It is basically GPT-4 but with vision.
On September 25, OpenAI gave ChatGPT the ability to see, hear, and speak, making it a truly multimodal large language model. And along came GPT-4V, which is basically GPT-4 but with vision.
This feature enables users to input image prompts of almost anything under the sun and ask GPT-4V to analyze them. Available currently only to ChatGPT Plus subscribers, users are posting on social media how they are using and utilizing the upgrade.
Leave a reply