Anthropic previews Model Hardware Standard to let AI agents run lab instruments

ivan_bezdomny · x · 2026-09-16

Anthropic has opened a research preview of the Model Hardware Standard (MHS), a shared specification that lets AI agents safely operate physical devices, starting with a group of scientific labs and advanced manufacturers.

The author also notes Anthropic runs a program for AI controlling hardware and experiments (biology-focused), part of a broader push into AI for science.

Original post →

More from coding & agent

coding & agent channel →