Anthropic has introduced a research version of the Model Hardware Standard (MHS), a new universal framework that allows AI agents to directly interact with physical equipment in scientific research and high-tech manufacturing.
Anthropic has introduced a research version of the Model Hardware Standard (MHS), a new universal framework that allows AI agents to directly interact with physical equipment in scientific research and high-tech manufacturing.
MHS allows AI agents to control laboratory and manufacturing equipment — such as microscopes and robotic manipulators — and perform complex tasks: from routine experiments to find new drugs to laser calibration on a quantum computer, Reuters reports .
The main goal of Anthropic is to help scientists and engineers automate complex, multi-step processes. AI agents will be able to perform routine experiments or debug lines 24/7 without constant human intervention. This should significantly accelerate the discovery of new drugs and the development of new technologies.
As stated by Anthropic, this standard works on any device with a programmable interface and allows devices and agents to interact with each other over the network.
The standard is not limited to the Claude family of models, but can be used by other AI systems. Anthropic has already provided early access to MHS to a limited number of partners to jointly test security protocols. Once the risk assessment is complete, the company plans to make the framework fully open.
