Simon Willison tests smolvm: hardware-isolated sandbox with 0.6s cold starts
yawnxyz · x · 2026-08-24
Simon Willison tasked Fable 5 in Claude Code for web with stress-testing smolmachines/smolvm as a fast, secure sandbox.
- Verdict: smolvm 1.8.3 is well suited for sandboxing untrusted Python/JS using hardware-isolated VMs rather than shared-kernel containers.
- Verified: offline local images, no-network execution, CPU/RAM limits, guest-enforced timeouts, storage quotas, read-only input mounts, writable output mounts, and --unprivileged all worked as intended.
- Performance: cold starts 0.6–1.5s, warm executions 50ms.
- Twist: the Claude Code container lacked /dev/kvm (no nested virt), so the agent pivoted to a GitHub Actions runner with KVM to run the full test battery — a notable display of agent autonomy in itself.
Related event: Simon Willison Tests smolvm's Hardware-Isolated Sandbox(2 posts)→
More from coding & agent
- Superconductor launches Linear integration: assign issues straight to coding agents — sergeykarayev · 2026-10-16
- Vercel Daemons enters public beta: background workers pulling from queues and DBs — cramforce · 2026-10-16
- Ferryman: solo-built cross-posting SaaS charges $30-$100/mo, syncs via Claude and Codex — KevinNaughtonJr · 2026-10-16
- Confusing Gemini site promises one-click Antigravity but delivers a dead end — dreamwieber · 2026-10-16
- Alibaba's Qoder adopts Unified Harness Protocol, an open standard for agent backends — nevrekaraishwa2 · 2026-10-16
- Vercel Drives is GA: persistent storage lets stateful agents survive environment changes — evilrabbit_ · 2026-10-16