Elon Musk's xAI unveils first version of Grok-1.5 which can 'understand' images

Elon Musk's artificial intelligence company xAI, a rival to OpenAI, has unveiled its first version of chatbot Grok, just couple of weeks after it introduced Grok-1.5, Mashable reported

The Tesla CEO said Grok-1.5V is its "first-generation multimodal model."

Grok-1.5V can not only "understand" images but also process visual information such as "documents, diagrams, charts, screenshots and photographs."

According to the company, Grok AI can reason through complicated texts, science diagrams, charts, screenshots, and images in addition to responding to your provided pictures and screenshots.

Furthermore, Grok-1.5V will acquire "real-world spatial understanding" to enhance its comprehension of the real world as portrayed in the photographs that its users upload.

The company in a statement said, "Advancing both our multimodal understanding and generation capabilities are important steps in building beneficial AGI that can understand the universe. In the coming months, we anticipate to make significant improvements in both capabilities, across various modalities such as images, audio, and video."

Examples of what Grok can do include converting diagram into python code, turning a child’s drawing into a story, pinpointing largest objects amongst a group of many and telling a driver if they have enough space to drive around an obstacle.

Grok-1.5V will be available to early testers and select users soon.