🕊 xAI Unveils Grok-1.5 Vision Preview Model
Today, Elon Musk's xAI company introduced its first multimodal model. It can not only understand text but also process a wide variety of visual information, including documents, diagrams, charts, screenshots, and photographs.
Grok-1.5 Vision will be available soon to early testers and existing Grok users.
The model can write code based on a hand-drawn diagram, explain a meme, or compose a fairy tale based on a child's drawing.
👀 The developers consider the main feature of the new model to be a better understanding of the physical world. For example, you can send a photo of a situation on the road and clarify whether to turn or go straight (although we don't recommend doing this while driving).
Is it time to get an X account?
❤️ — I have one
👍 — I don't have one, but it's time
👾 — No, Musk is already everywhere
Source and examples:
https://x.ai/blog/grok-1.5v
