期中题型专练-阅读理解- 2023-2024学年 牛津译林版 九年级英语下册

期中题型专练-阅读理解- 2023-2024学年 九年级英语下册 牛津译林版 A company called OpenAI has recently announced a new version (版本) of its AI artist, DALL-E 2. Given just a short sentence describing a picture, the tool can create different pictures in many different styles. The name “DALL-E” mixes the name of the robot in the movie WALL-E, and the name of the famous Spanish artist Salvador Dalí. He painted amazing, but impossible pictures. Like Dalí, DALL-E 2 can create pictures that are unbelievable, for example, Teddy bears doing crazy experiments as scientists.   OpenAI has already changed the world once with its AI writing tool, GPT-3. GPT-3 was trained on a great deal of writing in many different styles. When it was released (发布) in 2020, it surprised people by quickly creating complete, well-written articles in different styles. It is so powerful that OpenAI has tried to be prudent when it comes to how it allows people to use the tool, to make sure that it isn’t used for harmful purposes. DALL-E actually grew out of an effort to apply (应用) GPT-3 to pictures. OpenAI released the first version of DALL-E in 2021. DALL-E 2 is even more powerful. DALL-E 2 has been trained on huge numbers of pictures with matching descriptions, which means it “knows” a lot about how different things look, even when they’re shown in different styles, such as a photo, a painting or even a cartoon. The user can select an area of an image (图像) and ask DALL-E 2 to put something into the picture, or take it out. Some artists are worried that it will take their place if a computer system can create such high-quality pictures so easily. OpenAI says the tool will allow artists to be creative in new ways. To make sure the tool isn’t misused, OpenAI already has strict rules about the types of pictures that can be created with DALL-E. One of those rules prevents DALL-E from creating realistic pictures of actual (真实的) people. By now, the company hasn’t released DALL-E 2. Instead, it is allowing a small number of peo