答案第1页,共20页 答案第1页,共20页 专题03说明文专练一 1.(2023·四川内江·统考一模)A company called OpenAI has recently announced a new version of its artificial intelligence (AI) artist, DALL-E 2. Given just a short sentence describing a picture, the tool can create complicated images (图像) in many different styles. OpenAI has already changed the world once with its AI writing tool, GPT-3. GPT-3 was trained on huge amounts of writing in many different styles. When it was released in 2020, it shocked 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 suire that it isn’t used for harmful purposes. DALL-E actually grew out of an effort to apply GPT-3 to images. OpenAI released the first version of DALL-E last year. DALL-E 2 is even more powerful. DALL-E 2 has been trained on massive numbers of pictures with matching descriptions, which means it “knows” a lot about how different things look. DALL-E starts its images with a pattern of random dots. It then changes the pattern of those dots until different parts of the image begin to match the description the DALL-E is given. Does DALL-E 2 have something new? The user can select an area of an image and ask DALL-E 2 to put something into the picture, or take it out. Some artists are concerned that their job opportunities might be limited if a computer system can make such high quality pictures on demand so easy. 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 sorts of images that can be created with DALL-E. One of those rules prevents DALL-E from creating realistic pictures of actual people. For now, the company isn’t releasing DALL-E 2. Instead, it is allowing a small number of people to work with the tool to learn more about what works well, and to discover possible problems. 1.What does the underline