Blog · Tag

Safety

1 post tagged Safety.

June 6, 2026 · Leif

Give the agent its own VM

Where you let an autonomous AI agent run matters more than what you let it do, and isolation is what buys you the freedom to give it real autonomy.

Other tags

Agents 11 Using AI 7 Trust toolchain 4 Building in the open 3 Manifesto 2 Workflow 2 attest 1 augur 1 fledge 1 Local-first 1 Merlin 1 Philosophy 1 Quill 1 Spec-driven development 1 Tooling 1 Verification 1