Vibe School: Making dumb devices smart with AI
Demonstrates using AI-assisted coding to reverse engineer conventional hardware and integrate legacy sensors into Home Assistant.
Summary
Democratizing Smart Home Integration with AI
Commercial smart home sensors and specialized environmental monitors often carry high prices, while inexpensive conventional hardware lacks network connectivity. AI-assisted programming lowers the barrier to bridging legacy hardware into modern smart home platforms.
Sniffing Sensor Signals and Protocol Analysis
Katie Paxton Fear demonstrates how to intercept and decode communication signals from an inexpensive conventional weather station using basic hardware sniffers and radio receivers.
AI-Assisted Microcontroller Firmware Development
Using generative AI models (such as Gemini) to write C++ firmware for microcontrollers (ESP32 / Arduino), researchers rapidly translate raw sensor telemetry into structured MQTT payloads.
Integrating Legacy Hardware into Home Assistant
Connecting the custom firmware to Home Assistant creates an automated, low-cost smart weather station, illustrating how 'vibe coding' empowers makers to customize connected devices.
Related talks
Village Presentations·22 min
Craig Young
Tripwire VERT researcher Craig Young exposes zero-day vulnerabilities across consumer smart home automation hubs, door locks, and wireless power outlets.
Creator Stage·43 min
Zoltan Balazs
Surveys pervasive architectural and implementation failures in consumer IoT gadgets, highlighting cleartext credentials, command injections, and insecure defaults.
Creator Stage·21 min
Kevin · Tianqi
Presents a pocket-sized 10-watt bedside inference device running local 3B language models on a CM5 and RP2040 for private clinical workflows.