"Say goodbye to awkward dates and job interviews."

Charisma as a Service

A team of crafty student researchers at Stanford University have come up with a pair of smart glasses that can display the output of OpenAI's GPT-4 large language model — potentially giving you a leg up during the next job interview, or even coaching you during your next date.

The device, dubbed rizzGPT, offers its wearer "real-time Charisma as a Service" (CaaS) and "listens to your conversation and tells you exactly what to say next," as Stanford student Bryan Hau-Ping Chiang explained in a recent tweet.

"Say goodbye to awkward dates and job interviews," Chiang wrote.

Ear Worm

The glasses were made using a monocle-like device that can be snapped onto practically any glasses, built and donated by Brilliant Labs. It features a camera, microphone, and a high-resolution display that can output text generated by GPT-4.

OpenAI's speech recognition software, Whisper, allows the glasses to feed speech directly to the chatbot, which can generate answers in a matter of seconds to its wearer.

"Hi Varun, I hear you're looking for a job to teach React Native," Stanford instructor Alix Cui asked during a brief demo posted to Twitter.

The smart glasses' generated text, which was displayed on the device's tiny screen and read aloud by Stanford's Varun Shenoy, did feel a little stunted.

"Thank you for your interest," Shenoy replied, as prompted by the glasses. "I've been studying React Native for the past few months and I am confident that I have the skills and knowledge necessary for the job."

Judging by the fact that Shenoy kept stumbling over his own words while reading from the tiny screen, there's plenty of work to be done until such a device can be seamlessly used during a job interview, let alone a date.

But that might actually be a good thing. After all, entirely trusting GTP-4 with what to say during an encounter with a potential partner or employer is a terrible idea — and would almost certainly make things a million times more awkward than it already is.

More on OpenAI: Major News Site Warns ChatGPT Is Inaccurate, Announces Plans to Use It Anyway


Share This Article