在概率模型基础上构建确定性系统
我在公共市场工作了十年，投入了大约10亿美元的资本。有一点让我感到惊讶：核心市场基础设施中仍有相当一部分依赖手工操作。
关键工作流程始于混乱的源信息，这些信息必须经过解释、清理和对账，才能变得可用。为了弥补这一差距，专门的团队应运而生。
一小组工程师和行业专家开始构建Auxage，试图用不同的架构来解决这个问题。
到目前为止，我们在标准普尔500指数中生成的输出达到了约99%的准确率，已经在这一工作流程上超越了Claude等工具以及几家大型企业。
有趣的是，困难的部分并不是模型的能力，而是数据架构和系统设计。
我很好奇这里是否有其他人曾经参与过将混乱的现实世界信息转化为可靠、高精度基础设施的系统。如果有帮助，我很乐意分享更多关于我们在Auxage所构建的内容。
查看原文
I spent the last decade in public markets deploying ~$1B in capital. One thing that always struck me: a surprising amount of core market infrastructure still runs on manual work.<p>Critical workflows start from messy source information that has to be interpreted, cleaned, and reconciled before it becomes usable. Entire teams exist just to bridge that gap.<p>A small group of engineers and domain practitioners started building Auxage to see if this could be solved with a different architecture.<p>So far we’re generating human-analyst–grade outputs across the S&P 500 with ~99% accuracy, already outperforming tools like Claude and several large incumbents on this workflow.<p>Interestingly, the hard part hasn’t been model capability — it’s data architecture and system design.<p>Curious if others here have worked on systems that turn messy real-world information into reliable, high-accuracy infrastructure.
If helpful, happy to share more about what we're building at Auxage.