Just when you thought your mind couldn’t be blown any more, OpenAI is rolling out GPT4 Vision, aka ChatGPT Vision, a chatbot with multi modal capabilities.
As OpenAI puts it, “ChatGPT can now see, hear, and speak.” Yes, you heard that right. ChatGPT isn’t limited to chatting by text. Instead, ChatGPT can understand images and voice.
The level of understanding, especially in analyzing the content in images and giving a complete description of it, GPT4 Vision has is simply mind blowing. Take a look: