I gave codex a video-enabled remote KVM so it can automate e2e test the iMessage-integration on OpenClaw.
(iMessage is unreliable in VMs, and certain features such as read receipts require SIP to be disabled)
Peter Steinberger described giving OpenAI's Codex access to a video-enabled remote KVM, a connection for viewing and controlling another computer, to automate testing of OpenClaw's iMessage integration. His post attributes the setup to iMessage's unreliability in virtual machines.
The useful idea is to give the coding AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → access to the environment where the integration actually needs to work. The post describes a testing arrangement, without reporting completed test coverage or a pass rate.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.