Anand Srinivasan

Anand Srinivasan is a mathematician and researcher currently pursuing a PhD at the University of Cambridge in the Department of Applied Mathematics and Theoretical Physics (DAMTP), where he works in the Biological Physics and Mechanics group on active matter and distributed control systems. He holds a BS in Mathematics from MIT, where he worked on Ising models for image classification and fuzzy manifold learning (independently published at NeurIPS). He co-founded AlphaSheets, a cloud-based spreadsheet startup, and served as CTO managing a six-person engineering team from 2015 to 2019. Upon leaving the company, he redirected his focus toward AI safety research, receiving a $30,000 grant from the Long-Term Future Fund in 2019 for independent deconfusion work titled "Formalizing perceptual complexity with application to safe intelligence amplification," which aimed to develop a framework enabling provable claims about what AI systems can and cannot internally represent based on their architectures and training processes. He has since published research on contracting dynamical systems in Banach spaces with MIT's Jean-Jacques Slotine, and has worked as a senior research software engineer at Harvard University Research Computing.

No endorsements yet.

Personal Website

https://a0s.co/

LinkedIn

LinkedIn

Twitter / X

-

LessWrong

-

EA Forum

-