New Delhi, Aug. 28 -- Anthropic has rolled out a research preview of "Model Hardware Standard" (MHS) to enable AI agents to safely operate multiple physical devices used in scientific research and manufacturing. It plans to publish research findings and safety guidance when the standard is open-sourced, according to a company release.

The standard allows agents to coordinate instruments including -- microscopes, liquid handlers and robotic arms -- simultaneously and perform complex tasks, ranging from routine drug discovery experiments to laser calibration for quantum computers.

MHS is compatible with any device with a programmable interface and is model-agnostic, allowing AI agents to access it through standard protocols such as the Mo...