OpenAI releases GPT-4o AI model with multimodal capabilities, including interpreting faces, transcribing handwritten notes, and describing images.
OpenAI's latest AI model GPT-4o, released by CEO Sam Altman, boasts multimodal capabilities, including interpreting human faces, transcribing old handwritten notes, and accurately describing images. With its advanced language and visual skills, it has potential uses for researchers and academics. The model also identifies landmarks, translates foreign text, and identifies ingredients in global cuisine.
May 18, 2024
3 Articles
