Sora是什么？
近日，继ChatGPT之后，AI行业再次迎来重大技术突破，OpenAI宣布推出全新的文本生成视频大模型Sora，直接输入文字提示词，即可直接生成长达60秒的视频。
Prompt: A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.
🤔️小作业：
1. What potential misuse of Sora is mentioned in the article?
A) Enhancing video game graphics
B) Generating educational content
C) Creating misinformation and hateful content
D) Improving video editing software
A) Sora creates still images while Dall-E 2 generates videos.
B) Both Sora and Dall-E 2 are used for generating realistic videos.
C) Sora generates videos, whereas Dall-E 2 produces still images from text.
D) There is no difference in functionality between Sora and Dall-E 2.
无注释原文：
OpenAI Develops Tool to Create Realistic AI Videos
From: The Wall Street Journal
OpenAI has introduced new technology that uses artificial intelligence to create high-quality videos from text descriptions.
The company released short clips showcasing vivid, seemingly realistic videos, including woolly mammoths trekking across a snowy field, ocean waves crashing against a cliff’s shoreline and people doing everyday things like reading a book or walking down a city street.
OpenAI calls the new system Sora. It takes a written prompt and, through AI, renders a richly detailed video. OpenAI is one of many companies like Alphabet’s Google and Meta Platforms seeking to capitalize on new AI-video developments.
Microsoft-backed OpenAI, maker of the ChatGPT AI chatbot, said it is sharing the text-to-video technology with a select group of researchers and academics who will study it to find ways the AI program could be misused. It hasn’t been released to the public.
OpenAI previously released a program called Dall-E 2 that produces still images based on text descriptions.
Sam Altman, OpenAI’s chief executive, on Thursday asked users on X to submit text descriptions for Sora. He then shared their creations.
“We’d like to show you what Sora can do,” he wrote on X. “Don’t hold back on the detail or difficulty!”
One person asked for “a bicycle race on the ocean with different animals as athletes riding the bicycles with drone camera view.” Altman posted a Sora-generated video of penguins, dolphins and other aquatic creatures on bikes in his reply.
Another video showed a smiling, white-haired woman in an apron inviting viewers into her kitchen. Sora generated the AI video after Altman was asked for a cooking lesson “for homemade gnocchi hosted by a grandmother social media influencer set in a rustic Tuscan country kitchen with cinematic lighting.”
The technology still has some flaws, the company said, including some spatial issues.
The company said it is aware of Sora’s potential to create misinformation and hateful content, among other things. AI-powered deepfakes have emerged as a risk that could confuse the public ahead of the 2024 presidential election, researchers said. OpenAI has said it is taking actions to get ready for the election, including prohibiting the use of its tools for political campaigning.
Putting watermarks on AI-generated videos and images, as many companies have said they would do, might help, according to Siwei Lyu, director of the Media Forensic Lab at the University at Buffalo. But in many cases, watermarks can be removed or altered, he said.
As AI programs like Sora pop up, the technology will add to existing challenges with image and audio deepfakes, Lyu said.
- ◆ -
注：完整题目见本文开头；中文文本为华尔街日报官方译文，仅供参考
含注释全文：
OpenAI Develops Tool to Create Realistic AI Videos
From: The Wall Street Journal
OpenAI has introduced new technology that uses artificial intelligence to create high-quality videos from text descriptions.
OpenAI推出了一项新技术，利用人工智能（AI）可根据文字描述生成高质量视频。
artificial
artificial /ˌɑː.tɪˈfɪʃ.əl/ 表示“人造的，人工的；仿造的”，英文解释为“made by people, often as a copy of something natural”如：clothes made of artificial fibres 人造纤维面料的服装。
The company released short clips showcasing vivid, seemingly realistic videos, including woolly mammoths trekking across a snowy field, ocean waves crashing against a cliff's shoreline and people doing everyday things like reading a book or walking down a city street.
该公司发布了几个生动、看似逼真的短视频，内容有几头长毛猛犸象在雪地中前行；海浪拍打着悬崖边缘；人们的日常生活，比如正在读书或走在城市街道上。
clip
clip /klɪp/ 1）表示“（电影或电视节目的）剪辑，片断”，英文解释为“a short part of a film or television programme”举个🌰：I've seen a clip from the movie. 我看过这部电影的一个片断。
2）表示“夹子；别针；回形针”，英文解释为“a small object usually made of metal or plastic, used for fastening things together or holding them in position”如：a paper/hair/tie clip 回形针/发夹/领带夹。
showcase
showcase /ˈʃəʊ.keɪs/ 表示“展示…的优点；充分展示”，英文解释为“to show the best qualities or parts of something”举个🌰：The main aim of the exhibition is to showcase British design. 该展览的主要目的是一展英国设计的风采。
vivid
vivid /ˈvɪv.ɪd/ 表示“（描述、记忆等）栩栩如生的，鲜活的，生动的”，英文解释为“Vivid descriptions, memories, etc. produce very clear, powerful, and detailed images in the mind”举个🌰：He gave a very vivid and often shocking account/description of his time in prison. 他生动地讲述/描述了他的狱中生活，他说的常让人觉得很震惊。
woolly
woolly /ˈwʊl.i/ 表示“羊毛制的；仿羊毛的”，英文解释为“made of wool, or made of something that looks like wool”如：a woolly hat/jumper 羊毛帽子/套衫。
mammoth
mammoth /ˈmæm.əθ/ 作名词，表示“猛犸（象），毛象（现已绝种）”，英文解释为“a type of large elephant, now extinct, that was covered in hair and had tusks”
作形容词，表示“巨大的；庞大的”，英文解释为“extremely large”举个🌰：Cleaning up the city-wide mess is going to be a mammoth task. 清扫全市范围内的垃圾是一项艰巨的任务。
trek
trek /trek/ 可以作动词，也可以作名词，表示“长途跋涉（尤指徒步旅行），翻山越岭；艰苦的行程”，英文解释为“to make a long and difficult journey, especially on foot”举个🌰：We did an eight-hour trek yesterday. 昨天我们走了8个小时。The elevator was broken, so we had to trek up six flights of stairs. 电梯坏了，所以我们只好爬了六层楼梯。
cliff
cliff /klɪf/ 表示“（常指海岸的）悬崖，峭壁”，英文解释为“a high area of rock with a very steep side, often on a coast”举个🌰：Keep away from the edge of the cliff - you might fall. 离悬崖边远一点——会掉下去的。
OpenAI calls the new system Sora. It takes a written prompt and, through AI, renders a richly detailed video. OpenAI is one of many companies like Alphabet's Google and Meta Platforms seeking to capitalize on new AI-video developments.
OpenAI将这款新系统称为Sora。Sora会接收用户的文字提示，然后通过AI生成一段细节丰富的视频。Alphabet旗下谷歌（Google）以及Meta Platforms等许多公司都在寻求把握新的AI视频技术发展机会，OpenAI是其中之一。
prompt
prompt /prɒmpt/ 作名词，1）表示“（计算机屏幕上的）提示符（显示计算机已经准备好接受指令）”，英文解释为“a sign on a computer screen that shows that the computer is ready to receive your instructions”
📍在ChatGPT火热的今天，prompt通常指的是给模型的输入，用来激发或引导模型生成特定的输出或回答。简而言之，prompt是指用户提供给语言模型的一段文字或命令，以便模型据此理解用户的需求并给出相应的响应或信息。例如，在与像ChatGPT这样的大语言模型交互时，用户提出的问题或指令就是一个“prompt”。模型会根据这个prompt的内容分析、处理并生成回答或执行相关的任务。Prompt对于大语言模型来说是非常关键的，因为它直接决定了模型如何理解和回应用户的需求。
📍prompt中文里有译为“提示词”，prompt engineering 就是“提示工程/提示词工程”。
2）表示“（给演员的）提词，提白”，英文解释为“words that are spoken to an actor who has forgotten what he or she is going to say during the performance of a play”
3）作动词，表示“促使；导致；激起”，英文解释为“to make sb decide to do sth; to cause sth to happen”举个🌰：His speech prompted an angry outburst from a man in the crowd. 他的讲话激起了人群中一男子的愤怒。
📺美剧《斯巴达克斯：血与沙》（Spartacus: Blood and Sand）中的台词提到：One cannot but wonder what would prompt such an act 不知他们为何遭此不幸。
render
render /ˈren.dər/ 1）此前，在「经济学人」翻译的出路在哪里？这篇文章中出现过，render表示“翻译，把...译成...”，通常用法为render sth into English/Russian/Chinese etc，将sth译成英语/俄语/汉语等，举个🌰：She is rendering the book into English from French. 她正在把这本书从法语译成英语。
2）表示“（以某种方式）表达；表现”，英文解释为“to express or present something in a particular way”，如：a sculpture rendered in bronze 一尊青铜雕像；
3）表示“绘制（指用色彩和明暗使轮廓图像具立体感）”，英文解释为“using colour and shading in order to make it appear solid and three-dimensional”
4）表示“使成为；使变得；使处于某种状态”，英文解释为“to cause someone or something to be in a particular state”举个🌰：His rudeness rendered me speechless. 他的粗暴无礼让我无言以对。
5）还可以指“给予，提供”，英文解释为“to give something to someone or do something, because it is your duty or because someone expects you to”如：an obligation to render assistance to those in need 为有困难的人提供援助的义务，举个🌰：We see that freight railroads make good profits while rendering excellent service. 我们看到铁路货运公司在提供优质服务的同时也赢得了丰厚的利润。
6）还还还可以表示“粉刷；给（墙壁）抹灰（或水泥）”，英文解释为“to put a first layer of plaster or cement on a wall.”
capitalize on
表示“利用…获益；从…中获利；充分利用；从…中获得更多的好处”，英文解释为“to use a situation to your own advantage”举个🌰：She capitalized on her knowledge and experience to get a better job. 她凭借自己的学识和经验谋求了一份收入更高的新工作。
Microsoft-backed OpenAI, maker of the ChatGPT AI chatbot, said it is sharing the text-to-video technology with a select group of researchers and academics who will study it to find ways the AI program could be misused. It hasn't been released to the public.
背靠微软（Microsoft）的OpenAI开发了AI聊天机器人ChatGPT。OpenAI表示，正在把这项文字转视频技术分享给一批精选的研究人员和学者，他们将研究Sora，发现该AI程序被滥用的风险。Sora尚未向公众发布。
OpenAI previously released a program called Dall-E 2 that produces still images based on text descriptions.
OpenAI此前发布了一款名为Dall-E 2的程序，可以根据文字描述生成静态图像。
still
still /stɪl/ 作形容词，表示“静止的；不动的，安静的”，英文解释为“staying in the same position; not moving”举个🌰：The air was so still (= there was so little wind) that not even the leaves were moving. 一点儿风都没有，连树叶都一动不动。
作动词，表示“（使）静止，平静，安静”，英文解释为“to become calm and quiet; to make sth calm and quiet”如：to still sb's doubts/fears 消除某人的疑虑/恐惧，举个🌰：She cuddled her baby to still its cries. 她抱着自己的宝宝，哄他不哭。
Sam Altman, OpenAI's chief executive, on Thursday asked users on X to submit text descriptions for Sora. He then shared their creations.
OpenAI首席执行官阿尔特曼（Sam Altman）周四在X上让该平台用户把自己想给Sora的文字描述提交给他。然后，他分享了Sora根据这些描述生成的视频。
“We'd like to show you what Sora can do,” he wrote on X. “Don't hold back on the detail or difficulty!”
“我们想向你们展示Sora能做什么，”他在X上写道。“不用担心你的要求太细，或是难度太大！”
One person asked for “a bicycle race on the ocean with different animals as athletes riding the bicycles with drone camera view.” Altman posted a Sora-generated video of penguins, dolphins and other aquatic creatures on bikes in his reply.
有人提出想要“一段海上自行车比赛的视频，让各种动物作为运动员骑自行车，采用无人机拍摄视角”。阿尔特曼在回复中发布了一段由Sora生成的视频，视频中有企鹅、海豚和其他水生生物骑自行车。
aquatic
aquatic /əˈkwæt.ɪk/ 表示“水栖的；水生的；水上的；水中（进行）的”，英文解释为“living or growing in, happening in, or connected with water”如：aquatic plants 水生植物。
Another video showed a smiling, white-haired woman in an apron inviting viewers into her kitchen. Sora generated the AI video after Altman was asked for a cooking lesson “for homemade gnocchi hosted by a grandmother social media influencer set in a rustic Tuscan country kitchen with cinematic lighting.”
另一段视频显示，一位身穿围裙、面带微笑的白发女士邀请观众进入她的厨房。有人向阿尔特曼要一段“由一名祖母辈的网红主持的自制团子烹饪课程，背景是一个质朴的托斯卡纳乡村厨房，并配有电影级的灯光”，之后Sora生成了这段AI视频。
apron
apron /ˈeɪ.prən/ 表示“围裙”，英文解释为“a piece of clothing that you wear over the front of other clothes to keep the clothes clean while you are doing something dirty, such as cooking or cleaning”
gnocchi
gnocchi /ˈnjɒk.i/ 表示“（马铃薯或面粉做的）汤团，团子”，英文解释为“small round balls made from potato or wheat flour mixed with water, that you eat in soup or with sauce”
influencer
influencer /ˈɪn.flu.ən.sər/ 字面上的意思就是影响者，有影响力的人，柯林斯词典中的解释分为两种，一个就是字面上的意思：any person or thing that exerts an influence；另一种解释为：a person who uses social media to promote lifestyle choices, commercial products, etc to his or her followers. 利用社交媒体向自己的粉丝推广或推荐产品和服务的人，就是类似于现在网络中的“网红、博主”，或者说关键意见领袖，Key Opinion Leader，KOL.
rustic
rustic /ˈrʌs.tɪk/ 表示“粗制的；乡村的，乡村特色的；质朴的”，英文解释为“simple and often rough in appearance; typical of the countryside”如：a rustic bench/cabin 粗制的长椅/简陋的小木屋。
The technology still has some flaws, the company said, including some spatial issues.
OpenAI表示，这项技术仍存在一些缺陷，包括一些空间问题。
spatial
spatial /ˈspeɪ.ʃəl/ 表示“空间的”，英文解释为“relating to the position, area, and size of things”举个🌰：This task is designed to test children's spatial awareness (= their understanding of where things are in relation to other things). 这一任务是为测试孩子的空间意识而设计的。
The company said it is aware of Sora's potential to create misinformation and hateful content, among other things. AI-powered deepfakes have emerged as a risk that could confuse the public ahead of the 2024 presidential election, researchers said. OpenAI has said it is taking actions to get ready for the election, including prohibiting the use of its tools for political campaigning.
该公司表示，它意识到Sora有可能制造错误信息和仇恨内容等。研究人员说，AI驱动的深度伪造已成为一种风险，可能会在2024年总统大选前给公众造成困惑。OpenAI曾表示，公司正在采取行动为大选做好准备，包括禁止将其工具用于政治造势活动。
Putting watermarks on AI-generated videos and images, as many companies have said they would do, might help, according to Siwei Lyu, director of the Media Forensic Lab at the University at Buffalo. But in many cases, watermarks can be removed or altered, he said.
布法罗大学（University at Buffalo）的Media Forensic Lab主任吕思伟（Siwei Lyu）表示，在AI生成的视频和图像上加上水印可能会有所帮助，许多公司说它们会这样做。但他说，在很多情况下，水印是可以被移除或篡改的。
watermark
watermark /ˈwɔː.tə.mɑːk/ 表示“水印”，英文解释为“A watermark is a design that is put into paper when it is made, and that you can only see if you hold the paper up to the light. Paper money often has a watermark, to make it harder to copy illegally.”
As AI programs like Sora pop up, the technology will add to existing challenges with image and audio deepfakes, Lyu said.
吕思伟说，随着像Sora这样的AI程序不断涌现，除了由图像和音频深度伪造构成的现有挑战之外，这项技术将带来更多挑战。
pop up
表示“（尤指突然地）出现，发生”，英文解释为“to appear or happen, especially suddenly or unexpectedly”举个🌰：She's one of those movie stars who pops up everywhere, on TV, in magazines, on Broadway. 她是那种四处露脸的影星，在电视上、杂志上、百老汇，到处可见她的身影。
- 词汇盘点 -
- 词汇助记 By ChatGPT -
LearnAndRecord
2015年2月8日
2024年2月20日
第3300天
每天持续行动学外语