Anthropic said on Thursday (August 27) it is opening a research preview of the Model Hardware Standard (MHS). It’s a shared specification for AI agents to safely operate physical devices used in scientific research labs and by advanced manufacturers. Anthropic plans to publish research findings and safety guidance when the standard is open-sourced, according to a company release.
What is MHS?
Model Hardware Standard or MHS enables AI agents to operate multiple lab and manufacturing instruments, such as microscopes, liquid handlers, and robotic arms, in parallel.
It can perform complex tasks ranging from routine drug discovery experiments to laser calibration on a quantum computer, Anthropic said in its release.
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 Model Context Protocol.
“We’re sharing an early version of MHS with partners across science, robotics, electronics, and manufacturing so we can collaborate to build safety evaluations and develop best practices for AI systems operating physical equipment, ahead of making the standard open source.” Anthropic said.
The development of MHS started as a partnership between Anthropic and HHMI Janelia Research Campus.
From hours to minutes
As per Anthropic, setting up and integrating hardware in laboratories and manufacturing facilities can take weeks or even months, as most devices do not communicate with one another and require custom integrations.
The official release stated, “It typically takes a lab or manufacturing facility weeks, if not months, to set up and integrate their hardware. Most devices don’t communicate with each other, instead requiring specialists to build bespoke integrations.”
“MHS reduces this integration work to hours or minutes,” it added.
“And by incorporating AI into these tools, MHS also helps researchers and engineers more readily orchestrate autonomous, round-the-clock experiments and workflows, with agents able to reason through each step in an experiment, update parameters in real time, and, in some cases, recover from hardware errors without intervention,” Anthropic said.
Across its early projects, Anthropic found that MHS reduced device integration time, enabled faster iteration across different experimental settings, and supported live machine operations and real-time fault detection, as per the release.
It is worth noting, following its testing of MHS, Anthropic found that Claude interacts with experiments and hardware in an exploratory manner, similar to how a scientist would.
“We are only just beginning to see what people can do with frontier models and MHS, but our hope is that the standard can be of use to researchers, engineers, and other practitioners in speeding up the process of discovery and experimentation in any domain that uses devices with a programmable interface,” it said.
The challenge: Communication between devices
Anthropic said that getting multiple devices in a lab or on a factory floor to communicate with one another can be challenging, even setting aside the added difficulty of integrating AI into the setup.
Each device tends to have its own programming interface, and so far, there has been no standardised way to integrate them. “And once the devices are connected, there is no common way for them to share data with an AI agent, nor to let the agent operate them safely,” the company added.
MHS addresses these challenges by introducing a standardised driver: software that translates between a computer’s operating system and a hardware device.
The MHS driver uses a simple set of primitives—commands like “read” (for example, “get temperature”) or “write” (for example, “set temperature”)—that any hardware device can understand and act on.
And it makes each device discoverable in a standard format, so that devices and agents can find each other and communicate across networks without needing a bespoke “translator” program in between.
The MHS driver also helps an AI agent understand how to use a device it has never seen before, giving it information about machine characteristics that may not be discernable from code alone (for example, the weight of a robot arm, which is important for knowing how to manipulate it safely).
Additional safety measures
Anthropic is developing additional safety measures to address potential misuse of AI agents operating physical equipment and planning to publish findings from the research preview and safety guidance when it makes MHS open source.
“We will also use the research preview to build additional safety evaluations with our launch partners and strengthen protections for the use of AI in the physical world. We are developing a physical safety roadmap to further bolster our safeguards policy and enforcement coverage against the risk of misuse. When we open-source MHS, we will release findings from the research preview as part of our guidance for deploying the standard safely,” it said.
The company added, “We’re inviting stakeholders across industries to join the waitlist for our research preview of MHS,” it said.
Leave a Reply