Quentin Feuillade-Montixi
Seldon Labs#2
Seldon Labs#2
After MATS, I worked as a contractor for METR evaluating GPT-4 pre-release. I then co-founded PRISM Eval and created an automated red-teaming system (BehaviorElicitiationTool: https://github.com/qfeuilla/BehaviorEliciationTool) that I presented at the Paris AI Summit. I am now founding WeaveMind (https://weavemind.ai/) at Seldon Lab Batch 2.
2022—2023 年冬季班共有 58 位学员和 17 位导师，导师来自 Anthropic、MIRI、ARC、Redwood Research 等领先机构。本届首次设立 Scholar Support 团队，为学员提供研究指导，并协助他们解决研究过程中的障碍。项目先在线开展 6 周，随后在伯克利线下进行 2 个月。学员还组织了多种活动，包括机制可解释性和线性代数学习小组、每周闪电演讲，以及研究工具和技术写作工作坊。本届校友中，Marius Hobbhahn 创立了 Apollo Research 并发表了机制可解释性研究；Asa 与他人合著了关于测量情境意识以及大型语言模型“反转诅咒”的论文；Jesse Hoogland 创立了 Timaeus，并提出了发展式可解释性研究方向。
MATS was a life changing experience. I met and got mentored by amazing people, and I learned so much in such a small amount of time. Looking back at me before this program, I don't think I could even recognize myself 8 month ago. Even though I have no academic background, I felt listened, empowered and supported in order to tackle the biggest challenges that I (and possibly we) have ever faced.
Quentin Feuillade-Montixi
