]() Topics: [GitHub Issues](), [Next.js](), [AI-assisted coding](), [issue tracker](), [Maintainers](), [bug]() Tags: [agent](), [ai](), [bug](), [github-issues](), [issue-tracker](), [maintainers](), [next-js](), [sandbox](), [vercel]() ### AI overview The Next.js team describes using an AI research agent to help maintainers review an issue backlog, close outdated reports, and retain issues that still matter. ### Source excerpt How the Next.js team used an agent to research old reports and work through the issue backlog. ## YOLO Mode: Agent Autonomy Without the Guardrails DevFeed: [YOLO Mode: Agent Autonomy Without the Guardrails]() Original publisher: [Read original article]() Author: Srini Sekaran Published: 2026-09-03T18:00:00Z Content type: article Language: en Sources: [Docker]() Topics: [AI-assisted coding](), [Authorization](), [Command-line interface](), [cursor](), [GitHub Copilot CLI](), [Claude]() Tags: [agentic-ai](), [ai-agent](), [cli](), [concepts](), [cursor](), [docker-ai-governance](), [docker-sandboxes](), [products](), [sandbox](), [secrets](), [security]() ### AI overview The article defines YOLO mode as allowing AI coding agents to auto-approve actions without confirmation prompts. It argues that the key risk depends on the execution environment and recommends isolated, disposable sandboxes with scoped access and no real secrets. ### Source excerpt YOLO mode lets an AI agent run without asking permission. Learn what it is, why it's risky, and how to run it safely. ## Cursor Cloud Agents can now run in Vercel Sandbox DevFeed: [Cursor Cloud Agents can now run in Vercel Sandbox]() Original publisher: [Read original article]() Author: Allen Zhou Published: 2026-09-03T15:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [cursor](), [Vercel](), [Agent Harness](), [Firecracker]() Tags: [agents](), [apis](), [architecture](), [cursor](), [enterprise](), [firecracker](), [guide](), [sandbox](), [scale](), [vercel](), [virtual-machines](), [workflows]() ### AI overview Cursor Cloud Agents can run in Vercel Sandbox, using isolated Firecracker microVMs as their execution environment. The architecture combines Cursor's agent harness and inference loop with Vercel Functions and Workflows for durable request handling, worker provisioning, monitoring, retries, cleanup, and short-lived user-scoped credentials. ### Source excerpt Cursor Cloud Agents can now run in Vercel Sandbox instead of Cursor's hosted machines. Cursor manages the agent harness and inference loop. Its Self-Hosted Machines APIs let you supply the execution environment where agents clone repositories, edit files, and run commands and tests. Self-Hosted Machines requires a Cursor Enterprise plan. Vercel Sandbox provides that execution environment as an isolated Firecracker microVM for each agent request. Vercel Functions and Vercel Workflows form a durable control plane that claims queued agent requests, provisions workers, monitors sessions, and cleans up automatically. With this architecture, you get: A scale-to-zero worker pool without long-lived virtual machines A dedicated, isolated Sandbox for every agent request Durable retries when a worker or session fails Short-lived, user-scoped credentials inside each Sandbox Follow the step-by-step guide to deploy the reference implementation to your own Vercel account, or learn more in the Vercel Sandbox documentation. Read more ## Building Reproducible AI Evaluation Workflows with Docker Sandboxes DevFeed: [Building Reproducible AI Evaluation Workflows with Docker Sandboxes]() Original publisher: [Read original article]() Author: Jennifer Kohl Published: 2026-09-02T13:00:00Z Content type: tutorial Language: en Sources: [Docker]() Topics: [ai observability](), [Human-AI evaluation]() Tags: [ai](), [ai-agent](), [ai-ml](), [ai-models](), [benchmarks](), [claude](), [community](), [docker](), [docker-sandboxes](), [evaluation](), [genai](), [json](), [open-source](), [python](), [sandbox](), [sandboxes](), [workflow](), [workflows]() ### AI overview The article presents an open-source Docker Sandboxes Mixin Kit for making AI evaluation workflows reproducible. It runs configured commands in a consistent environment and records structured results and runtime evidence, without executing models or generating evaluation judgments itself. ### Source excerpt Learn how Docker Sandboxes can make AI evaluation workflows more reproducible with consistent execution, structured artifacts, and runtime evidence. ## Critical remote code execution in vm2, a widely used Node.js sandbox library DevFeed: [Critical remote code execution in vm2, a widely used Node.js sandbox library]() Original publisher: [Read original article]() Author: Daniel Abeles Published: 2026-09-02T00:00:00Z Content type: news Language: en Sources: [GitLab]() Topics: [vulnerability](), [Node.js](), [configuration](), [Threat Research]() Tags: [ai](), [containers](), [node-js](), [processes](), [sandbox](), [security](), [security-labs](), [threat-research](), [update](), [vulnerability]() ### AI overview GitLab reports a critical vm2 sandbox escape that can enable remote code execution. Version 3.11.7 blocks the reported attack, but the article advises hardening require.root and context settings and avoiding vm2 for truly untrusted code. ### Source excerpt GitLab's Threat Research Group found a critical sandbox escape vulnerability in vm2, one of the most widely adopted Node.js sandboxing libraries. The vulnerability uses a configuration copied straight from vm2's own README. We found the flaw, rated CVSS 3.1: 10.0, critical, using our own AI automated tools. Anyone running vm2 Version 3.11.6 or earlier with require.external turned on should treat this as directly exploitable. Once we found the vulnerability, we verified GitLab does not use vm2. We also reported it privately to vm2 and the maintainer fixed it fast, in vm2 Version 3.11.7. When we tested that fix again, it blocked the exact attack we reported. For anyone relying on vm2, it's worth flagging that there's a broader configuration risk here that goes beyond this one patch, based on the maintainer's own description of the fix. TL;DR Critical vulnerability: GitLab's Threat Research Group discovered a critical sandbox escape (CVSS 3.1: 10.0) in vm2, a widely used Node.js sandboxing library, which allows for remote code execution. The root cause: The vulnerability stems from default configurations found in the library's own "Quick Examples" README, where the sandbox fails to properly isolate itself from the host system, allowing malicious code to gain unrestricted access. Fix limitations: While updating to Version 3.11.7 blocks the specific attack reported, it does not fully resolve the underlying configuration risk; developers remain vulnerable if they continue to use require.external with overly broad require.root settings. Immediate recommendations: Users should update to Version 3.11.7, but must also manually harden their configurations by restricting require.root to only necessary files and setting context: 'sandbox' instead of relying on the default 'host' setting. Long-term advice: Due to vm2's history of recurring sandbox escape bugs, it is recommended to avoid using it for isolating truly untrusted code and instead opt for more robust methods like conta ## Compute that takes any shape DevFeed: [Compute that takes any shape]() Original publisher: [Read original article]() Author: Luke Phillips-Sheard Published: 2026-09-01T07:00:00Z Content type: article Language: en Sources: [Vercel News]() Topics: [Cloud](), [Provisioning](), [cloud-infrastructure](), [Vercel](), [cpu](), [IO](), [DRIVE]() Tags: [agent](), [cloud](), [code](), [compute](), [cpu](), [image](), [infrastructure](), [io](), [memory](), [pricing](), [real-time](), [sandbox](), [storage](), [vercel]() ### AI overview Vercel presents Fluid as a unified compute system that assembles machines for different workloads, changes configuration dynamically, and absorbs burst capacity in real time. It supports builds, sandboxes, and functions, using isolated virtual machines, custom images, and separate storage connections. ### Source excerpt Workloads differ in how long they run, how much memory they take, and how much of the environment they control. That previously meant a different compute primitive for each job, so product iterations required provisioning infrastructure, not just working on a feature. We built Vercel so that none of this has to be your problem. The compute layer is a single system with a simple job. Take any workload, assemble the machine it needs, swap configuration on the fly, and absorb burst capacity in real time. We call this Fluid. Builds ran on it first, then sandboxes, and now functions. If you've shipped on Vercel, you've been on Fluid without knowing it. Fluid compute now runs over 15 million builds a day, 25 million sandboxes a week, and a trillion requests a month. A history of compute Changing a machine used to mean changing it by hand. You went down to the computer store, bought a hard drive or a stick of RAM, and swapped it in yourself. Then you could rent bare metal when you needed it, and use it to serve a website, host a database, or send email. Then the cloud let you request a machine in any configuration you wanted, choose its operating system, use it, and throw it away when you were done. For agents, even the cloud is too slow. A standard VM can't provision fast enough to keep up with how they work, but this is where Fluid excels. How a workload runs on Fluid When a workload comes in, Fluid assembles a machine to fit its shape. If an agent needs to run code, Hive provides an isolated VM, usually one already warm, so it's ready instantly. Your own image boots on top as the environment. A Drive connects, and your files are right where you left them, because storage was never tied to the machine. Each workload needs something different. A build is compute-bound, so it wants a beefy machine, heavy on CPU and memory. A function is IO-bound, loading specific code to run the instant a request lands, usually on a small VM. A sandbox is flexibility-bound, taking whatever ## Prison-Break Comedy Sandbox Bad Inmate Coming Soon To Quest & PlayStation VR2 DevFeed: [Prison-Break Comedy Sandbox Bad Inmate Coming Soon To Quest & PlayStation VR2]() Original publisher: [Read original article]() Author: James Tocchio Published: 2026-08-31T15:43:03Z Content type: news Language: en Sources: [UploadVR]() Topics: [simulator]() Tags: [games](), [physics](), [release](), [sandbox](), [simulator](), [vr-gaming]() ### AI overview HyperVR Games announced that Bad Inmate, a physics-driven comedic prison-break sandbox game, will launch for Meta Quest and PlayStation VR2 on October 15. A SteamVR release is planned, but its date has not been announced. ### Source excerpt The physics-driven comedic prison-break sandbox game is coming to Quest and PlayStation VR2 in October. [Next page]()