Claude Controls Lab Gear: Laser Fix Rate Hits 99.3% in Tests
chrismattmann · x · 2026-08-28
Anthropic launched the Model Hardware Standard (MHS) research preview, enabling AI agents to safely operate physical equipment. Early cases show Claude handling microscopes and robotic arms:
- QuEra Quantum: Claude fixed quantum computer lasers autonomously, reducing a 5-10 minute task to 6 seconds with success rates jumping from 58% to 99.3%.
- Genentech: Claude self-optimized liquid pipetting settings, converging on expert baselines.
- Automation: University labs achieved 4 AM autonomous plate swapping; Claude ran qPCR experiments to detect sewage contamination.
Automated science labs are closer than expected, marking a strong return for Anthropic in the agent space.
Related event: Claude Learns to Control Lab Equipment with 99.3% Laser Calibration Success(2 posts)→
More from coding & agent
- Google Antigravity Teamwork Agent Solves Open Math Problems, Simulates CPU — behrouz_ali · 2026-08-28
- OpenCode Go aims to make AI agents accessible, nearing economic model clarity — ycombinator · 2026-08-28
- Dev suggests Amp Orbs should allow choosing the base OS for true remote development — bytebot · 2026-08-28
- AI agents need a different security model than chatbots — vasiliyivanov · 2026-08-28
- Benzi coding agent reads less source code, hits 78.2% on SWE-bench for under 10 cents a fix — DonkeyTheKing · 2026-08-28
- One-shot an entire business with Claude Code, then sell it as a Whop Blueprint for recurring cut — EXM7777 · 2026-08-28