YC 初创悬赏 100 万美元解五大 AI 材料难题

Discovered Materials 是一家成立仅数月、总部位于旧金山的初创公司,利用 AI 模型寻找用于制造先进芯片的新材料。该公司宣布发起一项百万美元挑战赛,悬赏 AI 模型解决材料科学领域的五个关键问题。
尽管前沿 AI 模型已经解决了一系列引人瞩目的数学未解难题,并在生命科学领域取得进展,但它们尚未真正深入探究先进材料背后复杂的物理机制。
「在材料科学中,把问题清晰地定义出来要更难,因为它不像数学那样有非常明确的定义,能够得出是或否的答案,」Discovered Materials 联合创始人 Advaith Sridhar 说。该公司是 Y Combinator 2026 年春季批次的一员。「我们展开这场讨论时(在想),这个领域的重大挑战是什么?我们怎么知道 AI 正在取得进展?」
尽管材料科学领域没有能与千禧年大奖难题(Millennium Prize Problems)相当的奖项,Discovered Materials 仍召集了一个由全球顶尖高校学者组成的顾问小组,梳理出五个开放问题。公司为这些问题的解决方案设立了奖金池,总额价值 100 万美元。
一种解释铜氧化物超导现象的理论,即某些材料在超低温下具有零电阻的能力。
一种预测硅与二氧化硅之间界面结构的数值方法,这种材料组合几乎出现在所有半导体中。
一种将晶粒结构映射到热性能的数值方法,从而能够设计出更好的散热材料。
一种理论,用于预测为何用光照射材料会改变其行为,尤其是在超导性方面。
一种改进密度泛函理论的数值方法,而密度泛函理论是材料科学中用于建模原子与分子结构的一项关键技术。
“在整个材料科学领域,存在一些我们观察到却无法解释的现象,”参与设计这些挑战的斯坦福大学教授 Felipe Jornada 在一份声明中表示。“解释这些现象将增进我们对物理学的理解,而答案会直接决定我们如何制造电子器件、储存能源,以及生产未来的材料。”
在公布这些挑战之前,Discovered Materials 曾让前沿实验室的模型尝试攻克它们,为 AI 智能体提供互联网访问和其他资源,使其能自主工作数天。这些模型在每个问题上花了数天时间,却没有取得多少进展。尽管如此,不难想象 OpenAI 或 Anthropic 会尝试用多得多的算力或更新的模型一次性解决它们。
“是我们找到答案,还是别人、某位教授或前沿实验室找到答案,对我们来说并不是特别值得担心的事,”Sridhar 说。“我们发布这些挑战,是因为希望它们能充当标杆。如果你去解决了这些挑战,我们就加深了对材料以及身边事物行为方式的理解。”
他补充说,追踪这些问题的解决进展将显示出“这些模型是否正在这一领域不断攀升”。
这些挑战也反映出科学探究性质的变化,因为 AI 已被证明能够揭示人类研究人员未曾预料到的洞见和技术。当答案显然比以往任何时候都更容易找到时,问题本身反而变得更为重要。
“这是一种全新的科学思维方式:我们先提出验证方法和挑战,然后再让别人提出解释问题的想法,”Sridhar 说。“在这个领域,知道该问哪些正确的问题绝非易事,而且非常困难,所以教授们真正帮助我们的地方,就在于帮我们厘清应该提出哪些正确的问题。”
Discovered Materials 的主要重点是开发用于半导体的新材料;这家初创公司与芯片巨头合作开展研究项目,同时也为自己的科研工作提供资金。该公司在 8 月宣布种子轮融资时,Sridhar 曾对 TechCrunch 表示,他希望公司能在一年内产出一种有用的材料。
“这些时间表已经有所提前,”他今天说。“我现在更有信心,我们能够在不到一年的时间内找到这些具有工业用途的材料。”
当您通过我们文章中的链接进行购买时,我们可能会赚取少量佣金。这不会影响我们编辑的独立性。
Tim Fernholz 是一名记者,撰写科技、金融和公共政策方面的报道。他长期跟踪报道私营航天产业的崛起,著有《Rocket Billionaires: Elon Musk, Jeff Bezos and the New Space Race》。此前,他曾在全球商业新闻网站 Quartz 担任高级记者十余年,职业生涯始于华盛顿特区的政治记者。您可以通过发送邮件至 [email protected],或通过 Signal 向 tim_fernholz.21 发送加密信息来联系 Tim 或核实其联络身份。
正在加载下一篇文章
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(A YC startup is putting $1M behind five unsolved materials science problems for AI)
A YC startup is putting $1M behind 5 unsolved materials science problems for AI | TechCrunch
Image Credits:Discovered Materials
A YC startup is putting $1M behind 5 unsolved materials science problems for AI
5:00 AM PST · November 5, 2026
Discovered Materials, a months-old San Francisco startup using AI models to find new substances for building advanced chips, announced a million-dollar challenge for AI models to solve five critical problems in materials science.
While frontier AI models have solved a remarkable series of outstanding mathematics problems and made progress in the life sciences, they have yet to truly plumb the complex physics in advanced materials.
“It’s more difficult to specify problems clearly in materials science because it’s not like math, where you have a very specific definition and can get to a yes or no,” said Advaith Sridhar, a co-founder of Discovered Materials, which was part of Y Combinator’s spring 2026 batch. “We came to this discussion [wondering], what are the grand challenges in this field? How do we know AI is making progress?”
Though materials science doesn’t have an equivalent of the Millennium Prize Problems, Discovered Materials recruited an advisory group of academics at leading global universities to spell out five open problems. The company is offering a pool of prizes, worth $1 million in total, for solutions to the problems.
A theory to explain cuprate superconductivity, or the ability of certain materials to have zero electrical resistance at ultra-low temperatures.
A numerical method to predict the structures of interfaces between silicon and silicon dioxide, a material combination found in almost all semiconductors.
A numerical method to map grain structure to thermal properties, enabling the design of better heat dissipation materials.
A theory to predict why shining light on materials can change their behavior, particularly around superconductivity.
A numerical method to improve density functional theory, a key technique used in materials science to model the structures of atoms and molecules.
“Across materials science, there are phenomena we observe but cannot explain,” Felipe Jornada, a Stanford professor who helped develop the challenges, said in a statement. “Explaining these phenomena would improve our understanding of physics, and the answers would directly shape how we build electronics, store energy, and manufacture the materials of the future.”
Before announcing the challenges, Discovered Materials turned frontier lab models loose on them, giving AI agents internet access and other resources to work autonomously for days. The models spent several days on each problem without making much headway. Still, it’s easy to imagine OpenAI or Anthropic attempting to one-shot them with significantly more compute or a newer model.
“It’s not particularly a concern to us whether we find it, or someone else finds it, or a professor finds it, or the frontier labs find it,” Sridhar said. “The reason we’re putting out these challenges is because we want them to serve as the goalposts. If you go and solve these challenges, we are deepening our understanding of materials and how things around us behave.”
Tracking efforts to solve the problems will show “whether the models are climbing in this domain,” he added.
The challenge also reflects the changing nature of scientific inquiry as AI proves capable of uncovering insights and techniques human researchers didn’t anticipate. With solutions apparently easier to find than ever, the questions become more important.
“This is a new way of thinking about science, where we come up with the verification and the challenges first, and then we let somebody come up with the ideas that explain the problem,” Sridhar said. “Knowing what are the right questions to ask is not trivial and very difficult in this domain, so this is where the professors have really helped us shape what are the right questions we should be asking.”
Discovered Materials’ main focus is developing new materials for use in semiconductors; the startup partners with chip giants on research projects while also funding its own scientific efforts. When the company announced its seed round in August, Sridhar told TechCrunch that he hoped the company would generate a useful material within a year.
“Those timelines have accelerated a little bit,” he says today. “I’m more confident now that we will be able to find these industrially useful materials in a timeline shorter than a year.”
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.

Tim Fernholz is a journalist who writes about technology, finance and public policy. He has closely covered the rise of the private space industry and is the author of Rocket Billionaires: Elon Musk, Jeff Bezos and the New Space Race. Formerly, he was a senior reporter at Quartz, the global business news site, for more than a decade, and began his career as a political reporter in Washington, D.C. You can contact or verify outreach from Tim by emailing [email protected] or via an encrypted message to tim_fernholz.21 on Signal.
Loading the next article
Error loading the next article
原文为英文,正文由自动抓取并保留原文。
原文发布于 TechCrunch AI(A YC startup is putting $1M behind five unsolved materials science problems for AI),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。