The Download: tricking LLMs, and reviving geothermal plants
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. A fundamental flaw leaves LLMs strikingly vulnerable to attack It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a…
本条来自 MIT Technology Review(AI / 科技),聚焦 LLM安全漏洞、地热发电、AI芯片、科技政策。 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.
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
- —Will Douglas Heaven
- —Casey Crownhart
- —Michelle Kim
- The must-reads
- 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
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
A fundamental flaw leaves LLMs strikingly vulnerable to attack It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a…
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.
A fundamental flaw leaves LLMs strikingly vulnerable to attack
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
How an overlooked geothermal plant got a second chance
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
This story is from The Spark, our weekly climate tech newsletter. Sign up to receive it in your inbox every Wednesday.
MIT Technology Review Narrated: South Korea’s hottest new bachelors are chip workers
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 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
This is our latest story to be turned into an MIT Technology Review Narrated podcast, which we publish each week on Spotify and Apple Podcasts . Just navigate to MIT Technology Review Narrated on either platform, and follow us to get all our new content as it’s released.
The must-reads
I’ve combed the internet to find you today’s most fun/important/scary/fascinating stories about technology.
本条目归入「Technology AI」垂直,涉及真实话题:LLM安全漏洞、地热发电、AI芯片、科技政策。
· 市场:关注 LLM安全漏洞、地热发电 对相关品类与竞争格局的潜在影响。
· 消费者:MIT Technology Review、Zanskar、SK Hynix、Google DeepMind、DoorDash、PsiQuantum、Helsing 的受众行为与偏好变化值得追踪。
· 品牌:MIT Technology Review、Zanskar、SK Hynix、Google DeepMind、DoorDash、PsiQuantum、Helsing 的叙事、产品与增长动作可拆解复用。
· 渠道:内容分发与触点组合(社媒 / 电商 / 线下)的协同值得复盘。
· 涉及品牌:MIT Technology Review、Zanskar、SK Hynix、Google DeepMind、DoorDash、PsiQuantum、Helsing。
· 核心话题:LLM安全漏洞、地热发电、AI芯片、科技政策。
· 可思考:如何把「LLM安全漏洞」的洞察,转化为可衡量的内容与增长动作?
面试中可引用「The Download: tricking LLMs, and reviving geothermal plants」:围绕 MIT Technology Review、Zanskar、SK Hynix、Google DeepMind、DoorDash、PsiQuantum、Helsing,说明你对行业动向的判断与可落地动作。
本条目相关英文术语可在「商务英语」模块按话题检索,用于外企面试表达训练。
—Ray Slater Berry, founder of marketing agency dslx, tells Wired why he’s drawn to text written by humans.…
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.…
A fundamental flaw leaves LLMs strikingly vulnerable to attack…