AI Coding Live News

Anthropic kicked off phase one of the Model Hardware Standard (MHS) research preview: a proposed interface so AI agents can safely operate scientific and advanced-manufacturing equipment. The company said MHS currently best covers lab and manufacturing gear, and that many developers are already using Claude Code to drive hardware such as boards and cameras. The research preview is intended to bring those devices under one interface rather than one-off scripts per instrument. For coding-agent vendors, this is a concrete expansion of the agent surface area from repositories, terminals, and browsers onto physical equipment, with safety and discoverability as first-class constraints. Anthropic published a dedicated news post and a collaboration story with HHMI on how the standard began. Teams already letting Claude Code touch cameras or lab controllers are the intended early adopters.

Anthropic opened the first research-preview phase of the Model Hardware Standard (MHS), a shared interface so AI agents can discover and safely operate physical lab and manufacturing equipment.

Anthropic kicked off phase one of the Model Hardware Standard (MHS) research preview: a standard so AI agents can safely operate scientific and advanced-manufacturing equipment. Bespoke hardware integration that took days or weeks is cut to hours or minutes, with discoverable devices and safer control. Early tests: real-time error handling on a Genentech drug-discovery run, compressing an HHMI Janelia imaging experiment from weeks to a day, and lifting QuEra laser stabilization from 58% to 99.3%. Developers already using Claude Code on boards and cameras are the next devices MHS aims to cover.