OpenAI has released a system card for its GPT-4V model, which is an extension of the GPT-4 language model. The GPT-4V model includes visual capabilities and can process text and images together. According to OpenAI, this allows the model to better understand and respond to questions that involve both text and images. --- Why it matters: This matters because it brings AI closer to human-like understanding and response, which is a key goal in natural language processing research. By combining visual and textual information, GPT-4V can provide more accurate and relevant answers to complex queries. Source: https://openai.com/index/gpt-4v-system-card