Human Tissue Models, Physical AI, and the Future of Testing

In this episode

Vivodyne’s Andrei Georgescu explains how vascularized human tissue models, robotics, multi-omic measurement, and foundation models could improve drug testing before clinical trials. Archetype AI’s Nick Gillian discusses Newton, a Physical AI model that combines sensor data to understand and predict events in the real world; the hosts also examine AI product safety, OpenAI and Anthropic’s alignment philosophies, CRISPR research, and whether AI can deliver useful advances in biology before it is fully understood.

• AI safety is not just about extinction scenarios—it also means making everyday AI products safe, reliable, and accountable. The hosts debate who should own product safety, why labs may be philosophically confused about model behavior, and how AI agents could change consumer power.
• Human tissue models could expose drug toxicity and efficacy problems before clinical trials. Andrei Georgescu explains how Vivodyne combines vascularized tissues, robotics, multi-omic measurement, and foundation models to test therapies at scale and guide better experiments.
• What is Physical AI, and how can one model understand machines, factories, and entire ecosystems? Nick Gillian explains how Archetype AI’s Newton model fuses radar, cameras, lidar, and time-series data to detect anomalies, predict safety events, and control physical systems in real time. The conversation covers sensor alignment, zero-shot adaptation, edge deployment, industrial productivity, and the bridge between digital and physical agents.
• Can AI create useful medical breakthroughs before scientists fully understand biology? This closing conversation examines specialist models, scientific discovery, CRISPR research, and why biology may deliver practical value before complete causal understanding.