Lessons from months building an automated tissue lab: AI helps, hardware bottlenecks
vqctran · x · 2026-11-09
FabioZBI shares takeaways from months building an automated lab for tissue manufacturing:
- Software and AI handle much of the troubleshooting and integrate instruments in previously impossible ways — but for advanced out-of-distribution workflows the bottleneck quickly shifts to hardware: temperature control, dead volumes, latency.
- As more powerful non-destructive measurement modalities come online, workflows must be redesigned around them, making lean process planning critical.
- Teams building truly novel simulations can't be far from the data generation engine — their "AI scientists" work in the lab alongside tissue engineers.
A hands-on retrospective on AI for Science and lab automation.
More from Embodied
- MoRE: Mixture-of-Experts 3D World Model Handles Rigid, Plush and Cloth Objects for Real Robots — anand_bhattad · 2026-11-09
- Billion-dollar Physical AI startups are coming, and most won't build their own hardware or models — Scobleizer · 2026-11-09
- Maker Spends $15,000 of His Own Money to Give 100 People Free Robot Kits — broodsugar · 2026-11-09
- Living Off Voice-Generated Dynamic Cards on an AI Wearable Pendant — EricBuess · 2026-11-09
- Austin streets now full of legit self-driving cybercabs, researcher says — chris_j_paxton · 2026-11-09
- CoRL sells out as robotics+intelligence becomes the conference to attend — chris_j_paxton · 2026-11-09