San Francisco, 17 March 2023 (GNP): The next-generation AI language model GPT-4, which can read photographs and describe what’s in them, was just released by OpenAI, according to a research blog post.
The world has been captivated by Chat GPT-3, although the deep learning language model previously only took text inputs. GPT-4 will also accept visual cues.
OpenAI issued a statement which read: “It generates text outputs given inputs consisting of interspersed text and images. Over a range of domains — including documents with text and photographs, diagrams, or screenshots — GPT-4 exhibits similar capabilities as it does on text-only inputs.”
Also Read: Divvy film festival to begin from March 17
The AI chatbot will be able to examine the contents of images as a result. For instance, it can explain to the user what’s strange about the image of a man ironing his clothing while affixed to a vehicle.