xAI shares an update on Grok 1.5 Vision release

Artificial Intelligence (AI) company xAI shared a development update and release date on Grok 1.5 Vision, its first multimodal model.

Toby Pohlen, an xAI team member has revealed that Grok 1.5 Vision is under testing. The company has provided this test opportunity for partners but no specific details are available.

Pohlen also said that the xAI is continuously experimenting with image support in the conversation user interface of Grok. It means the company is still testing the Grok 1.5 Vision update and the model is still under initial training.

He also shed some light on the 1.5 Vision launch by saying “Release date is TBD”. It suggests that xAI may need a little longer to launch this model.

In April, xAI released Grok -1.5 Vision with improved text capabilities and the ability to process different visual information. The model can comprehend documents, diagrams, charts, screenshots, and photographs.

In detail, the 1.5 Vision can translate a photograph of a rough code diagram and convert it into a real coding language. It can detect a specific value and look for it throughout the image. It can generate an entire story from a simple sketch on a white page and can explain memes.

You can give it a document and tell it to convert it into a different format or data type. This new multimodal can give you suggestions based on the question + image. Last but not least, it can solve coding problems, you can submit an image to this model and ask it to resolve any coding bug. It will reply with an answer with a code execution result.