OpenAI introduces two new GPT-3 models: CLIP, which classifies images into categories from arbitrary text, and DALLE, which can generate images from text (Will Douglas Heaven/MIT Technology Review)

gpt3 clip dallmiddotdouglas heaven technologyreview,
Will Douglas Heaven / MIT Technology Review:OpenAI introduces two new GPT-3 models: CLIP, which classifies images into categories from arbitrary text, and DALLE, which can generate images from textOpenAI has extended GPT-3 with two new models that combine NLP with image recognition to give its AI a better understanding of everyday concepts.