Elon Musk’s xAI, a rival of OpenAI, has unveiled Grok-1.5V, its first multimodal AI model capable of processing visual information. This innovative model can handle not just text, but also various visual elements like documents, diagrams, charts, screenshots, and photographs. xAI showcased some practical applications of Grok’s capabilities, such as translating a flow chart into Python code, generating a story from a drawing, and explaining perplexing memes. This advancement opens up a world of possibilities for leveraging AI in everyday scenarios where understanding visual data is crucial.
The recent release of Grok-1.5V follows closely on the heels of the earlier Grok-1.5 model. The new version boasts enhanced coding and mathematical abilities, along with the capacity to analyze longer contexts for more comprehensive data processing. Early testers of xAI’s technology have been impressed with its performance and potential…
2024-04-13 07:00:25
Originally published on www.engadget.com