Introducing Microsoft’s Kosmos-1: Pioneering the Next Stage of AI Beyond ChatGPT

Microsoft now has a new AI Model

Microsoft’s Kosmos-1 is able to take both audio and image prompts. This opens the door for the next step beyond ChatGPT text prompts.

Microsoft unveiled Kosmos-1. It describes it as a large multimodal language model (MLLM), which is able to respond not only to language cues but also visual ones. This can be used in a variety of ways, such as image captioning and visual question answering.

OpenAI’s ChatGPT helped popularize LLMs such as the GPT model (Generative Pre-trained Transformer), and the ability to transform a text input or prompt into an output.