The Download: tricking LLMs, and reviving geothermal plants

《下载》：诱骗大语言模型，以及复兴地热发电厂

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. 这是我们工作日时事通讯《下载》的今日版，为您提供每日科技界动态。

A fundamental flaw leaves LLMs strikingly vulnerable to attack

一个根本性缺陷使大语言模型极易受到攻击

It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a team of researchers argue in a paper presented at a top AI conference earlier this month. The flaw concerns how LLMs identify who or what is giving them instructions. By taking advantage of it, the researchers were able to make popular LLMs spit out information they had been trained not to provide, such as how to synthesize cocaine and how to sabotage a commercial aircraft’s navigation system. Read our story about the flaw the researchers found, its implications—and why it may never be fixed. —Will Douglas Heaven 本月初，在一场顶级人工智能会议上发表的一篇论文中，研究团队指出，由于大语言模型（LLM）的工作原理存在根本性缺陷，使其无法完全免受黑客攻击。该缺陷涉及 LLM 如何识别指令的来源。通过利用这一漏洞，研究人员成功诱导主流 LLM 输出其被禁止提供的信息，例如如何合成可卡因以及如何破坏商用飞机的导航系统。阅读我们关于该漏洞、其影响以及为何它可能永远无法修复的报道。——Will Douglas Heaven

How an overlooked geothermal plant got a second chance

一座被忽视的地热发电厂如何获得第二次生命

In June 2024, a small company called Zanskar purchased a geothermal power plant in New Mexico that was failing fast. The water coming from the underground reservoir was getting colder by the day, making the plant uneconomical to run. Now, two years later, that plant is running at full capacity again, thanks to a new well. With the help of advanced modeling and modern drilling technology, the company was able to identify a better well site, drill down thousands of feet, and revive the entire operation. As the world looks for more sources of emissions-free electricity that are available 24-7, Lightning Dock shows there’s still hidden potential deep beneath our feet. Read the full story. —Casey Crownhart 2024 年 6 月，一家名为 Zanskar 的小公司收购了新墨西哥州一座濒临倒闭的地热发电厂。来自地下储层的水温日益降低，导致该电厂运营成本过高。如今，两年过去了，得益于一口新井，该电厂已恢复满负荷运转。借助先进的建模和现代钻探技术，该公司成功找到了更好的井位，钻探至数千英尺深处，并使整个项目起死回生。随着世界寻求更多全天候零排放电力来源，Lightning Dock 的案例表明，我们脚下的深处仍蕴藏着巨大的潜力。阅读完整报道。——Casey Crownhart

Narrated: South Korea’s hottest new bachelors are chip workers

播客：韩国最抢手的单身汉是芯片工人

Baek, a 35-year-old manager at the South Korean semiconductor titan SK Hynix, was enrolled in a matchmaking company a year ago. In a move typical of typical of anxious South Korean parents, his mother signed him up, hoping to find a good wife for her son. Lately, says Baek, he and his coworkers are having better luck finding dates—perhaps because of the dazzling bonuses they just got. Flush with eye-popping profits from the AI chip boom, SK Hynix agreed to pay 10% of operating profits to employees, which translates to an extra $476,000 per employee this year. Read our story about how chip workers like Baek have become the most sought-after bachelors and bachelorettes in South Korea. —Michelle Kim 35 岁的 Baek 是韩国半导体巨头 SK 海力士的一名经理，一年前他注册了一家婚介公司。正如典型的焦虑的韩国父母一样，他的母亲为他报了名，希望能为儿子找到一位好妻子。Baek 说，最近他和同事们在约会方面运气不错——这或许是因为他们刚刚拿到了丰厚的奖金。得益于人工智能芯片热潮带来的惊人利润，SK 海力士同意将营业利润的 10% 分配给员工，这意味着今年每位员工可额外获得 47.6 万美元。阅读我们关于像 Baek 这样的芯片工人如何成为韩国最抢手单身男女的报道。——Michelle Kim

The must-reads

必读内容

The US government has just banned Roombas: It’s not just Chinese humanoids—robot vacuum cleaners are included in a new FCC ban too. 美国政府刚刚封禁了 Roomba 扫地机器人：不仅仅是中国的人形机器人，扫地机器人也被纳入了 FCC 的新禁令中。
The ongoing fires in Europe are breaking modern records: And there’s likely even more destruction coming. 欧洲持续的火灾正在打破现代记录：而且未来可能会造成更大的破坏。
Google DeepMind has dismantled its Nobel-winning AlphaFold team: It reflects a broader industry move away from specialist tools towards more general, AI-powered agents for science. 谷歌 DeepMind 解散了其获得诺贝尔奖的 AlphaFold 团队：这反映了整个行业正从专业工具转向更通用的、由人工智能驱动的科学智能体。
Data centers are easy to build. To run? Not so much: For that, you need time and money to invest in grid infrastructure, like new transmission lines. 数据中心易于建造，但运营却很难：这需要时间和金钱投入到电网基础设施中，例如新的输电线路。
DoorDash plans to launch a drone delivery program: It’ll be a while before we get to make use of it, though. DoorDash 计划推出无人机配送项目：不过，我们还需要一段时间才能真正用上它。
AI is accelerating global digital inequality: Money, infrastructure and talent are pooling in a relatively small number of places. 人工智能正在加剧全球数字不平等：资金、基础设施和人才正汇聚在少数几个地区。
Quantum computers promise mathematical superpowers: And it feels like we’re inching closer to a commercial machine. 量子计算机承诺带来数学上的“超能力”：我们似乎正一步步接近商用机器。
Anxious Chinese students are using AI for university admissions: It’s common to pay private coaches to help navigate this high-stakes decision, but AI companies now offer the service for free. 焦虑的中国学生正在利用人工智能进行大学申请：聘请私人教练来应对这一重大决策很常见，但现在人工智能公司免费提供这项服务。
Boomers keep giving their grandkids AI-generated slop books: And it’s driving millennial parents mad. 婴儿潮一代不断给孙辈购买人工智能生成的劣质书籍：这让千禧一代的父母们抓狂。
Minecraft is helping children to redesign their cities: It just goes to show how creativity can still flourish, even amid war. 《我的世界》正在帮助孩子们重新设计他们的城市：这证明了即使在战争中，创造力依然可以蓬勃发展。

Quote of the day

今日金句

“I want to see the blood, sweat, and tears that went into it.” —Ray Slater Berry, founder of marketing agency dslx, tells Wired why he’s drawn to text written by humans. “我想看到其中倾注的心血、汗水和泪水。”——营销机构 dslx 的创始人 Ray Slater Berry 在接受《连线》杂志采访时，解释了他为何更倾向于人类撰写的文本。

One More Thing

补充内容

HELSING: Europe’s drone-filled vision for the future of war HELSING：欧洲对未来战争的无人机愿景

Europe has started testing an invisible automated intelligence network, known as a “digital targeting web,” conceived under the name Project ASGARD. Its purpose is to connect everything that looks for targets—“sensors,” in military lingo—and everything that fires on them (“shooters”) to a single, shared wireless electronic brain. Eighty years after total war last transformed the continent, the system signals a brutal new calculus of European defense. “The Russians are knocking on the door,” says Sven Weizenegger, the head of the German military’s Cyber Innovation Hub. Read our story about how strategists and policymakers are… 欧洲已开始测试一个被称为“数字目标网络”的隐形自动化智能网络，该项目名为“阿斯加德计划”（Project ASGARD）。其目的是将所有寻找目标的设备（军事术语称为“传感器”）和所有攻击目标的设备（“射手”）连接到一个共享的无线电子大脑中。在全面战争最后一次改变欧洲大陆 80 年后，该系统标志着欧洲防御体系进入了一种残酷的新计算模式。“俄罗斯人正在敲门，”德国军方网络创新中心负责人 Sven Weizenegger 说道。阅读我们关于战略家和决策者如何……的报道。