If ChatGPT can help you write an article or plan a meal, can it also help you chat with other people?
That’s what 22-year-old Stanford University Computer Science student Bryan Chiang wondered earlier this year.
So, he grabbed an augmented reality eyepiece and his laptop and called a few friends to code what he called RizzGPT.
Lens – designed by Brilliant Labs and open-sourced so that its software can be tested, it has a camera, a microphone and a built-in projector screen where words are displayed in front of the user’s eyes.
When someone speaks to the user, RizzGPT monitors the conversation through the microphone, transcribes it into text and sends it via WiFi to OpenAI’s AI chatbot ChatGPT to generate a response.
This response appears after a short delay on the small monocle screen.
“RizzGPT is basically using AI to provide you with charisma on demand and so it listens to your current ongoing conversation and tells you exactly what to say next,” Chiang said.
The delay and the reaction are not yet very natural or charismatic.
But Chiang said it was a prototype aimed at showing what is possible with the technology.
“How we interact with computers has changed a long time ago. You see 5G connectivity, AR glasses, hardware and intelligence coming together to create a new way of interacting with these systems, a new operating system where it’s much more natural. The goal is not to completely replace natural human speech.”