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.
Quoting Felix Rieseberg
About this summary. This is a short excerpt from the description that Simon Willison published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://simonwillison.net/2026/Oct/5/felix-rieseberg/
Source attribution: headline and facts are from Simon Willison (simonwillison.net). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
From Hype to ROI: An Economic Model for LLM Adoption in Information Systems and Security Operations
arXiv:2610.33352v1 Announce Type: new Abstract: Large Language Models (LLMs) promise significant efficiency gains across information-intensive operations by automating…
Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs
arXiv:2610.32079v1 Announce Type: new Abstract: Edge-cloud split inference runs the early layers of a multimodal large language model (MLLM) on a device and sends…
Quoting Terk Terkowitz
If your work does not benefit from current AI tooling, that is a finding, not a failing. Document why, share it with your community of peers, bring it to your manager…
n0n Ransomware: Inside an AI-Assisted Extortion Operation
In September 2026, the SOCRadar Threat Research Unit (STRU) discovered an exposed staging server holding the live workspace of an operator tied to the n0n ransomware…
Merkle-Tree-Based Verifiable Public Data Auditing for Cloud Object Storage Using Smart Contracts
arXiv:2610.36001v1 Announce Type: new Abstract: Owners of data in cloud object storage cannot directly check whether the provider still keeps every object unchanged…
Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol
arXiv:2610.36108v1 Announce Type: new Abstract: LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadata…