Anthropic releases sandbox-runtime for AI agents
MarkTechPost: Meet Anthropic’s sandbox-runtime: OS-Level Sandboxing for AI Agents, No Containers
In this article, we will discuss newly trending open sourced Anthropic’s sandbox-runtime (srt), the OS-level sandbox behind Claude Code’s sandboxed bash tool. The Anthropic sandbox-runtime limits which files a process can touch and which hosts it can reach. It does this without spinning up a container. It is also not tied to Claude Code. Your own agents, local MCP servers and plain command-line programs can run inside it. TL;DR Size: npm package @anthropic-ai/sandbox-runtime
Get smart on it
Sandbox-runtime is an open-source tool that restricts which files and network hosts a process can access by using each operating system's built-in isolation features rather than containers. It matters because it reduces the number of permission prompts developers must approve when running AI agents, with one internal report showing an 84% reduction in such prompts. The tool works on macOS and Linux by default, with Windows support still in early stages, and can sandbox not just AI agents but any command-line program or script. Security requires both filesystem and network boundaries together, since a compromised agent could otherwise steal data like SSH keys or escape restrictions to access the network.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
OpenAI models are coming to Google Cloud
OpenAI and Google Cloud are bringing frontier models and Codex workflows to Gemini’s Model Garden, available through Google Cloud Marketplace.
Also reported by Ars Technica, The Decoder and SiliconANGLE
Only 13 percent of companies see real returns from AI, Gartner survey finds
Only 13 percent of companies are getting real business value from their AI investments, according to a Gartner survey of 2,002 CIOs. At the same time, 51 percent expect AI to actually increase their operating costs. Yet 75 percent of CEOs plan to keep raising their technology budgets. So far, strategic conviction is beating measurable results. The article Only 13 percent of companies see real returns from AI, Gartner survey finds appeared first on The Decoder.
Major US banks are locking out AI agents that log in with customer credentials
Customers are letting AI agents use their credentials to access accounts at Morgan Stanley, JPMorgan, and other major U.S. banks, sometimes without direct instructions. Morgan Stanley has blocked agents, while other banks are restricting access. Most plan to limit agents to read-only access. The article Major US banks are locking out AI agents that log in with customer credentials appeared first on The Decoder.
Anthropic's Claude now writes code and proves it safe automatically
Anthropic had Claude generate mathematical proofs that existing code is correct, producing roughly 180 million lines of proof code for 123 open-source libraries. Along the way, the model caught bugs that years of testing had missed. Anthropic's goal: making formal verification with AI as routine as standard testing. The article Anthropic's Claude now writes code and proves it safe automatically appeared first on The Decoder.
Claude Duet app is Anthropic’s bet on agents
Claude Duet is available through waitlist for Pro and Max plan users
Also reported by The Verge and SiliconANGLE
Uber brings ChatGPT Work to all employees with OpenAI
Uber is rolling out ChatGPT Work to more than 30,000 employees, helping teams research, analyze data, create presentations, and complete complex workflows.
Also reported by TechCrunch