Skip to content
AI News HubLIVE
Source content · Analysis pending1 min read

Quoting Felix Rieseberg

Summary

The "old" version of Cowork runs model inference in the cloud, executing tool calls in an Anthropic-provided VM we shipped to your computer. We added the VM for capability, safety, and security reasons - mapping in just the data you explicitly added to your session. People loved what they were able to do with Claude but didn't love the disk, battery, and performance cost of running the VM locally. Also, people didn't love that closing your laptop means the work stops. The "new" version of Cowork runs model inference and the VM in the cloud. Each session gets its own sandbox, not sharing state with other sessions. When the VM needs something on the users' device (like a file), the desktop app is responsible for that file access tool call. [...] We think this solves a lot of problems we've…

Quoting Felix Rieseberg
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

A quote from Felix Rieseberg

Simon Willison’s Weblog

Subscribe

5th October 2026

The "old" version of Cowork runs model inference in the cloud, executing tool calls in an Anthropic-provided VM we shipped to your computer. We added the VM for capability, safety, and security reasons - mapping in just the data you explicitly added to your session. People loved what they were able to do with Claude but didn't love the disk, battery, and performance cost of running the VM locally. Also, people didn't love that closing your laptop means the work stops.

The "new" version of Cowork runs model inference and the VM in the cloud. Each session gets its own sandbox, not sharing state with other sessions. When the VM needs something on the users' device (like a file), the desktop app is responsible for that file access tool call. [...]

We think this solves a lot of problems we've heard about (like using Cowork from a phone, keeping work running, or getting all the same power without losing battery to the VM)

— Felix Rieseberg, Anthropic, see also this help page

Recent articles

We're going to need default hard budget caps on pretty much everything - 3rd October 2026

OpenAI DevDay 2026 live blog - 29th September 2026

2026 in LLMs (so far) - 27th September 2026

This is a quotation collected by Simon Willison, posted on 5th October 2026.

ai 2,261

generative-ai 2,004

llms 1,971

anthropic 345

claude 315

claude-cowork 4

general-agents 16

Disclosures

Colophon

©

2002

2003

2004

2005

2006

2007

2008

2009

2010

2011

2012

2013

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023

2024

2025

2026

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • The "old" version of Cowork runs model inference in the cloud, executing tool calls in an Anthr…

Highlights and analysis are generated automatically and may contain errors. Check the original source.

Quoting Felix Rieseberg | AI News Hub