OpenAI has finally released the real-time video capabilities for ChatGPT that it demoed nearly seven months ago, greatly enhancing user interaction with the app.
Advanced Voice Mode with vision can also understand what's on a device's screen, via screen sharing. It can explain various settings menus or give suggestions on a math problem.
In a recent demo, ChatGPT's Advanced Voice Mode with vision was able to quiz Anderson Cooper on his anatomy skills, reacting to his drawings with accuracy.
Despite its advancements, Advanced Voice Mode with vision is still prone to errors; during a demo, it made a mistake on a geometry problem.
Collection
[
|
...
]