Anthropic MHS: Standard for AI to control lab hardware
AI寒武纪 · wechat · 2026-08-28
Anthropic launched the Model Hardware Standard (MHS) preview, enabling AI agents to safely control physical lab and manufacturing hardware. MHS standardizes drivers and basic commands (read/write), solving the fragmentation of vendor interfaces. It features auto-discovery, natural language input for physical parameters/safety limits, and control via MCP/CLI/API.
Early use cases:
- Genentech: Claude automated BCA assays, tuning pipette speeds to prevent bubbles (140µL/s for water) and recovering from tip failures.
- UW: Real-time qPCR monitoring stops reactions automatically; LeRobot arm swaps plates in 10s without collision.
- HHMI Janelia: Brain imaging cycle reduced from weeks to one day.
- QuEra: Quantum computer laser stability improved from 58% to 99.3%.
Partners include AWS, Tecan, Universal Robots, Danaher, and Hugging Face LeRobot.
More from Embodied
- Viral meme nails AI's irony: it can write symphonies but can't do the dishes — briannekimmel · 2026-10-16
- WEDGE turns navigation agents' own failures into targeted training worlds — mohitban47 · 2026-10-16
- Knödel Watch: animated vocabulary cards on ESP32-S3, open-sourced 4 days after unboxing — alexcovo_eth · 2026-10-16
- NVIDIA RTX Spark PC launches tomorrow with global events and strong early reviews — NVIDIA Blog · 2026-10-16
- SlipSense fuses pressure and vibration for 23ms zero-shot robotic slip detection — micoolcho · 2026-10-16
- Stanford's Fei-Fei Li team open-sources OpenWAM, a unified world-action model framework for robots — jiqizhixin · 2026-10-16