我们希望支持将奇异学习理论(SLT)应用于 AI 安全的研究项目,尤其是可解释性与对齐方向。
项目既可以是实证研究(例如运用贝叶斯影响函数研究或改进机器遗忘),也可以是理论研究(例如证明基于 SGMCMC 的采样方法具有收敛性)。多数项目会兼具这两个方面,具体侧重取决于你的背景和兴趣。
实证项目通常会用到以下 SLT 工具:
运用这些工具,我们会探索多个方向,例如:
SF Bay Area
直到不久前,我还是墨尔本大学的一名职业数学家,研究领域包括代数几何、数理逻辑、数理物理的若干方向,以及最近的统计学习理论。2025 年初,我离开学术界,加入 Timaeus 负责 AI 安全研究。
Jesse 是 Timaeus 的联合创始人兼执行主任。Timaeus 是一家 AI 安全非营利组织,研究奇异学习理论(SLT)在 AI 安全中的应用,尤其关注可解释性和对齐。Jesse 拥有物理学背景,除参与外联和运营外,还领导 Timaeus 的多个研究项目。
If you're interested in working on more of the empirical side, you should have prior experience with ML engineering (at least at the level of a program like ARENA) and prior research experience (potentially in a field outside of ML). A bonus would be prior familiarity with designing and running ML experiments or research specifically in AI safety.
If you're interested in working on more of the theoretical side, you should have prior research experience in a relevant field like mathematics, theoretical physics, or theoretical computer science.
Please make sure that your background and interests are clearly described in your application. By default, we'll be looking for evidence of research ability in the form of publications.
We do not expect you to already be aware of SLT, but if you pass the first round, please prepare by conducting some background reading (see: timaeus.co/learn).
导师会与学员讨论项目构想,并提供几个方向供选择。