Anthropic tests new way for Claude to work with robots and scientific lab tools
The new software standard essentially stores information for artificial intelligence assistants to understand how a piece of hardware works.
Anthropic, an AI startup, has unveiled a new standard called Model Hardware Standard (MHS) that enables artificial intelligence assistants like Claude to interact more effectively with robots and scientific lab tools. This research preview is aimed at developers in the scientific, robotics, and manufacturing industries, allowing them to test how Claude operates in the physical world and implement necessary safety measures before a wider release.
Essentially, MHS functions as a knowledge repository for AI assistants, storing information about how various hardware components function without relying on paper manuals or the tacit knowledge held by a small group of experts. For instance, a vendor of factory robot arms could provide specifications within MHS to guide AI in safely manipulating these heavy arms, such as limiting the arm's speed or movement angles.
Written by urgent.news from Japan Times's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
