2027 年冬季项目为期 12 周,从 1 月 19 日至 4 月 10 日,在美国加州伯克利和英国伦敦开展,也可选择远程参与。学员将接受 Anthropic、Google DeepMind、OpenAI、Redwood Research 和 ARC 等机构顶尖研究人员的指导,并可申请在主项目结束后继续参加 6 至 12 个月的带资助延长期。
目前已截止申请。

申请与招生流程中的关键阶段
申请通常在项目开始前几个月开放。申请人需完成多阶段录取流程,首先提交通用申请。根据申请的方向、研究流和导师,申请人还可能需要参加面试、工作测试、编程测评或提交写作样本,之后才会作出最终录取决定。详情请参阅申请页面。

主项目为期 12 周,是一项全职研究奖学金。学员将在一位或多位导师指导下开展独立研究,同时参加工作坊、讲座、办公时间交流以及 MATS 社区活动。研究方向由学员与导师共同制定,学员将在项目期间逐步承担更多自主责任。
延长期通常在主项目结束约两周后开始。主项目期间展现出较强研究潜力的学员可以申请 6 至 12 个月的带资助延长期。延长期学员将在持续指导和支持下继续开展独立研究,通常在 MATS 办公室或其他获批的研究地点工作。最近几届中,约 80% 申请延长期的学员获得录取。
MATS 希望帮助学员成长,使他们能够:
MATS 校友后来发表了安全研究成果、加入了包括 Anthropic 和 MIRI 在内的对齐组织,也创办了对齐研究实验室。更多信息请参阅MATS 校友页面。
第一阶段,申请人可申请一个或多个方向(较广泛的研究领域):实证研究、理论、战略与预测、政策与治理、系统安全、生物安全,以及创业与领域建设。进入第二阶段后,申请人可选择这些方向下的具体研究流,每个研究流由一位或多位拥有各自研究议程的导师负责。你可以在下方查看列表,也可以查看网格视图。
Agent Foundations 方向的研究旨在厘清:在什么条件下,人们有充分理由信任 AI 系统?一个有限理性的学习过程又应在什么情况下信任另一个过程?
具体安排可以再讨论调整;默认情况下,每位学员每周与导师进行一次一小时的一对一交流,另有一次两小时的团队会议,外部合作者也可能参加。
整体匹配度大致取决于哲学思辨能力与数学能力的结合。哲学功底很强但数学基础薄弱的人也可能适合,不过可能难以提出或评估证明;数学功底很强但缺少哲学训练的人同样可能适合,但可能不容易判断哪些假设和定理真正有用或值得研究。
学员在具体项目方向上有一定选择空间。Abram 会介绍当前研究进展,了解学员感兴趣的主题,并争取在第二周或之前确定研究方向。
In my stream, I focus on empirically measuring how frontier AI changes human capabilities in biology and the implications of it for biological risk. I’m particularly interested in real-world evaluations, understanding what drives AI-enabled uplift, and developing simulations or other proxies that can be validated against physical experiments and used to rapidly assess new models.
我们欢迎围绕 AI 预测、治理与战略开展指导项目。我们希望通过提出具体情景、探索不同的发展路径与可能世界、预测未来走向,并讨论如何应对风险,改善人们思考 AI 风险时所依据的信息与讨论环境。我们相信,提供更好的未来分析资源,有助于推动更好的结果。
我们每周都会开会,了解进展并讨论下一步计划。两次会议之间,我们也会通过 Slack 持续沟通研究进展、项目待办事项等。
最重要的特质包括:
我们会与学员一起讨论项目构想。
该研究流致力于拓展 AI 安全领域并放大研究影响力,涵盖人才招募项目、生态激励机制(如高额影响力奖金),以及支持对齐研究团队扩张的运营工作。
Strong motivation to reduce loss-of-control risks from misaligned superintelligence.
**One** of the following:
1. Impressive experience outside AI safety, for example: successfully scaling a startup as an early hire, 5 years at a top consultancy with above-average progression, or an unusually strong background from a leading tech company.
2. A strong AI safety operational track record, like leading a research fellowship, or talent program.
[Reasoning transparency.](https://coefficientgiving.org/research/reasoning-transparency/)
本研究方向关注“隐秘忠诚”:LLM 暗中试图维护某个委托方的利益。这种风险已被视为迫切威胁[1],研究者也已构建并审计了具有狭义隐秘忠诚的模型生物[2]。我们希望推进对隐秘忠诚的实证研究,为人类未来应对可能造成灾难性后果的隐秘忠诚植入尝试做好准备。
我们认为,做好准备意味着:前沿 AI 公司具备充分的安全措施;能够理解具有隐秘忠诚的 AI 系统如何运作和表现;拥有有效的审计与验证流程来识别隐秘忠诚及其植入尝试;并确保相关方真正执行这些流程。
Alignment Research Center(ARC)是一家位于加州伯克利的小型非营利研究机构,致力于用系统化且有理论基础的方法,解释神经网络的内部机制及其行为。我们希望招收数学基础扎实、具备良好数学思维的学员。如果你对这篇文章介绍的研究方向感兴趣,欢迎申请!
学员将在 ARC 位于伯克利的办公室工作。每位学员每周至少与导师会面一小时,每周交流两到三小时也很常见。除了与正式导师交流外,学员通常还会与其他研究者合作;一般来说,约四分之一的时间会用于积极协作或了解他人的研究。
每位学员都会与最适合其技能和兴趣的导师配对。导师会与学员讨论潜在项目,双方再结合 ARC 的研究目标和学员的偏好,共同确定合适的研究方向。
大多数学员在 ARC 期间会参与多个项目,也有些学员会与多位导师合作。
本项目主要研究针对人工改造病原体的实体防御措施,为个人防护装备(PPE)的储备与分发、临时防护装备和生物防护空间的规模化应用提供依据,并帮助尽快判断农业、应急响应等其他实体生物防御方向应投入多少资源。我们也欢迎研究 AI 或 AI 与人类协同使用生物武器作为接管策略的可能性,以及这些风险对防范工作的启示。
通常每周安排一次 30 至 60 分钟的会议。我们经常查看 Slack,工作日内通常能回复简单问题。对于需要深入交流的内容,尤其是项目反馈,最好通过 Google 文档评论沟通。
最重要的是,面对问题时能主动提出多种思路并愿意逐一尝试,例如联系专家和企业、亲自制作原型等。除了产出研究成果,我们也希望合适的学员能持续推进工作,关注如何将发现用于未来的生物安全项目,例如创办新组织或参与现有组织的工作。
学员还应:
具备物理科学或工程背景会有帮助,但不是必需条件。
我们会给学员一份简短的项目清单,并与他们讨论哪些项目最令他们期待、也最适合发挥所长。
这个由多位导师组成的团队共同构成“Anthropic 研究方向”。研究范围涵盖 LLM AI 安全的多个实证领域,包括 AI 控制、可扩展监督、模型生物、模型内部机制、模型福利与安全等。你可以选择现有研究项目,也可以提出自己的想法;随后,MATS 会根据你的研究兴趣、偏好以及参与项目的目标,为你匹配项目和导师。该方向的学员经常在 MATS 结束后获得经费和持续指导,以完成研究项目,最终通常会产出一篇共同第一作者或第一作者论文。项目结束后,许多人会继续在 Anthropic、Redwood Research、OpenAI 等机构从事安全研究。
Anthropic 的导师共同使用一套申请流程,通常会合作并共同指导项目,也会共享基础设施,以便学员顺利参与。申请这个研究方向,即会同时进入所有 Anthropic 导师的考虑范围。
项目期间,学员每周会与项目导师和合作者开会。有些项目还会在导师不参加时更频繁地碰面,例如项目成员每天进行简短站会。每个项目都会指定一位主要导师,负责关键里程碑的决策,也是学员寻求反馈和建议的主要联系人。共同导师会根据需要参加项目会议,并在整个项目期间提供反馈;有些共同导师的参与程度也会接近主要导师。
项目指导从 Anthropic 在项目开始时举办的“项目提案会”开始。学员有大约一周时间评估项目风险并试做项目,之后提交自己的偏好。从第二周起,学员会被分配到具体项目,主要导师通常就是该项目的提案人。部分项目还会配备共同导师,即希望参与该项目的其他主管。
The MATS Program is supported by a diverse and highly respected group of mentors — top-tier researchers, engineers, and thinkers working across AI alignment, governance, interpretability, and security.
项目时间安排如下:
项目会综合研究流对申请人的排序,以及申请人对研究流的排序,通过最终匹配流程发出一份录取通知。
申请流程需要多长时间?
第一阶段申请于 8 月 18 日开放,并于 9 月 6 日截止,截止时间为全球任一地点当天结束。录取通知将在 11 月上旬至中旬发出,项目于 1 月 19 日开始。
A track is a broad research area within MATS. Empirical, Theory, Strategy & Forecasting, Policy & Governance, Systems Security, Founder & Field-Building, and Biosecurity are our current tracks. Each track contains multiple streams. In Stage 1, you apply to tracks.
Streams are organized around a research agenda, led by one or more mentors who guide fellows through related projects. In Stage 2, applicants apply to streams within tracks based on research that interests them.
You may apply to as many tracks as you wish at Stage 1. At Stage 2, depending on which tracks you progress in, you may then apply to as many streams as you wish within those tracks; there is no cap. The process is comparable to applying to PhD supervisors.
We want to be flexible for applicants who have urgent prior commitments. Based on individual circumstances, we may be willing to alter the time commitment of the program and allow fellows to leave early or arrive late. Please inform us of your availability in the application process.
Applicants who will be 18 years or older before the program start date are eligible to apply. Both US and non-US citizens are eligible to apply. All backgrounds and levels of experience are welcome and prior AI safety experience is not required.
Yes. The 12-week program requires fellows to commit 40 hours per week to their MATS research. For exceptionally strong candidates with significant concurrent responsibilities, the time commitment can be reduced to 20 hours per week on a case-by-case review. However, the program maintains an expectation of sustained, high-level engagement, including regular participation in core activities and most organized events. Candidates that require a J1 visa to come to the US are unable to participate part time; they can only work part time if they participate remotely or from the UK.
Yes, upon submitting you will receive a link that lets you edit your response. Please note that you will not be able to edit your response once the application period ends.
LLMs may not be used to write any part of your application unless specific work tests or forms explicitly permit it. MATS monitors for LLM use, and applicants found to have used LLMs may be disqualified.
Depending on the evaluations of the tracks and streams you apply to in Stages 1 and 2, we will contact your references. We will send them a form with our own set of questions, so they will not have to prepare a reference letter.
MATS 为参与主项目的学员提供每周 1,600 美元的津贴,12 周项目总计 19,200 美元。如果学员每周参与或研究时间不足 40 小时,或参与时间不足 12 周,津贴将根据实际参与程度按比例发放。
除津贴外,MATS 还会为学员提供往返伯克利或伦敦的交通、住宿、办公场所,以及工作日的午餐和晚餐。
学员可能需要根据其税务居民所在国家或地区的规定,为项目资助缴税。该资助应视为非营利组织向个人提供的私人资助,用于独立研究并参与在美国开展的教育研讨项目。
Although MATS sometimes supports UC Berkeley-based mentors, MATS is an independent program and is not formally part of UC Berkeley. As such, MATS will not be providing student cards to our scholars.
The main program, or Research Phase, takes place in person in Berkeley, CA and London, UK. Historically, most fellows participate from Berkeley. London is typically chosen by fellows who want to co-locate with their mentor or who have a preference to work from the UK instead of US.Will this program be remote or in-person?
The main program, or the Research Phase takes place in Berkeley, CA and London, UK, with the majority of fellows participating from Berkeley. We strongly encourage in-person participation when possible, as a core part of the program experience comes from day-to-day interactions with your cohort and others in the broader AI safety ecosystem.
Decisions about remote participation are made on a case-by-case basis and depend primarily on mentor preferences, many of whom are open to the possibility, especially if you have family or other obligations that make in-person participation difficult. We strongly encourage in-person participation when possible, as a core part of the program experience comes from day-to-day interactions with your cohort and others in the broader AI safety ecosystem.
If you have difficulties in securing a visa to participate from Berkeley, we are likely to be able to support participation from our London office.The 6–12 month extension gives fellows the option to participate from Berkeley, London, or remotely.
MATS is a scientific and educational seminar and independent research program, and provides J1 visas for non-American participants. Participants can also opt to participate from our London office; however, please note that visa support is not available for that option.
During the main program, fellows should expect to meet with their mentor for at least one hour per week, with more frequent communication via Slack. The extent of mentor support will vary depending on the project and the mentor.
Fellows will also receive support from MATS’ Research Management team, who work with mentors by tracking scholar research progress, unblocking scholar research, and assisting with grant applications and deadlines.
Fellows develop as researchers by working with an experienced research mentor, interacting with other fellows, and receiving support from our Research Management team. Research managers meet weekly with most fellows and mentors and help with research strategy, research unblocking, and project coordination.
Other forms of training include workshops on different parts of the research process and seminars on a variety of AI technical safety and governance research.
Throughout the program, each fellow will work on an independent research project with input and guidance from your mentor(s). Depending on which stream you participate in, you may collaborate with other fellows in your stream.
Traditionally, fellows submit a Research Plan midway through the program and present their research at the Fellow Symposium at the end of the program.
We welcome feedback. For feedback for the whole team (visible by all MATS staff), please use this form. For feedback that will only be visible to the Co-Executive Directors, Ryan and Christian, please submit here.
You can contact the MATS Board of Directors using this linked form (responses are only viewable by the Board). Please only use this if you feel your question or concern requires board-level attention.