Real-time Experiments with an AI Co-Scientist
summary
Demo combines a low-cost, portable lab (under $300) built with micro:bit + JackDAC, webcams and a mobile REC camera tracking running on-device models, a React front end, and the Gemini API to close the loop on live experiments. It streams temperature, images and CSVs, plots real-time curves, and finds that salt crystal nucleation happens in sudden bursts. Systems for adaptive reaction monitoring, vision-guided assembly, and fermentation run end-to-end and the prototype works as a reproducible open-source lab-in-a-box.
AI-written summary · about
chapters (7)
- 0:00Introduction and demo setup
- 3:35From demo to real-time co-scientist
- 7:13Why real-time AI co-scientist matters
- 10:26System architecture and hardware
- 13:58Crystal growth experiments insights
- 15:24Open-source tools and future work
- 17:57Summary and Q&A
related talks
23mExperimenting with Hardware and AI to Create Dynamic Live Streaming User Experiences
42mAI in React JS
36mApps That See 👀 Practical AI Vision for Developers
46mSmall AI is the next Big Thing
15mThe future of AI is now: Real-life case studies for on client-side AI adoption in web apps
37mAI Lab Recipes: Cooking up AI Applications on your Laptop
19mReal-Time AI: Low Latency Solutions for Interactive Applications
21mBuilding at the Speed of Thought