Exciting Release: GPT-4 with Image and Text Capabilities Soon!

GPT-4 with (Image, Text) -> Text is being released in the coming weeks, really good write up below: https://twitter.com/DrJimFan/status/1706478482296021344 The potential of Multi-modal to open up an incredible new set of use-cases is massive. This was announced months ago and many of us have been waiting patiently for it. I'm a bit unclear if this will be available in the API anytime soon or whether it is only Chat. I'll check with the OpenAI team and let you all know what I hear!