Quoting Felix Rieseberg
- ID
- 32092
- Status
- summarized
- Published
- 06 Oct 2026, 7:56 AM
- Fetched
- 06 Oct 2026, 8:04 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Oct/5/felix-rieseberg/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 6.5
- Created
- 06 Oct 2026, 8:04 AM
- Tags
- Audience
- developersai_agent_usersai_ml_learners
What happened
In a quote collected by Simon Willison on 5 October 2026, Felix Rieseberg describes a change to Anthropic's Cowork: the old version ran model inference in the cloud but executed tool calls in an Anthropic-provided VM shipped to the user's computer, while the new version runs both model inference and the VM in the cloud, giving each session its own sandbox that does not share state with other sessions. When the VM needs something on the user's device, such as a file, the desktop app is responsible for that file-access tool call. Rieseberg cites user complaints about the local VM's disk, battery and performance cost, and about work stopping when the laptop is closed.
Why it matters
This is a concrete agent architecture pattern you can copy or argue with: session-scoped cloud sandboxes plus a thin desktop client whose only job is brokering device file access. It removes the local VM's disk/battery cost and lets a session keep running after you close the laptop, but it also means session state and the sandbox now live on Anthropic's side, not yours — so if you were relying on agent work happening on the local machine, or need to reason about where session data sits, that assumption changes with this release.
Discussion angle
Compare per-session ephemeral cloud sandboxes against persistent local VMs: what breaks first when agent state moves off the device — long-running jobs, cost per session, or data-location requirements for teams that have to care where the sandbox runs?