Apple secretly released Ferret, an open-source large language model integrating language understanding with image analysis.
In a surprising move, Apple has quietly launched Ferret, an open-source large language model developed in collaboration with Cornell University, as reported by Dataconomy. Unlike traditional language models, Ferret combines language understanding with image analysis, allowing it to analyze specific regions of images and respond to prompts involving both text and visuals. The release signifies Apple’s move towards openness, presenting challenges in scaling against larger models like GPT-4 due to infrastructure limitations. However, the potential impact on Apple devices is immense, promising improved image-based interactions, augmented user assistance, enriched media understanding, and a platform for developer innovation.