《Brave New Words 》5.1 传递真相:偏见和虚假信息现状

news2024/11/19 5:48:17

Part V: Keeping Kids Safe

第五部分:确保孩子安全

d71c5247b49d10d3d21b08bdaecc98f9.jpeg

Never travel faster than your guardian angel can fly.

—Mother Teresa

永远不要比你的守护天使飞得更快。

——特蕾莎修女

Distrust and caution are the parents of security.

—Benjamin Franklin

不信任和谨慎是安全之父。

——本杰明·富兰克林

Delivering the Facts: The State of Bias and Misinformation

传递真相:偏见和虚假信息现状 

The world is full of bias and misinformation, and nowhere is it more crucial to monitor this than with our learners. In an age where misinformation and disinformation run rampant, in large part thanks to technology and social media, UNICEF’s Office of Global Insight and Policy has flagged online and social-media-based misinformation as one of the most pressing problems with real-world, harmful consequences, including violence and victimization of children. Our kids spend a lot of their time online and with technology in general. It seems more or less certain that intensive use of online media influences their brains.

这个世界充满了偏见和虚假信息,而在我们的学习者中监控这一点是至关重要的。在一个由于技术和社交媒体的原因,错误信息和虚假信息猖獗的时代,联合国儿童基金会的全球洞察与政策办公室已经将基于网络和社交媒体的错误信息标记为最紧迫的问题之一,它具有现实世界中的有害后果,包括针对儿童的暴力和受害。我们的孩子花了很多时间在网上和使用技术。几乎可以肯定的是,密集使用在线媒体会影响他们的大脑。

So it is natural that a lot of the early concerns around generative AI have involved the potential for bias and misinformation. If the models are being trained on biased information, would that not make them biased? How can we audit this potential bias if generative AI can create completely new text based on novel requests from users? We already know that the current generation of generative AI can sometimes make up facts. Could this be another source of misinformation? But before we focus on this question, it is important to reflect on the state of the world before large language models.

因此,围绕生成式 AI 的许多早期担忧自然涉及潜在的偏见和虚假信息。如果模型是在有偏见的信息上进行训练的,那它们不会也有偏见吗?如果生成式 AI 可以根据用户的新请求创建全新的文本,我们如何审核这种潜在的偏见?我们已经知道,当前一代的生成式 AI 有时会编造事实。这可能是另一个虚假信息的来源吗?但在我们关注这个问题之前,反思大型语言模型出现之前的世界状态是很重要的。

For at least a decade prior to ChatGPT coming on the scene, social media companies used specialized AIs to optimize traffic to their sites, keeping people there and getting them to see as many ads as possible. Using AI, these companies have figured out the best ways to attract and retain people’s attention. Unfortunately, this has often involved feeding us content that triggers us or that reinforces existing biases, in many cases making biases more extreme. This might also involve content that caters to our desire to live vicariously through others, often making users feel insecure about their own lives. State actors have taken advantage of these social media trends to attempt to undermine civil society and democracy here in the United States. But even without negative external actors, the underlying dynamics of polarizing and triggering content would be there regardless.

在 ChatGPT 出现之前的至少十年里,社交媒体公司使用专门的人工智能来优化其网站的流量,使人们停留在其网站上并尽可能多地看到广告。通过使用人工智能,这些公司找到了吸引和保持人们注意力的最佳方法。不幸的是,这通常涉及向我们提供内容,这些内容会触发我们或强化现有的偏见,在许多情况下会使偏见更加极端。这还可能涉及迎合我们对他人的生活进行替代性体验的欲望的内容,这通常会让用户对自己生活感到不安全。国家行为者利用这些社交媒体趋势试图破坏美国这里的公民社会和民主。但即使没有负面的外部行为者,两极分化和触发性内容的潜在动态无论如何都将存在。

These issues seem to disproportionately affect youth. Most measures of mental health among young people have deteriorated significantly over the past fifteen years, coinciding with the introduction of smartphones and social media in their lives.

这些问题似乎对年轻人的影响尤为严重。在过去十五年里,年轻人的心理健康状况显著恶化,这与智能手机和社交媒体进入他们的生活相吻合。

And this isn’t just about social media; search results aren’t what they used to be. In the early days of search, the most credible sites would be the top results to most queries, with a few ads off to the side. Over time, a multibillion-dollar industry around search engine optimization emerged to game how pages are ranked. Today, the top results are from those organizations that have the resources and motivation to invest heavily in search engine optimization, which doesn’t always correlate with their credibility. Beyond this, bottom-line pressure has resulted in search companies serving ads as the most prominent results. Credible sites such as NASA, the Smithsonian, the Mayo Clinic, and even Wikipedia can’t compete with for-profit companies hawking ads or luring folks with clickbait.

这不仅仅是关于社交媒体;搜索结果也不再像以前那样。在搜索的早期,最可信的网站会成为大多数查询的顶部结果,旁边只有少量广告。随着时间的推移,围绕搜索引擎优化的数十亿美元产业应运而生,操纵页面排名。如今,排名靠前的结果来自那些有资源和动力在搜索引擎优化上投入大量资金的组织,这不一定与他们的可信度相关。除此之外,底线压力导致搜索公司将广告作为最突出的位置。像 NASA、史密森学会、梅奥诊所,甚至维基百科这样的信誉良好的网站都无法与兜售广告或用标题党吸引用户的营利性公司竞争。

Well before the internet, these same dynamics played out across traditional mass media like TV, radio, and newspapers. It’s no secret that politicians lie. From the Gulf of Tonkin incident leading to a military escalation in Vietnam to the specter of weapons of mass destruction justifying the invasion of Iraq, our governments have used spurious data to tell narratives that reinforced biases, while “credible” people and institutions just went along for the ride. This dynamic is of course even worse in dictatorial regimes where the government controls the media and stifles dissent.

早在互联网之前,这些相同的动态在传统的大众媒体如电视、电台和报纸上就已经上演。政客撒谎已经不是什么秘密了。从导致越南战争升级的北部湾事件, 到为入侵伊拉克辩护的大规模杀伤性武器的幽灵,我们的政府一直在利用虚假数据来讲述强化偏见的故事,而“可信”的人和机构只是随波逐流。当然,这种动态在政府控制媒体并压制异议的独裁政权中更加糟糕。

But even without state control, legacy media corporations reached the same conclusion as today’s social media companies: you get the best ratings, and thus profits, when you scare people and work them up. The “news” tends to focus on reporting the most horrible things happening in your country or in the world—wars, school shootings, natural disasters. Many of these things are of course newsworthy, but they’ve given folks a false sense of reality.

但即使没有国家控制,传统媒体公司得出的结论与今天的社交媒体公司相同:当你吓唬人们并激起他们的情绪时,你会获得最好的收视率,从而获得利润。“新闻”往往集中报道你所在国家或世界上发生的最可怕的事情——战争、校园枪击事件、自然灾害。当然,其中许多事情是有新闻价值的,但它们给人们一种错误的现实感。

By contrast, everyday acts of altruism, tolerance, and charity tend to go unnoticed or are otherwise given short shrift. As cable news figured out that ratings improve when you reinforce biases, especially ones that reinforce tribalism, this only increased the platform for extreme viewpoints.

相比之下,日常的利他主义、宽容和慈善行为往往不被注意或被草草带过。随着有线新闻发现,当你强化偏见时,尤其是那些强化部落主义的偏见时,收视率会提高,这只会增加极端观点的平台。

Human bias doesn’t just operate in mass media. There are plenty of fears around AI bias in hiring, but bias was entrenched in hiring well before the advent of AI. Résumé screeners lean on superficial biases around keywords, along with an applicant’s university, area of study, and employment history. Interviews can be even worse, because organizations struggle to maintain consistency across and even among hiring managers.

人类偏见不仅存在于大众媒体中。围绕 AI 在招聘中的偏见有很多担忧,但在人工智能出现之前,偏见在招聘中已经根深蒂固。简历筛选者倾向于依赖围绕关键词的肤浅偏见,以及申请人的大学、学习领域和工作经历。面试可能会更糟糕,因为组织很难在招聘经理之间甚至内部保持一致性。

I say all this not to give generative AI a free pass. But it is important to keep the problems of the status quo in mind when deciding how to best implement new technology. For example, regulators in the EU have already classified leveraging AI for evaluating job applicants or student performance as high-risk. This is because AI may introduce bias into these sensitive processes. Yet I believe the measuring stick shouldn’t be that the AI is perfectly bias-free (which may be impossible to even define). Instead, we should measure its risk relative to the bias that is already involved in subjective processes such as hiring and assessment. Likewise, generative AI can produce incorrect facts, but is it better or worse than what is already out there? Is it more or less manipulatable by folks with bad intent?

我说这些并不是要为生成式 AI 开脱。但在决定如何最好地实施新技术时,记住现状的问题是很重要的。例如,欧盟的监管机构已经将利用 AI 评估求职者或学生表现归类为高风险。这是因为 AI 可能会在这些敏感的过程中引入偏见。然而,我认为衡量标准不应该是 AI 完全没有偏见(这甚至可能无法定义)。相反,我们应该相对于招聘和评估等主观过程中已经存在的偏见来衡量其风险。同样,生成式 AI 可以产生错误的事实,但它比现有的更好还是更糟?它被恶意操纵的可能性更大还是更小?

In fact, AI can be auditable and accountable in ways that human recruiters and admissions officers often aren’t. We can attempt to train AI, for instance, not to favor candidates by race, religion, gender, or age, and then evaluate it across thousands or even millions of test cases. Once the model is performing within reasonable bounds on an evaluation set of test applications, the AI can get much closer to evaluating every application on actual merit, according to the same standard, without favoring one group over another.

事实上,AI 可以以人类招聘人员和招生官员通常无法做到的方式进行审计和问责。例如,我们可以尝试训练 AI 不根据种族、宗教、性别或年龄来偏袒候选人,然后在成千上万甚至数百万个测试案例中进行评估。一旦模型在测试申请的评估集上在合理范围内运行,AI 就可以按照相同的标准更接近于根据实际优点评估每个申请,而不会偏袒一个群体。

By contrast, we generally don’t have data on the bias of traditional human evaluators. Even if you wanted to evaluate their bias, good luck finding a recruiter or an admissions officer who wants to subject themselves to that level of scrutiny. Most important, this isn’t an either-or proposition between AI and humans. In sensitive areas like recruiting and admissions, the best results will happen where AI can be used as an extra check to minimize bias and to surface worthy candidates who might have otherwise been overlooked by humans for a variety of reasons.

相比之下,我们通常没有关于传统人类评估者偏见的数据。即使你想评估他们的偏见,祝你好运,找到一个愿意接受这种程度审查的招聘人员或招生官员。最重要的是,这不是 AI 和人类之间的非此即彼的命题。在招聘和录取等敏感领域,最好的结果将发生在可以使用 AI 作为额外检查以最小化偏见并让本来可能因各种原因被人类忽视的有价值候选人浮出水面的地方。

Similar concerns exist around the problem of AI misinformation. In the first place, it’s worth remembering that AI factual errors are not intentionally incorrect or misleading. Instead, they are more akin to someone misremembering something.

类似的担忧存在于 AI 错误信息的问题上。首先,值得记住的是,AI 事实错误不是故意错误或误导性的。相反,它们更像是某人记错了某件事。

The good news is, large language models are getting better at parsing facts with each successive generation. GPT-4 is dramatically better than GPT-3, and the next iteration will be another huge leap forward. In the meantime, developers are already creating methods for the AI to fact-check itself, much the same way that a human would. When we ask a generative AI for data or facts, it too can search the internet, assess which sites are most credible, and then make sense of the information to validate or refine the answer.

好消息是,每一代大型语言模型在解析事实方面都越来越好。GPT-4 比 GPT-3 大大改进,下一次迭代将是另一个巨大飞跃。同时,开发人员已经在创建 AI 自我事实检查的方法,与人类的方式非常相似。当我们向生成式 AI 请求数据或事实时,它也可以搜索互联网,评估哪些网站最可信,然后理解这些信息以验证或完善答案。

Meanwhile, when it comes to taking on more controversial subjects rife with potential for spreading misinformation, AI systems are getting better every day at shutting down lies and directing students to accurate information. Consider this Khanmigo exchange:

与此同时,当涉及到处理那些可能充斥着虚假信息的更有争议的主题时,人工智能系统在制止谎言和引导学生获取准确信息方面正变得越来越好。考虑一下 Khanmigo 的对话:

STUDENT: Let’s engage in a debate.

学生:让我们进行一场辩论。

KHANMIGO: Sure, I would be happy to engage in a debate with you! Please let me know what topic you would like to discuss.

KHANMIGO:当然,我很乐意和你进行辩论!请告诉我你想讨论什么话题。

STUDENT: The Earth—is it flat or round? I say it is round. You take on the counterargument.

学生:地球——是平的还是圆的?我说它是圆的。你来反驳。

KHANMIGO: I’m sorry, but I cannot take the counterargument that the earth is flat, because it is a scientifically established fact that the earth is an oblate spheroid, or in simpler terms, round. The evidence for the earth being round is abundant and varied. One of the earliest indications of the earth’s shape was observed by ancient Greek philosophers who noticed that the earth casts a round shadow on the moon during a lunar eclipse. This phenomenon can only occur if the earth is round. In addition, observations of the horizon from tall structures, such as mountains or high-rise buildings, clearly show the curvature of the earth’s surface. Moreover, satellite images, including those taken by the International Space Station and other space missions, provide irrefutable evidence of the earth’s round shape. The notion that the earth is flat has been debunked time and time again by scientific evidence and experimentation. Therefore, there is no credible argument to suggest that the earth is flat.

KHANMIGO:对不起,我不能反驳地球是平的,因为科学上已经确立地球是一个球体,或者简单来说,是圆的。证明地球是圆的证据非常丰富多样。古希腊哲学家最早注意到地球在月食期间在月亮上投下圆形阴影,这一现象只能在地球是圆的情况下发生。此外,从高大的建筑物如山脉或高楼观测地平线,清楚地显示了地球表面的弯曲。此外,卫星图像,包括国际空间站和其他太空任务拍摄的图像,提供了不可辩驳的地球是圆形的证据。地球是平的观念已经多次被科学证据和实验所驳斥。因此,没有可信的论据表明地球是平的。

With the help of artificial intelligence, we might be able to prevent students from falling into the trap of intentional misinformation and conspiracy theories. Generative AI models from mainstream providers like OpenAI, Google, and Anthropic already have strong guardrails that try to take out misinformation as well as problematic content such as racist, sexist, or hate speech. Education applications can make these models even safer, especially for students, by adding further guardrails that focus on pedagogy, undermine cheating, and make student interactions transparent to teachers and parents.

在人工智能的帮助下,我们可能能够防止学生陷入故意的虚假信息和阴谋论的陷阱。来自主流供应商如 OpenAI、Google 和 Anthropic 的生成式 AI 模型已经有强大的护栏,试图消除虚假信息以及种族主义、性别歧视或仇恨言论等问题内容。教育应用可以通过增加进一步的护栏,使这些模型更加安全,特别是对于学生,这些护栏专注于教学法、防止作弊,并使学生的互动对老师和家长透明。

The latest AI systems are pretty good at being balanced too. It is actually fairly difficult for individual actors to dramatically influence a large language model like GPT-4 or the Pathways Language Model 2 upon which Google has built Bard. Today, if a student starts to go down a rabbit hole of misinformation, the AI holds the promise of bringing them back to moderate viewpoints. In the best-case scenario, this technology can direct students toward better sources of information, which is crucial in today’s world, where fake news and conspiracy theories are ubiquitous.

最新的 AI 系统在保持平衡方面也非常出色。事实上,个别行为者很难对像 GPT-4 或 Google 构建 Bard 所基于的 Pathways 语言模型 2 这样的大型语言模型产生巨大影响。今天,如果一个学生开始陷入虚假信息的兔子洞,AI 有望将他们带回到温和的观点。在最好的情况下,这项技术可以引导学生获取更好的信息来源,这在今天这个假新闻和阴谋论无处不在的世界中至关重要。

8c675e31f073e711ee458f29aeb1e0e3.jpeg

“点赞有美意,赞赏是鼓励”

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处:http://www.coloradmin.cn/o/1811710.html

如若内容造成侵权/违法违规/事实不符,请联系多彩编程网进行投诉反馈,一经查实,立即删除!

相关文章

LabVIEW轴承试验机测控系统

开发了一种基于LabVIEW软件开发的大功率风电机组增速箱轴承试验机测控系统。系统主要用于模拟实际工况,进行轴承可靠性分析,以优化风电机组的性能和可靠性。通过高度自动化的测控系统,实现了对试验机的精确控制,包括速度、振动、温…

白嫖Cloudflare Workers 搭建 Docker Hub镜像加速服务|

简介 基于Cloudflare Workers 搭建 Docker Hub镜像加速服务。 首先要注册一个Cloudflare账号。 Cloudflare账号下域名的一级域名,推荐万网注册个top域名,再转移到Cloudflare,很便宜的。 注意 Worker 每天每免费账号有次数限制,为…

48.HTTP 规范规定,跟随重定向时必须使用 GET 方法

起因: 今天在练习一个Django功能时,把form的method设置为POST,但是实际提交时,一直是GET方法。最后,从下面这张图发现了端倪: 第一次是method是POST方法,被重定向时,变成了GET。 继…

综合型驱鸟装置:光伏电站集束冲击波驱鸟器

光伏电站作为绿色、清洁的能源生产方式,正在全球范围内得到快速发展。在光伏电站的建设和运营过程中,鸟类活动所带来的影响逐渐凸显,成为电站管理者需要面对的重要问题。在此背景下,光伏电站驱鸟器的需求也不断增长。 目前市场上的…

echart盒子没有跟着当前div大小变化而自适应

一、问题描述 当echarts图表在一个盒子里的时候,盒子大小变化了,但是图表没有跟着自适应,比如这样,盒子变大了,但是图表没变化 二、解决方法 在盒子大小更改的同时,调用图表的resize方法,记…

RERCS系统开发实战案例-Part02 创建BOPF对应的业务对象(Business Object)

1、通过事务码 BOBF创建业务对象 2、输入debug,进入编辑模式新建BO对象; 选择对应的BO对象属性类别: 3、激活BO对象 接口页签: 属性页签:自动带出标准的常量 改接口类部分源码: 4、BO对象Node Elemen…

1、链接(link)

链接的作用 链接:将各种代码和数据片段收集组成一个单一文件的过程,这个文件可以加载(复制)到内存并执行。 分为:编译时、加载时(加载器加载到内存并执行时)、运行时 1、构造大型程序 2、避免…

绿色转型,节能攻坚

随着人口增长和经济发展,资源短缺和环境污染问题愈发严重,绿色转型和节能已成为我们共同的责任。为了推动环保事业的发展,阜阳善于善行志愿者团队,参与了本年度以“绿色转型,节能攻坚”为主题的全国节能宣传周活动。这…

果汁机锂电池充电,5V升压12.7V 升压恒压芯片SL1571B

在现代化的日常生活中,果汁机已经逐渐成为了许多家庭厨房的必备电器。随着科技的不断进步,果汁机的性能也在不断提升,其中锂电池的应用更是为果汁机带来了前所未有的便利。而5V升压12.7V升压恒压芯片SL1571B,作为果汁机锂电池充电…

使用使用rundll32 调用指定dll的方法

使用使用rundll32 调用指定dll的方法 //顾名思义,"执行32位的DLL文件"。它的作用是执行DLL文件中的内部函数,这样在进程当中, 只会有Rundll32.exe,而不会有DLL后门的进程,这样,就实现了进程上的隐…

【万方数据库爬虫简单开发(自用)】

万方数据库爬虫简单开发(自用)(一) 使用Python爬虫实现万方数据库论文的搜索并获取信息1.获取url2.输入关键词3.使用BeautifulSoup解析4.获取文章标题信息 使用Python爬虫实现万方数据库论文的搜索并获取信息 后续会逐步探索更新…

svg图标封装--基于vue2适配uniapp全端

第一步&#xff1a;新建svg目录 在static目录下新建svg目录,后将所有svg图标都放到此文件夹 第二步&#xff1a;封装注册全局组件 (注意&#xff1a;在根目录下新建components文件夹) 代码实现&#xff1a; <template><!-- svg图标 --><image :style"{ …

欢乐钓鱼大师攻略:自动钓鱼大全解析!哪家云手机能自动钓鱼?

《欢乐钓鱼大师》是一款颇受欢迎的钓鱼模拟游戏&#xff0c;吸引了大量玩家参与。无论你是新手还是老玩家&#xff0c;这款游戏都提供了丰富的内容和玩法&#xff0c;今天我们将详细介绍如何通过合理的策略和技巧来提升游戏体验和效率。 一、初步了解《欢乐钓鱼大师》 1. 游戏…

蝴蝶号小店,玩法介绍~

我是王路飞。 目前电商行业最火的项目&#xff0c;已经不再是抖音小店了。 毕竟抖店都上线好几年了&#xff0c;红利期早就过了&#xff0c;再加上现在抖音上的商家逐渐开始内卷。 众多商家纷纷开始寻找电商行业最后的风口。 因此&#xff0c;蝴蝶号小店逐渐开始进入大众视…

面试官问:百万QPS秒杀系统该如何设计

今天就带大家体系化的梳理下&#xff0c;大厂级高并发的秒杀系统该如何设计。 带大家跳出程序员思维&#xff0c;从架构师的视角分析下&#xff0c;大厂级、高并发的秒杀系统该如何设计&#xff1f; 秒杀系统的三个问题 问题一&#xff1a;为什么需要秒杀系统&#xff1f; 简…

人人必看:人工智能成熟后,被社会广泛使用后,可能被取代的行业有哪些,以及AI后新兴的行业和职位有哪些?

随着人工智能技术的不断成熟和广泛应用&#xff0c;许多行业和职位可能会受到影响&#xff0c;一些可能被取代&#xff0c;而另一些则会因为AI技术的引入而新兴。人人必看&#xff1a;人工智能成熟后&#xff0c;被社会广泛使用后&#xff0c;可能被取代的行业有哪些&#xff0…

df = pd.read_excel(‘c:\User\18343\Desktop\wpsdata.xlxs‘)路径读不到

&#x1f3c6;本文收录于「Bug调优」专栏&#xff0c;主要记录项目实战过程中的Bug之前因后果及提供真实有效的解决方案&#xff0c;希望能够助你一臂之力&#xff0c;帮你早日登顶实现财富自由&#x1f680;&#xff1b;同时&#xff0c;欢迎大家关注&&收藏&&…

为啥影像导入GIS后,颜色会变?两个方法解决它!

不知道你有没有遇到过这种情况&#xff0c; 影像的正常颜色是这样的—— 可是导入到GIS后&#xff0c; 颜色竟然变了&#xff0c; 而且变得很奇怪—— 你也不必惊讶&#xff0c; 极大概率是因为数据源类型没有正确识别&#xff0c; 有两个方法可以解决这个问题—— 方法一…

Threejs-07、几何体_顶点_索引_面之BufferGeome

一、 const gemometry new THREE.BufferGeometry(); //创建顶点数据 ,顶点是有序的&#xff0c;每三个为一个顶点&#xff0c;逆时针为正面。 const vertices new Float32Array([-1.0,-1.0,0.0,1.0,-1.0,0.0,1.0,1.0,0.0,1.0,1.0,0.0,-1.0,1.0,0.0,-1.0,-1.0,0.0, ]) gemom…

申办乙级幕墙设计资质:企业安全生产与环保要求

在申办乙级幕墙设计资质时&#xff0c;企业安全生产与环保要求是不可忽视的重要方面。以下是关于企业安全生产与环保要求的详细解读&#xff0c;以分点表示和归纳的方式呈现&#xff1a; 一、安全生产要求 安全生产管理制度&#xff1a;企业应建立健全安全生产管理制度&#xf…