Technology

DIY smart home accessory – It all started with a question to ChatGPT

Few months ago, we bought a sculpture from a local art fair for our Palm Desert house. We found a great spot for it in the hallway but it bothered me that it was not properly lit. I wanted to put a small LED light behind it. Unfortunately, that spot doesn’t have a power socket.

So I asked ChatGPT: “Is there a battery-powered, Matter-supporting, Apple SmartKit-enabled LED accessory I could buy?”. I wanted to be able to control the LED via my smart home automation to minimize the number of times a human needed to reach behind the sculpture to turn the device on/off, reducing the chances of an accident.

The conversation with ChatGPT lasted a while and led to a decision to build the device on my own. ChatGPT listed the exact components I needed to buy for an Arduino-based solution. It gave me the step-by-step instructions and even wrote the program for the integration.

After the pieces arrived, I took a photograph of them and asked ChatGPT to confirm that I had everything I needed. It recognized everything and confirmed that I was ready to start putting things together.

30-40mins later, everything was in place and my little DIY device does exactly what I wanted. It cost about $400. Most of the cost is a very good battery (Anker Prime Power Bank, 26,250mAh) so that I can operate the light for months through my Apple smart home automation without having to worry about recharging.

And voila!

Savas Parastatidis

Savas Parastatidis works at Amazon as a Sr. Principal Engineer in Alexa AI'. Previously, he worked at Microsoft where he co-founded Cortana and led the effort as the team's architect. While at Microsoft, Savas also worked on distributed data storage and high-performance data processing technologies. He was involved in various e-Science projects while at Microsoft Research where he also investigated technologies related to knowledge representation & reasoning. Savas also worked on language understanding technologies at Facebook. Prior to joining Microsoft, Savas was a Principal Research Associate at Newcastle University where he undertook research in the areas of distributed, service-oriented computing and e-Science. He was also the Chief Software Architect at the North-East Regional e-Science Centre where he oversaw the architecture and the application of Web Services technologies for a number of large research projects. Savas worked as a Senior Software Engineer for Hewlett Packard where he co-lead the R&D effort for the industry's Web Service transactions service and protocol. You can find out more about Savas at https://savas.me/about

Share
Published by
Savas Parastatidis

Recent Posts

The Beginning of CVOYA

There’s a unique energy that comes with starting something new — a blend of excitement,…

2 months ago

Enhancements in Graph Model: Dynamic Entities & Full-Text Search

As I continued work on BrainExpanded and its MCP service, I came to realize that…

5 months ago

GraphModel: A .NET Abstraction for Graphs

Just over a month ago, I published "Playing with graphs and Neo4j". Back then, it…

6 months ago

Playing with graphs and neo4j

After my initial implementation of some BrainExpanded-related ideas on top of dgraph using its GraphQL…

7 months ago

A Graph Model DSL

Say hello to the Graph Model Domain Specific Language (GMDSL), created with the help of…

8 months ago

BrainExpanded – Web app and Data Sources

As I wrote in previous posts, the manual recording of memories for BrainExpanded is just…

8 months ago