待翻譯：Anthropic previews MHS standard for AI agents that operate machines

AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。

Anthropic PBC today previewed a standard that makes it easier for artificial intelligence agents to control machines such as microscopes. The Model Hardware Standard, or MHS, is the fruit of a collaboration between the Claude developer and medical research institute HHMI. Anthropic has so far only made the technology accessible to a limited number of partners. It will work with those early adopters to develop safety features before making MHS broadly available. The scientific instruments in a lab must precisely coordinate their work to avoid errors. For example, measuring the number of proteins in a biological sample requires multiple machines to process the object in a specific order. Implementing such automation workflows requires researchers to write custom code. Writing code for scientific instruments is difficult because each machine has a different application programming interface. Researchers must individually learn each API. Furthermore, they must account for the fact that those APIs often aren’t compatible. One machine may only support Python code while another might use Java. MHS aims to ease scientific instrument programming by replacing disparate device-specific APIs with a single, unified interface. That interface provides a standardized set of configuration commands. Coordinating machines that all take the same commands is simpler than navigating device-specific configuration rules. Notably, MHS eases scientific instrument programming to the point that AI agents can take over the task. HHMI, the research institute with which Anthropic developed the standard, built an AI agent that automatically manages microscopes. Startup QuEra Computing Inc. is using MHS and Claude to coordinate the lasers with which it programs its quantum computers. Anthropic says that the standard enables agents to automatically fix certain experiment errors. Furthermore, agents can write instrument control scripts. In one internal test, Anthropic had Claude generate a script that automatically adjusts the position of lasers. Such scripts cost less to run than an inference-based device configuration workflow. MHS also provides other automation features. According to Anthropic, it enables researchers to create a file that describes the key properties of each instrument. A scientist could specify the weight of a robotic arm or the wavelengths that a sensor can detect. Such data points help AI agents identify the best way of using each machine and avoid configuration mistakes. Researchers can further reduce the risk of errors by defining safety guardrails. For example, a lab could set a limit on the strength of laser beams used in microscopy projects. Excessive illumination can damage some samples and thereby compromise experiment results. Anthropic plans to make MHS available under an open-source license. The AI provider says that the standard will enable agents to control not only scientific instruments but also manufacturing equipment. Amazon Web Services Inc., Hugging Face Inc. and several industrial robot suppliers are currently working to integrate MHS with their products. Image: Anthropic A message from John Furrier, co-founder of SiliconANGLE: Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities. 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network Are you an AWS customer? Support SiliconANGLE financially by buying your AWS services from our Marketplace portal page and links: https://siliconangle.com/aws-marketplace/ About SiliconANGLE Media