Web developer Mate Marshalko told on Medium how he created a voice assistant based on Siri and the GPT-3 neural network.
The impressive thing is that he didn’t have to write code to make everything work. Instead, he explained to GPT-3 what he wants to do is transform the neural network into AI for smart home control. Marshalko suggested that she interpret spoken English and choose the appropriate JSON response.
I gave general information, the exact wording of the answer, and suggested that she behave like an intelligent AI, giving advice even on personal matters. I also report time, place, accommodation and rooms in the house. From this we check for a perfectly structured response. And that’s all there is to programming!
Our example request was: “Just noticed I’m recording this video in the dark at the office. Can you do something about it?”
And we got the answer:
{
“action”: “command”
“location”: “office”
“target”: “light”
“value”: “enabled”,
“comment”: “I turn on the light for you.”,
“ScheduleTimeStamp”: “”
}— Mate Marshalko
there were many such cases. Including the voice assistant, at its discretion, set the possible comfortable temperature in your home.
Work demo:
Marshalko uses a Siri command to get a real HomeKit tool. Surprisingly, everything worked perfectly the first time. [9to5]
Source: Iphones RU
